diff --git a/.cirrus.yml b/.cirrus.yml index f53c519447..02c43a074a 100644 --- a/.cirrus.yml +++ b/.cirrus.yml @@ -1,61 +1,6 @@ env: CIRRUS_CLONE_DEPTH: 1 -freebsd_12_task: - freebsd_instance: - image_family: freebsd-12-2 - cpu: 8 - memory: 8G - install_script: - - ASSUME_ALWAYS_YES=yes pkg bootstrap -f ; - - pkg install -y bash curl cyrus-sasl git glib gmake gnutls gsed - nettle perl5 pixman pkgconf png usbredir ninja - script: - - mkdir build - - cd build - # TODO: Enable gnutls again once FreeBSD's libtasn1 got fixed - # See: https://gitlab.com/gnutls/libtasn1/-/merge_requests/71 - - ../configure --enable-werror --disable-gnutls - || { cat config.log meson-logs/meson-log.txt; exit 1; } - - gmake -j$(sysctl -n hw.ncpu) - - gmake -j$(sysctl -n hw.ncpu) check V=1 - -macos_task: - osx_instance: - image: catalina-base - install_script: - - brew install pkg-config python gnu-sed glib pixman make sdl2 bash ninja - script: - - mkdir build - - cd build - - ../configure --python=/usr/local/bin/python3 --enable-werror - --extra-cflags='-Wno-error=deprecated-declarations' - || { cat config.log meson-logs/meson-log.txt; exit 1; } - - gmake -j$(sysctl -n hw.ncpu) - - gmake check-unit V=1 - - gmake check-block V=1 - - gmake check-qapi-schema V=1 - - gmake check-softfloat V=1 - - gmake check-qtest-x86_64 V=1 - -macos_xcode_task: - osx_instance: - # this is an alias for the latest Xcode - image: catalina-xcode - install_script: - - brew install pkg-config gnu-sed glib pixman make sdl2 bash ninja - script: - - mkdir build - - cd build - - ../configure --extra-cflags='-Wno-error=deprecated-declarations' --enable-modules - --enable-werror --cc=clang || { cat config.log meson-logs/meson-log.txt; exit 1; } - - gmake -j$(sysctl -n hw.ncpu) - - gmake check-unit V=1 - - gmake check-block V=1 - - gmake check-qapi-schema V=1 - - gmake check-softfloat V=1 - - gmake check-qtest-x86_64 V=1 - windows_msys2_task: timeout_in: 90m windows_container: @@ -67,7 +12,7 @@ windows_msys2_task: CIRRUS_SHELL: powershell MSYS: winsymlinks:nativestrict MSYSTEM: MINGW64 - MSYS2_URL: https://github.com/msys2/msys2-installer/releases/download/2021-01-05/msys2-base-x86_64-20210105.sfx.exe + MSYS2_URL: https://github.com/msys2/msys2-installer/releases/download/2021-04-19/msys2-base-x86_64-20210419.sfx.exe MSYS2_FINGERPRINT: 0 MSYS2_PACKAGES: " diffutils git grep make pkg-config sed @@ -130,7 +75,7 @@ windows_msys2_task: taskkill /F /FI "MODULES eq msys-2.0.dll" tasklist C:\tools\msys64\usr\bin\bash.exe -lc "mv -f /etc/pacman.conf.pacnew /etc/pacman.conf || true" - C:\tools\msys64\usr\bin\bash.exe -lc "pacman --noconfirm -Suu --overwrite=*" + C:\tools\msys64\usr\bin\bash.exe -lc "pacman --noconfirm -Syuu --overwrite=*" Write-Output "Core install time taken: $((Get-Date).Subtract($start_time))" $start_time = Get-Date diff --git a/.github/lockdown.yml b/.github/lockdown.yml index 07fc2f31ee..d3546bd2bc 100644 --- a/.github/lockdown.yml +++ b/.github/lockdown.yml @@ -14,11 +14,11 @@ issues: at https://gitlab.com/qemu-project/qemu.git. The project does not process issues filed on GitHub. - The project issues are tracked on Launchpad: - https://bugs.launchpad.net/qemu + The project issues are tracked on GitLab: + https://gitlab.com/qemu-project/qemu/-/issues QEMU welcomes bug report contributions. You can file new ones on: - https://bugs.launchpad.net/qemu/+filebug + https://gitlab.com/qemu-project/qemu/-/issues/new pulls: comment: | diff --git a/.gitignore b/.gitignore index 1dc75dccc0..c37cd58207 100644 --- a/.gitignore +++ b/.gitignore @@ -13,7 +13,9 @@ GTAGS *~ *.ast_raw *.depend_raw -build.log +*.swp +*.patch +build.log /dist /xemu.ini diff --git a/.gitlab-ci.d/buildtest-template.yml b/.gitlab-ci.d/buildtest-template.yml new file mode 100644 index 0000000000..fcbcc4e627 --- /dev/null +++ b/.gitlab-ci.d/buildtest-template.yml @@ -0,0 +1,81 @@ +.native_build_job_template: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest + before_script: + - JOBS=$(expr $(nproc) + 1) + script: + - if test -n "$LD_JOBS"; + then + scripts/git-submodule.sh update meson ; + fi + - mkdir build + - cd build + - if test -n "$TARGETS"; + then + ../configure --enable-werror --disable-docs ${LD_JOBS:+--meson=git} $CONFIGURE_ARGS --target-list="$TARGETS" ; + else + ../configure --enable-werror --disable-docs ${LD_JOBS:+--meson=git} $CONFIGURE_ARGS ; + fi || { cat config.log meson-logs/meson-log.txt && exit 1; } + - if test -n "$LD_JOBS"; + then + ../meson/meson.py configure . -Dbackend_max_links="$LD_JOBS" ; + fi || exit 1; + - make -j"$JOBS" + - if test -n "$MAKE_CHECK_ARGS"; + then + make -j"$JOBS" $MAKE_CHECK_ARGS ; + fi + +.native_test_job_template: + stage: test + image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest + script: + - scripts/git-submodule.sh update + $(sed -n '/GIT_SUBMODULES=/ s/.*=// p' build/config-host.mak) + - cd build + - find . -type f -exec touch {} + + # Avoid recompiling by hiding ninja with NINJA=":" + - make NINJA=":" $MAKE_CHECK_ARGS + +.acceptance_test_job_template: + extends: .native_test_job_template + cache: + key: "${CI_JOB_NAME}-cache" + paths: + - ${CI_PROJECT_DIR}/avocado-cache + policy: pull-push + artifacts: + name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG" + when: on_failure + expire_in: 7 days + paths: + - build/tests/results/latest/results.xml + - build/tests/results/latest/test-results + reports: + junit: build/tests/results/latest/results.xml + before_script: + - mkdir -p ~/.config/avocado + - echo "[datadir.paths]" > ~/.config/avocado/avocado.conf + - echo "cache_dirs = ['${CI_PROJECT_DIR}/avocado-cache']" + >> ~/.config/avocado/avocado.conf + - echo -e '[job.output.testlogs]\nstatuses = ["FAIL", "INTERRUPT"]' + >> ~/.config/avocado/avocado.conf + - if [ -d ${CI_PROJECT_DIR}/avocado-cache ]; then + du -chs ${CI_PROJECT_DIR}/avocado-cache ; + fi + - export AVOCADO_ALLOW_UNTRUSTED_CODE=1 + after_script: + - cd build + - du -chs ${CI_PROJECT_DIR}/avocado-cache + rules: + # Only run these jobs if running on the mainstream namespace, + # or if the user set the QEMU_CI_AVOCADO_TESTING variable (either + # in its namespace setting or via git-push option, see documentation + # in /.gitlab-ci.yml of this repository). + - if: '$CI_PROJECT_NAMESPACE == "qemu-project"' + when: on_success + - if: '$QEMU_CI_AVOCADO_TESTING' + when: on_success + # Otherwise, set to manual (the jobs are created but not run). + - when: manual + allow_failure: true diff --git a/.gitlab-ci.d/buildtest.yml b/.gitlab-ci.d/buildtest.yml new file mode 100644 index 0000000000..903ee65f32 --- /dev/null +++ b/.gitlab-ci.d/buildtest.yml @@ -0,0 +1,724 @@ +include: + - local: '/.gitlab-ci.d/buildtest-template.yml' + +build-system-alpine: + extends: .native_build_job_template + needs: + - job: amd64-alpine-container + variables: + IMAGE: alpine + TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu + microblazeel-softmmu mips64el-softmmu + MAKE_CHECK_ARGS: check-build + CONFIGURE_ARGS: --enable-docs --enable-trace-backends=log,simple,syslog + artifacts: + expire_in: 2 days + paths: + - .git-submodule-status + - build + +check-system-alpine: + extends: .native_test_job_template + needs: + - job: build-system-alpine + artifacts: true + variables: + IMAGE: alpine + MAKE_CHECK_ARGS: check + +acceptance-system-alpine: + extends: .acceptance_test_job_template + needs: + - job: build-system-alpine + artifacts: true + variables: + IMAGE: alpine + MAKE_CHECK_ARGS: check-acceptance + +build-system-ubuntu: + extends: .native_build_job_template + needs: + job: amd64-ubuntu2004-container + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --enable-docs --enable-fdt=system --enable-slirp=system + TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu + microblazeel-softmmu mips64el-softmmu + MAKE_CHECK_ARGS: check-build + artifacts: + expire_in: 2 days + paths: + - build + +check-system-ubuntu: + extends: .native_test_job_template + needs: + - job: build-system-ubuntu + artifacts: true + variables: + IMAGE: ubuntu2004 + MAKE_CHECK_ARGS: check + +acceptance-system-ubuntu: + extends: .acceptance_test_job_template + needs: + - job: build-system-ubuntu + artifacts: true + variables: + IMAGE: ubuntu2004 + MAKE_CHECK_ARGS: check-acceptance + +build-system-debian: + extends: .native_build_job_template + needs: + job: amd64-debian-container + variables: + IMAGE: debian-amd64 + CONFIGURE_ARGS: --enable-fdt=system + TARGETS: arm-softmmu avr-softmmu i386-softmmu mipsel-softmmu + riscv64-softmmu sh4eb-softmmu sparc-softmmu xtensaeb-softmmu + MAKE_CHECK_ARGS: check-build + artifacts: + expire_in: 2 days + paths: + - build + +check-system-debian: + extends: .native_test_job_template + needs: + - job: build-system-debian + artifacts: true + variables: + IMAGE: debian-amd64 + MAKE_CHECK_ARGS: check + +acceptance-system-debian: + extends: .acceptance_test_job_template + needs: + - job: build-system-debian + artifacts: true + variables: + IMAGE: debian-amd64 + MAKE_CHECK_ARGS: check-acceptance + +build-system-fedora: + extends: .native_build_job_template + needs: + job: amd64-fedora-container + variables: + IMAGE: fedora + CONFIGURE_ARGS: --disable-gcrypt --enable-nettle --enable-docs + --enable-fdt=system --enable-slirp=system --enable-capstone=system + TARGETS: tricore-softmmu microblaze-softmmu mips-softmmu + xtensa-softmmu m68k-softmmu riscv32-softmmu ppc-softmmu sparc64-softmmu + MAKE_CHECK_ARGS: check-build + artifacts: + expire_in: 2 days + paths: + - build + +check-system-fedora: + extends: .native_test_job_template + needs: + - job: build-system-fedora + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check + +acceptance-system-fedora: + extends: .acceptance_test_job_template + needs: + - job: build-system-fedora + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check-acceptance + +build-system-centos: + extends: .native_build_job_template + needs: + job: amd64-centos8-container + variables: + IMAGE: centos8 + CONFIGURE_ARGS: --disable-nettle --enable-gcrypt --enable-fdt=system + --enable-modules --enable-trace-backends=dtrace + TARGETS: ppc64-softmmu or1k-softmmu s390x-softmmu + x86_64-softmmu rx-softmmu sh4-softmmu nios2-softmmu + MAKE_CHECK_ARGS: check-build + artifacts: + expire_in: 2 days + paths: + - build + +check-system-centos: + extends: .native_test_job_template + needs: + - job: build-system-centos + artifacts: true + variables: + IMAGE: centos8 + MAKE_CHECK_ARGS: check + +acceptance-system-centos: + extends: .acceptance_test_job_template + needs: + - job: build-system-centos + artifacts: true + variables: + IMAGE: centos8 + MAKE_CHECK_ARGS: check-acceptance + +build-system-opensuse: + extends: .native_build_job_template + needs: + job: amd64-opensuse-leap-container + variables: + IMAGE: opensuse-leap + CONFIGURE_ARGS: --enable-fdt=system + TARGETS: s390x-softmmu x86_64-softmmu aarch64-softmmu + MAKE_CHECK_ARGS: check-build + artifacts: + expire_in: 2 days + paths: + - build + +check-system-opensuse: + extends: .native_test_job_template + needs: + - job: build-system-opensuse + artifacts: true + variables: + IMAGE: opensuse-leap + MAKE_CHECK_ARGS: check + +acceptance-system-opensuse: + extends: .acceptance_test_job_template + needs: + - job: build-system-opensuse + artifacts: true + variables: + IMAGE: opensuse-leap + MAKE_CHECK_ARGS: check-acceptance + + +build-disabled: + extends: .native_build_job_template + needs: + job: amd64-fedora-container + variables: + IMAGE: fedora + CONFIGURE_ARGS: + --disable-attr + --disable-auth-pam + --disable-avx2 + --disable-bochs + --disable-brlapi + --disable-bzip2 + --disable-cap-ng + --disable-capstone + --disable-cloop + --disable-coroutine-pool + --disable-curl + --disable-curses + --disable-dmg + --disable-docs + --disable-gcrypt + --disable-glusterfs + --disable-gnutls + --disable-gtk + --disable-guest-agent + --disable-iconv + --disable-keyring + --disable-kvm + --disable-libiscsi + --disable-libpmem + --disable-libssh + --disable-libudev + --disable-libusb + --disable-libxml2 + --disable-linux-aio + --disable-live-block-migration + --disable-lzo + --disable-malloc-trim + --disable-mpath + --disable-nettle + --disable-numa + --disable-opengl + --disable-parallels + --disable-pie + --disable-qcow1 + --disable-qed + --disable-qom-cast-debug + --disable-rbd + --disable-rdma + --disable-replication + --disable-sdl + --disable-seccomp + --disable-slirp + --disable-smartcard + --disable-snappy + --disable-sparse + --disable-spice + --disable-strip + --disable-tpm + --disable-usb-redir + --disable-vdi + --disable-vhost-crypto + --disable-vhost-net + --disable-vhost-scsi + --disable-vhost-kernel + --disable-vhost-user + --disable-vhost-vdpa + --disable-vhost-vsock + --disable-virglrenderer + --disable-vnc + --disable-vte + --disable-vvfat + --disable-xen + --disable-zstd + TARGETS: arm-softmmu i386-softmmu ppc64-softmmu mips64-softmmu + s390x-softmmu i386-linux-user + MAKE_CHECK_ARGS: check-qtest SPEED=slow + +# This jobs explicitly disable TCG (--disable-tcg), KVM is detected by +# the configure script. The container doesn't contain Xen headers so +# Xen accelerator is not detected / selected. As result it build the +# i386-softmmu and x86_64-softmmu with KVM being the single accelerator +# available. +# Also use a different coroutine implementation (which is only really of +# interest to KVM users, i.e. with TCG disabled) +build-tcg-disabled: + extends: .native_build_job_template + needs: + job: amd64-centos8-container + variables: + IMAGE: centos8 + script: + - mkdir build + - cd build + - ../configure --disable-tcg --audio-drv-list="" --with-coroutine=ucontext + || { cat config.log meson-logs/meson-log.txt && exit 1; } + - make -j"$JOBS" + - make check-unit + - make check-qapi-schema + - cd tests/qemu-iotests/ + - ./check -raw 001 002 003 004 005 008 009 010 011 012 021 025 032 033 048 + 052 063 077 086 101 104 106 113 148 150 151 152 157 159 160 163 + 170 171 183 184 192 194 208 221 222 226 227 236 253 277 + - ./check -qcow2 028 051 056 057 058 065 068 082 085 091 095 096 102 122 + 124 132 139 142 144 145 151 152 155 157 165 194 196 200 202 + 208 209 216 218 222 227 234 246 247 248 250 254 255 257 258 + 260 261 262 263 264 270 272 273 277 279 + +build-user: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools --disable-system + MAKE_CHECK_ARGS: check-tcg + +build-user-static: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools --disable-system --static + MAKE_CHECK_ARGS: check-tcg + +# Because the hexagon cross-compiler takes so long to build we don't rely +# on the CI system to build it and hence this job has an optional dependency +# declared. The image is manually uploaded. +build-user-hexagon: + extends: .native_build_job_template + needs: + job: hexagon-cross-container + optional: true + variables: + IMAGE: debian-hexagon-cross + TARGETS: hexagon-linux-user + CONFIGURE_ARGS: --disable-tools --disable-docs --enable-debug-tcg + MAKE_CHECK_ARGS: check-tcg + +# Only build the softmmu targets we have check-tcg tests for +build-some-softmmu: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools --enable-debug + TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu + MAKE_CHECK_ARGS: check-tcg + +# We build tricore in a very minimal tricore only container +build-tricore-softmmu: + extends: .native_build_job_template + needs: + job: tricore-debian-cross-container + variables: + IMAGE: debian-tricore-cross + CONFIGURE_ARGS: --disable-tools --disable-fdt --enable-debug + TARGETS: tricore-softmmu + MAKE_CHECK_ARGS: check-tcg + +clang-system: + extends: .native_build_job_template + needs: + job: amd64-fedora-container + variables: + IMAGE: fedora + CONFIGURE_ARGS: --cc=clang --cxx=clang++ + --extra-cflags=-fsanitize=undefined --extra-cflags=-fno-sanitize-recover=undefined + TARGETS: alpha-softmmu arm-softmmu m68k-softmmu mips64-softmmu + ppc-softmmu s390x-softmmu + MAKE_CHECK_ARGS: check-qtest check-tcg + +clang-user: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --cc=clang --cxx=clang++ --disable-system + --target-list-exclude=microblazeel-linux-user,aarch64_be-linux-user,i386-linux-user,m68k-linux-user,mipsn32el-linux-user,xtensaeb-linux-user + --extra-cflags=-fsanitize=undefined --extra-cflags=-fno-sanitize-recover=undefined + MAKE_CHECK_ARGS: check-unit check-tcg + +# Set LD_JOBS=1 because this requires LTO and ld consumes a large amount of memory. +# On gitlab runners, default value sometimes end up calling 2 lds concurrently and +# triggers an Out-Of-Memory error +# +# Since slirp callbacks are used in QEMU Timers, slirp needs to be compiled together +# with QEMU and linked as a static library to avoid false positives in CFI checks. +# This can be accomplished by using -enable-slirp=git, which avoids the use of +# a system-wide version of the library +# +# Split in three sets of build/check/acceptance to limit the execution time of each +# job +build-cfi-aarch64: + extends: .native_build_job_template + needs: + - job: amd64-fedora-container + variables: + LD_JOBS: 1 + AR: llvm-ar + IMAGE: fedora + CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug + --enable-safe-stack --enable-slirp=git + TARGETS: aarch64-softmmu + MAKE_CHECK_ARGS: check-build + timeout: 70m + artifacts: + expire_in: 2 days + paths: + - build + rules: + # FIXME: This job is often failing, likely due to out-of-memory problems in + # the constrained containers of the shared runners. Thus this is marked as + # manual until the situation has been solved. + - when: manual + allow_failure: true + +check-cfi-aarch64: + extends: .native_test_job_template + needs: + - job: build-cfi-aarch64 + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check + +acceptance-cfi-aarch64: + extends: .acceptance_test_job_template + needs: + - job: build-cfi-aarch64 + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check-acceptance + +build-cfi-ppc64-s390x: + extends: .native_build_job_template + needs: + - job: amd64-fedora-container + variables: + LD_JOBS: 1 + AR: llvm-ar + IMAGE: fedora + CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug + --enable-safe-stack --enable-slirp=git + TARGETS: ppc64-softmmu s390x-softmmu + MAKE_CHECK_ARGS: check-build + timeout: 70m + artifacts: + expire_in: 2 days + paths: + - build + rules: + # FIXME: This job is often failing, likely due to out-of-memory problems in + # the constrained containers of the shared runners. Thus this is marked as + # manual until the situation has been solved. + - when: manual + allow_failure: true + +check-cfi-ppc64-s390x: + extends: .native_test_job_template + needs: + - job: build-cfi-ppc64-s390x + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check + +acceptance-cfi-ppc64-s390x: + extends: .acceptance_test_job_template + needs: + - job: build-cfi-ppc64-s390x + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check-acceptance + +build-cfi-x86_64: + extends: .native_build_job_template + needs: + - job: amd64-fedora-container + variables: + LD_JOBS: 1 + AR: llvm-ar + IMAGE: fedora + CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug + --enable-safe-stack --enable-slirp=git + TARGETS: x86_64-softmmu + MAKE_CHECK_ARGS: check-build + timeout: 70m + artifacts: + expire_in: 2 days + paths: + - build + +check-cfi-x86_64: + extends: .native_test_job_template + needs: + - job: build-cfi-x86_64 + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check + +acceptance-cfi-x86_64: + extends: .acceptance_test_job_template + needs: + - job: build-cfi-x86_64 + artifacts: true + variables: + IMAGE: fedora + MAKE_CHECK_ARGS: check-acceptance + +tsan-build: + extends: .native_build_job_template + needs: + job: amd64-ubuntu2004-container + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --enable-tsan --cc=clang-10 --cxx=clang++-10 + --enable-trace-backends=ust --enable-fdt=system --enable-slirp=system + TARGETS: x86_64-softmmu ppc64-softmmu riscv64-softmmu x86_64-linux-user + MAKE_CHECK_ARGS: bench V=1 + +# These targets are on the way out +build-deprecated: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + CONFIGURE_ARGS: --disable-tools + MAKE_CHECK_ARGS: build-tcg + TARGETS: ppc64abi32-linux-user + artifacts: + expire_in: 2 days + paths: + - build + +# We split the check-tcg step as test failures are expected but we still +# want to catch the build breaking. +check-deprecated: + extends: .native_test_job_template + needs: + - job: build-deprecated + artifacts: true + variables: + IMAGE: debian-all-test-cross + MAKE_CHECK_ARGS: check-tcg + allow_failure: true + +# gprof/gcov are GCC features +build-gprof-gcov: + extends: .native_build_job_template + needs: + job: amd64-ubuntu2004-container + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --enable-gprof --enable-gcov + TARGETS: aarch64-softmmu ppc64-softmmu s390x-softmmu x86_64-softmmu + artifacts: + expire_in: 1 days + paths: + - build + +check-gprof-gcov: + extends: .native_test_job_template + needs: + - job: build-gprof-gcov + artifacts: true + variables: + IMAGE: ubuntu2004 + MAKE_CHECK_ARGS: check + after_script: + - ${CI_PROJECT_DIR}/scripts/ci/coverage-summary.sh + +build-oss-fuzz: + extends: .native_build_job_template + needs: + job: amd64-fedora-container + variables: + IMAGE: fedora + script: + - mkdir build-oss-fuzz + - CC="clang" CXX="clang++" CFLAGS="-fsanitize=address" + ./scripts/oss-fuzz/build.sh + - export ASAN_OPTIONS="fast_unwind_on_malloc=0" + - for fuzzer in $(find ./build-oss-fuzz/DEST_DIR/ -executable -type f + | grep -v slirp); do + grep "LLVMFuzzerTestOneInput" ${fuzzer} > /dev/null 2>&1 || continue ; + echo Testing ${fuzzer} ... ; + "${fuzzer}" -runs=1 -seed=1 || exit 1 ; + done + # Unrelated to fuzzer: run some tests with -fsanitize=address + - cd build-oss-fuzz && make check-qtest-i386 check-unit + +build-tci: + extends: .native_build_job_template + needs: + job: amd64-debian-user-cross-container + variables: + IMAGE: debian-all-test-cross + script: + - TARGETS="aarch64 alpha arm hppa m68k microblaze ppc64 s390x x86_64" + - mkdir build + - cd build + - ../configure --enable-tcg-interpreter + --target-list="$(for tg in $TARGETS; do echo -n ${tg}'-softmmu '; done)" || { cat config.log meson-logs/meson-log.txt && exit 1; } + - make -j"$JOBS" + - make tests/qtest/boot-serial-test tests/qtest/cdrom-test tests/qtest/pxe-test + - for tg in $TARGETS ; do + export QTEST_QEMU_BINARY="./qemu-system-${tg}" ; + ./tests/qtest/boot-serial-test || exit 1 ; + ./tests/qtest/cdrom-test || exit 1 ; + done + - QTEST_QEMU_BINARY="./qemu-system-x86_64" ./tests/qtest/pxe-test + - QTEST_QEMU_BINARY="./qemu-system-s390x" ./tests/qtest/pxe-test -m slow + - make check-tcg + +# Alternate coroutines implementations are only really of interest to KVM users +# However we can't test against KVM on Gitlab-CI so we can only run unit tests +build-coroutine-sigaltstack: + extends: .native_build_job_template + needs: + job: amd64-ubuntu2004-container + variables: + IMAGE: ubuntu2004 + CONFIGURE_ARGS: --with-coroutine=sigaltstack --disable-tcg + --enable-trace-backends=ftrace + MAKE_CHECK_ARGS: check-unit + +# Check our reduced build configurations +build-without-default-devices: + extends: .native_build_job_template + needs: + job: amd64-centos8-container + variables: + IMAGE: centos8 + CONFIGURE_ARGS: --without-default-devices --disable-user + +build-without-default-features: + extends: .native_build_job_template + needs: + job: amd64-debian-container + variables: + IMAGE: debian-amd64 + CONFIGURE_ARGS: --without-default-features --disable-user + --target-list-exclude=arm-softmmu,i386-softmmu,mipsel-softmmu,mips64-softmmu,ppc-softmmu + MAKE_CHECK_ARGS: check-unit + +build-libvhost-user: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/fedora:latest + needs: + job: amd64-fedora-container + before_script: + - dnf install -y meson ninja-build + script: + - mkdir subprojects/libvhost-user/build + - cd subprojects/libvhost-user/build + - meson + - ninja + +# No targets are built here, just tools, docs, and unit tests. This +# also feeds into the eventual documentation deployment steps later +build-tools-and-docs-debian: + extends: .native_build_job_template + needs: + job: amd64-debian-container + variables: + IMAGE: debian-amd64 + MAKE_CHECK_ARGS: check-unit check-softfloat ctags TAGS cscope + CONFIGURE_ARGS: --disable-system --disable-user --enable-docs --enable-tools + artifacts: + expire_in: 2 days + paths: + - build + +# Prepare for GitLab pages deployment. Anything copied into the +# "public" directory will be deployed to $USER.gitlab.io/$PROJECT +# +# GitLab publishes from any branch that triggers a CI pipeline +# +# For the main repo we don't want to publish from 'staging' +# since that content may not be pushed, nor do we wish to +# publish from 'stable-NNN' branches as that content is outdated. +# Thus we restrict to just the default branch +# +# For contributor forks we want to publish from any repo so +# that users can see the results of their commits, regardless +# of what topic branch they're currently using +pages: + image: $CI_REGISTRY_IMAGE/qemu/debian-amd64:latest + stage: test + needs: + - job: build-tools-and-docs-debian + script: + - mkdir -p public + # HTML-ised source tree + - make gtags + - htags -anT --tree-view=filetree -m qemu_init + -t "Welcome to the QEMU sourcecode" + - mv HTML public/src + # Project documentation + - make -C build install DESTDIR=$(pwd)/temp-install + - mv temp-install/usr/local/share/doc/qemu/* public/ + artifacts: + paths: + - public + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH' + when: on_success + - if: '$CI_PROJECT_NAMESPACE == "qemu-project"' + when: never + - if: '$CI_PROJECT_NAMESPACE != "qemu-project"' + when: on_success diff --git a/.gitlab-ci.d/cirrus.yml b/.gitlab-ci.d/cirrus.yml new file mode 100644 index 0000000000..675db69622 --- /dev/null +++ b/.gitlab-ci.d/cirrus.yml @@ -0,0 +1,87 @@ +# Jobs that we delegate to Cirrus CI because they require an operating +# system other than Linux. These jobs will only run if the required +# setup has been performed on the GitLab account. +# +# The Cirrus CI configuration is generated by replacing target-specific +# variables in a generic template: some of these variables are provided +# when the GitLab CI job is defined, others are taken from a shell +# snippet generated using lcitool. +# +# Note that the $PATH environment variable has to be treated with +# special care, because we can't just override it at the GitLab CI job +# definition level or we risk breaking it completely. +.cirrus_build_job: + stage: build + image: registry.gitlab.com/libvirt/libvirt-ci/cirrus-run:master + needs: [] + allow_failure: true + script: + - source .gitlab-ci.d/cirrus/$NAME.vars + - sed -e "s|[@]CI_REPOSITORY_URL@|$CI_REPOSITORY_URL|g" + -e "s|[@]CI_COMMIT_REF_NAME@|$CI_COMMIT_REF_NAME|g" + -e "s|[@]CI_COMMIT_SHA@|$CI_COMMIT_SHA|g" + -e "s|[@]CIRRUS_VM_INSTANCE_TYPE@|$CIRRUS_VM_INSTANCE_TYPE|g" + -e "s|[@]CIRRUS_VM_IMAGE_SELECTOR@|$CIRRUS_VM_IMAGE_SELECTOR|g" + -e "s|[@]CIRRUS_VM_IMAGE_NAME@|$CIRRUS_VM_IMAGE_NAME|g" + -e "s|[@]CIRRUS_VM_CPUS@|$CIRRUS_VM_CPUS|g" + -e "s|[@]CIRRUS_VM_RAM@|$CIRRUS_VM_RAM|g" + -e "s|[@]UPDATE_COMMAND@|$UPDATE_COMMAND|g" + -e "s|[@]INSTALL_COMMAND@|$INSTALL_COMMAND|g" + -e "s|[@]PATH@|$PATH_EXTRA${PATH_EXTRA:+:}\$PATH|g" + -e "s|[@]PKG_CONFIG_PATH@|$PKG_CONFIG_PATH|g" + -e "s|[@]PKGS@|$PKGS|g" + -e "s|[@]MAKE@|$MAKE|g" + -e "s|[@]PYTHON@|$PYTHON|g" + -e "s|[@]PIP3@|$PIP3|g" + -e "s|[@]PYPI_PKGS@|$PYPI_PKGS|g" + -e "s|[@]CONFIGURE_ARGS@|$CONFIGURE_ARGS|g" + -e "s|[@]TEST_TARGETSS@|$TEST_TARGETSS|g" + <.gitlab-ci.d/cirrus/build.yml >.gitlab-ci.d/cirrus/$NAME.yml + - cat .gitlab-ci.d/cirrus/$NAME.yml + - cirrus-run -v --show-build-log always .gitlab-ci.d/cirrus/$NAME.yml + rules: + - if: "$CIRRUS_GITHUB_REPO && $CIRRUS_API_TOKEN" + +x64-freebsd-12-build: + extends: .cirrus_build_job + variables: + NAME: freebsd-12 + CIRRUS_VM_INSTANCE_TYPE: freebsd_instance + CIRRUS_VM_IMAGE_SELECTOR: image_family + CIRRUS_VM_IMAGE_NAME: freebsd-12-2 + CIRRUS_VM_CPUS: 8 + CIRRUS_VM_RAM: 8G + UPDATE_COMMAND: pkg update + INSTALL_COMMAND: pkg install -y + # TODO: Enable gnutls again once FreeBSD's libtasn1 got fixed + # See: https://gitlab.com/gnutls/libtasn1/-/merge_requests/71 + CONFIGURE_ARGS: --disable-gnutls + TEST_TARGETS: check + +x64-freebsd-13-build: + extends: .cirrus_build_job + variables: + NAME: freebsd-13 + CIRRUS_VM_INSTANCE_TYPE: freebsd_instance + CIRRUS_VM_IMAGE_SELECTOR: image_family + CIRRUS_VM_IMAGE_NAME: freebsd-13-0 + CIRRUS_VM_CPUS: 8 + CIRRUS_VM_RAM: 8G + UPDATE_COMMAND: pkg update + INSTALL_COMMAND: pkg install -y + TEST_TARGETS: check + +x64-macos-11-base-build: + extends: .cirrus_build_job + variables: + NAME: macos-11 + CIRRUS_VM_INSTANCE_TYPE: osx_instance + CIRRUS_VM_IMAGE_SELECTOR: image + CIRRUS_VM_IMAGE_NAME: big-sur-base + CIRRUS_VM_CPUS: 12 + CIRRUS_VM_RAM: 24G + UPDATE_COMMAND: brew update + INSTALL_COMMAND: brew install + PATH_EXTRA: /usr/local/opt/ccache/libexec:/usr/local/opt/gettext/bin + PKG_CONFIG_PATH: /usr/local/opt/curl/lib/pkgconfig:/usr/local/opt/ncurses/lib/pkgconfig:/usr/local/opt/readline/lib/pkgconfig + TEST_TARGETS: check-unit check-block check-qapi-schema check-softfloat check-qtest-x86_64 diff --git a/.gitlab-ci.d/cirrus/README.rst b/.gitlab-ci.d/cirrus/README.rst new file mode 100644 index 0000000000..657b0706d7 --- /dev/null +++ b/.gitlab-ci.d/cirrus/README.rst @@ -0,0 +1,54 @@ +Cirrus CI integration +===================== + +GitLab CI shared runners only provide a docker environment running on Linux. +While it is possible to provide private runners for non-Linux platforms this +is not something most contributors/maintainers will wish to do. + +To work around this limitation, we take advantage of `Cirrus CI`_'s free +offering: more specifically, we use the `cirrus-run`_ script to trigger Cirrus +CI jobs from GitLab CI jobs so that Cirrus CI job output is integrated into +the main GitLab CI pipeline dashboard. + +There is, however, some one-time setup required. If you want FreeBSD and macOS +builds to happen when you push to your GitLab repository, you need to + +* set up a GitHub repository for the project, eg. ``yourusername/qemu``. + This repository needs to exist for cirrus-run to work, but it doesn't need to + be kept up to date, so you can create it and then forget about it; + +* enable the `Cirrus CI GitHub app`_ for your GitHub account; + +* sign up for Cirrus CI. It's enough to log into the website using your GitHub + account; + +* grab an API token from the `Cirrus CI settings`_ page; + +* it may be necessary to push an empty ``.cirrus.yml`` file to your github fork + for Cirrus CI to properly recognize the project. You can check whether + Cirrus CI knows about your project by navigating to: + + ``https://cirrus-ci.com/yourusername/qemu`` + +* in the *CI/CD / Variables* section of the settings page for your GitLab + repository, create two new variables: + + * ``CIRRUS_GITHUB_REPO``, containing the name of the GitHub repository + created earlier, eg. ``yourusername/qemu``; + + * ``CIRRUS_API_TOKEN``, containing the Cirrus CI API token generated earlier. + This variable **must** be marked as *Masked*, because anyone with knowledge + of it can impersonate you as far as Cirrus CI is concerned. + + Neither of these variables should be marked as *Protected*, because in + general you'll want to be able to trigger Cirrus CI builds from non-protected + branches. + +Once this one-time setup is complete, you can just keep pushing to your GitLab +repository as usual and you'll automatically get the additional CI coverage. + + +.. _Cirrus CI GitHub app: https://github.com/marketplace/cirrus-ci +.. _Cirrus CI settings: https://cirrus-ci.com/settings/profile/ +.. _Cirrus CI: https://cirrus-ci.com/ +.. _cirrus-run: https://github.com/sio/cirrus-run/ diff --git a/.gitlab-ci.d/cirrus/build.yml b/.gitlab-ci.d/cirrus/build.yml new file mode 100644 index 0000000000..857bdc5536 --- /dev/null +++ b/.gitlab-ci.d/cirrus/build.yml @@ -0,0 +1,35 @@ +@CIRRUS_VM_INSTANCE_TYPE@: + @CIRRUS_VM_IMAGE_SELECTOR@: @CIRRUS_VM_IMAGE_NAME@ + cpu: @CIRRUS_VM_CPUS@ + memory: @CIRRUS_VM_RAM@ + +env: + CIRRUS_CLONE_DEPTH: 1 + CI_REPOSITORY_URL: "@CI_REPOSITORY_URL@" + CI_COMMIT_REF_NAME: "@CI_COMMIT_REF_NAME@" + CI_COMMIT_SHA: "@CI_COMMIT_SHA@" + PATH: "@PATH@" + PKG_CONFIG_PATH: "@PKG_CONFIG_PATH@" + PYTHON: "@PYTHON@" + MAKE: "@MAKE@" + CONFIGURE_ARGS: "@CONFIGURE_ARGS@" + +build_task: + install_script: + - @UPDATE_COMMAND@ + - @INSTALL_COMMAND@ @PKGS@ + - if test -n "@PYPI_PKGS@" ; then @PIP3@ install @PYPI_PKGS@ ; fi + clone_script: + - git clone --depth 100 "$CI_REPOSITORY_URL" . + - git fetch origin "$CI_COMMIT_REF_NAME" + - git reset --hard "$CI_COMMIT_SHA" + build_script: + - mkdir build + - cd build + - ../configure --enable-werror $CONFIGURE_ARGS + || { cat config.log meson-logs/meson-log.txt; exit 1; } + - $MAKE -j$(sysctl -n hw.ncpu) + - for TARGET in $TEST_TARGETS ; + do + $MAKE -j$(sysctl -n hw.ncpu) $TARGET V=1 ; + done diff --git a/.gitlab-ci.d/cirrus/freebsd-12.vars b/.gitlab-ci.d/cirrus/freebsd-12.vars new file mode 100644 index 0000000000..2099b21354 --- /dev/null +++ b/.gitlab-ci.d/cirrus/freebsd-12.vars @@ -0,0 +1,13 @@ +# THIS FILE WAS AUTO-GENERATED +# +# $ lcitool variables freebsd-12 qemu +# +# https://gitlab.com/libvirt/libvirt-ci/-/commit/c7e275ab27ac0dcd09da290817b9adeea1fd1eb1 + +PACKAGING_COMMAND='pkg' +CCACHE='/usr/local/bin/ccache' +MAKE='/usr/local/bin/gmake' +NINJA='/usr/local/bin/ninja' +PYTHON='/usr/local/bin/python3' +PIP3='/usr/local/bin/pip-3.8' +PKGS='alsa-lib bash bzip2 ca_root_nss capstone4 ccache cdrkit-genisoimage ctags curl cyrus-sasl dbus diffutils gettext git glib gmake gnutls gsed gtk3 libepoxy libffi libgcrypt libjpeg-turbo libnfs libspice-server libssh libtasn1 libxml2 llvm lttng-ust lzo2 meson ncurses nettle ninja opencv p5-Test-Harness perl5 pixman pkgconf png py38-numpy py38-pillow py38-pip py38-sphinx py38-sphinx_rtd_theme py38-virtualenv py38-yaml python3 rpm2cpio sdl2 sdl2_image snappy spice-protocol tesseract texinfo usbredir virglrenderer vte3 zstd' diff --git a/.gitlab-ci.d/cirrus/freebsd-13.vars b/.gitlab-ci.d/cirrus/freebsd-13.vars new file mode 100644 index 0000000000..323fe806d5 --- /dev/null +++ b/.gitlab-ci.d/cirrus/freebsd-13.vars @@ -0,0 +1,13 @@ +# THIS FILE WAS AUTO-GENERATED +# +# $ lcitool variables freebsd-13 qemu +# +# https://gitlab.com/libvirt/libvirt-ci/-/commit/c7e275ab27ac0dcd09da290817b9adeea1fd1eb1 + +PACKAGING_COMMAND='pkg' +CCACHE='/usr/local/bin/ccache' +MAKE='/usr/local/bin/gmake' +NINJA='/usr/local/bin/ninja' +PYTHON='/usr/local/bin/python3' +PIP3='/usr/local/bin/pip-3.8' +PKGS='alsa-lib bash bzip2 ca_root_nss capstone4 ccache cdrkit-genisoimage ctags curl cyrus-sasl dbus diffutils gettext git glib gmake gnutls gsed gtk3 libepoxy libffi libgcrypt libjpeg-turbo libnfs libspice-server libssh libtasn1 libxml2 llvm lttng-ust lzo2 meson ncurses nettle ninja opencv p5-Test-Harness perl5 pixman pkgconf png py38-numpy py38-pillow py38-pip py38-sphinx py38-sphinx_rtd_theme py38-virtualenv py38-yaml python3 rpm2cpio sdl2 sdl2_image snappy spice-protocol tesseract texinfo usbredir virglrenderer vte3 zstd' diff --git a/.gitlab-ci.d/cirrus/macos-11.vars b/.gitlab-ci.d/cirrus/macos-11.vars new file mode 100644 index 0000000000..cbec8a44a3 --- /dev/null +++ b/.gitlab-ci.d/cirrus/macos-11.vars @@ -0,0 +1,15 @@ +# THIS FILE WAS AUTO-GENERATED +# +# $ lcitool variables macos-11 qemu +# +# https://gitlab.com/libvirt/libvirt-ci/-/commit/c7e275ab27ac0dcd09da290817b9adeea1fd1eb1 + +PACKAGING_COMMAND='brew' +CCACHE='/usr/local/bin/ccache' +MAKE='/usr/local/bin/gmake' +NINJA='/usr/local/bin/ninja' +PYTHON='/usr/local/bin/python3' +PIP3='/usr/local/bin/pip3' +PKGS='bash bc bzip2 capstone ccache cpanminus ctags curl dbus diffutils gcovr gettext git glib gnu-sed gnutls gtk+3 jemalloc jpeg-turbo libepoxy libffi libgcrypt libiscsi libnfs libpng libslirp libssh libtasn1 libusb libxml2 llvm lzo make meson ncurses nettle ninja perl pixman pkg-config python3 rpm2cpio sdl2 sdl2_image snappy sparse spice-protocol tesseract texinfo usbredir vde vte3 zlib zstd' +PYPI_PKGS='PyYAML numpy pillow sphinx sphinx-rtd-theme virtualenv' +CPAN_PKGS='Test::Harness' diff --git a/.gitlab-ci.d/container-core.yml b/.gitlab-ci.d/container-core.yml new file mode 100644 index 0000000000..e8dd1f476a --- /dev/null +++ b/.gitlab-ci.d/container-core.yml @@ -0,0 +1,17 @@ +include: + - local: '/.gitlab-ci.d/container-template.yml' + +amd64-centos8-container: + extends: .container_job_template + variables: + NAME: centos8 + +amd64-fedora-container: + extends: .container_job_template + variables: + NAME: fedora + +amd64-debian10-container: + extends: .container_job_template + variables: + NAME: debian10 diff --git a/.gitlab-ci.d/container-cross.yml b/.gitlab-ci.d/container-cross.yml new file mode 100644 index 0000000000..0fcebe363a --- /dev/null +++ b/.gitlab-ci.d/container-cross.yml @@ -0,0 +1,192 @@ +alpha-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-alpha-cross + +amd64-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-amd64-cross + +amd64-debian-user-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-all-test-cross + +arm64-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-arm64-cross + +arm64-test-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian11-container'] + variables: + NAME: debian-arm64-test-cross + +armel-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-armel-cross + +armhf-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-armhf-cross + +# We never want to build hexagon in the CI system and by default we +# always want to refer to the master registry where it lives. +hexagon-cross-container: + image: docker:stable + stage: containers + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project"' + when: never + - when: always + variables: + NAME: debian-hexagon-cross + GIT_DEPTH: 1 + services: + - docker:dind + before_script: + - export TAG="$CI_REGISTRY_IMAGE/qemu/$NAME:latest" + - export COMMON_TAG="$CI_REGISTRY/qemu-project/qemu/qemu/$NAME:latest" + - docker info + - docker login $CI_REGISTRY -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD" + script: + - echo "TAG:$TAG" + - echo "COMMON_TAG:$COMMON_TAG" + - docker pull $COMMON_TAG + - docker tag $COMMON_TAG $TAG + - docker push "$TAG" + after_script: + - docker logout + +hppa-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-hppa-cross + +m68k-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-m68k-cross + +mips64-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-mips64-cross + +mips64el-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-mips64el-cross + +mips-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-mips-cross + +mipsel-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-mipsel-cross + +powerpc-test-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian11-container'] + variables: + NAME: debian-powerpc-test-cross + +ppc64el-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-ppc64el-cross + +riscv64-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-riscv64-cross + +s390x-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-s390x-cross + +sh4-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-sh4-cross + +sparc64-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-sparc64-cross + +tricore-debian-cross-container: + extends: .container_job_template + stage: containers-layer2 + needs: ['amd64-debian10-container'] + variables: + NAME: debian-tricore-cross + +xtensa-debian-cross-container: + extends: .container_job_template + variables: + NAME: debian-xtensa-cross + +cris-fedora-cross-container: + extends: .container_job_template + variables: + NAME: fedora-cris-cross + +i386-fedora-cross-container: + extends: .container_job_template + variables: + NAME: fedora-i386-cross + +win32-fedora-cross-container: + extends: .container_job_template + variables: + NAME: fedora-win32-cross + +win64-fedora-cross-container: + extends: .container_job_template + variables: + NAME: fedora-win64-cross diff --git a/.gitlab-ci.d/container-template.yml b/.gitlab-ci.d/container-template.yml new file mode 100644 index 0000000000..1baecd9460 --- /dev/null +++ b/.gitlab-ci.d/container-template.yml @@ -0,0 +1,21 @@ +.container_job_template: + image: docker:stable + stage: containers + services: + - docker:dind + before_script: + - export TAG="$CI_REGISTRY_IMAGE/qemu/$NAME:latest" + - export COMMON_TAG="$CI_REGISTRY/qemu-project/qemu/$NAME:latest" + - apk add python3 + - docker info + - docker login $CI_REGISTRY -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD" + script: + - echo "TAG:$TAG" + - echo "COMMON_TAG:$COMMON_TAG" + - ./tests/docker/docker.py --engine docker build + -t "qemu/$NAME" -f "tests/docker/dockerfiles/$NAME.docker" + -r $CI_REGISTRY/qemu-project/qemu + - docker tag "qemu/$NAME" "$TAG" + - docker push "$TAG" + after_script: + - docker logout diff --git a/.gitlab-ci.d/containers.yml b/.gitlab-ci.d/containers.yml index 33e4046e23..cd06d3f5f4 100644 --- a/.gitlab-ci.d/containers.yml +++ b/.gitlab-ci.d/containers.yml @@ -1,251 +1,45 @@ -.container_job_template: &container_job_definition - image: docker:stable - stage: containers - services: - - docker:dind - before_script: - - export TAG="$CI_REGISTRY_IMAGE/qemu/$NAME:latest" - - export COMMON_TAG="$CI_REGISTRY/qemu-project/qemu/$NAME:latest" - - apk add python3 - - docker info - - docker login $CI_REGISTRY -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD" - script: - - echo "TAG:$TAG" - - echo "COMMON_TAG:$COMMON_TAG" - - docker pull "$TAG" || docker pull "$COMMON_TAG" || true - - ./tests/docker/docker.py --engine docker build - -t "qemu/$NAME" -f "tests/docker/dockerfiles/$NAME.docker" - -r $CI_REGISTRY_IMAGE - - docker tag "qemu/$NAME" "$TAG" - - docker push "$TAG" - after_script: - - docker logout +include: + - local: '/.gitlab-ci.d/container-core.yml' + - local: '/.gitlab-ci.d/container-cross.yml' amd64-alpine-container: - <<: *container_job_definition + extends: .container_job_template variables: NAME: alpine -amd64-centos7-container: - <<: *container_job_definition - variables: - NAME: centos7 - -amd64-centos8-container: - <<: *container_job_definition - variables: - NAME: centos8 - -amd64-debian10-container: - <<: *container_job_definition - variables: - NAME: debian10 - amd64-debian11-container: - <<: *container_job_definition + extends: .container_job_template variables: NAME: debian11 -alpha-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-alpha-cross - -amd64-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-amd64-cross - -amd64-debian-user-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-all-test-cross - amd64-debian-container: - <<: *container_job_definition + extends: .container_job_template stage: containers-layer2 needs: ['amd64-debian10-container'] variables: NAME: debian-amd64 -arm64-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-arm64-cross - -arm64-test-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian11-container'] - variables: - NAME: debian-arm64-test-cross - -armel-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-armel-cross - -armhf-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-armhf-cross - -hppa-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-hppa-cross - -m68k-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-m68k-cross - -mips64-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-mips64-cross - -mips64el-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-mips64el-cross - -mips-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-mips-cross - -mipsel-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-mipsel-cross - -powerpc-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-powerpc-cross - -ppc64-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-ppc64-cross - -ppc64el-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-ppc64el-cross - -riscv64-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-riscv64-cross - -s390x-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-s390x-cross - -sh4-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-sh4-cross - -sparc64-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-sparc64-cross - -tricore-debian-cross-container: - <<: *container_job_definition - stage: containers-layer2 - needs: ['amd64-debian10-container'] - variables: - NAME: debian-tricore-cross - -xtensa-debian-cross-container: - <<: *container_job_definition - variables: - NAME: debian-xtensa-cross - -cris-fedora-cross-container: - <<: *container_job_definition - variables: - NAME: fedora-cris-cross - -amd64-fedora-container: - <<: *container_job_definition - variables: - NAME: fedora - -i386-fedora-cross-container: - <<: *container_job_definition - variables: - NAME: fedora-i386-cross - -win32-fedora-cross-container: - <<: *container_job_definition - variables: - NAME: fedora-win32-cross - -win64-fedora-cross-container: - <<: *container_job_definition - variables: - NAME: fedora-win64-cross - amd64-ubuntu1804-container: - <<: *container_job_definition + extends: .container_job_template variables: NAME: ubuntu1804 amd64-ubuntu2004-container: - <<: *container_job_definition + extends: .container_job_template variables: NAME: ubuntu2004 amd64-ubuntu-container: - <<: *container_job_definition + extends: .container_job_template variables: NAME: ubuntu amd64-opensuse-leap-container: - <<: *container_job_definition + extends: .container_job_template variables: NAME: opensuse-leap + +python-container: + extends: .container_job_template + variables: + NAME: python diff --git a/.gitlab-ci.d/crossbuild-template.yml b/.gitlab-ci.d/crossbuild-template.yml new file mode 100644 index 0000000000..10d22dcf6c --- /dev/null +++ b/.gitlab-ci.d/crossbuild-template.yml @@ -0,0 +1,47 @@ +.cross_system_build_job: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest + timeout: 80m + script: + - mkdir build + - cd build + - PKG_CONFIG_PATH=$PKG_CONFIG_PATH + ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS + --disable-user --target-list-exclude="arm-softmmu cris-softmmu + i386-softmmu microblaze-softmmu mips-softmmu mipsel-softmmu + mips64-softmmu ppc-softmmu riscv32-softmmu sh4-softmmu + sparc-softmmu xtensa-softmmu $CROSS_SKIP_TARGETS" + - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS + - if grep -q "EXESUF=.exe" config-host.mak; + then make installer; + version="$(git describe --match v[0-9]*)"; + mv -v qemu-setup*.exe qemu-setup-${version}.exe; + fi + +# Job to cross-build specific accelerators. +# +# Set the $ACCEL variable to select the specific accelerator (default to +# KVM), and set extra options (such disabling other accelerators) via the +# $EXTRA_CONFIGURE_OPTS variable. +.cross_accel_build_job: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest + timeout: 30m + script: + - mkdir build + - cd build + - PKG_CONFIG_PATH=$PKG_CONFIG_PATH + ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS + --disable-tools --enable-${ACCEL:-kvm} $EXTRA_CONFIGURE_OPTS + - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS + +.cross_user_build_job: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest + script: + - mkdir build + - cd build + - PKG_CONFIG_PATH=$PKG_CONFIG_PATH + ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS + --disable-system + - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS diff --git a/.gitlab-ci.d/crossbuilds.yml b/.gitlab-ci.d/crossbuilds.yml index 2d95784ed5..f10168db2e 100644 --- a/.gitlab-ci.d/crossbuilds.yml +++ b/.gitlab-ci.d/crossbuilds.yml @@ -1,44 +1,5 @@ -.cross_system_build_job: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest - timeout: 80m - script: - - mkdir build - - cd build - - PKG_CONFIG_PATH=$PKG_CONFIG_PATH - ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS - --disable-user --target-list-exclude="arm-softmmu cris-softmmu - i386-softmmu microblaze-softmmu mips-softmmu mipsel-softmmu - mips64-softmmu ppc-softmmu sh4-softmmu xtensa-softmmu" - - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS - -# Job to cross-build specific accelerators. -# -# Set the $ACCEL variable to select the specific accelerator (default to -# KVM), and set extra options (such disabling other accelerators) via the -# $ACCEL_CONFIGURE_OPTS variable. -.cross_accel_build_job: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest - timeout: 30m - script: - - mkdir build - - cd build - - PKG_CONFIG_PATH=$PKG_CONFIG_PATH - ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS - --disable-tools --enable-${ACCEL:-kvm} $ACCEL_CONFIGURE_OPTS - - make -j$(expr $(nproc) + 1) all check-build - -.cross_user_build_job: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest - script: - - mkdir build - - cd build - - PKG_CONFIG_PATH=$PKG_CONFIG_PATH - ../configure --enable-werror --disable-docs $QEMU_CONFIGURE_OPTS - --disable-system - - make -j$(expr $(nproc) + 1) all check-build $MAKE_CHECK_ARGS +include: + - local: '/.gitlab-ci.d/crossbuild-template.yml' cross-armel-system: extends: .cross_system_build_job @@ -98,6 +59,15 @@ cross-i386-user: IMAGE: fedora-i386-cross MAKE_CHECK_ARGS: check +cross-i386-tci: + extends: .cross_accel_build_job + timeout: 60m + variables: + IMAGE: fedora-i386-cross + ACCEL: tcg-interpreter + EXTRA_CONFIGURE_OPTS: --target-list=i386-softmmu,i386-linux-user,aarch64-softmmu,aarch64-linux-user,ppc-softmmu,ppc-linux-user + MAKE_CHECK_ARGS: check check-tcg + cross-mips-system: extends: .cross_system_build_job needs: @@ -174,7 +144,15 @@ cross-s390x-kvm-only: job: s390x-debian-cross-container variables: IMAGE: debian-s390x-cross - ACCEL_CONFIGURE_OPTS: --disable-tcg + EXTRA_CONFIGURE_OPTS: --disable-tcg + +cross-mips64el-kvm-only: + extends: .cross_accel_build_job + needs: + job: mips64el-debian-cross-container + variables: + IMAGE: debian-mips64el-cross + EXTRA_CONFIGURE_OPTS: --disable-tcg --target-list=mips64el-softmmu cross-win32-system: extends: .cross_system_build_job @@ -182,6 +160,11 @@ cross-win32-system: job: win32-fedora-cross-container variables: IMAGE: fedora-win32-cross + CROSS_SKIP_TARGETS: alpha-softmmu avr-softmmu hppa-softmmu m68k-softmmu + microblazeel-softmmu mips64el-softmmu nios2-softmmu + artifacts: + paths: + - build/qemu-setup*.exe cross-win64-system: extends: .cross_system_build_job @@ -189,6 +172,11 @@ cross-win64-system: job: win64-fedora-cross-container variables: IMAGE: fedora-win64-cross + CROSS_SKIP_TARGETS: or1k-softmmu rx-softmmu sh4eb-softmmu sparc64-softmmu + tricore-softmmu xtensaeb-softmmu + artifacts: + paths: + - build/qemu-setup*.exe cross-amd64-xen-only: extends: .cross_accel_build_job @@ -197,7 +185,7 @@ cross-amd64-xen-only: variables: IMAGE: debian-amd64-cross ACCEL: xen - ACCEL_CONFIGURE_OPTS: --disable-tcg --disable-kvm + EXTRA_CONFIGURE_OPTS: --disable-tcg --disable-kvm cross-arm64-xen-only: extends: .cross_accel_build_job @@ -206,4 +194,4 @@ cross-arm64-xen-only: variables: IMAGE: debian-arm64-cross ACCEL: xen - ACCEL_CONFIGURE_OPTS: --disable-tcg --disable-kvm + EXTRA_CONFIGURE_OPTS: --disable-tcg --disable-kvm diff --git a/.gitlab-ci.d/custom-runners.yml b/.gitlab-ci.d/custom-runners.yml new file mode 100644 index 0000000000..564b94565d --- /dev/null +++ b/.gitlab-ci.d/custom-runners.yml @@ -0,0 +1,238 @@ +# The CI jobs defined here require GitLab runners installed and +# registered on machines that match their operating system names, +# versions and architectures. This is in contrast to the other CI +# jobs that are intended to run on GitLab's "shared" runners. + +# Different than the default approach on "shared" runners, based on +# containers, the custom runners have no such *requirement*, as those +# jobs should be capable of running on operating systems with no +# compatible container implementation, or no support from +# gitlab-runner. To avoid problems that gitlab-runner can cause while +# reusing the GIT repository, let's enable the clone strategy, which +# guarantees a fresh repository on each job run. +variables: + GIT_STRATEGY: clone + +# All ubuntu-18.04 jobs should run successfully in an environment +# setup by the scripts/ci/setup/build-environment.yml task +# "Install basic packages to build QEMU on Ubuntu 18.04/20.04" +ubuntu-18.04-s390x-all-linux-static: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_18.04 + - s390x + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + - if: "$S390X_RUNNER_AVAILABLE" + script: + # --disable-libssh is needed because of https://bugs.launchpad.net/qemu/+bug/1838763 + # --disable-glusterfs is needed because there's no static version of those libs in distro supplied packages + - mkdir build + - cd build + - ../configure --enable-debug --static --disable-system --disable-glusterfs --disable-libssh + - make --output-sync -j`nproc` + - make --output-sync -j`nproc` check V=1 + - make --output-sync -j`nproc` check-tcg V=1 + +ubuntu-18.04-s390x-all: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_18.04 + - s390x + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + - if: "$S390X_RUNNER_AVAILABLE" + script: + - mkdir build + - cd build + - ../configure --disable-libssh + - make --output-sync -j`nproc` + - make --output-sync -j`nproc` check V=1 + +ubuntu-18.04-s390x-alldbg: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_18.04 + - s390x + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + - if: "$S390X_RUNNER_AVAILABLE" + script: + - mkdir build + - cd build + - ../configure --enable-debug --disable-libssh + - make clean + - make --output-sync -j`nproc` + - make --output-sync -j`nproc` check V=1 + +ubuntu-18.04-s390x-clang: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_18.04 + - s390x + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + when: manual + - if: "$S390X_RUNNER_AVAILABLE" + when: manual + script: + - mkdir build + - cd build + - ../configure --disable-libssh --cc=clang --cxx=clang++ --enable-sanitizers + - make --output-sync -j`nproc` + - make --output-sync -j`nproc` check V=1 + +ubuntu-18.04-s390x-tci: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_18.04 + - s390x + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + - if: "$S390X_RUNNER_AVAILABLE" + script: + - mkdir build + - cd build + - ../configure --disable-libssh --enable-tcg-interpreter + - make --output-sync -j`nproc` + +ubuntu-18.04-s390x-notcg: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_18.04 + - s390x + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + when: manual + - if: "$S390X_RUNNER_AVAILABLE" + when: manual + script: + - mkdir build + - cd build + - ../configure --disable-libssh --disable-tcg + - make --output-sync -j`nproc` + - make --output-sync -j`nproc` check V=1 + +# All ubuntu-20.04 jobs should run successfully in an environment +# setup by the scripts/ci/setup/qemu/build-environment.yml task +# "Install basic packages to build QEMU on Ubuntu 18.04/20.04" +ubuntu-20.04-aarch64-all-linux-static: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_20.04 + - aarch64 + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + - if: "$S390X_RUNNER_AVAILABLE" + script: + # --disable-libssh is needed because of https://bugs.launchpad.net/qemu/+bug/1838763 + # --disable-glusterfs is needed because there's no static version of those libs in distro supplied packages + - mkdir build + - cd build + - ../configure --enable-debug --static --disable-system --disable-glusterfs --disable-libssh + - make --output-sync -j`nproc` + - make --output-sync -j`nproc` check V=1 + - make --output-sync -j`nproc` check-tcg V=1 + +ubuntu-20.04-aarch64-all: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_20.04 + - aarch64 + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + - if: "$S390X_RUNNER_AVAILABLE" + script: + - mkdir build + - cd build + - ../configure --disable-libssh + - make --output-sync -j`nproc` + - make --output-sync -j`nproc` check V=1 + +ubuntu-20.04-aarch64-alldbg: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_20.04 + - aarch64 + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + - if: "$S390X_RUNNER_AVAILABLE" + script: + - mkdir build + - cd build + - ../configure --enable-debug --disable-libssh + - make clean + - make --output-sync -j`nproc` + - make --output-sync -j`nproc` check V=1 + +ubuntu-20.04-aarch64-clang: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_20.04 + - aarch64 + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + when: manual + - if: "$S390X_RUNNER_AVAILABLE" + when: manual + script: + - mkdir build + - cd build + - ../configure --disable-libssh --cc=clang-10 --cxx=clang++-10 --enable-sanitizers + - make --output-sync -j`nproc` + - make --output-sync -j`nproc` check V=1 + +ubuntu-20.04-aarch64-tci: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_20.04 + - aarch64 + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + - if: "$S390X_RUNNER_AVAILABLE" + script: + - mkdir build + - cd build + - ../configure --disable-libssh --enable-tcg-interpreter + - make --output-sync -j`nproc` + +ubuntu-20.04-aarch64-notcg: + allow_failure: true + needs: [] + stage: build + tags: + - ubuntu_20.04 + - aarch64 + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' + when: manual + - if: "$S390X_RUNNER_AVAILABLE" + when: manual + script: + - mkdir build + - cd build + - ../configure --disable-libssh --disable-tcg + - make --output-sync -j`nproc` + - make --output-sync -j`nproc` check V=1 diff --git a/.gitlab-ci.d/edk2.yml b/.gitlab-ci.d/edk2.yml index ba7280605c..62497ba47f 100644 --- a/.gitlab-ci.d/edk2.yml +++ b/.gitlab-ci.d/edk2.yml @@ -1,10 +1,22 @@ -docker-edk2: - stage: containers - rules: # Only run this job when the Dockerfile is modified +# All jobs needing docker-edk2 must use the same rules it uses. +.edk2_job_rules: + rules: # Only run this job when ... - changes: + # this file is modified - .gitlab-ci.d/edk2.yml + # or the Dockerfile is modified - .gitlab-ci.d/edk2/Dockerfile - when: always + # or roms/edk2/ is modified (submodule updated) + - roms/edk2/* + when: on_success + - if: '$CI_COMMIT_REF_NAME =~ /^edk2/' # or the branch/tag starts with 'edk2' + when: on_success + - if: '$CI_COMMIT_MESSAGE =~ /edk2/i' # or last commit description contains 'EDK2' + when: on_success + +docker-edk2: + extends: .edk2_job_rules + stage: containers image: docker:19.03.1 services: - docker:19.03.1-dind @@ -24,16 +36,9 @@ docker-edk2: - docker push $IMAGE_TAG build-edk2: + extends: .edk2_job_rules stage: build needs: ['docker-edk2'] - rules: # Only run this job when ... - - changes: # ... roms/edk2/ is modified (submodule updated) - - roms/edk2/* - when: always - - if: '$CI_COMMIT_REF_NAME =~ /^edk2/' # or the branch/tag starts with 'edk2' - when: always - - if: '$CI_COMMIT_MESSAGE =~ /edk2/i' # or last commit description contains 'EDK2' - when: always artifacts: paths: # 'artifacts.zip' will contains the following files: - pc-bios/edk2*bz2 diff --git a/.gitlab-ci.d/opensbi.yml b/.gitlab-ci.d/opensbi.yml index f66cd1d908..5e0a2477c5 100644 --- a/.gitlab-ci.d/opensbi.yml +++ b/.gitlab-ci.d/opensbi.yml @@ -1,10 +1,23 @@ -docker-opensbi: - stage: containers - rules: # Only run this job when the Dockerfile is modified +# All jobs needing docker-opensbi must use the same rules it uses. +.opensbi_job_rules: + rules: # Only run this job when ... - changes: + # this file is modified - .gitlab-ci.d/opensbi.yml + # or the Dockerfile is modified - .gitlab-ci.d/opensbi/Dockerfile - when: always + when: on_success + - changes: # or roms/opensbi/ is modified (submodule updated) + - roms/opensbi/* + when: on_success + - if: '$CI_COMMIT_REF_NAME =~ /^opensbi/' # or the branch/tag starts with 'opensbi' + when: on_success + - if: '$CI_COMMIT_MESSAGE =~ /opensbi/i' # or last commit description contains 'OpenSBI' + when: on_success + +docker-opensbi: + extends: .opensbi_job_rules + stage: containers image: docker:19.03.1 services: - docker:19.03.1-dind @@ -24,16 +37,9 @@ docker-opensbi: - docker push $IMAGE_TAG build-opensbi: + extends: .opensbi_job_rules stage: build needs: ['docker-opensbi'] - rules: # Only run this job when ... - - changes: # ... roms/opensbi/ is modified (submodule updated) - - roms/opensbi/* - when: always - - if: '$CI_COMMIT_REF_NAME =~ /^opensbi/' # or the branch/tag starts with 'opensbi' - when: always - - if: '$CI_COMMIT_MESSAGE =~ /opensbi/i' # or last commit description contains 'OpenSBI' - when: always artifacts: paths: # 'artifacts.zip' will contains the following files: - pc-bios/opensbi-riscv32-generic-fw_dynamic.bin diff --git a/.gitlab-ci.d/qemu-project.yml b/.gitlab-ci.d/qemu-project.yml new file mode 100644 index 0000000000..b3d79bc429 --- /dev/null +++ b/.gitlab-ci.d/qemu-project.yml @@ -0,0 +1,13 @@ +# This file contains the set of jobs run by the QEMU project: +# https://gitlab.com/qemu-project/qemu/-/pipelines + +include: + - local: '/.gitlab-ci.d/stages.yml' + - local: '/.gitlab-ci.d/edk2.yml' + - local: '/.gitlab-ci.d/opensbi.yml' + - local: '/.gitlab-ci.d/containers.yml' + - local: '/.gitlab-ci.d/crossbuilds.yml' + - local: '/.gitlab-ci.d/buildtest.yml' + - local: '/.gitlab-ci.d/static_checks.yml' + - local: '/.gitlab-ci.d/custom-runners.yml' + - local: '/.gitlab-ci.d/cirrus.yml' diff --git a/.gitlab-ci.d/stages.yml b/.gitlab-ci.d/stages.yml new file mode 100644 index 0000000000..f50826018d --- /dev/null +++ b/.gitlab-ci.d/stages.yml @@ -0,0 +1,8 @@ +# Currently we have two build stages after our containers are built: +# - build (for traditional build and test or first stage build) +# - test (for test stages, using build artefacts from a build stage) +stages: + - containers + - containers-layer2 + - build + - test diff --git a/.gitlab-ci.d/static_checks.yml b/.gitlab-ci.d/static_checks.yml new file mode 100644 index 0000000000..96dbd9e310 --- /dev/null +++ b/.gitlab-ci.d/static_checks.yml @@ -0,0 +1,49 @@ +check-patch: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/centos8:latest + needs: + job: amd64-centos8-container + script: + - .gitlab-ci.d/check-patch.py + variables: + GIT_DEPTH: 1000 + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH' + when: never + - when: on_success + allow_failure: true + +check-dco: + stage: build + image: $CI_REGISTRY_IMAGE/qemu/centos8:latest + needs: + job: amd64-centos8-container + script: .gitlab-ci.d/check-dco.py + variables: + GIT_DEPTH: 1000 + rules: + - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH' + when: never + - when: on_success + +check-python-pipenv: + stage: test + image: $CI_REGISTRY_IMAGE/qemu/python:latest + script: + - make -C python check-pipenv + variables: + GIT_DEPTH: 1 + needs: + job: python-container + +check-python-tox: + stage: test + image: $CI_REGISTRY_IMAGE/qemu/python:latest + script: + - make -C python check-tox + variables: + GIT_DEPTH: 1 + QEMU_TOX_EXTRA_ARGS: --skip-missing-interpreters=false + needs: + job: python-container + allow_failure: true diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml index 52d65d6c04..9762dda2ee 100644 --- a/.gitlab-ci.yml +++ b/.gitlab-ci.yml @@ -1,837 +1,24 @@ -# Currently we have two build stages after our containers are built: -# - build (for traditional build and test or first stage build) -# - test (for test stages, using build artefacts from a build stage) -stages: - - containers - - containers-layer2 - - build - - test +# +# This is the GitLab CI configuration file for the mainstream QEMU +# project: https://gitlab.com/qemu-project/qemu/-/pipelines +# +# !!! DO NOT ADD ANY NEW CONFIGURATION TO THIS FILE !!! +# +# Only documentation or comments is accepted. +# +# To use a different set of jobs than the mainstream QEMU project, +# you need to set the location of your custom yml file at "custom CI/CD +# configuration path", on your GitLab CI namespace: +# https://docs.gitlab.com/ee/ci/pipelines/settings.html#custom-cicd-configuration-path +# +# ---------------------------------------------------------------------- +# +# QEMU CI jobs are based on templates. Some templates provide +# user-configurable options, modifiable via configuration variables. +# +# See https://qemu-project.gitlab.io/qemu/devel/ci.html#custom-ci-cd-variables +# for more information. +# include: - - local: '/.gitlab-ci.d/edk2.yml' - - local: '/.gitlab-ci.d/opensbi.yml' - - local: '/.gitlab-ci.d/containers.yml' - - local: '/.gitlab-ci.d/crossbuilds.yml' - -.native_build_job_template: &native_build_job_definition - stage: build - image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest - before_script: - - JOBS=$(expr $(nproc) + 1) - script: - - mkdir build - - cd build - - if test -n "$TARGETS"; - then - ../configure --enable-werror --disable-docs $CONFIGURE_ARGS --target-list="$TARGETS" ; - else - ../configure --enable-werror --disable-docs $CONFIGURE_ARGS ; - fi || { cat config.log meson-logs/meson-log.txt && exit 1; } - - if test -n "$LD_JOBS"; - then - meson configure . -Dbackend_max_links="$LD_JOBS" ; - fi || exit 1; - - make -j"$JOBS" - - if test -n "$MAKE_CHECK_ARGS"; - then - make -j"$JOBS" $MAKE_CHECK_ARGS ; - fi - -.native_test_job_template: &native_test_job_definition - stage: test - image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest - script: - - scripts/git-submodule.sh update - $(sed -n '/GIT_SUBMODULES=/ s/.*=// p' build/config-host.mak) - - cd build - - find . -type f -exec touch {} + - # Avoid recompiling by hiding ninja with NINJA=":" - - make NINJA=":" $MAKE_CHECK_ARGS - -.acceptance_template: &acceptance_definition - cache: - key: "${CI_JOB_NAME}-cache" - paths: - - ${CI_PROJECT_DIR}/avocado-cache - policy: pull-push - artifacts: - name: "$CI_JOB_NAME-$CI_COMMIT_REF_SLUG" - when: always - expire_in: 2 days - paths: - - build/tests/results/latest/results.xml - - build/tests/results/latest/test-results - reports: - junit: build/tests/results/latest/results.xml - before_script: - - mkdir -p ~/.config/avocado - - echo "[datadir.paths]" > ~/.config/avocado/avocado.conf - - echo "cache_dirs = ['${CI_PROJECT_DIR}/avocado-cache']" - >> ~/.config/avocado/avocado.conf - - echo -e '[job.output.testlogs]\nstatuses = ["FAIL", "INTERRUPT"]' - >> ~/.config/avocado/avocado.conf - - if [ -d ${CI_PROJECT_DIR}/avocado-cache ]; then - du -chs ${CI_PROJECT_DIR}/avocado-cache ; - fi - - export AVOCADO_ALLOW_UNTRUSTED_CODE=1 - after_script: - - cd build - - du -chs ${CI_PROJECT_DIR}/avocado-cache - -build-system-alpine: - <<: *native_build_job_definition - needs: - - job: amd64-alpine-container - variables: - IMAGE: alpine - TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu - moxie-softmmu microblazeel-softmmu mips64el-softmmu - MAKE_CHECK_ARGS: check-build - CONFIGURE_ARGS: --enable-docs --enable-trace-backends=log,simple,syslog - artifacts: - expire_in: 2 days - paths: - - .git-submodule-status - - build - -check-system-alpine: - <<: *native_test_job_definition - needs: - - job: build-system-alpine - artifacts: true - variables: - IMAGE: alpine - MAKE_CHECK_ARGS: check - -acceptance-system-alpine: - <<: *native_test_job_definition - needs: - - job: build-system-alpine - artifacts: true - variables: - IMAGE: alpine - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-system-ubuntu: - <<: *native_build_job_definition - needs: - job: amd64-ubuntu2004-container - variables: - IMAGE: ubuntu2004 - CONFIGURE_ARGS: --enable-docs --enable-fdt=system --enable-slirp=system - TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu - moxie-softmmu microblazeel-softmmu mips64el-softmmu - MAKE_CHECK_ARGS: check-build - artifacts: - expire_in: 2 days - paths: - - build - -check-system-ubuntu: - <<: *native_test_job_definition - needs: - - job: build-system-ubuntu - artifacts: true - variables: - IMAGE: ubuntu2004 - MAKE_CHECK_ARGS: check - -acceptance-system-ubuntu: - <<: *native_test_job_definition - needs: - - job: build-system-ubuntu - artifacts: true - variables: - IMAGE: ubuntu2004 - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-system-debian: - <<: *native_build_job_definition - needs: - job: amd64-debian-container - variables: - IMAGE: debian-amd64 - CONFIGURE_ARGS: --enable-fdt=system - TARGETS: arm-softmmu avr-softmmu i386-softmmu mipsel-softmmu - riscv64-softmmu sh4eb-softmmu sparc-softmmu xtensaeb-softmmu - MAKE_CHECK_ARGS: check-build - artifacts: - expire_in: 2 days - paths: - - build - -check-system-debian: - <<: *native_test_job_definition - needs: - - job: build-system-debian - artifacts: true - variables: - IMAGE: debian-amd64 - MAKE_CHECK_ARGS: check - -acceptance-system-debian: - <<: *native_test_job_definition - needs: - - job: build-system-debian - artifacts: true - variables: - IMAGE: debian-amd64 - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-system-fedora: - <<: *native_build_job_definition - needs: - job: amd64-fedora-container - variables: - IMAGE: fedora - CONFIGURE_ARGS: --disable-gcrypt --enable-nettle --enable-docs - --enable-fdt=system --enable-slirp=system --enable-capstone=system - TARGETS: tricore-softmmu microblaze-softmmu mips-softmmu - xtensa-softmmu m68k-softmmu riscv32-softmmu ppc-softmmu sparc64-softmmu - MAKE_CHECK_ARGS: check-build - artifacts: - expire_in: 2 days - paths: - - build - -check-system-fedora: - <<: *native_test_job_definition - needs: - - job: build-system-fedora - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check - -acceptance-system-fedora: - <<: *native_test_job_definition - needs: - - job: build-system-fedora - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-system-centos: - <<: *native_build_job_definition - needs: - job: amd64-centos8-container - variables: - IMAGE: centos8 - CONFIGURE_ARGS: --disable-nettle --enable-gcrypt --enable-fdt=system - --enable-modules --enable-trace-backends=dtrace - TARGETS: ppc64-softmmu or1k-softmmu s390x-softmmu - x86_64-softmmu rx-softmmu sh4-softmmu nios2-softmmu - MAKE_CHECK_ARGS: check-build - artifacts: - expire_in: 2 days - paths: - - build - -check-system-centos: - <<: *native_test_job_definition - needs: - - job: build-system-centos - artifacts: true - variables: - IMAGE: centos8 - MAKE_CHECK_ARGS: check - -acceptance-system-centos: - <<: *native_test_job_definition - needs: - - job: build-system-centos - artifacts: true - variables: - IMAGE: centos8 - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-system-opensuse: - <<: *native_build_job_definition - needs: - job: amd64-opensuse-leap-container - variables: - IMAGE: opensuse-leap - CONFIGURE_ARGS: --enable-fdt=system - TARGETS: s390x-softmmu x86_64-softmmu aarch64-softmmu - MAKE_CHECK_ARGS: check-build - artifacts: - expire_in: 2 days - paths: - - build - -check-system-opensuse: - <<: *native_test_job_definition - needs: - - job: build-system-opensuse - artifacts: true - variables: - IMAGE: opensuse-leap - MAKE_CHECK_ARGS: check - -acceptance-system-opensuse: - <<: *native_test_job_definition - needs: - - job: build-system-opensuse - artifacts: true - variables: - IMAGE: opensuse-leap - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - - -build-disabled: - <<: *native_build_job_definition - needs: - job: amd64-fedora-container - variables: - IMAGE: fedora - CONFIGURE_ARGS: - --disable-attr - --disable-auth-pam - --disable-avx2 - --disable-bochs - --disable-brlapi - --disable-bzip2 - --disable-cap-ng - --disable-capstone - --disable-cloop - --disable-coroutine-pool - --disable-curl - --disable-curses - --disable-dmg - --disable-docs - --disable-gcrypt - --disable-glusterfs - --disable-gnutls - --disable-gtk - --disable-guest-agent - --disable-iconv - --disable-keyring - --disable-kvm - --disable-libiscsi - --disable-libpmem - --disable-libssh - --disable-libudev - --disable-libusb - --disable-libxml2 - --disable-linux-aio - --disable-live-block-migration - --disable-lzo - --disable-malloc-trim - --disable-mpath - --disable-nettle - --disable-numa - --disable-opengl - --disable-parallels - --disable-pie - --disable-qcow1 - --disable-qed - --disable-qom-cast-debug - --disable-rbd - --disable-rdma - --disable-replication - --disable-sdl - --disable-seccomp - --disable-sheepdog - --disable-slirp - --disable-smartcard - --disable-snappy - --disable-sparse - --disable-spice - --disable-strip - --disable-tpm - --disable-usb-redir - --disable-vdi - --disable-vhost-crypto - --disable-vhost-net - --disable-vhost-scsi - --disable-vhost-kernel - --disable-vhost-user - --disable-vhost-vdpa - --disable-vhost-vsock - --disable-virglrenderer - --disable-vnc - --disable-vte - --disable-vvfat - --disable-xen - --disable-zstd - TARGETS: arm-softmmu i386-softmmu ppc64-softmmu mips64-softmmu - s390x-softmmu i386-linux-user - MAKE_CHECK_ARGS: check-qtest SPEED=slow - -# This jobs explicitly disable TCG (--disable-tcg), KVM is detected by -# the configure script. The container doesn't contain Xen headers so -# Xen accelerator is not detected / selected. As result it build the -# i386-softmmu and x86_64-softmmu with KVM being the single accelerator -# available. -# Also use a different coroutine implementation (which is only really of -# interest to KVM users, i.e. with TCG disabled) -build-tcg-disabled: - <<: *native_build_job_definition - needs: - job: amd64-centos8-container - variables: - IMAGE: centos8 - script: - - mkdir build - - cd build - - ../configure --disable-tcg --audio-drv-list="" --with-coroutine=ucontext - || { cat config.log meson-logs/meson-log.txt && exit 1; } - - make -j"$JOBS" - - make check-unit - - make check-qapi-schema - - cd tests/qemu-iotests/ - - ./check -raw 001 002 003 004 005 008 009 010 011 012 021 025 032 033 048 - 052 063 077 086 101 104 106 113 148 150 151 152 157 159 160 163 - 170 171 183 184 192 194 197 208 215 221 222 226 227 236 253 277 - - ./check -qcow2 028 051 056 057 058 065 068 082 085 091 095 096 102 122 - 124 132 139 142 144 145 151 152 155 157 165 194 196 197 200 202 - 208 209 215 216 218 222 227 234 246 247 248 250 254 255 257 258 - 260 261 262 263 264 270 272 273 277 279 - -build-user: - <<: *native_build_job_definition - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools --disable-system - MAKE_CHECK_ARGS: check-tcg - -build-user-static: - <<: *native_build_job_definition - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools --disable-system --static - MAKE_CHECK_ARGS: check-tcg - -# Only build the softmmu targets we have check-tcg tests for -build-some-softmmu: - <<: *native_build_job_definition - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools --enable-debug - TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu - MAKE_CHECK_ARGS: check-tcg - -# Run check-tcg against linux-user (with plugins) -# we skip sparc64-linux-user until it has been fixed somewhat -# we skip cris-linux-user as it doesn't use the common run loop -build-user-plugins: - <<: *native_build_job_definition - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools --disable-system --enable-plugins --enable-debug-tcg --target-list-exclude=sparc64-linux-user,cris-linux-user - MAKE_CHECK_ARGS: check-tcg - timeout: 1h 30m - -build-user-centos7: - <<: *native_build_job_definition - needs: - job: amd64-centos7-container - variables: - IMAGE: centos7 - CONFIGURE_ARGS: --disable-system --disable-tools --disable-docs - MAKE_CHECK_ARGS: check-tcg - -build-some-softmmu-plugins: - <<: *native_build_job_definition - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools --disable-user --enable-plugins --enable-debug-tcg - TARGETS: xtensa-softmmu arm-softmmu aarch64-softmmu alpha-softmmu - MAKE_CHECK_ARGS: check-tcg - -clang-system: - <<: *native_build_job_definition - needs: - job: amd64-fedora-container - variables: - IMAGE: fedora - CONFIGURE_ARGS: --cc=clang --cxx=clang++ - --extra-cflags=-fsanitize=undefined --extra-cflags=-fno-sanitize-recover=undefined - TARGETS: alpha-softmmu arm-softmmu m68k-softmmu mips64-softmmu - ppc-softmmu s390x-softmmu - MAKE_CHECK_ARGS: check-qtest check-tcg - -clang-user: - <<: *native_build_job_definition - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --cc=clang --cxx=clang++ --disable-system - --target-list-exclude=microblazeel-linux-user,aarch64_be-linux-user,i386-linux-user,m68k-linux-user,mipsn32el-linux-user,xtensaeb-linux-user - --extra-cflags=-fsanitize=undefined --extra-cflags=-fno-sanitize-recover=undefined - MAKE_CHECK_ARGS: check-unit check-tcg - -# Set LD_JOBS=1 because this requires LTO and ld consumes a large amount of memory. -# On gitlab runners, default value sometimes end up calling 2 lds concurrently and -# triggers an Out-Of-Memory error -# -# Since slirp callbacks are used in QEMU Timers, slirp needs to be compiled together -# with QEMU and linked as a static library to avoid false positives in CFI checks. -# This can be accomplished by using -enable-slirp=git, which avoids the use of -# a system-wide version of the library -# -# Split in three sets of build/check/acceptance to limit the execution time of each -# job -build-cfi-aarch64: - <<: *native_build_job_definition - needs: - - job: amd64-fedora-container - variables: - LD_JOBS: 1 - AR: llvm-ar - IMAGE: fedora - CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug - --enable-safe-stack --enable-slirp=git - TARGETS: aarch64-softmmu - MAKE_CHECK_ARGS: check-build - timeout: 70m - artifacts: - expire_in: 2 days - paths: - - build - -check-cfi-aarch64: - <<: *native_test_job_definition - needs: - - job: build-cfi-aarch64 - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check - -acceptance-cfi-aarch64: - <<: *native_test_job_definition - needs: - - job: build-cfi-aarch64 - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-cfi-ppc64-s390x: - <<: *native_build_job_definition - needs: - - job: amd64-fedora-container - variables: - LD_JOBS: 1 - AR: llvm-ar - IMAGE: fedora - CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug - --enable-safe-stack --enable-slirp=git - TARGETS: ppc64-softmmu s390x-softmmu - MAKE_CHECK_ARGS: check-build - timeout: 70m - artifacts: - expire_in: 2 days - paths: - - build - -check-cfi-ppc64-s390x: - <<: *native_test_job_definition - needs: - - job: build-cfi-ppc64-s390x - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check - -acceptance-cfi-ppc64-s390x: - <<: *native_test_job_definition - needs: - - job: build-cfi-ppc64-s390x - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -build-cfi-x86_64: - <<: *native_build_job_definition - needs: - - job: amd64-fedora-container - variables: - LD_JOBS: 1 - AR: llvm-ar - IMAGE: fedora - CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug - --enable-safe-stack --enable-slirp=git - TARGETS: x86_64-softmmu - MAKE_CHECK_ARGS: check-build - timeout: 70m - artifacts: - expire_in: 2 days - paths: - - build - -check-cfi-x86_64: - <<: *native_test_job_definition - needs: - - job: build-cfi-x86_64 - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check - -acceptance-cfi-x86_64: - <<: *native_test_job_definition - needs: - - job: build-cfi-x86_64 - artifacts: true - variables: - IMAGE: fedora - MAKE_CHECK_ARGS: check-acceptance - <<: *acceptance_definition - -tsan-build: - <<: *native_build_job_definition - needs: - job: amd64-ubuntu2004-container - variables: - IMAGE: ubuntu2004 - CONFIGURE_ARGS: --enable-tsan --cc=clang-10 --cxx=clang++-10 - --enable-trace-backends=ust --enable-fdt=system --enable-slirp=system - TARGETS: x86_64-softmmu ppc64-softmmu riscv64-softmmu x86_64-linux-user - MAKE_CHECK_ARGS: bench V=1 - -# These targets are on the way out -build-deprecated: - <<: *native_build_job_definition - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - CONFIGURE_ARGS: --disable-tools - MAKE_CHECK_ARGS: build-tcg - TARGETS: ppc64abi32-linux-user lm32-softmmu unicore32-softmmu - artifacts: - expire_in: 2 days - paths: - - build - -# We split the check-tcg step as test failures are expected but we still -# want to catch the build breaking. -check-deprecated: - <<: *native_test_job_definition - needs: - - job: build-deprecated - artifacts: true - variables: - IMAGE: debian-all-test-cross - MAKE_CHECK_ARGS: check-tcg - allow_failure: true - -# gprof/gcov are GCC features -gprof-gcov: - <<: *native_build_job_definition - needs: - job: amd64-ubuntu2004-container - variables: - IMAGE: ubuntu2004 - CONFIGURE_ARGS: --enable-gprof --enable-gcov - MAKE_CHECK_ARGS: check - TARGETS: aarch64-softmmu ppc64-softmmu s390x-softmmu x86_64-softmmu - timeout: 70m - after_script: - - ${CI_PROJECT_DIR}/scripts/ci/coverage-summary.sh - -build-oss-fuzz: - <<: *native_build_job_definition - needs: - job: amd64-fedora-container - variables: - IMAGE: fedora - script: - - mkdir build-oss-fuzz - - CC="clang" CXX="clang++" CFLAGS="-fsanitize=address" - ./scripts/oss-fuzz/build.sh - - export ASAN_OPTIONS="fast_unwind_on_malloc=0" - - for fuzzer in $(find ./build-oss-fuzz/DEST_DIR/ -executable -type f - | grep -v slirp); do - grep "LLVMFuzzerTestOneInput" ${fuzzer} > /dev/null 2>&1 || continue ; - echo Testing ${fuzzer} ... ; - "${fuzzer}" -runs=1 -seed=1 || exit 1 ; - done - # Unrelated to fuzzer: run some tests with -fsanitize=address - - cd build-oss-fuzz && make check-qtest-i386 check-unit - -build-tci: - <<: *native_build_job_definition - needs: - job: amd64-debian-user-cross-container - variables: - IMAGE: debian-all-test-cross - script: - - TARGETS="aarch64 alpha arm hppa m68k microblaze moxie ppc64 s390x x86_64" - - mkdir build - - cd build - - ../configure --enable-tcg-interpreter - --target-list="$(for tg in $TARGETS; do echo -n ${tg}'-softmmu '; done)" || { cat config.log meson-logs/meson-log.txt && exit 1; } - - make -j"$JOBS" - - make tests/qtest/boot-serial-test tests/qtest/cdrom-test tests/qtest/pxe-test - - for tg in $TARGETS ; do - export QTEST_QEMU_BINARY="./qemu-system-${tg}" ; - ./tests/qtest/boot-serial-test || exit 1 ; - ./tests/qtest/cdrom-test || exit 1 ; - done - - QTEST_QEMU_BINARY="./qemu-system-x86_64" ./tests/qtest/pxe-test - - QTEST_QEMU_BINARY="./qemu-system-s390x" ./tests/qtest/pxe-test -m slow - - make check-tcg - -# Alternate coroutines implementations are only really of interest to KVM users -# However we can't test against KVM on Gitlab-CI so we can only run unit tests -build-coroutine-sigaltstack: - <<: *native_build_job_definition - needs: - job: amd64-ubuntu2004-container - variables: - IMAGE: ubuntu2004 - CONFIGURE_ARGS: --with-coroutine=sigaltstack --disable-tcg - --enable-trace-backends=ftrace - MAKE_CHECK_ARGS: check-unit - -# Most jobs test latest gcrypt or nettle builds -# -# These jobs test old gcrypt and nettle from RHEL7 -# which had some API differences. -crypto-old-nettle: - <<: *native_build_job_definition - needs: - job: amd64-centos7-container - variables: - IMAGE: centos7 - TARGETS: x86_64-softmmu x86_64-linux-user - CONFIGURE_ARGS: --disable-gcrypt --enable-nettle - MAKE_CHECK_ARGS: check - -crypto-old-gcrypt: - <<: *native_build_job_definition - needs: - job: amd64-centos7-container - variables: - IMAGE: centos7 - TARGETS: x86_64-softmmu x86_64-linux-user - CONFIGURE_ARGS: --disable-nettle --enable-gcrypt - MAKE_CHECK_ARGS: check - -crypto-only-gnutls: - <<: *native_build_job_definition - needs: - job: amd64-centos7-container - variables: - IMAGE: centos7 - TARGETS: x86_64-softmmu x86_64-linux-user - CONFIGURE_ARGS: --disable-nettle --disable-gcrypt --enable-gnutls - MAKE_CHECK_ARGS: check - - -# Check our reduced build configurations -build-without-default-devices: - <<: *native_build_job_definition - needs: - job: amd64-centos8-container - variables: - IMAGE: centos8 - CONFIGURE_ARGS: --without-default-devices --disable-user - -build-without-default-features: - <<: *native_build_job_definition - needs: - job: amd64-debian-container - variables: - IMAGE: debian-amd64 - CONFIGURE_ARGS: --without-default-features --disable-user - --target-list-exclude=arm-softmmu,i386-softmmu,mipsel-softmmu,mips64-softmmu,ppc-softmmu - MAKE_CHECK_ARGS: check-unit - -check-patch: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/centos8:latest - needs: - job: amd64-centos8-container - script: .gitlab-ci.d/check-patch.py - except: - variables: - - $CI_PROJECT_NAMESPACE == 'qemu-project' && $CI_COMMIT_BRANCH == 'master' - variables: - GIT_DEPTH: 1000 - allow_failure: true - -check-dco: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/centos8:latest - needs: - job: amd64-centos8-container - script: .gitlab-ci.d/check-dco.py - except: - variables: - - $CI_PROJECT_NAMESPACE == 'qemu-project' && $CI_COMMIT_BRANCH == 'master' - variables: - GIT_DEPTH: 1000 - -build-libvhost-user: - stage: build - image: $CI_REGISTRY_IMAGE/qemu/fedora:latest - needs: - job: amd64-fedora-container - before_script: - - dnf install -y meson ninja-build - script: - - mkdir subprojects/libvhost-user/build - - cd subprojects/libvhost-user/build - - meson - - ninja - -# No targets are built here, just tools, docs, and unit tests. This -# also feeds into the eventual documentation deployment steps later -build-tools-and-docs-debian: - <<: *native_build_job_definition - needs: - job: amd64-debian-container - variables: - IMAGE: debian-amd64 - MAKE_CHECK_ARGS: check-unit check-softfloat ctags TAGS cscope - CONFIGURE_ARGS: --disable-system --disable-user --enable-docs --enable-tools - artifacts: - expire_in: 2 days - paths: - - build - -# Prepare for GitLab pages deployment. Anything copied into the -# "public" directory will be deployed to $USER.gitlab.io/$PROJECT -pages: - image: $CI_REGISTRY_IMAGE/qemu/debian-amd64:latest - stage: test - needs: - - job: build-tools-and-docs-debian - script: - - mkdir -p public - # HTML-ised source tree - - make gtags - - htags -anT --tree-view=filetree -m qemu_init - -t "Welcome to the QEMU sourcecode" - - mv HTML public/src - # Project documentation - - make -C build install DESTDIR=$(pwd)/temp-install - - mv temp-install/usr/local/share/doc/qemu/* public/ - artifacts: - paths: - - public + - local: '/.gitlab-ci.d/qemu-project.yml' diff --git a/.gitlab/issue_templates/bug.md b/.gitlab/issue_templates/bug.md new file mode 100644 index 0000000000..e910f7b1c2 --- /dev/null +++ b/.gitlab/issue_templates/bug.md @@ -0,0 +1,64 @@ + + +## Host environment + - Operating system: (Windows 10 21H1, Fedora 34, etc.) + - OS/kernel version: (For POSIX hosts, use `uname -a`) + - Architecture: (x86, ARM, s390x, etc.) + - QEMU flavor: (qemu-system-x86_64, qemu-aarch64, qemu-img, etc.) + - QEMU version: (e.g. `qemu-system-x86_64 --version`) + - QEMU command line: + + ``` + ./qemu-system-x86_64 -M q35 -m 4096 -enable-kvm -hda fedora32.qcow2 + ``` + +## Emulated/Virtualized environment + - Operating system: (Windows 10 21H1, Fedora 34, etc.) + - OS/kernel version: (For POSIX guests, use `uname -a`.) + - Architecture: (x86, ARM, s390x, etc.) + + +## Description of problem + + + +## Steps to reproduce +1. +2. +3. + + +## Additional information + + + + +/label ~"kind::Bug" diff --git a/.gitlab/issue_templates/feature_request.md b/.gitlab/issue_templates/feature_request.md new file mode 100644 index 0000000000..7de02dcc2c --- /dev/null +++ b/.gitlab/issue_templates/feature_request.md @@ -0,0 +1,32 @@ + + +## Goal + + + +## Technical details + + + +## Additional information + + + +/label ~"kind::Feature Request" diff --git a/.mailmap b/.mailmap index a1bd659817..f029d1c21f 100644 --- a/.mailmap +++ b/.mailmap @@ -27,6 +27,10 @@ Paul Brook pbrook ths malc malc +# Corrupted Author fields +Marek Dolata mkdolata@us.ibm.com +Nick Hudson hnick@vmware.com + # There is also a: # (no author) <(no author)@c046a42c-6fe2-441c-8c8c-71466251a162> # for the cvs2svn initialization commit e63c3dc74bf. @@ -96,6 +100,7 @@ Gautham R. Shenoy Gonglei (Arei) Guang Wang Hailiang Zhang +Hanna Reitz Hervé Poussineau Jakub Jermář Jakub Jermář diff --git a/.patchew.yml b/.patchew.yml index 988c29261f..1b78262ce5 100644 --- a/.patchew.yml +++ b/.patchew.yml @@ -88,7 +88,7 @@ email: more information: {{ logtext }} - {% elif test == "docker-mingw@fedora" or test == "docker-quick@centos7" or test == "asan" %} + {% elif test == "docker-mingw@fedora" or test == "docker-quick@centos8" or test == "asan" %} Hi, This series failed the {{ test }} build test. Please find the testing commands and @@ -124,13 +124,13 @@ testing: script: | #!/bin/bash time make docker-test-debug@fedora TARGET_LIST=x86_64-softmmu J=14 NETWORK=1 - docker-quick@centos7: + docker-quick@centos8: enabled: false requirements: docker,x86_64 timeout: 3600 script: | #!/bin/bash - time make docker-test-quick@centos7 SHOW_ENV=1 J=14 NETWORK=1 + time make docker-test-quick@centos8 SHOW_ENV=1 J=14 NETWORK=1 checkpatch: enabled: true requirements: '' @@ -138,9 +138,6 @@ testing: script: | #!/bin/bash git rev-parse base > /dev/null || exit 0 - git config --local diff.renamelimit 0 - git config --local diff.renames True - git config --local diff.algorithm histogram ./scripts/checkpatch.pl --mailback base.. docker-mingw@fedora: enabled: true diff --git a/.travis.yml b/.travis.yml index 4609240b5a..0faddf7b4e 100644 --- a/.travis.yml +++ b/.travis.yml @@ -27,6 +27,7 @@ addons: - libattr1-dev - libbrlapi-dev - libcap-ng-dev + - libcacard-dev - libgcc-7-dev - libgnutls28-dev - libgtk-3-dev @@ -34,7 +35,6 @@ addons: - liblttng-ust-dev - libncurses5-dev - libnfs-dev - - libnss3-dev - libpixman-1-dev - libpng-dev - librados-dev @@ -129,6 +129,7 @@ jobs: - libaio-dev - libattr1-dev - libbrlapi-dev + - libcacard-dev - libcap-ng-dev - libgcrypt20-dev - libgnutls28-dev @@ -137,7 +138,6 @@ jobs: - liblttng-ust-dev - libncurses5-dev - libnfs-dev - - libnss3-dev - libpixman-1-dev - libpng-dev - librados-dev @@ -163,6 +163,7 @@ jobs: - libaio-dev - libattr1-dev - libbrlapi-dev + - libcacard-dev - libcap-ng-dev - libgcrypt20-dev - libgnutls28-dev @@ -171,7 +172,6 @@ jobs: - liblttng-ust-dev - libncurses5-dev - libnfs-dev - - libnss3-dev - libpixman-1-dev - libpng-dev - librados-dev @@ -196,6 +196,7 @@ jobs: - libaio-dev - libattr1-dev - libbrlapi-dev + - libcacard-dev - libcap-ng-dev - libgcrypt20-dev - libgnutls28-dev @@ -204,7 +205,6 @@ jobs: - liblttng-ust-dev - libncurses5-dev - libnfs-dev - - libnss3-dev - libpixman-1-dev - libpng-dev - librados-dev @@ -238,6 +238,7 @@ jobs: apt_packages: - libaio-dev - libattr1-dev + - libcacard-dev - libcap-ng-dev - libgnutls28-dev - libiscsi-dev @@ -245,7 +246,6 @@ jobs: - liblzo2-dev - libncurses-dev - libnfs-dev - - libnss3-dev - libpixman-1-dev - libsdl2-dev - libsdl2-image-dev @@ -281,6 +281,7 @@ jobs: - libaio-dev - libattr1-dev - libbrlapi-dev + - libcacard-dev - libcap-ng-dev - libgcrypt20-dev - libgnutls28-dev @@ -289,7 +290,6 @@ jobs: - liblttng-ust-dev - libncurses5-dev - libnfs-dev - - libnss3-dev - libpixman-1-dev - libpng-dev - librados-dev diff --git a/Kconfig b/Kconfig index d52ebd839b..fb6a24a2de 100644 --- a/Kconfig +++ b/Kconfig @@ -1,5 +1,6 @@ source Kconfig.host source backends/Kconfig source accel/Kconfig +source target/Kconfig source hw/Kconfig source semihosting/Kconfig diff --git a/MAINTAINERS b/MAINTAINERS index 36055f14c5..6b3697962c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -87,7 +87,7 @@ S390 general architecture support M: Cornelia Huck M: Thomas Huth S: Supported -F: default-configs/*/s390x-softmmu.mak +F: configs/devices/s390x-softmmu/default.mak F: gdb-xml/s390*.xml F: hw/char/sclp*.[hc] F: hw/char/terminal3270.c @@ -128,7 +128,6 @@ F: docs/devel/decodetree.rst F: include/exec/cpu*.h F: include/exec/exec-all.h F: include/exec/helper*.h -F: include/exec/tb-hash.h F: include/sysemu/cpus.h F: include/sysemu/tcg.h F: include/hw/core/tcg-cpu-ops.h @@ -156,6 +155,7 @@ S: Maintained F: target/arm/ F: tests/tcg/arm/ F: tests/tcg/aarch64/ +F: tests/qtest/arm-cpu-features.c F: hw/arm/ F: hw/cpu/a*mpcore.c F: include/hw/cpu/a*mpcore.h @@ -171,6 +171,7 @@ L: qemu-arm@nongnu.org S: Maintained F: hw/arm/smmu* F: include/hw/arm/smmu* +F: tests/acceptance/smmu.py AVR TCG CPUs M: Michael Rolnik @@ -196,7 +197,9 @@ F: target/hexagon/ F: linux-user/hexagon/ F: tests/tcg/hexagon/ F: disas/hexagon.c -F: default-configs/targets/hexagon-linux-user.mak +F: configs/targets/hexagon-linux-user/default.mak +F: docker/dockerfiles/debian-hexagon-cross.docker +F: docker/dockerfiles/debian-hexagon-cross.docker.d/build-toolchain.sh HPPA (PA-RISC) TCG CPUs M: Richard Henderson @@ -207,19 +210,6 @@ F: disas/hppa.c F: hw/net/*i82596* F: include/hw/net/lasi_82596.h -LM32 TCG CPUs -R: Michael Walle -S: Orphan -F: target/lm32/ -F: disas/lm32.c -F: hw/lm32/ -F: hw/*/lm32_* -F: hw/*/milkymist-* -F: include/hw/display/milkymist_tmu2.h -F: include/hw/char/lm32_juart.h -F: include/hw/lm32/ -F: tests/tcg/lm32/ - M68K TCG CPUs M: Laurent Vivier S: Maintained @@ -240,7 +230,7 @@ R: Jiaxun Yang R: Aleksandar Rikalo S: Odd Fixes F: target/mips/ -F: default-configs/*/*mips* +F: configs/devices/mips*/* F: disas/mips.c F: docs/system/cpu-models-mips.rst.inc F: hw/intc/mips_gic.c @@ -257,14 +247,7 @@ K: ^Subject:.*(?i)mips MIPS TCG CPUs (nanoMIPS ISA) S: Orphan F: disas/nanomips.* - -Moxie TCG CPUs -M: Anthony Green -S: Maintained -F: target/moxie/ -F: disas/moxie.c -F: hw/moxie/ -F: default-configs/*/moxie-softmmu.mak +F: target/mips/tcg/*nanomips* NiosII TCG CPUs M: Chris Wulff @@ -273,7 +256,7 @@ S: Maintained F: target/nios2/ F: hw/nios2/ F: disas/nios2.c -F: default-configs/*/nios2-softmmu.mak +F: configs/devices/nios2-softmmu/default.mak OpenRISC TCG CPUs M: Stafford Horne @@ -295,9 +278,8 @@ F: tests/acceptance/machine_ppc.py RISC-V TCG CPUs M: Palmer Dabbelt -M: Alistair Francis -M: Sagar Karandikar -M: Bastian Koppelmann +M: Alistair Francis +M: Bin Meng L: qemu-riscv@nongnu.org S: Supported F: target/riscv/ @@ -316,6 +298,8 @@ M: Richard Henderson M: David Hildenbrand S: Maintained F: target/s390x/ +F: target/s390x/tcg +F: target/s390x/cpu_models_*.[ch] F: hw/s390x/ F: disas/s390.c F: tests/tcg/s390x/ @@ -339,24 +323,17 @@ F: hw/sparc64/ F: include/hw/sparc/sparc64.h F: disas/sparc.c -UniCore32 TCG CPUs -M: Guan Xuetao -S: Maintained -F: target/unicore32/ -F: hw/unicore32/ -F: include/hw/unicore32/ - X86 TCG CPUs M: Paolo Bonzini M: Richard Henderson M: Eduardo Habkost S: Maintained -F: target/i386/ +F: target/i386/tcg/ F: tests/tcg/i386/ F: tests/tcg/x86_64/ F: hw/i386/ F: disas/i386.c -F: docs/system/cpu-models-x86.rst.inc +F: docs/system/cpu-models-x86* T: git https://gitlab.com/ehabkost/qemu.git x86-next Xtensa TCG CPUs @@ -368,7 +345,7 @@ F: hw/xtensa/ F: tests/tcg/xtensa/ F: disas/xtensa.c F: include/hw/xtensa/xtensa-isa.h -F: default-configs/*/xtensa*.mak +F: configs/devices/xtensa*/default.mak TriCore TCG CPUs M: Bastian Koppelmann @@ -376,6 +353,7 @@ S: Maintained F: target/tricore/ F: hw/tricore/ F: include/hw/tricore/ +F: tests/tcg/tricore/ Multiarch Linux User Tests M: Alex Bennée @@ -404,7 +382,8 @@ F: target/arm/kvm.c MIPS KVM CPUs M: Huacai Chen S: Odd Fixes -F: target/mips/kvm.c +F: target/mips/kvm* +F: target/mips/sysemu/ PPC KVM CPUs M: David Gibson @@ -417,9 +396,7 @@ M: Halil Pasic M: Cornelia Huck M: Christian Borntraeger S: Supported -F: target/s390x/kvm.c -F: target/s390x/kvm_s390x.h -F: target/s390x/kvm-stub.c +F: target/s390x/kvm/ F: target/s390x/ioinst.[ch] F: target/s390x/machine.c F: target/s390x/sigp.c @@ -462,7 +439,15 @@ M: Roman Bolshakov W: https://wiki.qemu.org/Features/HVF S: Maintained F: target/i386/hvf/ + +HVF +M: Cameron Esfahani +M: Roman Bolshakov +W: https://wiki.qemu.org/Features/HVF +S: Maintained +F: accel/hvf/ F: include/sysemu/hvf.h +F: include/sysemu/hvf_int.h WHPX CPUs M: Sunil Muthuswamy @@ -509,6 +494,15 @@ F: accel/stubs/hax-stub.c F: include/sysemu/hax.h F: target/i386/hax/ +Guest CPU Cores (NVMM) +---------------------- +NetBSD Virtual Machine Monitor (NVMM) CPU support +M: Kamil Rytarowski +M: Reinoud Zandijk +S: Maintained +F: include/sysemu/nvmm.h +F: target/i386/nvmm/ + Hosts ----- LINUX @@ -529,6 +523,8 @@ F: include/qemu/*posix*.h NETBSD M: Kamil Rytarowski +M: Reinoud Zandijk +M: Ryo ONODERA S: Maintained K: ^Subject:.*(?i)NetBSD @@ -564,6 +560,7 @@ S: Odd Fixes F: hw/*/allwinner* F: include/hw/*/allwinner* F: hw/arm/cubieboard.c +F: docs/system/arm/cubieboard.rst Allwinner-h3 M: Niek Linnenbank @@ -646,6 +643,7 @@ L: qemu-arm@nongnu.org S: Odd Fixes F: hw/arm/highbank.c F: hw/net/xgmac.c +F: docs/system/arm/highbank.rst Canon DIGIC M: Antony Pavlov @@ -686,6 +684,7 @@ F: hw/watchdog/wdt_imx2.c F: include/hw/arm/fsl-imx25.h F: include/hw/misc/imx25_ccm.h F: include/hw/watchdog/wdt_imx2.h +F: docs/system/arm/imx25-pdk.rst i.MX31 (kzm) M: Peter Maydell @@ -696,6 +695,7 @@ F: hw/*/imx_* F: hw/*/*imx31* F: include/hw/*/imx_* F: include/hw/*/*imx31* +F: docs/system/arm/kzm.rst Integrator CP M: Peter Maydell @@ -788,7 +788,6 @@ F: roms/vbootrom F: docs/system/arm/nuvoton.rst nSeries -M: Andrzej Zaborowski M: Peter Maydell L: qemu-arm@nongnu.org S: Odd Fixes @@ -799,13 +798,13 @@ F: hw/input/tsc2005.c F: hw/misc/cbus.c F: hw/rtc/twl92230.c F: include/hw/display/blizzard.h +F: include/hw/input/lm832x.h F: include/hw/input/tsc2xxx.h F: include/hw/misc/cbus.h F: tests/acceptance/machine_arm_n8x0.py F: docs/system/arm/nseries.rst Palm -M: Andrzej Zaborowski M: Peter Maydell L: qemu-arm@nongnu.org S: Odd Fixes @@ -838,7 +837,6 @@ F: include/hw/intc/realview_gic.h F: docs/system/arm/realview.rst PXA2XX -M: Andrzej Zaborowski M: Peter Maydell L: qemu-arm@nongnu.org S: Odd Fixes @@ -851,12 +849,13 @@ F: hw/display/tc6393xb.c F: hw/gpio/max7310.c F: hw/gpio/zaurus.c F: hw/misc/mst_fpga.c -F: hw/misc/max111x.c -F: include/hw/misc/max111x.h +F: hw/adc/max111x.c +F: include/hw/adc/max111x.h F: include/hw/arm/pxa.h F: include/hw/arm/sharpsl.h F: include/hw/display/tc6393xb.h F: docs/system/arm/xscale.rst +F: docs/system/arm/mainstone.rst SABRELITE / i.MX6 M: Peter Maydell @@ -898,6 +897,13 @@ F: hw/*/stellaris* F: include/hw/input/gamepad.h F: docs/system/arm/stellaris.rst +STM32VLDISCOVERY +M: Alexandre Iooss +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/stm32vldiscovery.c +F: docs/system/arm/stm32.rst + Versatile Express M: Peter Maydell L: qemu-arm@nongnu.org @@ -930,8 +936,10 @@ L: qemu-arm@nongnu.org S: Maintained F: hw/*/xilinx_* F: hw/*/cadence_* -F: hw/misc/zynq* -F: include/hw/misc/zynq* +F: hw/misc/zynq_slcr.c +F: hw/adc/zynq-xadc.c +F: include/hw/misc/zynq_slcr.h +F: include/hw/adc/zynq-xadc.h X: hw/ssi/xilinx_* Xilinx ZynqMP and Versal @@ -953,6 +961,12 @@ L: qemu-arm@nongnu.org S: Maintained F: hw/arm/virt-acpi-build.c +STM32F100 +M: Alexandre Iooss +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/stm32f100_soc.c + STM32F205 M: Alistair Francis M: Peter Maydell @@ -1011,6 +1025,7 @@ M: Peter Maydell L: qemu-arm@nongnu.org S: Maintained F: hw/arm/msf2-som.c +F: docs/system/arm/emcraft-sf2.rst ASPEED BMCs M: Cédric Le Goater @@ -1026,6 +1041,7 @@ F: include/hw/misc/pca9552*.h F: hw/net/ftgmac100.c F: include/hw/net/ftgmac100.h F: docs/system/arm/aspeed.rst +F: tests/qtest/*aspeed* NRF51 M: Joel Stanley @@ -1037,6 +1053,7 @@ F: hw/*/microbit*.c F: include/hw/*/nrf51*.h F: include/hw/*/microbit*.h F: tests/qtest/microbit-test.c +F: docs/system/arm/nrf.rst AVR Machines ------------- @@ -1044,7 +1061,7 @@ AVR Machines AVR MCUs M: Michael Rolnik S: Maintained -F: default-configs/*/avr-softmmu.mak +F: configs/devices/avr-softmmu/default.mak F: hw/avr/ F: include/hw/char/avr_usart.h F: hw/char/avr_usart.c @@ -1072,22 +1089,10 @@ HP B160L M: Richard Henderson R: Helge Deller S: Odd Fixes -F: default-configs/*/hppa-softmmu.mak +F: configs/devices/hppa-softmmu/default.mak F: hw/hppa/ F: pc-bios/hppa-firmware.img -LM32 Machines -------------- -EVR32 and uclinux BSP -R: Michael Walle -S: Orphan -F: hw/lm32/lm32_boards.c - -milkymist -R: Michael Walle -S: Orphan -F: hw/lm32/milkymist.c - M68K Machines ------------- an5206 @@ -1193,6 +1198,7 @@ F: hw/isa/vt82c686.c F: hw/pci-host/bonito.c F: hw/usb/vt82c686-uhci-pci.c F: include/hw/isa/vt82c686.h +F: tests/acceptance/machine_mips_fuloong2e.py Loongson-3 virtual platforms M: Huacai Chen @@ -1302,7 +1308,7 @@ S: Maintained F: hw/ppc/prep.c F: hw/ppc/prep_systemio.c F: hw/ppc/rs6000_mc.c -F: hw/pci-host/prep.[hc] +F: hw/pci-host/raven.c F: hw/isa/i82378.c F: hw/isa/pc87312.c F: hw/dma/i82374.c @@ -1364,6 +1370,28 @@ F: pc-bios/canyonlands.dt[sb] F: pc-bios/u-boot-sam460ex-20100605.bin F: roms/u-boot-sam460ex +pegasos2 +M: BALATON Zoltan +R: David Gibson +L: qemu-ppc@nongnu.org +S: Maintained +F: hw/ppc/pegasos2.c +F: hw/pci-host/mv64361.c +F: hw/pci-host/mv643xx.h +F: include/hw/pci-host/mv64361.h + +Virtual Open Firmware (VOF) +M: Alexey Kardashevskiy +R: David Gibson +R: Greg Kurz +L: qemu-ppc@nongnu.org +S: Maintained +F: hw/ppc/spapr_vof* +F: hw/ppc/vof* +F: include/hw/ppc/vof* +F: pc-bios/vof/* +F: pc-bios/vof* + RISC-V Machines --------------- OpenTitan @@ -1371,11 +1399,9 @@ M: Alistair Francis L: qemu-riscv@nongnu.org S: Supported F: hw/riscv/opentitan.c -F: hw/char/ibex_uart.c -F: hw/intc/ibex_plic.c +F: hw/*/ibex_*.c F: include/hw/riscv/opentitan.h -F: include/hw/char/ibex_uart.h -F: include/hw/intc/ibex_plic.h +F: include/hw/*/ibex_*.h Microchip PolarFire SoC Icicle Kit M: Bin Meng @@ -1392,6 +1418,15 @@ F: include/hw/misc/mchp_pfsoc_dmc.h F: include/hw/misc/mchp_pfsoc_ioscb.h F: include/hw/misc/mchp_pfsoc_sysreg.h +Shakti C class SoC +M: Vijai Kumar K +L: qemu-riscv@nongnu.org +S: Supported +F: hw/riscv/shakti_c.c +F: hw/char/shakti_uart.c +F: include/hw/riscv/shakti_c.h +F: include/hw/char/shakti_uart.h + SiFive Machines M: Alistair Francis M: Bin Meng @@ -1493,7 +1528,7 @@ F: hw/s390x/ F: include/hw/s390x/ F: hw/watchdog/wdt_diag288.c F: include/hw/watchdog/wdt_diag288.h -F: default-configs/*/s390x-softmmu.mak +F: configs/devices/s390x-softmmu/default.mak F: tests/acceptance/machine_s390_ccw_virtio.py T: git https://gitlab.com/cohuck/qemu.git s390-next T: git https://github.com/borntraeger/qemu.git s390-next @@ -1518,14 +1553,6 @@ F: hw/s390x/s390-pci* F: include/hw/s390x/s390-pci* L: qemu-s390x@nongnu.org -UniCore32 Machines ------------------- -PKUnity-3 SoC initramfs-with-busybox -M: Guan Xuetao -S: Maintained -F: hw/*/puv3* -F: hw/unicore32/ - X86 Machines ------------ PC @@ -1676,6 +1703,9 @@ M: John Snow L: qemu-block@nongnu.org S: Supported F: hw/block/fdc.c +F: hw/block/fdc-internal.h +F: hw/block/fdc-isa.c +F: hw/block/fdc-sysbus.c F: include/hw/block/fdc.h F: tests/qtest/fdc-test.c T: git https://gitlab.com/jsnow/qemu.git ide @@ -1705,7 +1735,6 @@ F: hw/pci-bridge/* F: qapi/pci.json F: docs/pci* F: docs/specs/*pci* -F: default-configs/pci.mak ACPI/SMBIOS M: Michael S. Tsirkin @@ -1798,21 +1827,21 @@ F: include/hw/sd/sd* F: hw/sd/core.c F: hw/sd/sd* F: hw/sd/ssi-sd.c -F: tests/qtest/sd* +F: tests/qtest/fuzz-sdcard-test.c +F: tests/qtest/sdhci-test.c USB M: Gerd Hoffmann -S: Maintained +S: Odd Fixes F: hw/usb/* +F: stubs/usb-dev-stub.c F: tests/qtest/usb-*-test.c -F: docs/usb2.txt -F: docs/usb-storage.txt +F: docs/system/devices/usb.rst F: include/hw/usb.h F: include/hw/usb/ -F: default-configs/usb.mak USB (serial adapter) -M: Gerd Hoffmann +R: Gerd Hoffmann M: Samuel Thibault S: Maintained F: hw/usb/dev-serial.c @@ -1823,6 +1852,7 @@ S: Supported F: hw/vfio/* F: include/hw/vfio/ F: docs/igd-assign.txt +F: docs/devel/vfio-migration.rst vfio-ccw M: Cornelia Huck @@ -1881,6 +1911,7 @@ virtio-9p M: Greg Kurz M: Christian Schoenebeck S: Odd Fixes +W: https://wiki.qemu.org/Documentation/9p F: hw/9pfs/ X: hw/9pfs/xen-9p* F: fsdev/ @@ -1920,7 +1951,7 @@ L: virtio-fs@redhat.com virtio-input M: Gerd Hoffmann -S: Maintained +S: Odd Fixes F: hw/input/vhost-user-input.c F: hw/input/virtio-input*.c F: include/hw/virtio/virtio-input.h @@ -1951,6 +1982,15 @@ F: include/sysemu/rng*.h F: backends/rng*.c F: tests/qtest/virtio-rng-test.c +vhost-user-rng +M: Mathieu Poirier +S: Supported +F: docs/tools/vhost-user-rng.rst +F: hw/virtio/vhost-user-rng.c +F: hw/virtio/vhost-user-rng-pci.c +F: include/hw/virtio/vhost-user-rng.h +F: tools/vhost-user-rng/* + virtio-crypto M: Gonglei S: Supported @@ -1972,7 +2012,7 @@ M: Keith Busch M: Klaus Jensen L: qemu-block@nongnu.org S: Supported -F: hw/block/nvme* +F: hw/nvme/* F: include/block/nvme.h F: tests/qtest/nvme-test.c F: docs/system/nvme.rst @@ -2040,6 +2080,12 @@ S: Maintained F: hw/net/tulip.c F: hw/net/tulip.h +pca954x +M: Patrick Venture +S: Maintained +F: hw/i2c/i2c_mux_pca954x.c +F: include/hw/i2c/i2c_mux_pca954x.h + Generic Loader M: Alistair Francis S: Maintained @@ -2111,7 +2157,7 @@ F: include/hw/display/ramfb.h virtio-gpu M: Gerd Hoffmann -S: Maintained +S: Odd Fixes F: hw/display/virtio-gpu* F: hw/display/virtio-vga.* F: include/hw/virtio/virtio-gpu.h @@ -2130,7 +2176,7 @@ F: include/hw/virtio/vhost-user-scsi.h vhost-user-gpu M: Marc-André Lureau -M: Gerd Hoffmann +R: Gerd Hoffmann S: Maintained F: docs/interop/vhost-user-gpu.rst F: contrib/vhost-user-gpu @@ -2158,7 +2204,6 @@ F: include/hw/southbridge/piix.h Firmware configuration (fw_cfg) M: Philippe Mathieu-Daudé -R: Laszlo Ersek R: Gerd Hoffmann S: Supported F: docs/specs/fw_cfg.txt @@ -2213,7 +2258,7 @@ Subsystems ---------- Audio M: Gerd Hoffmann -S: Maintained +S: Odd Fixes F: audio/ F: hw/audio/ F: include/hw/audio/ @@ -2221,10 +2266,11 @@ F: qapi/audio.json F: tests/qtest/ac97-test.c F: tests/qtest/es1370-test.c F: tests/qtest/intel-hda-test.c +F: tests/qtest/fuzz-sb16-test.c Block layer core M: Kevin Wolf -M: Max Reitz +M: Hanna Reitz L: qemu-block@nongnu.org S: Supported F: block* @@ -2405,22 +2451,26 @@ F: tests/tcg/multiarch/gdbstub/ Memory API M: Paolo Bonzini +M: Peter Xu +M: David Hildenbrand S: Supported F: include/exec/ioport.h F: include/exec/memop.h F: include/exec/memory.h F: include/exec/ram_addr.h F: include/exec/ramblock.h +F: include/sysemu/memory_mapping.h F: softmmu/dma-helpers.c F: softmmu/ioport.c F: softmmu/memory.c +F: softmmu/memory_mapping.c F: softmmu/physmem.c F: include/exec/memory-internal.h F: scripts/coccinelle/memory-region-housekeeping.cocci SPICE M: Gerd Hoffmann -S: Supported +S: Odd Fixes F: include/ui/qemu-spice.h F: include/ui/spice-display.h F: ui/spice-*.c @@ -2445,6 +2495,7 @@ F: ui/cocoa.m Main loop M: Paolo Bonzini S: Maintained +F: include/exec/gen-icount.h F: include/qemu/main-loop.h F: include/sysemu/runstate.h F: include/sysemu/runstate-action.h @@ -2499,7 +2550,7 @@ S: Maintained F: net/netmap.c Host Memory Backends -M: Eduardo Habkost +M: David Hildenbrand M: Igor Mammedov S: Maintained F: backends/hostmem*.c @@ -2531,6 +2582,13 @@ Benchmark util M: Vladimir Sementsov-Ogievskiy S: Maintained F: scripts/simplebench/ +T: git https://src.openvz.org/scm/~vsementsov/qemu.git simplebench + +Transactions helper +M: Vladimir Sementsov-Ogievskiy +S: Maintained +F: include/qemu/transactions.h +F: util/transactions.c QAPI M: Markus Armbruster @@ -2692,14 +2750,13 @@ F: scripts/tracetool.py F: scripts/tracetool/ F: scripts/qemu-trace-stap* F: docs/tools/qemu-trace-stap.rst -F: docs/devel/tracing.txt +F: docs/devel/tracing.rst T: git https://github.com/stefanha/qemu.git tracing TPM M: Stefan Berger S: Maintained F: tpm.c -F: stubs/tpm.c F: hw/tpm/* F: include/hw/acpi/tpm.h F: include/sysemu/tpm* @@ -2786,7 +2843,6 @@ F: tests/unit/test-authz-* Sockets M: Daniel P. Berrange -M: Gerd Hoffmann S: Maintained F: include/qemu/sockets.h F: util/qemu-sockets.c @@ -2882,7 +2938,6 @@ F: include/hw/i2c/smbus_slave.h F: include/hw/i2c/smbus_eeprom.h Firmware schema specifications -M: Laszlo Ersek M: Philippe Mathieu-Daudé R: Daniel P. Berrange R: Kashyap Chamarthy @@ -2890,9 +2945,10 @@ S: Maintained F: docs/interop/firmware.json EDK2 Firmware -M: Laszlo Ersek M: Philippe Mathieu-Daudé +R: Gerd Hoffmann S: Supported +F: hw/i386/*ovmf* F: pc-bios/descriptors/??-edk2-*.json F: pc-bios/edk2-* F: roms/Makefile.edk2 @@ -2943,14 +2999,14 @@ M: Warner Losh R: Kyle Evans S: Maintained F: bsd-user/ -F: default-configs/targets/*-bsd-user.mak +F: configs/targets/*-bsd-user.mak T: git https://github.com/qemu-bsd-user/qemu-bsd-user bsd-user-rebase-3.1 Linux user M: Laurent Vivier S: Maintained F: linux-user/ -F: default-configs/targets/*linux-user.mak +F: configs/targets/*linux-user.mak F: scripts/qemu-binfmt-conf.sh F: scripts/update-syscalltbl.sh F: scripts/update-mips-syscall-args.sh @@ -2966,6 +3022,8 @@ F: include/tcg/ TCG Plugins M: Alex Bennée +R: Alexandre Iooss +R: Mahmoud Mandour S: Maintained F: docs/devel/tcg-plugins.rst F: plugins/ @@ -2982,7 +3040,7 @@ F: disas/arm-a64.cc F: disas/libvixl/ ARM TCG target -M: Andrzej Zaborowski +M: Richard Henderson S: Maintained L: qemu-arm@nongnu.org F: tcg/arm/ @@ -3045,17 +3103,12 @@ S: Supported F: block/vmdk.c RBD -M: Jason Dillaman +M: Ilya Dryomov +R: Peter Lieven L: qemu-block@nongnu.org S: Supported F: block/rbd.c -Sheepdog -M: Liu Yuan -L: qemu-block@nongnu.org -S: Odd Fixes -F: block/sheepdog.c - VHDX M: Jeff Cody L: qemu-block@nongnu.org @@ -3124,6 +3177,7 @@ F: block/null.c NVMe Block Driver M: Stefan Hajnoczi R: Fam Zheng +R: Philippe Mathieu-Daudé L: qemu-block@nongnu.org S: Supported F: block/nvme* @@ -3203,6 +3257,7 @@ Linux io_uring M: Aarushi Mehta M: Julia Suvorova M: Stefan Hajnoczi +R: Stefano Garzarella L: qemu-block@nongnu.org S: Maintained F: block/io_uring.c @@ -3210,7 +3265,7 @@ F: stubs/io_uring.c qcow2 M: Kevin Wolf -M: Max Reitz +M: Hanna Reitz L: qemu-block@nongnu.org S: Supported F: block/qcow2* @@ -3224,7 +3279,7 @@ F: block/qcow.c blkdebug M: Kevin Wolf -M: Max Reitz +M: Hanna Reitz L: qemu-block@nongnu.org S: Supported F: block/blkdebug.c @@ -3254,10 +3309,12 @@ F: block/export/vhost-user-blk-server.c F: block/export/vhost-user-blk-server.h F: include/qemu/vhost-user-server.h F: tests/qtest/libqos/vhost-user-blk.c +F: tests/qtest/libqos/vhost-user-blk.h +F: tests/qtest/vhost-user-blk-test.c F: util/vhost-user-server.c FUSE block device exports -M: Max Reitz +M: Hanna Reitz L: qemu-block@nongnu.org S: Supported F: block/export/fuse.c @@ -3312,6 +3369,14 @@ F: include/hw/remote/proxy-memory-listener.h F: hw/remote/iohub.c F: include/hw/remote/iohub.h +EBPF: +M: Jason Wang +R: Andrew Melnychenko +R: Yuri Benditovich +S: Maintained +F: ebpf/* +F: tools/ebpf/* + Build and test automation ------------------------- Build and test automation, general continuous integration @@ -3365,7 +3430,7 @@ Documentation Build system architecture M: Daniel P. Berrange S: Odd Fixes -F: docs/devel/build-system.txt +F: docs/devel/build-system.rst GIT Data Mining Config M: Alex Bennée @@ -3375,7 +3440,7 @@ F: contrib/gitdm/* Incompatible changes R: libvir-list@redhat.com -F: docs/system/deprecated.rst +F: docs/about/deprecated.rst Build System ------------ @@ -3394,6 +3459,7 @@ S: Maintained F: docs/conf.py F: docs/*/conf.py F: docs/sphinx/ +F: docs/_templates/ Miscellaneous ------------- diff --git a/Makefile b/Makefile index bcbbec71a1..401c623a65 100644 --- a/Makefile +++ b/Makefile @@ -14,7 +14,7 @@ SRC_PATH=. # we have explicit rules for everything MAKEFLAGS += -rR -SHELL = /usr/bin/env bash -o pipefail +SHELL = bash -o pipefail # Usage: $(call quiet-command,command and args,"NAME","args to print") # This will run "command and args", and either: @@ -48,9 +48,11 @@ Makefile: .git-submodule-status .PHONY: git-submodule-update git-submodule-update: +ifneq ($(GIT_SUBMODULES_ACTION),ignore) $(call quiet-command, \ (GIT="$(GIT)" "$(SRC_PATH)/scripts/git-submodule.sh" $(GIT_SUBMODULES_ACTION) $(GIT_SUBMODULES)), \ "GIT","$(GIT_SUBMODULES)") +endif # 0. ensure the build tree is okay @@ -127,9 +129,11 @@ endif # 4. Rules to bridge to other makefiles ifneq ($(NINJA),) -MAKE.n = $(findstring n,$(firstword $(MAKEFLAGS))) -MAKE.k = $(findstring k,$(firstword $(MAKEFLAGS))) -MAKE.q = $(findstring q,$(firstword $(MAKEFLAGS))) +# Filter out long options to avoid flags like --no-print-directory which +# may result in false positive match for MAKE.n +MAKE.n = $(findstring n,$(firstword $(filter-out --%,$(MAKEFLAGS)))) +MAKE.k = $(findstring k,$(firstword $(filter-out --%,$(MAKEFLAGS)))) +MAKE.q = $(findstring q,$(firstword $(filter-out --%,$(MAKEFLAGS)))) MAKE.nq = $(if $(word 2, $(MAKE.n) $(MAKE.q)),nq) NINJAFLAGS = $(if $V,-v) $(if $(MAKE.n), -n) $(if $(MAKE.k), -k0) \ $(filter-out -j, $(lastword -j1 $(filter -l% -j%, $(MAKEFLAGS)))) \ @@ -213,7 +217,7 @@ qemu-%.tar.bz2: distclean: clean -$(quiet-@)test -f build.ninja && $(NINJA) $(NINJAFLAGS) -t clean -g || : - rm -f config-host.mak config-host.h* + rm -f config-host.mak config-host.h* config-poison.h rm -f tests/tcg/config-*.mak rm -f config-all-disas.mak config.status rm -f roms/seabios/config.mak roms/vgabios/config.mak diff --git a/README.rst b/README.rst index a92c7394b7..79b19f1481 100644 --- a/README.rst +++ b/README.rst @@ -131,16 +131,16 @@ will be tagged as my-feature-v2. Bug reporting ============= -The QEMU project uses Launchpad as its primary upstream bug tracker. Bugs +The QEMU project uses GitLab issues to track bugs. Bugs found when running code built from QEMU git or upstream released sources should be reported via: -* ``_ +* ``_ If using QEMU via an operating system vendor pre-built binary package, it is preferable to report bugs to the vendor's own bug tracker first. If the bug is also known to affect latest upstream code, it can also be -reported via launchpad. +reported via GitLab. For additional information on bug reporting consult: diff --git a/VERSION b/VERSION index e479d55a5e..dfda3e0b4f 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -5.2.95 +6.1.0 diff --git a/accel/Kconfig b/accel/Kconfig index 461104c771..8bdedb7d15 100644 --- a/accel/Kconfig +++ b/accel/Kconfig @@ -1,6 +1,9 @@ config WHPX bool +config NVMM + bool + config HAX bool diff --git a/accel/accel-common.c b/accel/accel-common.c index 9901b0531c..7b8ec7e0f7 100644 --- a/accel/accel-common.c +++ b/accel/accel-common.c @@ -44,7 +44,7 @@ static const TypeInfo accel_type = { AccelClass *accel_find(const char *opt_name) { char *class_name = g_strdup_printf(ACCEL_CLASS_NAME("%s"), opt_name); - AccelClass *ac = ACCEL_CLASS(object_class_by_name(class_name)); + AccelClass *ac = ACCEL_CLASS(module_object_class_by_name(class_name)); g_free(class_name); return ac; } @@ -54,10 +54,23 @@ static void accel_init_cpu_int_aux(ObjectClass *klass, void *opaque) CPUClass *cc = CPU_CLASS(klass); AccelCPUClass *accel_cpu = opaque; + /* + * The first callback allows accel-cpu to run initializations + * for the CPU, customizing CPU behavior according to the accelerator. + * + * The second one allows the CPU to customize the accel-cpu + * behavior according to the CPU. + * + * The second is currently only used by TCG, to specialize the + * TCGCPUOps depending on the CPU type. + */ cc->accel_cpu = accel_cpu; if (accel_cpu->cpu_class_init) { accel_cpu->cpu_class_init(cc); } + if (cc->init_accel_cpu) { + cc->init_accel_cpu(accel_cpu, cc); + } } /* initialize the arch-specific accel CpuClass interfaces */ @@ -89,6 +102,25 @@ void accel_init_interfaces(AccelClass *ac) accel_init_cpu_interfaces(ac); } +void accel_cpu_instance_init(CPUState *cpu) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (cc->accel_cpu && cc->accel_cpu->cpu_instance_init) { + cc->accel_cpu->cpu_instance_init(cpu); + } +} + +bool accel_cpu_realizefn(CPUState *cpu, Error **errp) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (cc->accel_cpu && cc->accel_cpu->cpu_realizefn) { + return cc->accel_cpu->cpu_realizefn(cpu, errp); + } + return true; +} + static const TypeInfo accel_cpu_type = { .name = TYPE_ACCEL_CPU, .parent = TYPE_OBJECT, diff --git a/accel/accel-softmmu.c b/accel/accel-softmmu.c index 50fa5acaa4..67276e4f52 100644 --- a/accel/accel-softmmu.c +++ b/accel/accel-softmmu.c @@ -72,7 +72,7 @@ void accel_init_ops_interfaces(AccelClass *ac) g_assert(ac_name != NULL); ops_name = g_strdup_printf("%s" ACCEL_OPS_SUFFIX, ac_name); - ops = ACCEL_OPS_CLASS(object_class_by_name(ops_name)); + ops = ACCEL_OPS_CLASS(module_object_class_by_name(ops_name)); g_free(ops_name); /* diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c new file mode 100644 index 0000000000..d1691be989 --- /dev/null +++ b/accel/hvf/hvf-accel-ops.c @@ -0,0 +1,471 @@ +/* + * Copyright 2008 IBM Corporation + * 2008 Red Hat, Inc. + * Copyright 2011 Intel Corporation + * Copyright 2016 Veertu, Inc. + * Copyright 2017 The Android Open Source Project + * + * QEMU Hypervisor.framework support + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + * + * This file contain code under public domain from the hvdos project: + * https://github.com/mist64/hvdos + * + * Parts Copyright (c) 2011 NetApp, Inc. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY NETAPP, INC ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL NETAPP, INC OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "exec/address-spaces.h" +#include "exec/exec-all.h" +#include "sysemu/cpus.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" +#include "sysemu/runstate.h" +#include "qemu/guest-random.h" + +HVFState *hvf_state; + +/* Memory slots */ + +hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size) +{ + hvf_slot *slot; + int x; + for (x = 0; x < hvf_state->num_slots; ++x) { + slot = &hvf_state->slots[x]; + if (slot->size && start < (slot->start + slot->size) && + (start + size) > slot->start) { + return slot; + } + } + return NULL; +} + +struct mac_slot { + int present; + uint64_t size; + uint64_t gpa_start; + uint64_t gva; +}; + +struct mac_slot mac_slots[32]; + +static int do_hvf_set_memory(hvf_slot *slot, hv_memory_flags_t flags) +{ + struct mac_slot *macslot; + hv_return_t ret; + + macslot = &mac_slots[slot->slot_id]; + + if (macslot->present) { + if (macslot->size != slot->size) { + macslot->present = 0; + ret = hv_vm_unmap(macslot->gpa_start, macslot->size); + assert_hvf_ok(ret); + } + } + + if (!slot->size) { + return 0; + } + + macslot->present = 1; + macslot->gpa_start = slot->start; + macslot->size = slot->size; + ret = hv_vm_map(slot->mem, slot->start, slot->size, flags); + assert_hvf_ok(ret); + return 0; +} + +static void hvf_set_phys_mem(MemoryRegionSection *section, bool add) +{ + hvf_slot *mem; + MemoryRegion *area = section->mr; + bool writeable = !area->readonly && !area->rom_device; + hv_memory_flags_t flags; + + if (!memory_region_is_ram(area)) { + if (writeable) { + return; + } else if (!memory_region_is_romd(area)) { + /* + * If the memory device is not in romd_mode, then we actually want + * to remove the hvf memory slot so all accesses will trap. + */ + add = false; + } + } + + mem = hvf_find_overlap_slot( + section->offset_within_address_space, + int128_get64(section->size)); + + if (mem && add) { + if (mem->size == int128_get64(section->size) && + mem->start == section->offset_within_address_space && + mem->mem == (memory_region_get_ram_ptr(area) + + section->offset_within_region)) { + return; /* Same region was attempted to register, go away. */ + } + } + + /* Region needs to be reset. set the size to 0 and remap it. */ + if (mem) { + mem->size = 0; + if (do_hvf_set_memory(mem, 0)) { + error_report("Failed to reset overlapping slot"); + abort(); + } + } + + if (!add) { + return; + } + + if (area->readonly || + (!memory_region_is_ram(area) && memory_region_is_romd(area))) { + flags = HV_MEMORY_READ | HV_MEMORY_EXEC; + } else { + flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC; + } + + /* Now make a new slot. */ + int x; + + for (x = 0; x < hvf_state->num_slots; ++x) { + mem = &hvf_state->slots[x]; + if (!mem->size) { + break; + } + } + + if (x == hvf_state->num_slots) { + error_report("No free slots"); + abort(); + } + + mem->size = int128_get64(section->size); + mem->mem = memory_region_get_ram_ptr(area) + section->offset_within_region; + mem->start = section->offset_within_address_space; + mem->region = area; + + if (do_hvf_set_memory(mem, flags)) { + error_report("Error registering new memory slot"); + abort(); + } +} + +static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg) +{ + if (!cpu->vcpu_dirty) { + hvf_get_registers(cpu); + cpu->vcpu_dirty = true; + } +} + +static void hvf_cpu_synchronize_state(CPUState *cpu) +{ + if (!cpu->vcpu_dirty) { + run_on_cpu(cpu, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL); + } +} + +static void do_hvf_cpu_synchronize_set_dirty(CPUState *cpu, + run_on_cpu_data arg) +{ + /* QEMU state is the reference, push it to HVF now and on next entry */ + cpu->vcpu_dirty = true; +} + +static void hvf_cpu_synchronize_post_reset(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_set_dirty, RUN_ON_CPU_NULL); +} + +static void hvf_cpu_synchronize_post_init(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_set_dirty, RUN_ON_CPU_NULL); +} + +static void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu) +{ + run_on_cpu(cpu, do_hvf_cpu_synchronize_set_dirty, RUN_ON_CPU_NULL); +} + +static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on) +{ + hvf_slot *slot; + + slot = hvf_find_overlap_slot( + section->offset_within_address_space, + int128_get64(section->size)); + + /* protect region against writes; begin tracking it */ + if (on) { + slot->flags |= HVF_SLOT_LOG; + hv_vm_protect((uintptr_t)slot->start, (size_t)slot->size, + HV_MEMORY_READ); + /* stop tracking region*/ + } else { + slot->flags &= ~HVF_SLOT_LOG; + hv_vm_protect((uintptr_t)slot->start, (size_t)slot->size, + HV_MEMORY_READ | HV_MEMORY_WRITE); + } +} + +static void hvf_log_start(MemoryListener *listener, + MemoryRegionSection *section, int old, int new) +{ + if (old != 0) { + return; + } + + hvf_set_dirty_tracking(section, 1); +} + +static void hvf_log_stop(MemoryListener *listener, + MemoryRegionSection *section, int old, int new) +{ + if (new != 0) { + return; + } + + hvf_set_dirty_tracking(section, 0); +} + +static void hvf_log_sync(MemoryListener *listener, + MemoryRegionSection *section) +{ + /* + * sync of dirty pages is handled elsewhere; just make sure we keep + * tracking the region. + */ + hvf_set_dirty_tracking(section, 1); +} + +static void hvf_region_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + hvf_set_phys_mem(section, true); +} + +static void hvf_region_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + hvf_set_phys_mem(section, false); +} + +static MemoryListener hvf_memory_listener = { + .priority = 10, + .region_add = hvf_region_add, + .region_del = hvf_region_del, + .log_start = hvf_log_start, + .log_stop = hvf_log_stop, + .log_sync = hvf_log_sync, +}; + +static void dummy_signal(int sig) +{ +} + +bool hvf_allowed; + +static int hvf_accel_init(MachineState *ms) +{ + int x; + hv_return_t ret; + HVFState *s; + + ret = hv_vm_create(HV_VM_DEFAULT); + assert_hvf_ok(ret); + + s = g_new0(HVFState, 1); + + s->num_slots = 32; + for (x = 0; x < s->num_slots; ++x) { + s->slots[x].size = 0; + s->slots[x].slot_id = x; + } + + hvf_state = s; + memory_listener_register(&hvf_memory_listener, &address_space_memory); + return 0; +} + +static void hvf_accel_class_init(ObjectClass *oc, void *data) +{ + AccelClass *ac = ACCEL_CLASS(oc); + ac->name = "HVF"; + ac->init_machine = hvf_accel_init; + ac->allowed = &hvf_allowed; +} + +static const TypeInfo hvf_accel_type = { + .name = TYPE_HVF_ACCEL, + .parent = TYPE_ACCEL, + .class_init = hvf_accel_class_init, +}; + +static void hvf_type_init(void) +{ + type_register_static(&hvf_accel_type); +} + +type_init(hvf_type_init); + +static void hvf_vcpu_destroy(CPUState *cpu) +{ + hv_return_t ret = hv_vcpu_destroy(cpu->hvf->fd); + assert_hvf_ok(ret); + + hvf_arch_vcpu_destroy(cpu); + g_free(cpu->hvf); + cpu->hvf = NULL; +} + +static int hvf_init_vcpu(CPUState *cpu) +{ + int r; + + cpu->hvf = g_malloc0(sizeof(*cpu->hvf)); + + /* init cpu signals */ + sigset_t set; + struct sigaction sigact; + + memset(&sigact, 0, sizeof(sigact)); + sigact.sa_handler = dummy_signal; + sigaction(SIG_IPI, &sigact, NULL); + + pthread_sigmask(SIG_BLOCK, NULL, &set); + sigdelset(&set, SIG_IPI); + + r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf->fd, HV_VCPU_DEFAULT); + cpu->vcpu_dirty = 1; + assert_hvf_ok(r); + + return hvf_arch_init_vcpu(cpu); +} + +/* + * The HVF-specific vCPU thread function. This one should only run when the host + * CPU supports the VMX "unrestricted guest" feature. + */ +static void *hvf_cpu_thread_fn(void *arg) +{ + CPUState *cpu = arg; + + int r; + + assert(hvf_enabled()); + + rcu_register_thread(); + + qemu_mutex_lock_iothread(); + qemu_thread_get_self(cpu->thread); + + cpu->thread_id = qemu_get_thread_id(); + cpu->can_do_io = 1; + current_cpu = cpu; + + hvf_init_vcpu(cpu); + + /* signal CPU creation */ + cpu_thread_signal_created(cpu); + qemu_guest_random_seed_thread_part2(cpu->random_seed); + + do { + if (cpu_can_run(cpu)) { + r = hvf_vcpu_exec(cpu); + if (r == EXCP_DEBUG) { + cpu_handle_guest_debug(cpu); + } + } + qemu_wait_io_event(cpu); + } while (!cpu->unplug || cpu_can_run(cpu)); + + hvf_vcpu_destroy(cpu); + cpu_thread_signal_destroyed(cpu); + qemu_mutex_unlock_iothread(); + rcu_unregister_thread(); + return NULL; +} + +static void hvf_start_vcpu_thread(CPUState *cpu) +{ + char thread_name[VCPU_THREAD_NAME_SIZE]; + + /* + * HVF currently does not support TCG, and only runs in + * unrestricted-guest mode. + */ + assert(hvf_enabled()); + + cpu->thread = g_malloc0(sizeof(QemuThread)); + cpu->halt_cond = g_malloc0(sizeof(QemuCond)); + qemu_cond_init(cpu->halt_cond); + + snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/HVF", + cpu->cpu_index); + qemu_thread_create(cpu->thread, thread_name, hvf_cpu_thread_fn, + cpu, QEMU_THREAD_JOINABLE); +} + +static void hvf_accel_ops_class_init(ObjectClass *oc, void *data) +{ + AccelOpsClass *ops = ACCEL_OPS_CLASS(oc); + + ops->create_vcpu_thread = hvf_start_vcpu_thread; + + ops->synchronize_post_reset = hvf_cpu_synchronize_post_reset; + ops->synchronize_post_init = hvf_cpu_synchronize_post_init; + ops->synchronize_state = hvf_cpu_synchronize_state; + ops->synchronize_pre_loadvm = hvf_cpu_synchronize_pre_loadvm; +}; +static const TypeInfo hvf_accel_ops_type = { + .name = ACCEL_OPS_NAME("hvf"), + + .parent = TYPE_ACCEL_OPS, + .class_init = hvf_accel_ops_class_init, + .abstract = true, +}; +static void hvf_accel_ops_register_types(void) +{ + type_register_static(&hvf_accel_ops_type); +} +type_init(hvf_accel_ops_register_types); diff --git a/accel/hvf/hvf-all.c b/accel/hvf/hvf-all.c new file mode 100644 index 0000000000..f185b0830a --- /dev/null +++ b/accel/hvf/hvf-all.c @@ -0,0 +1,47 @@ +/* + * QEMU Hypervisor.framework support + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "sysemu/hvf.h" +#include "sysemu/hvf_int.h" + +void assert_hvf_ok(hv_return_t ret) +{ + if (ret == HV_SUCCESS) { + return; + } + + switch (ret) { + case HV_ERROR: + error_report("Error: HV_ERROR"); + break; + case HV_BUSY: + error_report("Error: HV_BUSY"); + break; + case HV_BAD_ARGUMENT: + error_report("Error: HV_BAD_ARGUMENT"); + break; + case HV_NO_RESOURCES: + error_report("Error: HV_NO_RESOURCES"); + break; + case HV_NO_DEVICE: + error_report("Error: HV_NO_DEVICE"); + break; + case HV_UNSUPPORTED: + error_report("Error: HV_UNSUPPORTED"); + break; + default: + error_report("Unknown Error"); + } + + abort(); +} diff --git a/accel/hvf/meson.build b/accel/hvf/meson.build new file mode 100644 index 0000000000..fc52cb7843 --- /dev/null +++ b/accel/hvf/meson.build @@ -0,0 +1,7 @@ +hvf_ss = ss.source_set() +hvf_ss.add(files( + 'hvf-all.c', + 'hvf-accel-ops.c', +)) + +specific_ss.add_all(when: 'CONFIG_HVF', if_true: hvf_ss) diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index b6d9f92f15..0125c17edb 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -15,6 +15,7 @@ #include "qemu/osdep.h" #include +#include #include @@ -30,11 +31,9 @@ #include "sysemu/kvm_int.h" #include "sysemu/runstate.h" #include "sysemu/cpus.h" -#include "sysemu/sysemu.h" #include "qemu/bswap.h" #include "exec/memory.h" #include "exec/ram_addr.h" -#include "exec/address-spaces.h" #include "qemu/event_notifier.h" #include "qemu/main-loop.h" #include "trace.h" @@ -80,6 +79,25 @@ struct KVMParkedVcpu { QLIST_ENTRY(KVMParkedVcpu) node; }; +enum KVMDirtyRingReaperState { + KVM_DIRTY_RING_REAPER_NONE = 0, + /* The reaper is sleeping */ + KVM_DIRTY_RING_REAPER_WAIT, + /* The reaper is reaping for dirty pages */ + KVM_DIRTY_RING_REAPER_REAPING, +}; + +/* + * KVM reaper instance, responsible for collecting the KVM dirty bits + * via the dirty ring. + */ +struct KVMDirtyRingReaper { + /* The reaper thread */ + QemuThread reaper_thr; + volatile uint64_t reaper_iteration; /* iteration number of reaper thr */ + volatile enum KVMDirtyRingReaperState reaper_state; /* reap thr state */ +}; + struct KVMState { AccelState parent_obj; @@ -128,6 +146,9 @@ struct KVMState KVMMemoryListener *ml; AddressSpace *as; } *as; + uint64_t kvm_dirty_ring_bytes; /* Size of the per-vcpu dirty ring */ + uint32_t kvm_dirty_ring_size; /* Number of dirty GFNs per ring */ + struct KVMDirtyRingReaper reaper; }; KVMState *kvm_state; @@ -174,8 +195,12 @@ typedef struct KVMResampleFd KVMResampleFd; static QLIST_HEAD(, KVMResampleFd) kvm_resample_fd_list = QLIST_HEAD_INITIALIZER(kvm_resample_fd_list); -#define kvm_slots_lock(kml) qemu_mutex_lock(&(kml)->slots_lock) -#define kvm_slots_unlock(kml) qemu_mutex_unlock(&(kml)->slots_lock) +static QemuMutex kml_slots_lock; + +#define kvm_slots_lock() qemu_mutex_lock(&kml_slots_lock) +#define kvm_slots_unlock() qemu_mutex_unlock(&kml_slots_lock) + +static void kvm_slot_init_dirty_bitmap(KVMSlot *mem); static inline void kvm_resample_fd_remove(int gsi) { @@ -241,9 +266,9 @@ bool kvm_has_free_slot(MachineState *ms) bool result; KVMMemoryListener *kml = &s->memory_listener; - kvm_slots_lock(kml); + kvm_slots_lock(); result = !!kvm_get_free_slot(kml); - kvm_slots_unlock(kml); + kvm_slots_unlock(); return result; } @@ -309,7 +334,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram, KVMMemoryListener *kml = &s->memory_listener; int i, ret = 0; - kvm_slots_lock(kml); + kvm_slots_lock(); for (i = 0; i < s->nr_slots; i++) { KVMSlot *mem = &kml->slots[i]; @@ -319,7 +344,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram, break; } } - kvm_slots_unlock(kml); + kvm_slots_unlock(); return ret; } @@ -385,6 +410,13 @@ static int do_kvm_destroy_vcpu(CPUState *cpu) goto err; } + if (cpu->kvm_dirty_gfns) { + ret = munmap(cpu->kvm_dirty_gfns, s->kvm_dirty_ring_bytes); + if (ret < 0) { + goto err; + } + } + vcpu = g_malloc0(sizeof(*vcpu)); vcpu->vcpu_id = kvm_arch_vcpu_id(cpu); vcpu->kvm_fd = cpu->kvm_fd; @@ -461,6 +493,19 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp) (void *)cpu->kvm_run + s->coalesced_mmio * PAGE_SIZE; } + if (s->kvm_dirty_ring_size) { + /* Use MAP_SHARED to share pages with the kernel */ + cpu->kvm_dirty_gfns = mmap(NULL, s->kvm_dirty_ring_bytes, + PROT_READ | PROT_WRITE, MAP_SHARED, + cpu->kvm_fd, + PAGE_SIZE * KVM_DIRTY_LOG_PAGE_OFFSET); + if (cpu->kvm_dirty_gfns == MAP_FAILED) { + ret = -errno; + DPRINTF("mmap'ing vcpu dirty gfns failed: %d\n", ret); + goto err; + } + } + ret = kvm_arch_init_vcpu(cpu); if (ret < 0) { error_setg_errno(errp, -ret, @@ -500,6 +545,7 @@ static int kvm_slot_update_flags(KVMMemoryListener *kml, KVMSlot *mem, return 0; } + kvm_slot_init_dirty_bitmap(mem); return kvm_set_user_memory_region(kml, mem, false); } @@ -515,7 +561,7 @@ static int kvm_section_update_flags(KVMMemoryListener *kml, return 0; } - kvm_slots_lock(kml); + kvm_slots_lock(); while (size && !ret) { slot_size = MIN(kvm_max_slot_size, size); @@ -531,7 +577,7 @@ static int kvm_section_update_flags(KVMMemoryListener *kml, } out: - kvm_slots_unlock(kml); + kvm_slots_unlock(); return ret; } @@ -570,22 +616,28 @@ static void kvm_log_stop(MemoryListener *listener, } /* get kvm's dirty pages bitmap and update qemu's */ -static int kvm_get_dirty_pages_log_range(MemoryRegionSection *section, - unsigned long *bitmap) +static void kvm_slot_sync_dirty_pages(KVMSlot *slot) { - ram_addr_t start = section->offset_within_region + - memory_region_get_ram_addr(section->mr); - ram_addr_t pages = int128_get64(section->size) / qemu_real_host_page_size; + ram_addr_t start = slot->ram_start_offset; + ram_addr_t pages = slot->memory_size / qemu_real_host_page_size; - cpu_physical_memory_set_dirty_lebitmap(bitmap, start, pages); - return 0; + cpu_physical_memory_set_dirty_lebitmap(slot->dirty_bmap, start, pages); +} + +static void kvm_slot_reset_dirty_pages(KVMSlot *slot) +{ + memset(slot->dirty_bmap, 0, slot->dirty_bmap_size); } #define ALIGN(x, y) (((x)+(y)-1) & ~((y)-1)) /* Allocate the dirty bitmap for a slot */ -static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem) +static void kvm_slot_init_dirty_bitmap(KVMSlot *mem) { + if (!(mem->flags & KVM_MEM_LOG_DIRTY_PAGES) || mem->dirty_bmap) { + return; + } + /* * XXX bad kernel interface alert * For dirty bitmap, kernel allocates array of size aligned to @@ -606,6 +658,196 @@ static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem) hwaddr bitmap_size = ALIGN(mem->memory_size / qemu_real_host_page_size, /*HOST_LONG_BITS*/ 64) / 8; mem->dirty_bmap = g_malloc0(bitmap_size); + mem->dirty_bmap_size = bitmap_size; +} + +/* + * Sync dirty bitmap from kernel to KVMSlot.dirty_bmap, return true if + * succeeded, false otherwise + */ +static bool kvm_slot_get_dirty_log(KVMState *s, KVMSlot *slot) +{ + struct kvm_dirty_log d = {}; + int ret; + + d.dirty_bitmap = slot->dirty_bmap; + d.slot = slot->slot | (slot->as_id << 16); + ret = kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d); + + if (ret == -ENOENT) { + /* kernel does not have dirty bitmap in this slot */ + ret = 0; + } + if (ret) { + error_report_once("%s: KVM_GET_DIRTY_LOG failed with %d", + __func__, ret); + } + return ret == 0; +} + +/* Should be with all slots_lock held for the address spaces. */ +static void kvm_dirty_ring_mark_page(KVMState *s, uint32_t as_id, + uint32_t slot_id, uint64_t offset) +{ + KVMMemoryListener *kml; + KVMSlot *mem; + + if (as_id >= s->nr_as) { + return; + } + + kml = s->as[as_id].ml; + mem = &kml->slots[slot_id]; + + if (!mem->memory_size || offset >= + (mem->memory_size / qemu_real_host_page_size)) { + return; + } + + set_bit(offset, mem->dirty_bmap); +} + +static bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn) +{ + return gfn->flags == KVM_DIRTY_GFN_F_DIRTY; +} + +static void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn) +{ + gfn->flags = KVM_DIRTY_GFN_F_RESET; +} + +/* + * Should be with all slots_lock held for the address spaces. It returns the + * dirty page we've collected on this dirty ring. + */ +static uint32_t kvm_dirty_ring_reap_one(KVMState *s, CPUState *cpu) +{ + struct kvm_dirty_gfn *dirty_gfns = cpu->kvm_dirty_gfns, *cur; + uint32_t ring_size = s->kvm_dirty_ring_size; + uint32_t count = 0, fetch = cpu->kvm_fetch_index; + + assert(dirty_gfns && ring_size); + trace_kvm_dirty_ring_reap_vcpu(cpu->cpu_index); + + while (true) { + cur = &dirty_gfns[fetch % ring_size]; + if (!dirty_gfn_is_dirtied(cur)) { + break; + } + kvm_dirty_ring_mark_page(s, cur->slot >> 16, cur->slot & 0xffff, + cur->offset); + dirty_gfn_set_collected(cur); + trace_kvm_dirty_ring_page(cpu->cpu_index, fetch, cur->offset); + fetch++; + count++; + } + cpu->kvm_fetch_index = fetch; + + return count; +} + +/* Must be with slots_lock held */ +static uint64_t kvm_dirty_ring_reap_locked(KVMState *s) +{ + int ret; + CPUState *cpu; + uint64_t total = 0; + int64_t stamp; + + stamp = get_clock(); + + CPU_FOREACH(cpu) { + total += kvm_dirty_ring_reap_one(s, cpu); + } + + if (total) { + ret = kvm_vm_ioctl(s, KVM_RESET_DIRTY_RINGS); + assert(ret == total); + } + + stamp = get_clock() - stamp; + + if (total) { + trace_kvm_dirty_ring_reap(total, stamp / 1000); + } + + return total; +} + +/* + * Currently for simplicity, we must hold BQL before calling this. We can + * consider to drop the BQL if we're clear with all the race conditions. + */ +static uint64_t kvm_dirty_ring_reap(KVMState *s) +{ + uint64_t total; + + /* + * We need to lock all kvm slots for all address spaces here, + * because: + * + * (1) We need to mark dirty for dirty bitmaps in multiple slots + * and for tons of pages, so it's better to take the lock here + * once rather than once per page. And more importantly, + * + * (2) We must _NOT_ publish dirty bits to the other threads + * (e.g., the migration thread) via the kvm memory slot dirty + * bitmaps before correctly re-protect those dirtied pages. + * Otherwise we can have potential risk of data corruption if + * the page data is read in the other thread before we do + * reset below. + */ + kvm_slots_lock(); + total = kvm_dirty_ring_reap_locked(s); + kvm_slots_unlock(); + + return total; +} + +static void do_kvm_cpu_synchronize_kick(CPUState *cpu, run_on_cpu_data arg) +{ + /* No need to do anything */ +} + +/* + * Kick all vcpus out in a synchronized way. When returned, we + * guarantee that every vcpu has been kicked and at least returned to + * userspace once. + */ +static void kvm_cpu_synchronize_kick_all(void) +{ + CPUState *cpu; + + CPU_FOREACH(cpu) { + run_on_cpu(cpu, do_kvm_cpu_synchronize_kick, RUN_ON_CPU_NULL); + } +} + +/* + * Flush all the existing dirty pages to the KVM slot buffers. When + * this call returns, we guarantee that all the touched dirty pages + * before calling this function have been put into the per-kvmslot + * dirty bitmap. + * + * This function must be called with BQL held. + */ +static void kvm_dirty_ring_flush(void) +{ + trace_kvm_dirty_ring_flush(0); + /* + * The function needs to be serialized. Since this function + * should always be with BQL held, serialization is guaranteed. + * However, let's be sure of it. + */ + assert(qemu_mutex_iothread_locked()); + /* + * First make sure to flush the hardware buffers by kicking all + * vcpus out in a synchronous way. + */ + kvm_cpu_synchronize_kick_all(); + kvm_dirty_ring_reap(kvm_state); + trace_kvm_dirty_ring_flush(1); } /** @@ -619,53 +861,28 @@ static void kvm_memslot_init_dirty_bitmap(KVMSlot *mem) * @kml: the KVM memory listener object * @section: the memory section to sync the dirty bitmap with */ -static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml, - MemoryRegionSection *section) +static void kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml, + MemoryRegionSection *section) { KVMState *s = kvm_state; - struct kvm_dirty_log d = {}; KVMSlot *mem; hwaddr start_addr, size; - hwaddr slot_size, slot_offset = 0; - int ret = 0; + hwaddr slot_size; size = kvm_align_section(section, &start_addr); while (size) { - MemoryRegionSection subsection = *section; - slot_size = MIN(kvm_max_slot_size, size); mem = kvm_lookup_matching_slot(kml, start_addr, slot_size); if (!mem) { /* We don't have a slot if we want to trap every access. */ - goto out; + return; } - - if (!mem->dirty_bmap) { - /* Allocate on the first log_sync, once and for all */ - kvm_memslot_init_dirty_bitmap(mem); + if (kvm_slot_get_dirty_log(s, mem)) { + kvm_slot_sync_dirty_pages(mem); } - - d.dirty_bitmap = mem->dirty_bmap; - d.slot = mem->slot | (kml->as_id << 16); - ret = kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d); - if (ret == -ENOENT) { - /* kernel does not have dirty bitmap in this slot */ - ret = 0; - } else if (ret < 0) { - error_report("ioctl KVM_GET_DIRTY_LOG failed: %d", errno); - goto out; - } else { - subsection.offset_within_region += slot_offset; - subsection.size = int128_make64(slot_size); - kvm_get_dirty_pages_log_range(&subsection, d.dirty_bitmap); - } - - slot_offset += slot_size; start_addr += slot_size; size -= slot_size; } -out: - return ret; } /* Alignment requirement for KVM_CLEAR_DIRTY_LOG - 64 pages */ @@ -812,7 +1029,7 @@ static int kvm_physical_log_clear(KVMMemoryListener *kml, return ret; } - kvm_slots_lock(kml); + kvm_slots_lock(); for (i = 0; i < s->nr_slots; i++) { mem = &kml->slots[i]; @@ -838,7 +1055,7 @@ static int kvm_physical_log_clear(KVMMemoryListener *kml, } } - kvm_slots_unlock(kml); + kvm_slots_unlock(); return ret; } @@ -1121,7 +1338,8 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, int err; MemoryRegion *mr = section->mr; bool writeable = !mr->readonly && !mr->rom_device; - hwaddr start_addr, size, slot_size; + hwaddr start_addr, size, slot_size, mr_offset; + ram_addr_t ram_start_offset; void *ram; if (!memory_region_is_ram(mr)) { @@ -1139,11 +1357,15 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, return; } - /* use aligned delta to align the ram address */ - ram = memory_region_get_ram_ptr(mr) + section->offset_within_region + - (start_addr - section->offset_within_address_space); + /* The offset of the kvmslot within the memory region */ + mr_offset = section->offset_within_region + start_addr - + section->offset_within_address_space; - kvm_slots_lock(kml); + /* use aligned delta to align the ram address and offset */ + ram = memory_region_get_ram_ptr(mr) + mr_offset; + ram_start_offset = memory_region_get_ram_addr(mr) + mr_offset; + + kvm_slots_lock(); if (!add) { do { @@ -1153,7 +1375,25 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, goto out; } if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { - kvm_physical_sync_dirty_bitmap(kml, section); + /* + * NOTE: We should be aware of the fact that here we're only + * doing a best effort to sync dirty bits. No matter whether + * we're using dirty log or dirty ring, we ignored two facts: + * + * (1) dirty bits can reside in hardware buffers (PML) + * + * (2) after we collected dirty bits here, pages can be dirtied + * again before we do the final KVM_SET_USER_MEMORY_REGION to + * remove the slot. + * + * Not easy. Let's cross the fingers until it's fixed. + */ + if (kvm_state->kvm_dirty_ring_size) { + kvm_dirty_ring_reap_locked(kvm_state); + } else { + kvm_slot_get_dirty_log(kvm_state, mem); + } + kvm_slot_sync_dirty_pages(mem); } /* unregister the slot */ @@ -1177,18 +1417,13 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, do { slot_size = MIN(kvm_max_slot_size, size); mem = kvm_alloc_slot(kml); + mem->as_id = kml->as_id; mem->memory_size = slot_size; mem->start_addr = start_addr; + mem->ram_start_offset = ram_start_offset; mem->ram = ram; mem->flags = kvm_mem_flags(mr); - - if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { - /* - * Reallocate the bmap; it means it doesn't disappear in - * middle of a migrate. - */ - kvm_memslot_init_dirty_bitmap(mem); - } + kvm_slot_init_dirty_bitmap(mem); err = kvm_set_user_memory_region(kml, mem, true); if (err) { fprintf(stderr, "%s: error registering slot: %s\n", __func__, @@ -1196,12 +1431,58 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, abort(); } start_addr += slot_size; + ram_start_offset += slot_size; ram += slot_size; size -= slot_size; } while (size); out: - kvm_slots_unlock(kml); + kvm_slots_unlock(); +} + +static void *kvm_dirty_ring_reaper_thread(void *data) +{ + KVMState *s = data; + struct KVMDirtyRingReaper *r = &s->reaper; + + rcu_register_thread(); + + trace_kvm_dirty_ring_reaper("init"); + + while (true) { + r->reaper_state = KVM_DIRTY_RING_REAPER_WAIT; + trace_kvm_dirty_ring_reaper("wait"); + /* + * TODO: provide a smarter timeout rather than a constant? + */ + sleep(1); + + trace_kvm_dirty_ring_reaper("wakeup"); + r->reaper_state = KVM_DIRTY_RING_REAPER_REAPING; + + qemu_mutex_lock_iothread(); + kvm_dirty_ring_reap(s); + qemu_mutex_unlock_iothread(); + + r->reaper_iteration++; + } + + trace_kvm_dirty_ring_reaper("exit"); + + rcu_unregister_thread(); + + return NULL; +} + +static int kvm_dirty_ring_reaper_init(KVMState *s) +{ + struct KVMDirtyRingReaper *r = &s->reaper; + + qemu_thread_create(&r->reaper_thr, "kvm-reaper", + kvm_dirty_ring_reaper_thread, + s, QEMU_THREAD_JOINABLE); + + return 0; } static void kvm_region_add(MemoryListener *listener, @@ -1226,14 +1507,40 @@ static void kvm_log_sync(MemoryListener *listener, MemoryRegionSection *section) { KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener); - int r; - kvm_slots_lock(kml); - r = kvm_physical_sync_dirty_bitmap(kml, section); - kvm_slots_unlock(kml); - if (r < 0) { - abort(); + kvm_slots_lock(); + kvm_physical_sync_dirty_bitmap(kml, section); + kvm_slots_unlock(); +} + +static void kvm_log_sync_global(MemoryListener *l) +{ + KVMMemoryListener *kml = container_of(l, KVMMemoryListener, listener); + KVMState *s = kvm_state; + KVMSlot *mem; + int i; + + /* Flush all kernel dirty addresses into KVMSlot dirty bitmap */ + kvm_dirty_ring_flush(); + + /* + * TODO: make this faster when nr_slots is big while there are + * only a few used slots (small VMs). + */ + kvm_slots_lock(); + for (i = 0; i < s->nr_slots; i++) { + mem = &kml->slots[i]; + if (mem->memory_size && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { + kvm_slot_sync_dirty_pages(mem); + /* + * This is not needed by KVM_GET_DIRTY_LOG because the + * ioctl will unconditionally overwrite the whole region. + * However kvm dirty ring has no such side effect. + */ + kvm_slot_reset_dirty_pages(mem); + } } + kvm_slots_unlock(); } static void kvm_log_clear(MemoryListener *listener, @@ -1330,7 +1637,6 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, { int i; - qemu_mutex_init(&kml->slots_lock); kml->slots = g_malloc0(s->nr_slots * sizeof(KVMSlot)); kml->as_id = as_id; @@ -1342,10 +1648,15 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, kml->listener.region_del = kvm_region_del; kml->listener.log_start = kvm_log_start; kml->listener.log_stop = kvm_log_stop; - kml->listener.log_sync = kvm_log_sync; - kml->listener.log_clear = kvm_log_clear; kml->listener.priority = 10; + if (s->kvm_dirty_ring_size) { + kml->listener.log_sync_global = kvm_log_sync_global; + } else { + kml->listener.log_sync = kvm_log_sync; + kml->listener.log_clear = kvm_log_clear; + } + memory_listener_register(&kml->listener, as); for (i = 0; i < s->nr_as; ++i) { @@ -2003,6 +2314,8 @@ static int kvm_init(MachineState *ms) int type = 0; uint64_t dirty_log_manual_caps; + qemu_mutex_init(&kml_slots_lock); + s = KVM_STATE(ms->accelerator); /* @@ -2019,7 +2332,6 @@ static int kvm_init(MachineState *ms) QTAILQ_INIT(&s->kvm_sw_breakpoints); #endif QLIST_INIT(&s->kvm_parked_vcpus); - s->vmfd = -1; s->fd = qemu_open_old("/dev/kvm", O_RDWR); if (s->fd == -1) { fprintf(stderr, "Could not access KVM kernel module: %m\n"); @@ -2085,6 +2397,12 @@ static int kvm_init(MachineState *ms) "- for kernels supporting the vm.allocate_pgste sysctl, " "whether it is enabled\n"); } +#elif defined(TARGET_PPC) + if (ret == -EINVAL) { + fprintf(stderr, + "PPC KVM module is not loaded. Try modprobe kvm_%s.\n", + (type == 2) ? "pr" : "hv"); + } #endif goto err; } @@ -2127,20 +2445,70 @@ static int kvm_init(MachineState *ms) s->coalesced_pio = s->coalesced_mmio && kvm_check_extension(s, KVM_CAP_COALESCED_PIO); - dirty_log_manual_caps = - kvm_check_extension(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); - dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | - KVM_DIRTY_LOG_INITIALLY_SET); - s->manual_dirty_log_protect = dirty_log_manual_caps; - if (dirty_log_manual_caps) { - ret = kvm_vm_enable_cap(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, 0, - dirty_log_manual_caps); - if (ret) { - warn_report("Trying to enable capability %"PRIu64" of " - "KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 but failed. " - "Falling back to the legacy mode. ", - dirty_log_manual_caps); - s->manual_dirty_log_protect = 0; + /* + * Enable KVM dirty ring if supported, otherwise fall back to + * dirty logging mode + */ + if (s->kvm_dirty_ring_size > 0) { + uint64_t ring_bytes; + + ring_bytes = s->kvm_dirty_ring_size * sizeof(struct kvm_dirty_gfn); + + /* Read the max supported pages */ + ret = kvm_vm_check_extension(s, KVM_CAP_DIRTY_LOG_RING); + if (ret > 0) { + if (ring_bytes > ret) { + error_report("KVM dirty ring size %" PRIu32 " too big " + "(maximum is %ld). Please use a smaller value.", + s->kvm_dirty_ring_size, + (long)ret / sizeof(struct kvm_dirty_gfn)); + ret = -EINVAL; + goto err; + } + + ret = kvm_vm_enable_cap(s, KVM_CAP_DIRTY_LOG_RING, 0, ring_bytes); + if (ret) { + error_report("Enabling of KVM dirty ring failed: %s. " + "Suggested mininum value is 1024.", strerror(-ret)); + goto err; + } + + s->kvm_dirty_ring_bytes = ring_bytes; + } else { + warn_report("KVM dirty ring not available, using bitmap method"); + s->kvm_dirty_ring_size = 0; + } + } + + /* + * KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is not needed when dirty ring is + * enabled. More importantly, KVM_DIRTY_LOG_INITIALLY_SET will assume no + * page is wr-protected initially, which is against how kvm dirty ring is + * usage - kvm dirty ring requires all pages are wr-protected at the very + * beginning. Enabling this feature for dirty ring causes data corruption. + * + * TODO: Without KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 and kvm clear dirty log, + * we may expect a higher stall time when starting the migration. In the + * future we can enable KVM_CLEAR_DIRTY_LOG to work with dirty ring too: + * instead of clearing dirty bit, it can be a way to explicitly wr-protect + * guest pages. + */ + if (!s->kvm_dirty_ring_size) { + dirty_log_manual_caps = + kvm_check_extension(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); + s->manual_dirty_log_protect = dirty_log_manual_caps; + if (dirty_log_manual_caps) { + ret = kvm_vm_enable_cap(s, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, 0, + dirty_log_manual_caps); + if (ret) { + warn_report("Trying to enable capability %"PRIu64" of " + "KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 but failed. " + "Falling back to the legacy mode. ", + dirty_log_manual_caps); + s->manual_dirty_log_protect = 0; + } } } @@ -2226,6 +2594,14 @@ static int kvm_init(MachineState *ms) ret = ram_block_discard_disable(true); assert(!ret); } + + if (s->kvm_dirty_ring_size) { + ret = kvm_dirty_ring_reaper_init(s); + if (ret) { + goto err; + } + } + return 0; err: @@ -2269,7 +2645,7 @@ static int kvm_handle_internal_error(CPUState *cpu, struct kvm_run *run) int i; for (i = 0; i < run->internal.ndata; ++i) { - fprintf(stderr, "extra data[%d]: %"PRIx64"\n", + fprintf(stderr, "extra data[%d]: 0x%016"PRIx64"\n", i, (uint64_t)run->internal.data[i]); } } @@ -2538,6 +2914,17 @@ int kvm_cpu_exec(CPUState *cpu) case KVM_EXIT_INTERNAL_ERROR: ret = kvm_handle_internal_error(cpu, run); break; + case KVM_EXIT_DIRTY_RING_FULL: + /* + * We shouldn't continue if the dirty ring of this vcpu is + * still full. Got kicked by KVM_RESET_DIRTY_RINGS. + */ + trace_kvm_dirty_ring_full(cpu->cpu_index); + qemu_mutex_lock_iothread(); + kvm_dirty_ring_reap(kvm_state); + qemu_mutex_unlock_iothread(); + ret = 0; + break; case KVM_EXIT_SYSTEM_EVENT: switch (run->system_event.type) { case KVM_SYSTEM_EVENT_SHUTDOWN: @@ -3114,6 +3501,11 @@ static void kvm_set_kvm_shadow_mem(Object *obj, Visitor *v, KVMState *s = KVM_STATE(obj); int64_t value; + if (s->fd != -1) { + error_setg(errp, "Cannot set properties after the accelerator has been initialized"); + return; + } + if (!visit_type_int(v, name, &value, errp)) { return; } @@ -3128,6 +3520,11 @@ static void kvm_set_kernel_irqchip(Object *obj, Visitor *v, KVMState *s = KVM_STATE(obj); OnOffSplit mode; + if (s->fd != -1) { + error_setg(errp, "Cannot set properties after the accelerator has been initialized"); + return; + } + if (!visit_type_OnOffSplit(v, name, &mode, errp)) { return; } @@ -3170,13 +3567,53 @@ bool kvm_kernel_irqchip_split(void) return kvm_state->kernel_irqchip_split == ON_OFF_AUTO_ON; } +static void kvm_get_dirty_ring_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + KVMState *s = KVM_STATE(obj); + uint32_t value = s->kvm_dirty_ring_size; + + visit_type_uint32(v, name, &value, errp); +} + +static void kvm_set_dirty_ring_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + KVMState *s = KVM_STATE(obj); + Error *error = NULL; + uint32_t value; + + if (s->fd != -1) { + error_setg(errp, "Cannot set properties after the accelerator has been initialized"); + return; + } + + visit_type_uint32(v, name, &value, &error); + if (error) { + error_propagate(errp, error); + return; + } + if (value & (value - 1)) { + error_setg(errp, "dirty-ring-size must be a power of two."); + return; + } + + s->kvm_dirty_ring_size = value; +} + static void kvm_accel_instance_init(Object *obj) { KVMState *s = KVM_STATE(obj); + s->fd = -1; + s->vmfd = -1; s->kvm_shadow_mem = -1; s->kernel_irqchip_allowed = true; s->kernel_irqchip_split = ON_OFF_AUTO_AUTO; + /* KVM dirty ring is by default off */ + s->kvm_dirty_ring_size = 0; } static void kvm_accel_class_init(ObjectClass *oc, void *data) @@ -3198,6 +3635,12 @@ static void kvm_accel_class_init(ObjectClass *oc, void *data) NULL, NULL); object_class_property_set_description(oc, "kvm-shadow-mem", "KVM shadow MMU size"); + + object_class_property_add(oc, "dirty-ring-size", "uint32", + kvm_get_dirty_ring_size, kvm_set_dirty_ring_size, + NULL, NULL); + object_class_property_set_description(oc, "dirty-ring-size", + "Size of KVM dirty page ring buffer (default: 0, i.e. use bitmap)"); } static const TypeInfo kvm_accel_type = { diff --git a/accel/kvm/trace-events b/accel/kvm/trace-events index e15ae8980d..399aaeb0ec 100644 --- a/accel/kvm/trace-events +++ b/accel/kvm/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # kvm-all.c kvm_ioctl(int type, void *arg) "type 0x%x, arg %p" @@ -18,4 +18,11 @@ kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint32_t val, bool assign, uint32_t kvm_set_user_memory(uint32_t slot, uint32_t flags, uint64_t guest_phys_addr, uint64_t memory_size, uint64_t userspace_addr, int ret) "Slot#%d flags=0x%x gpa=0x%"PRIx64 " size=0x%"PRIx64 " ua=0x%"PRIx64 " ret=%d" kvm_clear_dirty_log(uint32_t slot, uint64_t start, uint32_t size) "slot#%"PRId32" start 0x%"PRIx64" size 0x%"PRIx32 kvm_resample_fd_notify(int gsi) "gsi %d" +kvm_dirty_ring_full(int id) "vcpu %d" +kvm_dirty_ring_reap_vcpu(int id) "vcpu %d" +kvm_dirty_ring_page(int vcpu, uint32_t slot, uint64_t offset) "vcpu %d fetch %"PRIu32" offset 0x%"PRIx64 +kvm_dirty_ring_reaper(const char *s) "%s" +kvm_dirty_ring_reap(uint64_t count, int64_t t) "reaped %"PRIu64" pages (took %"PRIi64" us)" +kvm_dirty_ring_reaper_kick(const char *reason) "%s" +kvm_dirty_ring_flush(int finished) "%d" diff --git a/accel/meson.build b/accel/meson.build index b44ba30c86..dfd808d2c8 100644 --- a/accel/meson.build +++ b/accel/meson.build @@ -2,6 +2,7 @@ specific_ss.add(files('accel-common.c')) softmmu_ss.add(files('accel-softmmu.c')) user_ss.add(files('accel-user.c')) +subdir('hvf') subdir('qtest') subdir('kvm') subdir('tcg') diff --git a/accel/qtest/meson.build b/accel/qtest/meson.build index a2f3276459..4c65600293 100644 --- a/accel/qtest/meson.build +++ b/accel/qtest/meson.build @@ -1,6 +1,2 @@ -qtest_ss = ss.source_set() -qtest_ss.add(files( - 'qtest.c', -)) - -specific_ss.add_all(when: ['CONFIG_SOFTMMU', 'CONFIG_POSIX'], if_true: qtest_ss) +qtest_module_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_POSIX'], + if_true: files('qtest.c')) diff --git a/accel/qtest/qtest.c b/accel/qtest/qtest.c index edb29f6fa4..7e6b8110d5 100644 --- a/accel/qtest/qtest.c +++ b/accel/qtest/qtest.c @@ -45,6 +45,7 @@ static const TypeInfo qtest_accel_type = { .parent = TYPE_ACCEL, .class_init = qtest_accel_class_init, }; +module_obj(TYPE_QTEST_ACCEL); static void qtest_accel_ops_class_init(ObjectClass *oc, void *data) { @@ -61,6 +62,7 @@ static const TypeInfo qtest_accel_ops_type = { .class_init = qtest_accel_ops_class_init, .abstract = true, }; +module_obj(ACCEL_OPS_NAME("qtest")); static void qtest_type_init(void) { diff --git a/accel/stubs/kvm-stub.c b/accel/stubs/kvm-stub.c index 0f17acfac0..5b1d00a222 100644 --- a/accel/stubs/kvm-stub.c +++ b/accel/stubs/kvm-stub.c @@ -11,7 +11,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "sysemu/kvm.h" #ifndef CONFIG_USER_ONLY diff --git a/accel/stubs/tcg-stub.c b/accel/stubs/tcg-stub.c index 2304606f8e..d8162673ae 100644 --- a/accel/stubs/tcg-stub.c +++ b/accel/stubs/tcg-stub.c @@ -11,7 +11,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "exec/exec-all.h" void tb_flush(CPUState *cpu) diff --git a/accel/tcg/atomic_common.c.inc b/accel/tcg/atomic_common.c.inc index 344525b0bb..6c0339f610 100644 --- a/accel/tcg/atomic_common.c.inc +++ b/accel/tcg/atomic_common.c.inc @@ -13,42 +13,125 @@ * See the COPYING file in the top-level directory. */ -static inline -void atomic_trace_rmw_pre(CPUArchState *env, target_ulong addr, uint16_t info) +static uint16_t atomic_trace_rmw_pre(CPUArchState *env, target_ulong addr, + TCGMemOpIdx oi) { CPUState *cpu = env_cpu(env); + uint16_t info = trace_mem_get_info(get_memop(oi), get_mmuidx(oi), false); trace_guest_mem_before_exec(cpu, addr, info); trace_guest_mem_before_exec(cpu, addr, info | TRACE_MEM_ST); + + return info; } -static inline void -atomic_trace_rmw_post(CPUArchState *env, target_ulong addr, uint16_t info) +static void atomic_trace_rmw_post(CPUArchState *env, target_ulong addr, + uint16_t info) { qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info); qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info | TRACE_MEM_ST); } -static inline -void atomic_trace_ld_pre(CPUArchState *env, target_ulong addr, uint16_t info) +#if HAVE_ATOMIC128 +static uint16_t atomic_trace_ld_pre(CPUArchState *env, target_ulong addr, + TCGMemOpIdx oi) { + uint16_t info = trace_mem_get_info(get_memop(oi), get_mmuidx(oi), false); + trace_guest_mem_before_exec(env_cpu(env), addr, info); + + return info; } -static inline -void atomic_trace_ld_post(CPUArchState *env, target_ulong addr, uint16_t info) +static void atomic_trace_ld_post(CPUArchState *env, target_ulong addr, + uint16_t info) { qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info); } -static inline -void atomic_trace_st_pre(CPUArchState *env, target_ulong addr, uint16_t info) +static uint16_t atomic_trace_st_pre(CPUArchState *env, target_ulong addr, + TCGMemOpIdx oi) { + uint16_t info = trace_mem_get_info(get_memop(oi), get_mmuidx(oi), true); + trace_guest_mem_before_exec(env_cpu(env), addr, info); + + return info; } -static inline -void atomic_trace_st_post(CPUArchState *env, target_ulong addr, uint16_t info) +static void atomic_trace_st_post(CPUArchState *env, target_ulong addr, + uint16_t info) { qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info); } +#endif + +/* + * Atomic helpers callable from TCG. + * These have a common interface and all defer to cpu_atomic_* + * using the host return address from GETPC(). + */ + +#define CMPXCHG_HELPER(OP, TYPE) \ + TYPE HELPER(atomic_##OP)(CPUArchState *env, target_ulong addr, \ + TYPE oldv, TYPE newv, uint32_t oi) \ + { return cpu_atomic_##OP##_mmu(env, addr, oldv, newv, oi, GETPC()); } + +CMPXCHG_HELPER(cmpxchgb, uint32_t) +CMPXCHG_HELPER(cmpxchgw_be, uint32_t) +CMPXCHG_HELPER(cmpxchgw_le, uint32_t) +CMPXCHG_HELPER(cmpxchgl_be, uint32_t) +CMPXCHG_HELPER(cmpxchgl_le, uint32_t) + +#ifdef CONFIG_ATOMIC64 +CMPXCHG_HELPER(cmpxchgq_be, uint64_t) +CMPXCHG_HELPER(cmpxchgq_le, uint64_t) +#endif + +#undef CMPXCHG_HELPER + +#define ATOMIC_HELPER(OP, TYPE) \ + TYPE HELPER(glue(atomic_,OP))(CPUArchState *env, target_ulong addr, \ + TYPE val, uint32_t oi) \ + { return glue(glue(cpu_atomic_,OP),_mmu)(env, addr, val, oi, GETPC()); } + +#ifdef CONFIG_ATOMIC64 +#define GEN_ATOMIC_HELPERS(OP) \ + ATOMIC_HELPER(glue(OP,b), uint32_t) \ + ATOMIC_HELPER(glue(OP,w_be), uint32_t) \ + ATOMIC_HELPER(glue(OP,w_le), uint32_t) \ + ATOMIC_HELPER(glue(OP,l_be), uint32_t) \ + ATOMIC_HELPER(glue(OP,l_le), uint32_t) \ + ATOMIC_HELPER(glue(OP,q_be), uint64_t) \ + ATOMIC_HELPER(glue(OP,q_le), uint64_t) +#else +#define GEN_ATOMIC_HELPERS(OP) \ + ATOMIC_HELPER(glue(OP,b), uint32_t) \ + ATOMIC_HELPER(glue(OP,w_be), uint32_t) \ + ATOMIC_HELPER(glue(OP,w_le), uint32_t) \ + ATOMIC_HELPER(glue(OP,l_be), uint32_t) \ + ATOMIC_HELPER(glue(OP,l_le), uint32_t) +#endif + +GEN_ATOMIC_HELPERS(fetch_add) +GEN_ATOMIC_HELPERS(fetch_and) +GEN_ATOMIC_HELPERS(fetch_or) +GEN_ATOMIC_HELPERS(fetch_xor) +GEN_ATOMIC_HELPERS(fetch_smin) +GEN_ATOMIC_HELPERS(fetch_umin) +GEN_ATOMIC_HELPERS(fetch_smax) +GEN_ATOMIC_HELPERS(fetch_umax) + +GEN_ATOMIC_HELPERS(add_fetch) +GEN_ATOMIC_HELPERS(and_fetch) +GEN_ATOMIC_HELPERS(or_fetch) +GEN_ATOMIC_HELPERS(xor_fetch) +GEN_ATOMIC_HELPERS(smin_fetch) +GEN_ATOMIC_HELPERS(umin_fetch) +GEN_ATOMIC_HELPERS(smax_fetch) +GEN_ATOMIC_HELPERS(umax_fetch) + +GEN_ATOMIC_HELPERS(xchg) + +#undef ATOMIC_HELPER +#undef GEN_ATOMIC_HELPERS diff --git a/accel/tcg/atomic_template.h b/accel/tcg/atomic_template.h index 0ff7f913e1..8098a1be31 100644 --- a/accel/tcg/atomic_template.h +++ b/accel/tcg/atomic_template.h @@ -28,8 +28,8 @@ # define SHIFT 4 #elif DATA_SIZE == 8 # define SUFFIX q -# define DATA_TYPE uint64_t -# define SDATA_TYPE int64_t +# define DATA_TYPE aligned_uint64_t +# define SDATA_TYPE aligned_int64_t # define BSWAP bswap64 # define SHIFT 3 #elif DATA_SIZE == 4 @@ -71,15 +71,14 @@ #endif ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, - ABI_TYPE cmpv, ABI_TYPE newv EXTRA_ARGS) + ABI_TYPE cmpv, ABI_TYPE newv, + TCGMemOpIdx oi, uintptr_t retaddr) { - ATOMIC_MMU_DECLS; - DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, + PAGE_READ | PAGE_WRITE, retaddr); DATA_TYPE ret; - uint16_t info = trace_mem_build_info(SHIFT, false, 0, false, - ATOMIC_MMU_IDX); + uint16_t info = atomic_trace_rmw_pre(env, addr, oi); - atomic_trace_rmw_pre(env, addr, info); #if DATA_SIZE == 16 ret = atomic16_cmpxchg(haddr, cmpv, newv); #else @@ -92,45 +91,41 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, #if DATA_SIZE >= 16 #if HAVE_ATOMIC128 -ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr EXTRA_ARGS) +ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr, + TCGMemOpIdx oi, uintptr_t retaddr) { - ATOMIC_MMU_DECLS; - DATA_TYPE val, *haddr = ATOMIC_MMU_LOOKUP; - uint16_t info = trace_mem_build_info(SHIFT, false, 0, false, - ATOMIC_MMU_IDX); + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, + PAGE_READ, retaddr); + DATA_TYPE val; + uint16_t info = atomic_trace_ld_pre(env, addr, oi); - atomic_trace_ld_pre(env, addr, info); val = atomic16_read(haddr); ATOMIC_MMU_CLEANUP; atomic_trace_ld_post(env, addr, info); return val; } -void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, - ABI_TYPE val EXTRA_ARGS) +void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, ABI_TYPE val, + TCGMemOpIdx oi, uintptr_t retaddr) { - ATOMIC_MMU_DECLS; - DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; - uint16_t info = trace_mem_build_info(SHIFT, false, 0, true, - ATOMIC_MMU_IDX); + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, + PAGE_WRITE, retaddr); + uint16_t info = atomic_trace_st_pre(env, addr, oi); - atomic_trace_st_pre(env, addr, info); atomic16_set(haddr, val); ATOMIC_MMU_CLEANUP; atomic_trace_st_post(env, addr, info); } #endif #else -ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, - ABI_TYPE val EXTRA_ARGS) +ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ABI_TYPE val, + TCGMemOpIdx oi, uintptr_t retaddr) { - ATOMIC_MMU_DECLS; - DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, + PAGE_READ | PAGE_WRITE, retaddr); DATA_TYPE ret; - uint16_t info = trace_mem_build_info(SHIFT, false, 0, false, - ATOMIC_MMU_IDX); + uint16_t info = atomic_trace_rmw_pre(env, addr, oi); - atomic_trace_rmw_pre(env, addr, info); ret = qatomic_xchg__nocheck(haddr, val); ATOMIC_MMU_CLEANUP; atomic_trace_rmw_post(env, addr, info); @@ -139,14 +134,12 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, #define GEN_ATOMIC_HELPER(X) \ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ - ABI_TYPE val EXTRA_ARGS) \ + ABI_TYPE val, TCGMemOpIdx oi, uintptr_t retaddr) \ { \ - ATOMIC_MMU_DECLS; \ - DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ + PAGE_READ | PAGE_WRITE, retaddr); \ DATA_TYPE ret; \ - uint16_t info = trace_mem_build_info(SHIFT, false, 0, false, \ - ATOMIC_MMU_IDX); \ - atomic_trace_rmw_pre(env, addr, info); \ + uint16_t info = atomic_trace_rmw_pre(env, addr, oi); \ ret = qatomic_##X(haddr, val); \ ATOMIC_MMU_CLEANUP; \ atomic_trace_rmw_post(env, addr, info); \ @@ -164,7 +157,8 @@ GEN_ATOMIC_HELPER(xor_fetch) #undef GEN_ATOMIC_HELPER -/* These helpers are, as a whole, full barriers. Within the helper, +/* + * These helpers are, as a whole, full barriers. Within the helper, * the leading barrier is explicit and the trailing barrier is within * cmpxchg primitive. * @@ -173,14 +167,12 @@ GEN_ATOMIC_HELPER(xor_fetch) */ #define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET) \ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ - ABI_TYPE xval EXTRA_ARGS) \ + ABI_TYPE xval, TCGMemOpIdx oi, uintptr_t retaddr) \ { \ - ATOMIC_MMU_DECLS; \ - XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ + XDATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ + PAGE_READ | PAGE_WRITE, retaddr); \ XDATA_TYPE cmp, old, new, val = xval; \ - uint16_t info = trace_mem_build_info(SHIFT, false, 0, false, \ - ATOMIC_MMU_IDX); \ - atomic_trace_rmw_pre(env, addr, info); \ + uint16_t info = atomic_trace_rmw_pre(env, addr, oi); \ smp_mb(); \ cmp = qatomic_read__nocheck(haddr); \ do { \ @@ -218,15 +210,14 @@ GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new) #endif ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, - ABI_TYPE cmpv, ABI_TYPE newv EXTRA_ARGS) + ABI_TYPE cmpv, ABI_TYPE newv, + TCGMemOpIdx oi, uintptr_t retaddr) { - ATOMIC_MMU_DECLS; - DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, + PAGE_READ | PAGE_WRITE, retaddr); DATA_TYPE ret; - uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, false, - ATOMIC_MMU_IDX); + uint16_t info = atomic_trace_rmw_pre(env, addr, oi); - atomic_trace_rmw_pre(env, addr, info); #if DATA_SIZE == 16 ret = atomic16_cmpxchg(haddr, BSWAP(cmpv), BSWAP(newv)); #else @@ -239,30 +230,27 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, #if DATA_SIZE >= 16 #if HAVE_ATOMIC128 -ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr EXTRA_ARGS) +ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr, + TCGMemOpIdx oi, uintptr_t retaddr) { - ATOMIC_MMU_DECLS; - DATA_TYPE val, *haddr = ATOMIC_MMU_LOOKUP; - uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, false, - ATOMIC_MMU_IDX); + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, + PAGE_READ, retaddr); + DATA_TYPE val; + uint16_t info = atomic_trace_ld_pre(env, addr, oi); - atomic_trace_ld_pre(env, addr, info); val = atomic16_read(haddr); ATOMIC_MMU_CLEANUP; atomic_trace_ld_post(env, addr, info); return BSWAP(val); } -void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, - ABI_TYPE val EXTRA_ARGS) +void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, ABI_TYPE val, + TCGMemOpIdx oi, uintptr_t retaddr) { - ATOMIC_MMU_DECLS; - DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; - uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, true, - ATOMIC_MMU_IDX); + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, + PAGE_WRITE, retaddr); + uint16_t info = atomic_trace_st_pre(env, addr, oi); - val = BSWAP(val); - atomic_trace_st_pre(env, addr, info); val = BSWAP(val); atomic16_set(haddr, val); ATOMIC_MMU_CLEANUP; @@ -270,16 +258,14 @@ void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, } #endif #else -ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, - ABI_TYPE val EXTRA_ARGS) +ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ABI_TYPE val, + TCGMemOpIdx oi, uintptr_t retaddr) { - ATOMIC_MMU_DECLS; - DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, + PAGE_READ | PAGE_WRITE, retaddr); ABI_TYPE ret; - uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, false, - ATOMIC_MMU_IDX); + uint16_t info = atomic_trace_rmw_pre(env, addr, oi); - atomic_trace_rmw_pre(env, addr, info); ret = qatomic_xchg__nocheck(haddr, BSWAP(val)); ATOMIC_MMU_CLEANUP; atomic_trace_rmw_post(env, addr, info); @@ -288,14 +274,12 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, #define GEN_ATOMIC_HELPER(X) \ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ - ABI_TYPE val EXTRA_ARGS) \ + ABI_TYPE val, TCGMemOpIdx oi, uintptr_t retaddr) \ { \ - ATOMIC_MMU_DECLS; \ - DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ + DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ + PAGE_READ | PAGE_WRITE, retaddr); \ DATA_TYPE ret; \ - uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, \ - false, ATOMIC_MMU_IDX); \ - atomic_trace_rmw_pre(env, addr, info); \ + uint16_t info = atomic_trace_rmw_pre(env, addr, oi); \ ret = qatomic_##X(haddr, BSWAP(val)); \ ATOMIC_MMU_CLEANUP; \ atomic_trace_rmw_post(env, addr, info); \ @@ -320,14 +304,12 @@ GEN_ATOMIC_HELPER(xor_fetch) */ #define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET) \ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ - ABI_TYPE xval EXTRA_ARGS) \ + ABI_TYPE xval, TCGMemOpIdx oi, uintptr_t retaddr) \ { \ - ATOMIC_MMU_DECLS; \ - XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ + XDATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ + PAGE_READ | PAGE_WRITE, retaddr); \ XDATA_TYPE ldo, ldn, old, new, val = xval; \ - uint16_t info = trace_mem_build_info(SHIFT, false, MO_BSWAP, \ - false, ATOMIC_MMU_IDX); \ - atomic_trace_rmw_pre(env, addr, info); \ + uint16_t info = atomic_trace_rmw_pre(env, addr, oi); \ smp_mb(); \ ldn = qatomic_read__nocheck(haddr); \ do { \ diff --git a/accel/tcg/cpu-exec-common.c b/accel/tcg/cpu-exec-common.c index 12c1e3e974..be6fe45aa5 100644 --- a/accel/tcg/cpu-exec-common.c +++ b/accel/tcg/cpu-exec-common.c @@ -18,7 +18,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "sysemu/cpus.h" #include "sysemu/tcg.h" #include "exec/exec-all.h" diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index f62f12e717..e5c0ccd1a2 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -20,7 +20,6 @@ #include "qemu/osdep.h" #include "qemu-common.h" #include "qemu/qemu-print.h" -#include "cpu.h" #include "hw/core/tcg-cpu-ops.h" #include "trace.h" #include "disas/disas.h" @@ -30,8 +29,6 @@ #include "qemu/compiler.h" #include "qemu/timer.h" #include "qemu/rcu.h" -#include "exec/tb-hash.h" -#include "exec/tb-lookup.h" #include "exec/log.h" #include "qemu/main-loop.h" #if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY) @@ -41,6 +38,9 @@ #include "exec/cpu-all.h" #include "sysemu/cpu-timers.h" #include "sysemu/replay.h" +#include "exec/helper-proto.h" +#include "tb-hash.h" +#include "tb-context.h" #include "internal.h" /* -icount align implementation. */ @@ -145,6 +145,190 @@ static void init_delay_params(SyncClocks *sc, const CPUState *cpu) } #endif /* CONFIG USER ONLY */ +uint32_t curr_cflags(CPUState *cpu) +{ + uint32_t cflags = cpu->tcg_cflags; + + /* + * Record gdb single-step. We should be exiting the TB by raising + * EXCP_DEBUG, but to simplify other tests, disable chaining too. + * + * For singlestep and -d nochain, suppress goto_tb so that + * we can log -d cpu,exec after every TB. + */ + if (unlikely(cpu->singlestep_enabled)) { + cflags |= CF_NO_GOTO_TB | CF_NO_GOTO_PTR | CF_SINGLE_STEP | 1; + } else if (singlestep) { + cflags |= CF_NO_GOTO_TB | 1; + } else if (qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) { + cflags |= CF_NO_GOTO_TB; + } + + return cflags; +} + +/* Might cause an exception, so have a longjmp destination ready */ +static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, + target_ulong cs_base, + uint32_t flags, uint32_t cflags) +{ + TranslationBlock *tb; + uint32_t hash; + + /* we should never be trying to look up an INVALID tb */ + tcg_debug_assert(!(cflags & CF_INVALID)); + + hash = tb_jmp_cache_hash_func(pc); + tb = qatomic_rcu_read(&cpu->tb_jmp_cache[hash]); + + if (likely(tb && + tb->pc == pc && + tb->cs_base == cs_base && + tb->flags == flags && + tb->trace_vcpu_dstate == *cpu->trace_dstate && + tb_cflags(tb) == cflags)) { + return tb; + } + tb = tb_htable_lookup(cpu, pc, cs_base, flags, cflags); + if (tb == NULL) { + return NULL; + } + qatomic_set(&cpu->tb_jmp_cache[hash], tb); + return tb; +} + +static inline void log_cpu_exec(target_ulong pc, CPUState *cpu, + const TranslationBlock *tb) +{ + if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_CPU | CPU_LOG_EXEC)) + && qemu_log_in_addr_range(pc)) { + + qemu_log_mask(CPU_LOG_EXEC, + "Trace %d: %p [" TARGET_FMT_lx + "/" TARGET_FMT_lx "/%08x/%08x] %s\n", + cpu->cpu_index, tb->tc.ptr, tb->cs_base, pc, + tb->flags, tb->cflags, lookup_symbol(pc)); + +#if defined(DEBUG_DISAS) + if (qemu_loglevel_mask(CPU_LOG_TB_CPU)) { + FILE *logfile = qemu_log_lock(); + int flags = 0; + + if (qemu_loglevel_mask(CPU_LOG_TB_FPU)) { + flags |= CPU_DUMP_FPU; + } +#if defined(TARGET_I386) + flags |= CPU_DUMP_CCOP; +#endif + log_cpu_state(cpu, flags); + qemu_log_unlock(logfile); + } +#endif /* DEBUG_DISAS */ + } +} + +static bool check_for_breakpoints(CPUState *cpu, target_ulong pc, + uint32_t *cflags) +{ + CPUBreakpoint *bp; + bool match_page = false; + + if (likely(QTAILQ_EMPTY(&cpu->breakpoints))) { + return false; + } + + /* + * Singlestep overrides breakpoints. + * This requirement is visible in the record-replay tests, where + * we would fail to make forward progress in reverse-continue. + * + * TODO: gdb singlestep should only override gdb breakpoints, + * so that one could (gdb) singlestep into the guest kernel's + * architectural breakpoint handler. + */ + if (cpu->singlestep_enabled) { + return false; + } + + QTAILQ_FOREACH(bp, &cpu->breakpoints, entry) { + /* + * If we have an exact pc match, trigger the breakpoint. + * Otherwise, note matches within the page. + */ + if (pc == bp->pc) { + bool match_bp = false; + + if (bp->flags & BP_GDB) { + match_bp = true; + } else if (bp->flags & BP_CPU) { +#ifdef CONFIG_USER_ONLY + g_assert_not_reached(); +#else + CPUClass *cc = CPU_GET_CLASS(cpu); + assert(cc->tcg_ops->debug_check_breakpoint); + match_bp = cc->tcg_ops->debug_check_breakpoint(cpu); +#endif + } + + if (match_bp) { + cpu->exception_index = EXCP_DEBUG; + return true; + } + } else if (((pc ^ bp->pc) & TARGET_PAGE_MASK) == 0) { + match_page = true; + } + } + + /* + * Within the same page as a breakpoint, single-step, + * returning to helper_lookup_tb_ptr after each insn looking + * for the actual breakpoint. + * + * TODO: Perhaps better to record all of the TBs associated + * with a given virtual page that contains a breakpoint, and + * then invalidate them when a new overlapping breakpoint is + * set on the page. Non-overlapping TBs would not be + * invalidated, nor would any TB need to be invalidated as + * breakpoints are removed. + */ + if (match_page) { + *cflags = (*cflags & ~CF_COUNT_MASK) | CF_NO_GOTO_TB | 1; + } + return false; +} + +/** + * helper_lookup_tb_ptr: quick check for next tb + * @env: current cpu state + * + * Look for an existing TB matching the current cpu state. + * If found, return the code pointer. If not found, return + * the tcg epilogue so that we return into cpu_tb_exec. + */ +const void *HELPER(lookup_tb_ptr)(CPUArchState *env) +{ + CPUState *cpu = env_cpu(env); + TranslationBlock *tb; + target_ulong cs_base, pc; + uint32_t flags, cflags; + + cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags); + + cflags = curr_cflags(cpu); + if (check_for_breakpoints(cpu, pc, &cflags)) { + cpu_loop_exit(cpu); + } + + tb = tb_lookup(cpu, pc, cs_base, flags, cflags); + if (tb == NULL) { + return tcg_code_gen_epilogue; + } + + log_cpu_exec(pc, cpu, tb); + + return tb->tc.ptr; +} + /* Execute a TB, and fix up the CPU state afterwards if necessary */ /* * Disable CFI checks. @@ -163,28 +347,7 @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit) TranslationBlock *last_tb; const void *tb_ptr = itb->tc.ptr; - qemu_log_mask_and_addr(CPU_LOG_EXEC, itb->pc, - "Trace %d: %p [" - TARGET_FMT_lx "/" TARGET_FMT_lx "/%#x] %s\n", - cpu->cpu_index, itb->tc.ptr, - itb->cs_base, itb->pc, itb->flags, - lookup_symbol(itb->pc)); - -#if defined(DEBUG_DISAS) - if (qemu_loglevel_mask(CPU_LOG_TB_CPU) - && qemu_log_in_addr_range(itb->pc)) { - FILE *logfile = qemu_log_lock(); - int flags = 0; - if (qemu_loglevel_mask(CPU_LOG_TB_FPU)) { - flags |= CPU_DUMP_FPU; - } -#if defined(TARGET_I386) - flags |= CPU_DUMP_CCOP; -#endif - log_cpu_state(cpu, flags); - qemu_log_unlock(logfile); - } -#endif /* DEBUG_DISAS */ + log_cpu_exec(itb->pc, cpu, itb); qemu_thread_jit_execute(); ret = tcg_qemu_tb_exec(env, tb_ptr); @@ -247,8 +410,7 @@ void cpu_exec_step_atomic(CPUState *cpu) CPUArchState *env = (CPUArchState *)cpu->env_ptr; TranslationBlock *tb; target_ulong cs_base, pc; - uint32_t flags; - uint32_t cflags = (curr_cflags(cpu) & ~CF_PARALLEL) | 1; + uint32_t flags, cflags; int tb_exit; if (sigsetjmp(cpu->jmp_env, 0) == 0) { @@ -258,8 +420,20 @@ void cpu_exec_step_atomic(CPUState *cpu) cpu->running = true; cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags); - tb = tb_lookup(cpu, pc, cs_base, flags, cflags); + cflags = curr_cflags(cpu); + /* Execute in a serial context. */ + cflags &= ~CF_PARALLEL; + /* After 1 insn, return and release the exclusive lock. */ + cflags |= CF_NO_GOTO_TB | CF_NO_GOTO_PTR | 1; + /* + * No need to check_for_breakpoints here. + * We only arrive in cpu_exec_step_atomic after beginning execution + * of an insn that includes an atomic operation we can't handle. + * Any breakpoint for this insn will have been recognized earlier. + */ + + tb = tb_lookup(cpu, pc, cs_base, flags, cflags); if (tb == NULL) { mmap_lock(); tb = tb_gen_code(cpu, pc, cs_base, flags, cflags); @@ -412,41 +586,6 @@ static inline void tb_add_jump(TranslationBlock *tb, int n, return; } -static inline TranslationBlock *tb_find(CPUState *cpu, - TranslationBlock *last_tb, - int tb_exit, uint32_t cflags) -{ - CPUArchState *env = (CPUArchState *)cpu->env_ptr; - TranslationBlock *tb; - target_ulong cs_base, pc; - uint32_t flags; - - cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags); - - tb = tb_lookup(cpu, pc, cs_base, flags, cflags); - if (tb == NULL) { - mmap_lock(); - tb = tb_gen_code(cpu, pc, cs_base, flags, cflags); - mmap_unlock(); - /* We add the TB in the virtual pc hash table for the fast lookup */ - qatomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb); - } -#ifndef CONFIG_USER_ONLY - /* We don't take care of direct jumps when address mapping changes in - * system emulation. So it's not safe to make a direct jump to a TB - * spanning two pages because the mapping for the second page can change. - */ - if (tb->page_addr[1] != -1) { - last_tb = NULL; - } -#endif - /* See if we can patch the calling TB. */ - if (last_tb) { - tb_add_jump(last_tb, tb_exit, tb); - } - return tb; -} - static inline bool cpu_handle_halt(CPUState *cpu) { if (cpu->halted) { @@ -695,7 +834,7 @@ static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb, /* Ensure global icount has gone forward */ icount_update(cpu); /* Refill decrementer and continue execution. */ - insns_left = MIN(CF_COUNT_MASK, cpu->icount_budget); + insns_left = MIN(0xffff, cpu->icount_budget); cpu_neg(cpu)->icount_decr.u16.low = insns_left; cpu->icount_extra = cpu->icount_budget - insns_left; @@ -704,7 +843,9 @@ static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb, * execute we need to ensure we find/generate a TB with exactly * insns_left instructions in it. */ - if (!cpu->icount_extra && insns_left > 0 && insns_left < tb->icount) { + if (insns_left > 0 && insns_left < tb->icount) { + assert(insns_left <= CF_COUNT_MASK); + assert(cpu->icount_extra == 0); cpu->cflags_next_tb = (tb->cflags & ~CF_COUNT_MASK) | insns_left; } #endif @@ -714,7 +855,6 @@ static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb, int cpu_exec(CPUState *cpu) { - CPUClass *cc = CPU_GET_CLASS(cpu); int ret; SyncClocks sc = { 0 }; @@ -748,19 +888,14 @@ int cpu_exec(CPUState *cpu) * that we support, but is still unfixed in clang: * https://bugs.llvm.org/show_bug.cgi?id=21183 * - * Reload essential local variables here for those compilers. + * Reload an essential local variable here for those compilers. * Newer versions of gcc would complain about this code (-Wclobbered), * so we only perform the workaround for clang. */ cpu = current_cpu; - cc = CPU_GET_CLASS(cpu); #else - /* - * Non-buggy compilers preserve these locals; assert that - * they have the correct value. - */ + /* Non-buggy compilers preserve this; assert the correct value. */ g_assert(cpu == current_cpu); - g_assert(cc == CPU_GET_CLASS(cpu)); #endif #ifndef CONFIG_SOFTMMU @@ -780,22 +915,60 @@ int cpu_exec(CPUState *cpu) int tb_exit = 0; while (!cpu_handle_interrupt(cpu, &last_tb)) { - uint32_t cflags = cpu->cflags_next_tb; TranslationBlock *tb; + target_ulong cs_base, pc; + uint32_t flags, cflags; - /* When requested, use an exact setting for cflags for the next - execution. This is used for icount, precise smc, and stop- - after-access watchpoints. Since this request should never - have CF_INVALID set, -1 is a convenient invalid value that - does not require tcg headers for cpu_common_reset. */ + cpu_get_tb_cpu_state(cpu->env_ptr, &pc, &cs_base, &flags); + + /* + * When requested, use an exact setting for cflags for the next + * execution. This is used for icount, precise smc, and stop- + * after-access watchpoints. Since this request should never + * have CF_INVALID set, -1 is a convenient invalid value that + * does not require tcg headers for cpu_common_reset. + */ + cflags = cpu->cflags_next_tb; if (cflags == -1) { cflags = curr_cflags(cpu); } else { cpu->cflags_next_tb = -1; } - tb = tb_find(cpu, last_tb, tb_exit, cflags); + if (check_for_breakpoints(cpu, pc, &cflags)) { + break; + } + + tb = tb_lookup(cpu, pc, cs_base, flags, cflags); + if (tb == NULL) { + mmap_lock(); + tb = tb_gen_code(cpu, pc, cs_base, flags, cflags); + mmap_unlock(); + /* + * We add the TB in the virtual pc hash table + * for the fast lookup + */ + qatomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb); + } + +#ifndef CONFIG_USER_ONLY + /* + * We don't take care of direct jumps when address mapping + * changes in system emulation. So it's not safe to make a + * direct jump to a TB spanning two pages because the mapping + * for the second page can change. + */ + if (tb->page_addr[1] != -1) { + last_tb = NULL; + } +#endif + /* See if we can patch the calling TB. */ + if (last_tb) { + tb_add_jump(last_tb, tb_exit, tb); + } + cpu_loop_exec_tb(cpu, tb, &last_tb, &tb_exit); + /* Try to align the host and virtual clocks if the guest is in advance */ align_clocks(&sc, cpu); diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index 7b078982d0..d6025e6d1b 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -19,14 +19,11 @@ #include "qemu/osdep.h" #include "qemu/main-loop.h" -#include "cpu.h" #include "hw/core/tcg-cpu-ops.h" #include "exec/exec-all.h" #include "exec/memory.h" -#include "exec/address-spaces.h" #include "exec/cpu_ldst.h" #include "exec/cputlb.h" -#include "exec/tb-hash.h" #include "exec/memory-internal.h" #include "exec/ram_addr.h" #include "tcg/tcg.h" @@ -38,6 +35,7 @@ #include "exec/translate-all.h" #include "trace/trace-root.h" #include "trace/mem.h" +#include "tb-hash.h" #include "internal.h" #ifdef CONFIG_PLUGIN #include "qemu/plugin-memory.h" @@ -709,8 +707,9 @@ void tlb_flush_page_all_cpus_synced(CPUState *src, target_ulong addr) tlb_flush_page_by_mmuidx_all_cpus_synced(src, addr, ALL_MMUIDX_BITS); } -static void tlb_flush_page_bits_locked(CPUArchState *env, int midx, - target_ulong page, unsigned bits) +static void tlb_flush_range_locked(CPUArchState *env, int midx, + target_ulong addr, target_ulong len, + unsigned bits) { CPUTLBDesc *d = &env_tlb(env)->d[midx]; CPUTLBDescFast *f = &env_tlb(env)->f[midx]; @@ -720,20 +719,26 @@ static void tlb_flush_page_bits_locked(CPUArchState *env, int midx, * If @bits is smaller than the tlb size, there may be multiple entries * within the TLB; otherwise all addresses that match under @mask hit * the same TLB entry. - * * TODO: Perhaps allow bits to be a few bits less than the size. * For now, just flush the entire TLB. + * + * If @len is larger than the tlb size, then it will take longer to + * test all of the entries in the TLB than it will to flush it all. */ - if (mask < f->mask) { + if (mask < f->mask || len > f->mask) { tlb_debug("forcing full flush midx %d (" - TARGET_FMT_lx "/" TARGET_FMT_lx ")\n", - midx, page, mask); + TARGET_FMT_lx "/" TARGET_FMT_lx "+" TARGET_FMT_lx ")\n", + midx, addr, mask, len); tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime()); return; } - /* Check if we need to flush due to large pages. */ - if ((page & d->large_page_mask) == d->large_page_addr) { + /* + * Check if we need to flush due to large pages. + * Because large_page_mask contains all 1's from the msb, + * we only need to test the end of the range. + */ + if (((addr + len - 1) & d->large_page_mask) == d->large_page_addr) { tlb_debug("forcing full flush midx %d (" TARGET_FMT_lx "/" TARGET_FMT_lx ")\n", midx, d->large_page_addr, d->large_page_mask); @@ -741,85 +746,67 @@ static void tlb_flush_page_bits_locked(CPUArchState *env, int midx, return; } - if (tlb_flush_entry_mask_locked(tlb_entry(env, midx, page), page, mask)) { - tlb_n_used_entries_dec(env, midx); + for (target_ulong i = 0; i < len; i += TARGET_PAGE_SIZE) { + target_ulong page = addr + i; + CPUTLBEntry *entry = tlb_entry(env, midx, page); + + if (tlb_flush_entry_mask_locked(entry, page, mask)) { + tlb_n_used_entries_dec(env, midx); + } + tlb_flush_vtlb_page_mask_locked(env, midx, page, mask); } - tlb_flush_vtlb_page_mask_locked(env, midx, page, mask); } typedef struct { target_ulong addr; + target_ulong len; uint16_t idxmap; uint16_t bits; -} TLBFlushPageBitsByMMUIdxData; +} TLBFlushRangeData; -static void -tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu, - TLBFlushPageBitsByMMUIdxData d) +static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu, + TLBFlushRangeData d) { CPUArchState *env = cpu->env_ptr; int mmu_idx; assert_cpu_is_self(cpu); - tlb_debug("page addr:" TARGET_FMT_lx "/%u mmu_map:0x%x\n", - d.addr, d.bits, d.idxmap); + tlb_debug("range:" TARGET_FMT_lx "/%u+" TARGET_FMT_lx " mmu_map:0x%x\n", + d.addr, d.bits, d.len, d.idxmap); qemu_spin_lock(&env_tlb(env)->c.lock); for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) { if ((d.idxmap >> mmu_idx) & 1) { - tlb_flush_page_bits_locked(env, mmu_idx, d.addr, d.bits); + tlb_flush_range_locked(env, mmu_idx, d.addr, d.len, d.bits); } } qemu_spin_unlock(&env_tlb(env)->c.lock); - tb_flush_jmp_cache(cpu, d.addr); -} - -static bool encode_pbm_to_runon(run_on_cpu_data *out, - TLBFlushPageBitsByMMUIdxData d) -{ - /* We need 6 bits to hold to hold @bits up to 63. */ - if (d.idxmap <= MAKE_64BIT_MASK(0, TARGET_PAGE_BITS - 6)) { - *out = RUN_ON_CPU_TARGET_PTR(d.addr | (d.idxmap << 6) | d.bits); - return true; + for (target_ulong i = 0; i < d.len; i += TARGET_PAGE_SIZE) { + tb_flush_jmp_cache(cpu, d.addr + i); } - return false; } -static TLBFlushPageBitsByMMUIdxData -decode_runon_to_pbm(run_on_cpu_data data) +static void tlb_flush_range_by_mmuidx_async_1(CPUState *cpu, + run_on_cpu_data data) { - target_ulong addr_map_bits = (target_ulong) data.target_ptr; - return (TLBFlushPageBitsByMMUIdxData){ - .addr = addr_map_bits & TARGET_PAGE_MASK, - .idxmap = (addr_map_bits & ~TARGET_PAGE_MASK) >> 6, - .bits = addr_map_bits & 0x3f - }; -} - -static void tlb_flush_page_bits_by_mmuidx_async_1(CPUState *cpu, - run_on_cpu_data runon) -{ - tlb_flush_page_bits_by_mmuidx_async_0(cpu, decode_runon_to_pbm(runon)); -} - -static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu, - run_on_cpu_data data) -{ - TLBFlushPageBitsByMMUIdxData *d = data.host_ptr; - tlb_flush_page_bits_by_mmuidx_async_0(cpu, *d); + TLBFlushRangeData *d = data.host_ptr; + tlb_flush_range_by_mmuidx_async_0(cpu, *d); g_free(d); } -void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, - uint16_t idxmap, unsigned bits) +void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits) { - TLBFlushPageBitsByMMUIdxData d; - run_on_cpu_data runon; + TLBFlushRangeData d; - /* If all bits are significant, this devolves to tlb_flush_page. */ - if (bits >= TARGET_LONG_BITS) { + /* + * If all bits are significant, and len is small, + * this devolves to tlb_flush_page. + */ + if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) { tlb_flush_page_by_mmuidx(cpu, addr, idxmap); return; } @@ -831,34 +818,38 @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; + d.len = len; d.idxmap = idxmap; d.bits = bits; if (qemu_cpu_is_self(cpu)) { - tlb_flush_page_bits_by_mmuidx_async_0(cpu, d); - } else if (encode_pbm_to_runon(&runon, d)) { - async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); + tlb_flush_range_by_mmuidx_async_0(cpu, d); } else { - TLBFlushPageBitsByMMUIdxData *p - = g_new(TLBFlushPageBitsByMMUIdxData, 1); - /* Otherwise allocate a structure, freed by the worker. */ - *p = d; - async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_2, + TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); + async_run_on_cpu(cpu, tlb_flush_range_by_mmuidx_async_1, RUN_ON_CPU_HOST_PTR(p)); } } -void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, - target_ulong addr, - uint16_t idxmap, - unsigned bits) +void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, + uint16_t idxmap, unsigned bits) { - TLBFlushPageBitsByMMUIdxData d; - run_on_cpu_data runon; + tlb_flush_range_by_mmuidx(cpu, addr, TARGET_PAGE_SIZE, idxmap, bits); +} - /* If all bits are significant, this devolves to tlb_flush_page. */ - if (bits >= TARGET_LONG_BITS) { +void tlb_flush_range_by_mmuidx_all_cpus(CPUState *src_cpu, + target_ulong addr, target_ulong len, + uint16_t idxmap, unsigned bits) +{ + TLBFlushRangeData d; + CPUState *dst_cpu; + + /* + * If all bits are significant, and len is small, + * this devolves to tlb_flush_page. + */ + if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) { tlb_flush_page_by_mmuidx_all_cpus(src_cpu, addr, idxmap); return; } @@ -870,40 +861,45 @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; + d.len = len; d.idxmap = idxmap; d.bits = bits; - if (encode_pbm_to_runon(&runon, d)) { - flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); - } else { - CPUState *dst_cpu; - TLBFlushPageBitsByMMUIdxData *p; - - /* Allocate a separate data block for each destination cpu. */ - CPU_FOREACH(dst_cpu) { - if (dst_cpu != src_cpu) { - p = g_new(TLBFlushPageBitsByMMUIdxData, 1); - *p = d; - async_run_on_cpu(dst_cpu, - tlb_flush_page_bits_by_mmuidx_async_2, - RUN_ON_CPU_HOST_PTR(p)); - } + /* Allocate a separate data block for each destination cpu. */ + CPU_FOREACH(dst_cpu) { + if (dst_cpu != src_cpu) { + TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); + async_run_on_cpu(dst_cpu, + tlb_flush_range_by_mmuidx_async_1, + RUN_ON_CPU_HOST_PTR(p)); } } - tlb_flush_page_bits_by_mmuidx_async_0(src_cpu, d); + tlb_flush_range_by_mmuidx_async_0(src_cpu, d); } -void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, - target_ulong addr, - uint16_t idxmap, - unsigned bits) +void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, + target_ulong addr, + uint16_t idxmap, unsigned bits) { - TLBFlushPageBitsByMMUIdxData d; - run_on_cpu_data runon; + tlb_flush_range_by_mmuidx_all_cpus(src_cpu, addr, TARGET_PAGE_SIZE, + idxmap, bits); +} - /* If all bits are significant, this devolves to tlb_flush_page. */ - if (bits >= TARGET_LONG_BITS) { +void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *src_cpu, + target_ulong addr, + target_ulong len, + uint16_t idxmap, + unsigned bits) +{ + TLBFlushRangeData d, *p; + CPUState *dst_cpu; + + /* + * If all bits are significant, and len is small, + * this devolves to tlb_flush_page. + */ + if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) { tlb_flush_page_by_mmuidx_all_cpus_synced(src_cpu, addr, idxmap); return; } @@ -915,32 +911,31 @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; + d.len = len; d.idxmap = idxmap; d.bits = bits; - if (encode_pbm_to_runon(&runon, d)) { - flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); - async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, - runon); - } else { - CPUState *dst_cpu; - TLBFlushPageBitsByMMUIdxData *p; - - /* Allocate a separate data block for each destination cpu. */ - CPU_FOREACH(dst_cpu) { - if (dst_cpu != src_cpu) { - p = g_new(TLBFlushPageBitsByMMUIdxData, 1); - *p = d; - async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2, - RUN_ON_CPU_HOST_PTR(p)); - } + /* Allocate a separate data block for each destination cpu. */ + CPU_FOREACH(dst_cpu) { + if (dst_cpu != src_cpu) { + p = g_memdup(&d, sizeof(d)); + async_run_on_cpu(dst_cpu, tlb_flush_range_by_mmuidx_async_1, + RUN_ON_CPU_HOST_PTR(p)); } - - p = g_new(TLBFlushPageBitsByMMUIdxData, 1); - *p = d; - async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2, - RUN_ON_CPU_HOST_PTR(p)); } + + p = g_memdup(&d, sizeof(d)); + async_safe_run_on_cpu(src_cpu, tlb_flush_range_by_mmuidx_async_1, + RUN_ON_CPU_HOST_PTR(p)); +} + +void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, + target_ulong addr, + uint16_t idxmap, + unsigned bits) +{ + tlb_flush_range_by_mmuidx_all_cpus_synced(src_cpu, addr, TARGET_PAGE_SIZE, + idxmap, bits); } /* update the TLBs so that writes to code in the virtual page 'addr' @@ -1742,7 +1737,7 @@ bool tlb_plugin_lookup(CPUState *cpu, target_ulong addr, int mmu_idx, data->v.io.offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; } else { data->is_io = false; - data->v.ram.hostaddr = addr + tlbe->addend; + data->v.ram.hostaddr = (void *)((uintptr_t)addr + tlbe->addend); } return true; } else { @@ -1756,18 +1751,22 @@ bool tlb_plugin_lookup(CPUState *cpu, target_ulong addr, int mmu_idx, #endif -/* Probe for a read-modify-write atomic operation. Do not allow unaligned - * operations, or io operations to proceed. Return the host address. */ +/* + * Probe for an atomic operation. Do not allow unaligned operations, + * or io operations to proceed. Return the host address. + * + * @prot may be PAGE_READ, PAGE_WRITE, or PAGE_READ|PAGE_WRITE. + */ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + TCGMemOpIdx oi, int size, int prot, + uintptr_t retaddr) { size_t mmu_idx = get_mmuidx(oi); - uintptr_t index = tlb_index(env, mmu_idx, addr); - CPUTLBEntry *tlbe = tlb_entry(env, mmu_idx, addr); - target_ulong tlb_addr = tlb_addr_write(tlbe); MemOp mop = get_memop(oi); int a_bits = get_alignment_bits(mop); - int s_bits = mop & MO_SIZE; + uintptr_t index; + CPUTLBEntry *tlbe; + target_ulong tlb_addr; void *hostaddr; /* Adjust the given return address. */ @@ -1781,7 +1780,7 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, } /* Enforce qemu required alignment. */ - if (unlikely(addr & ((1 << s_bits) - 1))) { + if (unlikely(addr & (size - 1))) { /* We get here if guest alignment was not requested, or was not enforced by cpu_unaligned_access above. We might widen the access and emulate, but for now @@ -1789,15 +1788,45 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, goto stop_the_world; } + index = tlb_index(env, mmu_idx, addr); + tlbe = tlb_entry(env, mmu_idx, addr); + /* Check TLB entry and enforce page permissions. */ - if (!tlb_hit(tlb_addr, addr)) { - if (!VICTIM_TLB_HIT(addr_write, addr)) { - tlb_fill(env_cpu(env), addr, 1 << s_bits, MMU_DATA_STORE, - mmu_idx, retaddr); - index = tlb_index(env, mmu_idx, addr); - tlbe = tlb_entry(env, mmu_idx, addr); + if (prot & PAGE_WRITE) { + tlb_addr = tlb_addr_write(tlbe); + if (!tlb_hit(tlb_addr, addr)) { + if (!VICTIM_TLB_HIT(addr_write, addr)) { + tlb_fill(env_cpu(env), addr, size, + MMU_DATA_STORE, mmu_idx, retaddr); + index = tlb_index(env, mmu_idx, addr); + tlbe = tlb_entry(env, mmu_idx, addr); + } + tlb_addr = tlb_addr_write(tlbe) & ~TLB_INVALID_MASK; + } + + /* Let the guest notice RMW on a write-only page. */ + if ((prot & PAGE_READ) && + unlikely(tlbe->addr_read != (tlb_addr & ~TLB_NOTDIRTY))) { + tlb_fill(env_cpu(env), addr, size, + MMU_DATA_LOAD, mmu_idx, retaddr); + /* + * Since we don't support reads and writes to different addresses, + * and we do have the proper page loaded for write, this shouldn't + * ever return. But just in case, handle via stop-the-world. + */ + goto stop_the_world; + } + } else /* if (prot & PAGE_READ) */ { + tlb_addr = tlbe->addr_read; + if (!tlb_hit(tlb_addr, addr)) { + if (!VICTIM_TLB_HIT(addr_write, addr)) { + tlb_fill(env_cpu(env), addr, size, + MMU_DATA_LOAD, mmu_idx, retaddr); + index = tlb_index(env, mmu_idx, addr); + tlbe = tlb_entry(env, mmu_idx, addr); + } + tlb_addr = tlbe->addr_read & ~TLB_INVALID_MASK; } - tlb_addr = tlb_addr_write(tlbe) & ~TLB_INVALID_MASK; } /* Notice an IO access or a needs-MMU-lookup access */ @@ -1807,20 +1836,10 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, goto stop_the_world; } - /* Let the guest notice RMW on a write-only page. */ - if (unlikely(tlbe->addr_read != (tlb_addr & ~TLB_NOTDIRTY))) { - tlb_fill(env_cpu(env), addr, 1 << s_bits, MMU_DATA_LOAD, - mmu_idx, retaddr); - /* Since we don't support reads and writes to different addresses, - and we do have the proper page loaded for write, this shouldn't - ever return. But just in case, handle via stop-the-world. */ - goto stop_the_world; - } - hostaddr = (void *)((uintptr_t)addr + tlbe->addend); if (unlikely(tlb_addr & TLB_NOTDIRTY)) { - notdirty_write(env_cpu(env), addr, 1 << s_bits, + notdirty_write(env_cpu(env), addr, size, &env_tlb(env)->d[mmu_idx].iotlb[index], retaddr); } @@ -2703,14 +2722,14 @@ void cpu_stq_le_data(CPUArchState *env, target_ulong ptr, uint64_t val) cpu_stq_le_data_ra(env, ptr, val, 0); } -/* First set of helpers allows passing in of OI and RETADDR. This makes - them callable from other helpers. */ +/* + * First set of functions passes in OI and RETADDR. + * This makes them callable from other helpers. + */ -#define EXTRA_ARGS , TCGMemOpIdx oi, uintptr_t retaddr #define ATOMIC_NAME(X) \ - HELPER(glue(glue(glue(atomic_ ## X, SUFFIX), END), _mmu)) -#define ATOMIC_MMU_DECLS -#define ATOMIC_MMU_LOOKUP atomic_mmu_lookup(env, addr, oi, retaddr) + glue(glue(glue(cpu_atomic_ ## X, SUFFIX), END), _mmu) + #define ATOMIC_MMU_CLEANUP #define ATOMIC_MMU_IDX get_mmuidx(oi) @@ -2735,30 +2754,6 @@ void cpu_stq_le_data(CPUArchState *env, target_ulong ptr, uint64_t val) #include "atomic_template.h" #endif -/* Second set of helpers are directly callable from TCG as helpers. */ - -#undef EXTRA_ARGS -#undef ATOMIC_NAME -#undef ATOMIC_MMU_LOOKUP -#define EXTRA_ARGS , TCGMemOpIdx oi -#define ATOMIC_NAME(X) HELPER(glue(glue(atomic_ ## X, SUFFIX), END)) -#define ATOMIC_MMU_LOOKUP atomic_mmu_lookup(env, addr, oi, GETPC()) - -#define DATA_SIZE 1 -#include "atomic_template.h" - -#define DATA_SIZE 2 -#include "atomic_template.h" - -#define DATA_SIZE 4 -#include "atomic_template.h" - -#ifdef CONFIG_ATOMIC64 -#define DATA_SIZE 8 -#include "atomic_template.h" -#endif -#undef ATOMIC_MMU_IDX - /* Code access functions. */ static uint64_t full_ldub_code(CPUArchState *env, target_ulong addr, diff --git a/accel/tcg/hmp.c b/accel/tcg/hmp.c new file mode 100644 index 0000000000..a6e72fdb3e --- /dev/null +++ b/accel/tcg/hmp.c @@ -0,0 +1,29 @@ +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "exec/exec-all.h" +#include "monitor/monitor.h" +#include "sysemu/tcg.h" + +static void hmp_info_jit(Monitor *mon, const QDict *qdict) +{ + if (!tcg_enabled()) { + error_report("JIT information is only available with accel=tcg"); + return; + } + + dump_exec_info(); + dump_drift_info(); +} + +static void hmp_info_opcount(Monitor *mon, const QDict *qdict) +{ + dump_opcount_info(); +} + +static void hmp_tcg_register(void) +{ + monitor_register_hmp("jit", true, hmp_info_jit); + monitor_register_hmp("opcount", true, hmp_info_opcount); +} + +type_init(hmp_tcg_register); diff --git a/accel/tcg/internal.h b/accel/tcg/internal.h index e9c145e0fb..881bc1ede0 100644 --- a/accel/tcg/internal.h +++ b/accel/tcg/internal.h @@ -16,5 +16,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu, target_ulong pc, int cflags); void QEMU_NORETURN cpu_io_recompile(CPUState *cpu, uintptr_t retaddr); +void page_init(void); +void tb_htable_init(void); #endif /* ACCEL_TCG_INTERNAL_H */ diff --git a/accel/tcg/meson.build b/accel/tcg/meson.build index 1236ac7b91..137a1a44cc 100644 --- a/accel/tcg/meson.build +++ b/accel/tcg/meson.build @@ -15,8 +15,12 @@ specific_ss.add_all(when: 'CONFIG_TCG', if_true: tcg_ss) specific_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_TCG'], if_true: files( 'cputlb.c', + 'hmp.c', +)) + +tcg_module_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_TCG'], if_true: files( 'tcg-accel-ops.c', 'tcg-accel-ops-mttcg.c', 'tcg-accel-ops-icount.c', - 'tcg-accel-ops-rr.c' + 'tcg-accel-ops-rr.c', )) diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c index c3dc3effe7..88e25c6df9 100644 --- a/accel/tcg/plugin-gen.c +++ b/accel/tcg/plugin-gen.c @@ -43,7 +43,6 @@ * CPU's index into a TCG temp, since the first callback did it already. */ #include "qemu/osdep.h" -#include "cpu.h" #include "tcg/tcg.h" #include "tcg/tcg-op.h" #include "trace/mem.h" @@ -161,9 +160,8 @@ static void gen_empty_mem_helper(void) tcg_temp_free_ptr(ptr); } -static inline -void gen_plugin_cb_start(enum plugin_gen_from from, - enum plugin_gen_cb type, unsigned wr) +static void gen_plugin_cb_start(enum plugin_gen_from from, + enum plugin_gen_cb type, unsigned wr) { TCGOp *op; @@ -180,7 +178,7 @@ static void gen_wrapped(enum plugin_gen_from from, tcg_gen_plugin_cb_end(); } -static inline void plugin_gen_empty_callback(enum plugin_gen_from from) +static void plugin_gen_empty_callback(enum plugin_gen_from from) { switch (from) { case PLUGIN_GEN_AFTER_INSN: @@ -386,7 +384,7 @@ static TCGOp *copy_st_ptr(TCGOp **begin_op, TCGOp *op) } static TCGOp *copy_call(TCGOp **begin_op, TCGOp *op, void *empty_func, - void *func, unsigned tcg_flags, int *cb_idx) + void *func, int *cb_idx) { /* copy all ops until the call */ do { @@ -413,7 +411,7 @@ static TCGOp *copy_call(TCGOp **begin_op, TCGOp *op, void *empty_func, tcg_debug_assert(i < MAX_OPC_PARAM_ARGS); } op->args[*cb_idx] = (uintptr_t)func; - op->args[*cb_idx + 1] = tcg_flags; + op->args[*cb_idx + 1] = (*begin_op)->args[*cb_idx + 1]; return op; } @@ -440,7 +438,7 @@ static TCGOp *append_udata_cb(const struct qemu_plugin_dyn_cb *cb, /* call */ op = copy_call(&begin_op, op, HELPER(plugin_vcpu_udata_cb), - cb->f.vcpu_udata, cb->tcg_flags, cb_idx); + cb->f.vcpu_udata, cb_idx); return op; } @@ -491,7 +489,7 @@ static TCGOp *append_mem_cb(const struct qemu_plugin_dyn_cb *cb, if (type == PLUGIN_GEN_CB_MEM) { /* call */ op = copy_call(&begin_op, op, HELPER(plugin_vcpu_mem_cb), - cb->f.vcpu_udata, cb->tcg_flags, cb_idx); + cb->f.vcpu_udata, cb_idx); } return op; @@ -514,9 +512,8 @@ static bool op_rw(const TCGOp *op, const struct qemu_plugin_dyn_cb *cb) return !!(cb->rw & (w + 1)); } -static inline -void inject_cb_type(const GArray *cbs, TCGOp *begin_op, inject_fn inject, - op_ok_fn ok) +static void inject_cb_type(const GArray *cbs, TCGOp *begin_op, + inject_fn inject, op_ok_fn ok) { TCGOp *end_op; TCGOp *op; diff --git a/accel/tcg/plugin-helpers.h b/accel/tcg/plugin-helpers.h index 1916ee7920..9829abe4a9 100644 --- a/accel/tcg/plugin-helpers.h +++ b/accel/tcg/plugin-helpers.h @@ -1,5 +1,4 @@ #ifdef CONFIG_PLUGIN -/* Note: no TCG flags because those are overwritten later */ -DEF_HELPER_2(plugin_vcpu_udata_cb, void, i32, ptr) -DEF_HELPER_4(plugin_vcpu_mem_cb, void, i32, i32, i64, ptr) +DEF_HELPER_FLAGS_2(plugin_vcpu_udata_cb, TCG_CALL_NO_RWG, void, i32, ptr) +DEF_HELPER_FLAGS_4(plugin_vcpu_mem_cb, TCG_CALL_NO_RWG, void, i32, i32, i64, ptr) #endif diff --git a/include/exec/tb-context.h b/accel/tcg/tb-context.h similarity index 96% rename from include/exec/tb-context.h rename to accel/tcg/tb-context.h index cc33979113..cac62d9749 100644 --- a/include/exec/tb-context.h +++ b/accel/tcg/tb-context.h @@ -34,6 +34,7 @@ struct TBContext { /* statistics */ unsigned tb_flush_count; + unsigned tb_phys_invalidate_count; }; extern TBContext tb_ctx; diff --git a/include/exec/tb-hash.h b/accel/tcg/tb-hash.h similarity index 100% rename from include/exec/tb-hash.h rename to accel/tcg/tb-hash.h diff --git a/accel/tcg/tcg-accel-ops-icount.c b/accel/tcg/tcg-accel-ops-icount.c index 13b8fbeb69..ea42d1d51b 100644 --- a/accel/tcg/tcg-accel-ops-icount.c +++ b/accel/tcg/tcg-accel-ops-icount.c @@ -30,7 +30,6 @@ #include "qemu/main-loop.h" #include "qemu/guest-random.h" #include "exec/exec-all.h" -#include "hw/boards.h" #include "tcg-accel-ops.h" #include "tcg-accel-ops-icount.h" diff --git a/accel/tcg/tcg-accel-ops-rr.c b/accel/tcg/tcg-accel-ops-rr.c index 018b54c508..c02c061ecb 100644 --- a/accel/tcg/tcg-accel-ops-rr.c +++ b/accel/tcg/tcg-accel-ops-rr.c @@ -30,7 +30,6 @@ #include "qemu/main-loop.h" #include "qemu/guest-random.h" #include "exec/exec-all.h" -#include "hw/boards.h" #include "tcg-accel-ops.h" #include "tcg-accel-ops-rr.h" diff --git a/accel/tcg/tcg-accel-ops.c b/accel/tcg/tcg-accel-ops.c index 6cdcaa2855..1a8e8390bd 100644 --- a/accel/tcg/tcg-accel-ops.c +++ b/accel/tcg/tcg-accel-ops.c @@ -32,7 +32,6 @@ #include "qemu/main-loop.h" #include "qemu/guest-random.h" #include "exec/exec-all.h" -#include "hw/boards.h" #include "tcg-accel-ops.h" #include "tcg-accel-ops-mttcg.h" @@ -125,6 +124,7 @@ static const TypeInfo tcg_accel_ops_type = { .class_init = tcg_accel_ops_class_init, .abstract = true, }; +module_obj(ACCEL_OPS_NAME("tcg")); static void tcg_accel_ops_register_types(void) { diff --git a/accel/tcg/tcg-all.c b/accel/tcg/tcg-all.c index e378c2db73..d6336a9c96 100644 --- a/accel/tcg/tcg-all.c +++ b/accel/tcg/tcg-all.c @@ -32,6 +32,11 @@ #include "qemu/error-report.h" #include "qemu/accel.h" #include "qapi/qapi-builtin-visit.h" +#include "qemu/units.h" +#if !defined(CONFIG_USER_ONLY) +#include "hw/boards.h" +#endif +#include "internal.h" struct TCGState { AccelState parent_obj; @@ -105,22 +110,29 @@ static void tcg_accel_instance_init(Object *obj) bool mttcg_enabled; -static int tcg_init(MachineState *ms) +static int tcg_init_machine(MachineState *ms) { TCGState *s = TCG_STATE(current_accel()); +#ifdef CONFIG_USER_ONLY + unsigned max_cpus = 1; +#else + unsigned max_cpus = ms->smp.max_cpus; +#endif - tcg_exec_init(s->tb_size * 1024 * 1024, s->splitwx_enabled); + tcg_allowed = true; mttcg_enabled = s->mttcg_enabled; + page_init(); + tb_htable_init(); + tcg_init(s->tb_size * MiB, s->splitwx_enabled, max_cpus); + +#if defined(CONFIG_SOFTMMU) /* - * Initialize TCG regions only for softmmu. - * - * This needs to be done later for user mode, because the prologue - * generation needs to be delayed so that GUEST_BASE is already set. + * There's no guest base to take into account, so go ahead and + * initialize the prologue now. */ -#ifndef CONFIG_USER_ONLY - tcg_region_init(); -#endif /* !CONFIG_USER_ONLY */ + tcg_prologue_init(tcg_ctx); +#endif return 0; } @@ -200,7 +212,7 @@ static void tcg_accel_class_init(ObjectClass *oc, void *data) { AccelClass *ac = ACCEL_CLASS(oc); ac->name = "tcg"; - ac->init_machine = tcg_init; + ac->init_machine = tcg_init_machine; ac->allowed = &tcg_allowed; object_class_property_add_str(oc, "thread", @@ -226,6 +238,7 @@ static const TypeInfo tcg_accel_type = { .class_init = tcg_accel_class_init, .instance_size = sizeof(TCGState), }; +module_obj(TYPE_TCG_ACCEL); static void register_accel_types(void) { diff --git a/accel/tcg/tcg-runtime-gvec.c b/accel/tcg/tcg-runtime-gvec.c index 521da4a813..ac7d28c251 100644 --- a/accel/tcg/tcg-runtime-gvec.c +++ b/accel/tcg/tcg-runtime-gvec.c @@ -1073,9 +1073,8 @@ void HELPER(gvec_ssadd32)(void *d, void *a, void *b, uint32_t desc) for (i = 0; i < oprsz; i += sizeof(int32_t)) { int32_t ai = *(int32_t *)(a + i); int32_t bi = *(int32_t *)(b + i); - int32_t di = ai + bi; - if (((di ^ ai) &~ (ai ^ bi)) < 0) { - /* Signed overflow. */ + int32_t di; + if (sadd32_overflow(ai, bi, &di)) { di = (di < 0 ? INT32_MAX : INT32_MIN); } *(int32_t *)(d + i) = di; @@ -1091,9 +1090,8 @@ void HELPER(gvec_ssadd64)(void *d, void *a, void *b, uint32_t desc) for (i = 0; i < oprsz; i += sizeof(int64_t)) { int64_t ai = *(int64_t *)(a + i); int64_t bi = *(int64_t *)(b + i); - int64_t di = ai + bi; - if (((di ^ ai) &~ (ai ^ bi)) < 0) { - /* Signed overflow. */ + int64_t di; + if (sadd64_overflow(ai, bi, &di)) { di = (di < 0 ? INT64_MAX : INT64_MIN); } *(int64_t *)(d + i) = di; @@ -1143,9 +1141,8 @@ void HELPER(gvec_sssub32)(void *d, void *a, void *b, uint32_t desc) for (i = 0; i < oprsz; i += sizeof(int32_t)) { int32_t ai = *(int32_t *)(a + i); int32_t bi = *(int32_t *)(b + i); - int32_t di = ai - bi; - if (((di ^ ai) & (ai ^ bi)) < 0) { - /* Signed overflow. */ + int32_t di; + if (ssub32_overflow(ai, bi, &di)) { di = (di < 0 ? INT32_MAX : INT32_MIN); } *(int32_t *)(d + i) = di; @@ -1161,9 +1158,8 @@ void HELPER(gvec_sssub64)(void *d, void *a, void *b, uint32_t desc) for (i = 0; i < oprsz; i += sizeof(int64_t)) { int64_t ai = *(int64_t *)(a + i); int64_t bi = *(int64_t *)(b + i); - int64_t di = ai - bi; - if (((di ^ ai) & (ai ^ bi)) < 0) { - /* Signed overflow. */ + int64_t di; + if (ssub64_overflow(ai, bi, &di)) { di = (di < 0 ? INT64_MAX : INT64_MIN); } *(int64_t *)(d + i) = di; @@ -1209,8 +1205,8 @@ void HELPER(gvec_usadd32)(void *d, void *a, void *b, uint32_t desc) for (i = 0; i < oprsz; i += sizeof(uint32_t)) { uint32_t ai = *(uint32_t *)(a + i); uint32_t bi = *(uint32_t *)(b + i); - uint32_t di = ai + bi; - if (di < ai) { + uint32_t di; + if (uadd32_overflow(ai, bi, &di)) { di = UINT32_MAX; } *(uint32_t *)(d + i) = di; @@ -1226,8 +1222,8 @@ void HELPER(gvec_usadd64)(void *d, void *a, void *b, uint32_t desc) for (i = 0; i < oprsz; i += sizeof(uint64_t)) { uint64_t ai = *(uint64_t *)(a + i); uint64_t bi = *(uint64_t *)(b + i); - uint64_t di = ai + bi; - if (di < ai) { + uint64_t di; + if (uadd64_overflow(ai, bi, &di)) { di = UINT64_MAX; } *(uint64_t *)(d + i) = di; @@ -1273,8 +1269,8 @@ void HELPER(gvec_ussub32)(void *d, void *a, void *b, uint32_t desc) for (i = 0; i < oprsz; i += sizeof(uint32_t)) { uint32_t ai = *(uint32_t *)(a + i); uint32_t bi = *(uint32_t *)(b + i); - uint32_t di = ai - bi; - if (ai < bi) { + uint32_t di; + if (usub32_overflow(ai, bi, &di)) { di = 0; } *(uint32_t *)(d + i) = di; @@ -1290,8 +1286,8 @@ void HELPER(gvec_ussub64)(void *d, void *a, void *b, uint32_t desc) for (i = 0; i < oprsz; i += sizeof(uint64_t)) { uint64_t ai = *(uint64_t *)(a + i); uint64_t bi = *(uint64_t *)(b + i); - uint64_t di = ai - bi; - if (ai < bi) { + uint64_t di; + if (usub64_overflow(ai, bi, &di)) { di = 0; } *(uint64_t *)(d + i) = di; diff --git a/accel/tcg/tcg-runtime.c b/accel/tcg/tcg-runtime.c index 49f5de37e8..e4e030043f 100644 --- a/accel/tcg/tcg-runtime.c +++ b/accel/tcg/tcg-runtime.c @@ -30,7 +30,6 @@ #include "disas/disas.h" #include "exec/log.h" #include "tcg/tcg.h" -#include "exec/tb-lookup.h" /* 32-bit helpers */ @@ -145,27 +144,6 @@ uint64_t HELPER(ctpop_i64)(uint64_t arg) return ctpop64(arg); } -const void *HELPER(lookup_tb_ptr)(CPUArchState *env) -{ - CPUState *cpu = env_cpu(env); - TranslationBlock *tb; - target_ulong cs_base, pc; - uint32_t flags; - - cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags); - - tb = tb_lookup(cpu, pc, cs_base, flags, curr_cflags(cpu)); - if (tb == NULL) { - return tcg_code_gen_epilogue; - } - qemu_log_mask_and_addr(CPU_LOG_EXEC, pc, - "Chain %d: %p [" - TARGET_FMT_lx "/" TARGET_FMT_lx "/%#x] %s\n", - cpu->cpu_index, tb->tc.ptr, cs_base, pc, flags, - lookup_symbol(pc)); - return tb->tc.ptr; -} - void HELPER(exit_atomic)(CPUArchState *env) { cpu_loop_exit_atomic(env_cpu(env), GETPC()); diff --git a/accel/tcg/tcg-runtime.h b/accel/tcg/tcg-runtime.h index 91a5b7e85f..37cbd722bf 100644 --- a/accel/tcg/tcg-runtime.h +++ b/accel/tcg/tcg-runtime.h @@ -39,8 +39,6 @@ DEF_HELPER_FLAGS_1(exit_atomic, TCG_CALL_NO_WG, noreturn, env) DEF_HELPER_FLAGS_3(memset, TCG_CALL_NO_RWG, ptr, ptr, int, ptr) #endif /* IN_HELPER_PROTO */ -#ifdef CONFIG_SOFTMMU - DEF_HELPER_FLAGS_5(atomic_cmpxchgb, TCG_CALL_NO_WG, i32, env, tl, i32, i32, i32) DEF_HELPER_FLAGS_5(atomic_cmpxchgw_be, TCG_CALL_NO_WG, @@ -88,50 +86,6 @@ DEF_HELPER_FLAGS_5(atomic_cmpxchgq_le, TCG_CALL_NO_WG, TCG_CALL_NO_WG, i32, env, tl, i32, i32) #endif /* CONFIG_ATOMIC64 */ -#else - -DEF_HELPER_FLAGS_4(atomic_cmpxchgb, TCG_CALL_NO_WG, i32, env, tl, i32, i32) -DEF_HELPER_FLAGS_4(atomic_cmpxchgw_be, TCG_CALL_NO_WG, i32, env, tl, i32, i32) -DEF_HELPER_FLAGS_4(atomic_cmpxchgw_le, TCG_CALL_NO_WG, i32, env, tl, i32, i32) -DEF_HELPER_FLAGS_4(atomic_cmpxchgl_be, TCG_CALL_NO_WG, i32, env, tl, i32, i32) -DEF_HELPER_FLAGS_4(atomic_cmpxchgl_le, TCG_CALL_NO_WG, i32, env, tl, i32, i32) -#ifdef CONFIG_ATOMIC64 -DEF_HELPER_FLAGS_4(atomic_cmpxchgq_be, TCG_CALL_NO_WG, i64, env, tl, i64, i64) -DEF_HELPER_FLAGS_4(atomic_cmpxchgq_le, TCG_CALL_NO_WG, i64, env, tl, i64, i64) -#endif - -#ifdef CONFIG_ATOMIC64 -#define GEN_ATOMIC_HELPERS(NAME) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), b), \ - TCG_CALL_NO_WG, i32, env, tl, i32) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), w_le), \ - TCG_CALL_NO_WG, i32, env, tl, i32) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), w_be), \ - TCG_CALL_NO_WG, i32, env, tl, i32) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), l_le), \ - TCG_CALL_NO_WG, i32, env, tl, i32) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), l_be), \ - TCG_CALL_NO_WG, i32, env, tl, i32) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), q_le), \ - TCG_CALL_NO_WG, i64, env, tl, i64) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), q_be), \ - TCG_CALL_NO_WG, i64, env, tl, i64) -#else -#define GEN_ATOMIC_HELPERS(NAME) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), b), \ - TCG_CALL_NO_WG, i32, env, tl, i32) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), w_le), \ - TCG_CALL_NO_WG, i32, env, tl, i32) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), w_be), \ - TCG_CALL_NO_WG, i32, env, tl, i32) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), l_le), \ - TCG_CALL_NO_WG, i32, env, tl, i32) \ - DEF_HELPER_FLAGS_3(glue(glue(atomic_, NAME), l_be), \ - TCG_CALL_NO_WG, i32, env, tl, i32) -#endif /* CONFIG_ATOMIC64 */ - -#endif /* CONFIG_SOFTMMU */ - GEN_ATOMIC_HELPERS(fetch_add) GEN_ATOMIC_HELPERS(fetch_and) GEN_ATOMIC_HELPERS(fetch_or) diff --git a/accel/tcg/trace-events b/accel/tcg/trace-events index 6eefb37f5d..59eab96f26 100644 --- a/accel/tcg/trace-events +++ b/accel/tcg/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # TCG related tracing # cpu-exec.c diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index b12d0898d0..bbfcfb698c 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -18,11 +18,9 @@ */ #include "qemu/osdep.h" -#include "qemu/units.h" #include "qemu-common.h" #define NO_CPU_IO_DEFS -#include "cpu.h" #include "trace.h" #include "disas/disas.h" #include "exec/exec-all.h" @@ -48,10 +46,8 @@ #endif #include "exec/cputlb.h" -#include "exec/tb-hash.h" #include "exec/translate-all.h" #include "qemu/bitmap.h" -#include "qemu/error-report.h" #include "qemu/qemu-print.h" #include "qemu/timer.h" #include "qemu/main-loop.h" @@ -61,6 +57,8 @@ #include "sysemu/tcg.h" #include "qapi/error.h" #include "hw/core/tcg-cpu-ops.h" +#include "tb-hash.h" +#include "tb-context.h" #include "internal.h" /* #define DEBUG_TB_INVALIDATE */ @@ -220,9 +218,6 @@ static int v_l2_levels; static void *l1_map[V_L1_MAX_SIZE]; -/* code generation context */ -TCGContext tcg_init_ctx; -__thread TCGContext *tcg_ctx; TBContext tb_ctx; static void page_table_config_init(void) @@ -245,11 +240,6 @@ static void page_table_config_init(void) assert(v_l2_levels >= 0); } -static void cpu_gen_init(void) -{ - tcg_context_init(&tcg_init_ctx); -} - /* Encode VAL as a signed leb128 sequence at P. Return P incremented past the encoded value. */ static uint8_t *encode_sleb128(uint8_t *p, target_long val) @@ -388,11 +378,6 @@ static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb, return 0; } -void tb_destroy(TranslationBlock *tb) -{ - qemu_spin_destroy(&tb->jmp_lock); -} - bool cpu_restore_state(CPUState *cpu, uintptr_t host_pc, bool will_exit) { /* @@ -415,7 +400,7 @@ bool cpu_restore_state(CPUState *cpu, uintptr_t host_pc, bool will_exit) return false; } -static void page_init(void) +void page_init(void) { page_size_init(); page_table_config_init(); @@ -900,408 +885,6 @@ static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1, } } -/* Minimum size of the code gen buffer. This number is randomly chosen, - but not so small that we can't have a fair number of TB's live. */ -#define MIN_CODE_GEN_BUFFER_SIZE (1 * MiB) - -/* Maximum size of the code gen buffer we'd like to use. Unless otherwise - indicated, this is constrained by the range of direct branches on the - host cpu, as used by the TCG implementation of goto_tb. */ -#if defined(__x86_64__) -# define MAX_CODE_GEN_BUFFER_SIZE (2 * GiB) -#elif defined(__sparc__) -# define MAX_CODE_GEN_BUFFER_SIZE (2 * GiB) -#elif defined(__powerpc64__) -# define MAX_CODE_GEN_BUFFER_SIZE (2 * GiB) -#elif defined(__powerpc__) -# define MAX_CODE_GEN_BUFFER_SIZE (32 * MiB) -#elif defined(__aarch64__) -# define MAX_CODE_GEN_BUFFER_SIZE (2 * GiB) -#elif defined(__s390x__) - /* We have a +- 4GB range on the branches; leave some slop. */ -# define MAX_CODE_GEN_BUFFER_SIZE (3 * GiB) -#elif defined(__mips__) - /* We have a 256MB branch region, but leave room to make sure the - main executable is also within that region. */ -# define MAX_CODE_GEN_BUFFER_SIZE (128 * MiB) -#else -# define MAX_CODE_GEN_BUFFER_SIZE ((size_t)-1) -#endif - -#if TCG_TARGET_REG_BITS == 32 -#define DEFAULT_CODE_GEN_BUFFER_SIZE_1 (32 * MiB) -#ifdef CONFIG_USER_ONLY -/* - * For user mode on smaller 32 bit systems we may run into trouble - * allocating big chunks of data in the right place. On these systems - * we utilise a static code generation buffer directly in the binary. - */ -#define USE_STATIC_CODE_GEN_BUFFER -#endif -#else /* TCG_TARGET_REG_BITS == 64 */ -#ifdef CONFIG_USER_ONLY -/* - * As user-mode emulation typically means running multiple instances - * of the translator don't go too nuts with our default code gen - * buffer lest we make things too hard for the OS. - */ -#define DEFAULT_CODE_GEN_BUFFER_SIZE_1 (128 * MiB) -#else -/* - * We expect most system emulation to run one or two guests per host. - * Users running large scale system emulation may want to tweak their - * runtime setup via the tb-size control on the command line. - */ -#define DEFAULT_CODE_GEN_BUFFER_SIZE_1 (1 * GiB) -#endif -#endif - -#define DEFAULT_CODE_GEN_BUFFER_SIZE \ - (DEFAULT_CODE_GEN_BUFFER_SIZE_1 < MAX_CODE_GEN_BUFFER_SIZE \ - ? DEFAULT_CODE_GEN_BUFFER_SIZE_1 : MAX_CODE_GEN_BUFFER_SIZE) - -static size_t size_code_gen_buffer(size_t tb_size) -{ - /* Size the buffer. */ - if (tb_size == 0) { - size_t phys_mem = qemu_get_host_physmem(); - if (phys_mem == 0) { - tb_size = DEFAULT_CODE_GEN_BUFFER_SIZE; - } else { - tb_size = MIN(DEFAULT_CODE_GEN_BUFFER_SIZE, phys_mem / 8); - } - } - if (tb_size < MIN_CODE_GEN_BUFFER_SIZE) { - tb_size = MIN_CODE_GEN_BUFFER_SIZE; - } - if (tb_size > MAX_CODE_GEN_BUFFER_SIZE) { - tb_size = MAX_CODE_GEN_BUFFER_SIZE; - } - return tb_size; -} - -#ifdef __mips__ -/* In order to use J and JAL within the code_gen_buffer, we require - that the buffer not cross a 256MB boundary. */ -static inline bool cross_256mb(void *addr, size_t size) -{ - return ((uintptr_t)addr ^ ((uintptr_t)addr + size)) & ~0x0ffffffful; -} - -/* We weren't able to allocate a buffer without crossing that boundary, - so make do with the larger portion of the buffer that doesn't cross. - Returns the new base of the buffer, and adjusts code_gen_buffer_size. */ -static inline void *split_cross_256mb(void *buf1, size_t size1) -{ - void *buf2 = (void *)(((uintptr_t)buf1 + size1) & ~0x0ffffffful); - size_t size2 = buf1 + size1 - buf2; - - size1 = buf2 - buf1; - if (size1 < size2) { - size1 = size2; - buf1 = buf2; - } - - tcg_ctx->code_gen_buffer_size = size1; - return buf1; -} -#endif - -#ifdef USE_STATIC_CODE_GEN_BUFFER -static uint8_t static_code_gen_buffer[DEFAULT_CODE_GEN_BUFFER_SIZE] - __attribute__((aligned(CODE_GEN_ALIGN))); - -static bool alloc_code_gen_buffer(size_t tb_size, int splitwx, Error **errp) -{ - void *buf, *end; - size_t size; - - if (splitwx > 0) { - error_setg(errp, "jit split-wx not supported"); - return false; - } - - /* page-align the beginning and end of the buffer */ - buf = static_code_gen_buffer; - end = static_code_gen_buffer + sizeof(static_code_gen_buffer); - buf = QEMU_ALIGN_PTR_UP(buf, qemu_real_host_page_size); - end = QEMU_ALIGN_PTR_DOWN(end, qemu_real_host_page_size); - - size = end - buf; - - /* Honor a command-line option limiting the size of the buffer. */ - if (size > tb_size) { - size = QEMU_ALIGN_DOWN(tb_size, qemu_real_host_page_size); - } - tcg_ctx->code_gen_buffer_size = size; - -#ifdef __mips__ - if (cross_256mb(buf, size)) { - buf = split_cross_256mb(buf, size); - size = tcg_ctx->code_gen_buffer_size; - } -#endif - - if (qemu_mprotect_rwx(buf, size)) { - error_setg_errno(errp, errno, "mprotect of jit buffer"); - return false; - } - qemu_madvise(buf, size, QEMU_MADV_HUGEPAGE); - - tcg_ctx->code_gen_buffer = buf; - return true; -} -#elif defined(_WIN32) -static bool alloc_code_gen_buffer(size_t size, int splitwx, Error **errp) -{ - void *buf; - - if (splitwx > 0) { - error_setg(errp, "jit split-wx not supported"); - return false; - } - - buf = VirtualAlloc(NULL, size, MEM_RESERVE | MEM_COMMIT, - PAGE_EXECUTE_READWRITE); - if (buf == NULL) { - error_setg_win32(errp, GetLastError(), - "allocate %zu bytes for jit buffer", size); - return false; - } - - tcg_ctx->code_gen_buffer = buf; - tcg_ctx->code_gen_buffer_size = size; - return true; -} -#else -static bool alloc_code_gen_buffer_anon(size_t size, int prot, - int flags, Error **errp) -{ - void *buf; - - buf = mmap(NULL, size, prot, flags, -1, 0); - if (buf == MAP_FAILED) { - error_setg_errno(errp, errno, - "allocate %zu bytes for jit buffer", size); - return false; - } - tcg_ctx->code_gen_buffer_size = size; - -#ifdef __mips__ - if (cross_256mb(buf, size)) { - /* - * Try again, with the original still mapped, to avoid re-acquiring - * the same 256mb crossing. - */ - size_t size2; - void *buf2 = mmap(NULL, size, prot, flags, -1, 0); - switch ((int)(buf2 != MAP_FAILED)) { - case 1: - if (!cross_256mb(buf2, size)) { - /* Success! Use the new buffer. */ - munmap(buf, size); - break; - } - /* Failure. Work with what we had. */ - munmap(buf2, size); - /* fallthru */ - default: - /* Split the original buffer. Free the smaller half. */ - buf2 = split_cross_256mb(buf, size); - size2 = tcg_ctx->code_gen_buffer_size; - if (buf == buf2) { - munmap(buf + size2, size - size2); - } else { - munmap(buf, size - size2); - } - size = size2; - break; - } - buf = buf2; - } -#endif - - /* Request large pages for the buffer. */ - qemu_madvise(buf, size, QEMU_MADV_HUGEPAGE); - - tcg_ctx->code_gen_buffer = buf; - return true; -} - -#ifndef CONFIG_TCG_INTERPRETER -#ifdef CONFIG_POSIX -#include "qemu/memfd.h" - -static bool alloc_code_gen_buffer_splitwx_memfd(size_t size, Error **errp) -{ - void *buf_rw = NULL, *buf_rx = MAP_FAILED; - int fd = -1; - -#ifdef __mips__ - /* Find space for the RX mapping, vs the 256MiB regions. */ - if (!alloc_code_gen_buffer_anon(size, PROT_NONE, - MAP_PRIVATE | MAP_ANONYMOUS | - MAP_NORESERVE, errp)) { - return false; - } - /* The size of the mapping may have been adjusted. */ - size = tcg_ctx->code_gen_buffer_size; - buf_rx = tcg_ctx->code_gen_buffer; -#endif - - buf_rw = qemu_memfd_alloc("tcg-jit", size, 0, &fd, errp); - if (buf_rw == NULL) { - goto fail; - } - -#ifdef __mips__ - void *tmp = mmap(buf_rx, size, PROT_READ | PROT_EXEC, - MAP_SHARED | MAP_FIXED, fd, 0); - if (tmp != buf_rx) { - goto fail_rx; - } -#else - buf_rx = mmap(NULL, size, PROT_READ | PROT_EXEC, MAP_SHARED, fd, 0); - if (buf_rx == MAP_FAILED) { - goto fail_rx; - } -#endif - - close(fd); - tcg_ctx->code_gen_buffer = buf_rw; - tcg_ctx->code_gen_buffer_size = size; - tcg_splitwx_diff = buf_rx - buf_rw; - - /* Request large pages for the buffer and the splitwx. */ - qemu_madvise(buf_rw, size, QEMU_MADV_HUGEPAGE); - qemu_madvise(buf_rx, size, QEMU_MADV_HUGEPAGE); - return true; - - fail_rx: - error_setg_errno(errp, errno, "failed to map shared memory for execute"); - fail: - if (buf_rx != MAP_FAILED) { - munmap(buf_rx, size); - } - if (buf_rw) { - munmap(buf_rw, size); - } - if (fd >= 0) { - close(fd); - } - return false; -} -#endif /* CONFIG_POSIX */ - -#ifdef CONFIG_DARWIN -#include - -extern kern_return_t mach_vm_remap(vm_map_t target_task, - mach_vm_address_t *target_address, - mach_vm_size_t size, - mach_vm_offset_t mask, - int flags, - vm_map_t src_task, - mach_vm_address_t src_address, - boolean_t copy, - vm_prot_t *cur_protection, - vm_prot_t *max_protection, - vm_inherit_t inheritance); - -static bool alloc_code_gen_buffer_splitwx_vmremap(size_t size, Error **errp) -{ - kern_return_t ret; - mach_vm_address_t buf_rw, buf_rx; - vm_prot_t cur_prot, max_prot; - - /* Map the read-write portion via normal anon memory. */ - if (!alloc_code_gen_buffer_anon(size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, errp)) { - return false; - } - - buf_rw = (mach_vm_address_t)tcg_ctx->code_gen_buffer; - buf_rx = 0; - ret = mach_vm_remap(mach_task_self(), - &buf_rx, - size, - 0, - VM_FLAGS_ANYWHERE, - mach_task_self(), - buf_rw, - false, - &cur_prot, - &max_prot, - VM_INHERIT_NONE); - if (ret != KERN_SUCCESS) { - /* TODO: Convert "ret" to a human readable error message. */ - error_setg(errp, "vm_remap for jit splitwx failed"); - munmap((void *)buf_rw, size); - return false; - } - - if (mprotect((void *)buf_rx, size, PROT_READ | PROT_EXEC) != 0) { - error_setg_errno(errp, errno, "mprotect for jit splitwx"); - munmap((void *)buf_rx, size); - munmap((void *)buf_rw, size); - return false; - } - - tcg_splitwx_diff = buf_rx - buf_rw; - return true; -} -#endif /* CONFIG_DARWIN */ -#endif /* CONFIG_TCG_INTERPRETER */ - -static bool alloc_code_gen_buffer_splitwx(size_t size, Error **errp) -{ -#ifndef CONFIG_TCG_INTERPRETER -# ifdef CONFIG_DARWIN - return alloc_code_gen_buffer_splitwx_vmremap(size, errp); -# endif -# ifdef CONFIG_POSIX - return alloc_code_gen_buffer_splitwx_memfd(size, errp); -# endif -#endif - error_setg(errp, "jit split-wx not supported"); - return false; -} - -static bool alloc_code_gen_buffer(size_t size, int splitwx, Error **errp) -{ - ERRP_GUARD(); - int prot, flags; - - if (splitwx) { - if (alloc_code_gen_buffer_splitwx(size, errp)) { - return true; - } - /* - * If splitwx force-on (1), fail; - * if splitwx default-on (-1), fall through to splitwx off. - */ - if (splitwx > 0) { - return false; - } - error_free_or_abort(errp); - } - - prot = PROT_READ | PROT_WRITE | PROT_EXEC; - flags = MAP_PRIVATE | MAP_ANONYMOUS; -#ifdef CONFIG_TCG_INTERPRETER - /* The tcg interpreter does not need execute permission. */ - prot = PROT_READ | PROT_WRITE; -#elif defined(CONFIG_DARWIN) - /* Applicable to both iOS and macOS (Apple Silicon). */ - if (!splitwx) { - flags |= MAP_JIT; - } -#endif - - return alloc_code_gen_buffer_anon(size, prot, flags, errp); -} -#endif /* USE_STATIC_CODE_GEN_BUFFER, WIN32, POSIX */ - static bool tb_cmp(const void *ap, const void *bp) { const TranslationBlock *a = ap; @@ -1316,36 +899,13 @@ static bool tb_cmp(const void *ap, const void *bp) a->page_addr[1] == b->page_addr[1]; } -static void tb_htable_init(void) +void tb_htable_init(void) { unsigned int mode = QHT_MODE_AUTO_RESIZE; qht_init(&tb_ctx.htable, tb_cmp, CODE_GEN_HTABLE_SIZE, mode); } -/* Must be called before using the QEMU cpus. 'tb_size' is the size - (in bytes) allocated to the translation buffer. Zero means default - size. */ -void tcg_exec_init(unsigned long tb_size, int splitwx) -{ - bool ok; - - tcg_allowed = true; - cpu_gen_init(); - page_init(); - tb_htable_init(); - - ok = alloc_code_gen_buffer(size_code_gen_buffer(tb_size), - splitwx, &error_fatal); - assert(ok); - -#if defined(CONFIG_SOFTMMU) - /* There's no guest base to take into account, so go ahead and - initialize the prologue now. */ - tcg_prologue_init(tcg_ctx); -#endif -} - /* call with @p->lock held */ static inline void invalidate_page_bitmap(PageDesc *p) { @@ -1659,8 +1219,8 @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list) /* suppress any remaining jumps to this TB */ tb_jmp_unlink(tb); - qatomic_set(&tcg_ctx->tb_phys_invalidate_count, - tcg_ctx->tb_phys_invalidate_count + 1); + qatomic_set(&tb_ctx.tb_phys_invalidate_count, + tb_ctx.tb_phys_invalidate_count + 1); } static void tb_phys_invalidate__locked(TranslationBlock *tb) @@ -1868,14 +1428,9 @@ TranslationBlock *tb_gen_code(CPUState *cpu, max_insns = cflags & CF_COUNT_MASK; if (max_insns == 0) { - max_insns = CF_COUNT_MASK; - } - if (max_insns > TCG_MAX_INSNS) { max_insns = TCG_MAX_INSNS; } - if (cpu->singlestep_enabled || singlestep) { - max_insns = 1; - } + QEMU_BUILD_BUG_ON(CF_COUNT_MASK + 1 != TCG_MAX_INSNS); buffer_overflow: tb = tcg_tb_alloc(tcg_ctx); @@ -1913,6 +1468,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu, tcg_ctx->cpu = env_cpu(env); gen_intermediate_code(cpu, tb, max_insns); + assert(tb->size != 0); tcg_ctx->cpu = NULL; max_insns = tb->icount; @@ -2043,8 +1599,15 @@ TranslationBlock *tb_gen_code(CPUState *cpu, int i; qemu_log(" data: [size=%d]\n", data_size); for (i = 0; i < data_size / sizeof(tcg_target_ulong); i++) { - qemu_log("0x%08" PRIxPTR ": .quad 0x%" TCG_PRIlx "\n", - (uintptr_t)&rx_data_gen_ptr[i], rx_data_gen_ptr[i]); + if (sizeof(tcg_target_ulong) == 8) { + qemu_log("0x%08" PRIxPTR ": .quad 0x%016" TCG_PRIlx "\n", + (uintptr_t)&rx_data_gen_ptr[i], rx_data_gen_ptr[i]); + } else if (sizeof(tcg_target_ulong) == 4) { + qemu_log("0x%08" PRIxPTR ": .long 0x%08" TCG_PRIlx "\n", + (uintptr_t)&rx_data_gen_ptr[i], rx_data_gen_ptr[i]); + } else { + qemu_build_not_reached(); + } } } qemu_log("\n"); @@ -2084,6 +1647,13 @@ TranslationBlock *tb_gen_code(CPUState *cpu, return tb; } + /* + * Insert TB into the corresponding region tree before publishing it + * through QHT. Otherwise rewinding happened in the TB might fail to + * lookup itself using host PC. + */ + tcg_tb_insert(tb); + /* check next page if needed */ virt_page2 = (pc + tb->size - 1) & TARGET_PAGE_MASK; phys_page2 = -1; @@ -2101,10 +1671,9 @@ TranslationBlock *tb_gen_code(CPUState *cpu, orig_aligned -= ROUND_UP(sizeof(*tb), qemu_icache_linesize); qatomic_set(&tcg_ctx->code_gen_ptr, (void *)orig_aligned); - tb_destroy(tb); + tcg_tb_remove(tb); return existing_tb; } - tcg_tb_insert(tb); return tb; } @@ -2554,8 +2123,8 @@ void dump_exec_info(void) qemu_printf("\nStatistics:\n"); qemu_printf("TB flush count %u\n", qatomic_read(&tb_ctx.tb_flush_count)); - qemu_printf("TB invalidate count %zu\n", - tcg_tb_phys_invalidate_count()); + qemu_printf("TB invalidate count %u\n", + qatomic_read(&tb_ctx.tb_phys_invalidate_count)); tlb_flush_counts(&flush_full, &flush_part, &flush_elide); qemu_printf("TLB full flushes %zu\n", flush_full); diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c index 2dfc27102f..c53a7f8e44 100644 --- a/accel/tcg/translator.c +++ b/accel/tcg/translator.c @@ -9,7 +9,6 @@ #include "qemu/osdep.h" #include "qemu/error-report.h" -#include "cpu.h" #include "tcg/tcg.h" #include "tcg/tcg-op.h" #include "exec/exec-all.h" @@ -32,10 +31,21 @@ void translator_loop_temp_check(DisasContextBase *db) } } +bool translator_use_goto_tb(DisasContextBase *db, target_ulong dest) +{ + /* Suppress goto_tb if requested. */ + if (tb_cflags(db->tb) & CF_NO_GOTO_TB) { + return false; + } + + /* Check for the dest on the same page as the start of the TB. */ + return ((db->pc_first ^ dest) & TARGET_PAGE_MASK) == 0; +} + void translator_loop(const TranslatorOps *ops, DisasContextBase *db, CPUState *cpu, TranslationBlock *tb, int max_insns) { - int bp_insn = 0; + uint32_t cflags = tb_cflags(tb); bool plugin_enabled; /* Initialize DisasContext */ @@ -45,7 +55,7 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db, db->is_jmp = DISAS_NEXT; db->num_insns = 0; db->max_insns = max_insns; - db->singlestep_enabled = cpu->singlestep_enabled; + db->singlestep_enabled = cflags & CF_SINGLE_STEP; ops->init_disas_context(db, cpu); tcg_debug_assert(db->is_jmp == DISAS_NEXT); /* no early exit */ @@ -58,8 +68,7 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db, ops->tb_start(db, cpu); tcg_debug_assert(db->is_jmp == DISAS_NEXT); /* no early exit */ - plugin_enabled = plugin_gen_tb_start(cpu, tb, - tb_cflags(db->tb) & CF_MEMI_ONLY); + plugin_enabled = plugin_gen_tb_start(cpu, tb, cflags & CF_MEMI_ONLY); while (true) { db->num_insns++; @@ -70,39 +79,17 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db, plugin_gen_insn_start(cpu, db); } - /* Pass breakpoint hits to target for further processing */ - if (!db->singlestep_enabled - && unlikely(!QTAILQ_EMPTY(&cpu->breakpoints))) { - CPUBreakpoint *bp; - QTAILQ_FOREACH(bp, &cpu->breakpoints, entry) { - if (bp->pc == db->pc_next) { - if (ops->breakpoint_check(db, cpu, bp)) { - bp_insn = 1; - break; - } - } - } - /* The breakpoint_check hook may use DISAS_TOO_MANY to indicate - that only one more instruction is to be executed. Otherwise - it should use DISAS_NORETURN when generating an exception, - but may use a DISAS_TARGET_* value for Something Else. */ - if (db->is_jmp > DISAS_TOO_MANY) { - break; - } - } - /* Disassemble one instruction. The translate_insn hook should update db->pc_next and db->is_jmp to indicate what should be done next -- either exiting this loop or locate the start of the next instruction. */ - if (db->num_insns == db->max_insns - && (tb_cflags(db->tb) & CF_LAST_IO)) { + if (db->num_insns == db->max_insns && (cflags & CF_LAST_IO)) { /* Accept I/O on the last instruction. */ gen_io_start(); ops->translate_insn(db, cpu); } else { /* we should only see CF_MEMI_ONLY for io_recompile */ - tcg_debug_assert(!(tb_cflags(db->tb) & CF_MEMI_ONLY)); + tcg_debug_assert(!(cflags & CF_MEMI_ONLY)); ops->translate_insn(db, cpu); } @@ -129,7 +116,7 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db, /* Emit code to exit the TB, as indicated by db->is_jmp. */ ops->tb_stop(db, cpu); - gen_tb_end(db->tb, db->num_insns - bp_insn); + gen_tb_end(db->tb, db->num_insns); if (plugin_enabled) { plugin_gen_tb_end(cpu); diff --git a/accel/tcg/user-exec-stub.c b/accel/tcg/user-exec-stub.c index b876f5c1e4..968cd3ca60 100644 --- a/accel/tcg/user-exec-stub.c +++ b/accel/tcg/user-exec-stub.c @@ -1,7 +1,6 @@ #include "qemu/osdep.h" #include "hw/core/cpu.h" #include "sysemu/replay.h" -#include "sysemu/sysemu.h" bool enable_cpu_pm = false; diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c index 0d8cc27b21..90d1a2d327 100644 --- a/accel/tcg/user-exec.c +++ b/accel/tcg/user-exec.c @@ -17,7 +17,6 @@ * License along with this library; if not, see . */ #include "qemu/osdep.h" -#include "cpu.h" #include "hw/core/tcg-cpu-ops.h" #include "disas/disas.h" #include "exec/exec-all.h" @@ -255,28 +254,35 @@ void *probe_access(CPUArchState *env, target_ulong addr, int size, #if defined(__NetBSD__) #include +#include #define EIP_sig(context) ((context)->uc_mcontext.__gregs[_REG_EIP]) #define TRAP_sig(context) ((context)->uc_mcontext.__gregs[_REG_TRAPNO]) #define ERROR_sig(context) ((context)->uc_mcontext.__gregs[_REG_ERR]) #define MASK_sig(context) ((context)->uc_sigmask) +#define PAGE_FAULT_TRAP T_PAGEFLT #elif defined(__FreeBSD__) || defined(__DragonFly__) #include +#include #define EIP_sig(context) (*((unsigned long *)&(context)->uc_mcontext.mc_eip)) #define TRAP_sig(context) ((context)->uc_mcontext.mc_trapno) #define ERROR_sig(context) ((context)->uc_mcontext.mc_err) #define MASK_sig(context) ((context)->uc_sigmask) +#define PAGE_FAULT_TRAP T_PAGEFLT #elif defined(__OpenBSD__) +#include #define EIP_sig(context) ((context)->sc_eip) #define TRAP_sig(context) ((context)->sc_trapno) #define ERROR_sig(context) ((context)->sc_err) #define MASK_sig(context) ((context)->sc_mask) +#define PAGE_FAULT_TRAP T_PAGEFLT #else #define EIP_sig(context) ((context)->uc_mcontext.gregs[REG_EIP]) #define TRAP_sig(context) ((context)->uc_mcontext.gregs[REG_TRAPNO]) #define ERROR_sig(context) ((context)->uc_mcontext.gregs[REG_ERR]) #define MASK_sig(context) ((context)->uc_sigmask) +#define PAGE_FAULT_TRAP 0xe #endif int cpu_signal_handler(int host_signum, void *pinfo, @@ -302,34 +308,42 @@ int cpu_signal_handler(int host_signum, void *pinfo, pc = EIP_sig(uc); trapno = TRAP_sig(uc); return handle_cpu_signal(pc, info, - trapno == 0xe ? (ERROR_sig(uc) >> 1) & 1 : 0, + trapno == PAGE_FAULT_TRAP ? + (ERROR_sig(uc) >> 1) & 1 : 0, &MASK_sig(uc)); } #elif defined(__x86_64__) #ifdef __NetBSD__ +#include #define PC_sig(context) _UC_MACHINE_PC(context) #define TRAP_sig(context) ((context)->uc_mcontext.__gregs[_REG_TRAPNO]) #define ERROR_sig(context) ((context)->uc_mcontext.__gregs[_REG_ERR]) #define MASK_sig(context) ((context)->uc_sigmask) +#define PAGE_FAULT_TRAP T_PAGEFLT #elif defined(__OpenBSD__) +#include #define PC_sig(context) ((context)->sc_rip) #define TRAP_sig(context) ((context)->sc_trapno) #define ERROR_sig(context) ((context)->sc_err) #define MASK_sig(context) ((context)->sc_mask) +#define PAGE_FAULT_TRAP T_PAGEFLT #elif defined(__FreeBSD__) || defined(__DragonFly__) #include +#include #define PC_sig(context) (*((unsigned long *)&(context)->uc_mcontext.mc_rip)) #define TRAP_sig(context) ((context)->uc_mcontext.mc_trapno) #define ERROR_sig(context) ((context)->uc_mcontext.mc_err) #define MASK_sig(context) ((context)->uc_sigmask) +#define PAGE_FAULT_TRAP T_PAGEFLT #else #define PC_sig(context) ((context)->uc_mcontext.gregs[REG_RIP]) #define TRAP_sig(context) ((context)->uc_mcontext.gregs[REG_TRAPNO]) #define ERROR_sig(context) ((context)->uc_mcontext.gregs[REG_ERR]) #define MASK_sig(context) ((context)->uc_sigmask) +#define PAGE_FAULT_TRAP 0xe #endif int cpu_signal_handler(int host_signum, void *pinfo, @@ -347,7 +361,8 @@ int cpu_signal_handler(int host_signum, void *pinfo, pc = PC_sig(uc); return handle_cpu_signal(pc, info, - TRAP_sig(uc) == 0xe ? (ERROR_sig(uc) >> 1) & 1 : 0, + TRAP_sig(uc) == PAGE_FAULT_TRAP ? + (ERROR_sig(uc) >> 1) & 1 : 0, &MASK_sig(uc)); } @@ -1206,9 +1221,14 @@ uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr ptr) return ret; } -/* Do not allow unaligned operations to proceed. Return the host address. */ +/* + * Do not allow unaligned operations to proceed. Return the host address. + * + * @prot may be PAGE_READ, PAGE_WRITE, or PAGE_READ|PAGE_WRITE. + */ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, - int size, uintptr_t retaddr) + TCGMemOpIdx oi, int size, int prot, + uintptr_t retaddr) { /* Enforce qemu required alignment. */ if (unlikely(addr & (size - 1))) { @@ -1219,17 +1239,18 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, return ret; } -/* Macro to call the above, with local variables from the use context. */ -#define ATOMIC_MMU_DECLS do {} while (0) -#define ATOMIC_MMU_LOOKUP atomic_mmu_lookup(env, addr, DATA_SIZE, GETPC()) +#include "atomic_common.c.inc" + +/* + * First set of functions passes in OI and RETADDR. + * This makes them callable from other helpers. + */ + +#define ATOMIC_NAME(X) \ + glue(glue(glue(cpu_atomic_ ## X, SUFFIX), END), _mmu) #define ATOMIC_MMU_CLEANUP do { clear_helper_retaddr(); } while (0) #define ATOMIC_MMU_IDX MMU_USER_IDX -#define ATOMIC_NAME(X) HELPER(glue(glue(atomic_ ## X, SUFFIX), END)) -#define EXTRA_ARGS - -#include "atomic_common.c.inc" - #define DATA_SIZE 1 #include "atomic_template.h" @@ -1244,20 +1265,7 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, #include "atomic_template.h" #endif -/* The following is only callable from other helpers, and matches up - with the softmmu version. */ - #if HAVE_ATOMIC128 || HAVE_CMPXCHG128 - -#undef EXTRA_ARGS -#undef ATOMIC_NAME -#undef ATOMIC_MMU_LOOKUP - -#define EXTRA_ARGS , TCGMemOpIdx oi, uintptr_t retaddr -#define ATOMIC_NAME(X) \ - HELPER(glue(glue(glue(atomic_ ## X, SUFFIX), END), _mmu)) -#define ATOMIC_MMU_LOOKUP atomic_mmu_lookup(env, addr, DATA_SIZE, retaddr) - #define DATA_SIZE 16 #include "atomic_template.h" #endif diff --git a/audio/alsaaudio.c b/audio/alsaaudio.c index fcc2f62864..2b9789e647 100644 --- a/audio/alsaaudio.c +++ b/audio/alsaaudio.c @@ -34,6 +34,8 @@ #define AUDIO_CAP "alsa" #include "audio_int.h" +#define DEBUG_ALSA 0 + struct pollhlp { snd_pcm_t *handle; struct pollfd *pfds; @@ -587,16 +589,12 @@ static int alsa_open(bool in, struct alsa_params_req *req, *handlep = handle; - if (obtfmt != req->fmt || - obt->nchannels != req->nchannels || - obt->freq != req->freq) { + if (DEBUG_ALSA || obtfmt != req->fmt || + obt->nchannels != req->nchannels || obt->freq != req->freq) { dolog ("Audio parameters for %s\n", typ); alsa_dump_info(req, obt, obtfmt, apdo); } -#ifdef DEBUG - alsa_dump_info(req, obt, obtfmt, apdo); -#endif return 0; err: diff --git a/audio/audio.c b/audio/audio.c index 534278edfe..54a153c0ef 100644 --- a/audio/audio.c +++ b/audio/audio.c @@ -32,6 +32,7 @@ #include "qapi/qapi-visit-audio.h" #include "qemu/cutils.h" #include "qemu/module.h" +#include "qemu-common.h" #include "sysemu/replay.h" #include "sysemu/runstate.h" #include "ui/qemu-spice.h" @@ -704,7 +705,7 @@ static size_t audio_pcm_sw_write(SWVoiceOut *sw, void *buf, size_t size) if (live == hwsamples) { #ifdef DEBUG_OUT - dolog ("%s is full %d\n", sw->name, live); + dolog ("%s is full %zu\n", sw->name, live); #endif return 0; } @@ -994,7 +995,7 @@ static size_t audio_get_avail (SWVoiceIn *sw) } ldebug ( - "%s: get_avail live %d ret %" PRId64 "\n", + "%s: get_avail live %zu ret %" PRId64 "\n", SW_NAME (sw), live, (((int64_t) live << 32) / sw->ratio) * sw->info.bytes_per_frame ); @@ -1021,7 +1022,7 @@ static size_t audio_get_free(SWVoiceOut *sw) dead = sw->hw->mix_buf->size - live; #ifdef DEBUG_OUT - dolog ("%s: get_free live %d dead %d ret %" PRId64 "\n", + dolog ("%s: get_free live %zu dead %zu ret %" PRId64 "\n", SW_NAME (sw), live, dead, (((int64_t) dead << 32) / sw->ratio) * sw->info.bytes_per_frame); @@ -1621,10 +1622,20 @@ void audio_cleanup(void) } } +static bool vmstate_audio_needed(void *opaque) +{ + /* + * Never needed, this vmstate only exists in case + * an old qemu sends it to us. + */ + return false; +} + static const VMStateDescription vmstate_audio = { .name = "audio", .version_id = 1, .minimum_version_id = 1, + .needed = vmstate_audio_needed, .fields = (VMStateField[]) { VMSTATE_END_OF_LIST() } @@ -2172,6 +2183,14 @@ const char *audio_get_id(QEMUSoundCard *card) } } +const char *audio_application_name(void) +{ + const char *vm_name; + + vm_name = qemu_get_vm_name(); + return vm_name ? vm_name : "qemu"; +} + void audio_rate_start(RateCtl *rate) { memset(rate, 0, sizeof(RateCtl)); diff --git a/audio/audio_int.h b/audio/audio_int.h index 06f0913835..6d685e24a3 100644 --- a/audio/audio_int.h +++ b/audio/audio_int.h @@ -243,6 +243,8 @@ void *audio_calloc (const char *funcname, int nmemb, size_t size); void audio_run(AudioState *s, const char *msg); +const char *audio_application_name(void); + typedef struct RateCtl { int64_t start_ticks; int64_t bytes_sent; diff --git a/audio/coreaudio.c b/audio/coreaudio.c index 578ec9b8b2..d8a21d3e50 100644 --- a/audio/coreaudio.c +++ b/audio/coreaudio.c @@ -26,6 +26,7 @@ #include #include /* pthread_X */ +#include "qemu/main-loop.h" #include "qemu/module.h" #include "audio.h" @@ -34,12 +35,11 @@ typedef struct coreaudioVoiceOut { HWVoiceOut hw; - pthread_mutex_t mutex; + pthread_mutex_t buf_mutex; AudioDeviceID outputDeviceID; int frameSizeSetting; uint32_t bufferCount; UInt32 audioDevicePropertyBufferFrameSize; - AudioStreamBasicDescription outputStreamBasicDescription; AudioDeviceIOProcID ioprocid; bool enabled; } coreaudioVoiceOut; @@ -114,24 +114,6 @@ static OSStatus coreaudio_set_framesize(AudioDeviceID id, UInt32 *framesize) framesize); } -static OSStatus coreaudio_get_streamformat(AudioDeviceID id, - AudioStreamBasicDescription *d) -{ - UInt32 size = sizeof(*d); - AudioObjectPropertyAddress addr = { - kAudioDevicePropertyStreamFormat, - kAudioDevicePropertyScopeOutput, - kAudioObjectPropertyElementMaster - }; - - return AudioObjectGetPropertyData(id, - &addr, - 0, - NULL, - &size, - d); -} - static OSStatus coreaudio_set_streamformat(AudioDeviceID id, AudioStreamBasicDescription *d) { @@ -260,11 +242,11 @@ static void GCC_FMT_ATTR (3, 4) coreaudio_logerr2 ( #define coreaudio_playback_logerr(status, ...) \ coreaudio_logerr2(status, "playback", __VA_ARGS__) -static int coreaudio_lock (coreaudioVoiceOut *core, const char *fn_name) +static int coreaudio_buf_lock (coreaudioVoiceOut *core, const char *fn_name) { int err; - err = pthread_mutex_lock (&core->mutex); + err = pthread_mutex_lock (&core->buf_mutex); if (err) { dolog ("Could not lock voice for %s\nReason: %s\n", fn_name, strerror (err)); @@ -273,11 +255,11 @@ static int coreaudio_lock (coreaudioVoiceOut *core, const char *fn_name) return 0; } -static int coreaudio_unlock (coreaudioVoiceOut *core, const char *fn_name) +static int coreaudio_buf_unlock (coreaudioVoiceOut *core, const char *fn_name) { int err; - err = pthread_mutex_unlock (&core->mutex); + err = pthread_mutex_unlock (&core->buf_mutex); if (err) { dolog ("Could not unlock voice for %s\nReason: %s\n", fn_name, strerror (err)); @@ -292,13 +274,13 @@ static int coreaudio_unlock (coreaudioVoiceOut *core, const char *fn_name) coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw; \ ret_type ret; \ \ - if (coreaudio_lock(core, "coreaudio_" #name)) { \ + if (coreaudio_buf_lock(core, "coreaudio_" #name)) { \ return 0; \ } \ \ ret = glue(audio_generic_, name)args; \ \ - coreaudio_unlock(core, "coreaudio_" #name); \ + coreaudio_buf_unlock(core, "coreaudio_" #name); \ return ret; \ } COREAUDIO_WRAPPER_FUNC(get_buffer_out, void *, (HWVoiceOut *hw, size_t *size), @@ -310,7 +292,10 @@ COREAUDIO_WRAPPER_FUNC(write, size_t, (HWVoiceOut *hw, void *buf, size_t size), (hw, buf, size)) #undef COREAUDIO_WRAPPER_FUNC -/* callback to feed audiooutput buffer */ +/* + * callback to feed audiooutput buffer. called without iothread lock. + * allowed to lock "buf_mutex", but disallowed to have any other locks. + */ static OSStatus audioDeviceIOProc( AudioDeviceID inDevice, const AudioTimeStamp *inNow, @@ -326,13 +311,13 @@ static OSStatus audioDeviceIOProc( coreaudioVoiceOut *core = (coreaudioVoiceOut *) hwptr; size_t len; - if (coreaudio_lock (core, "audioDeviceIOProc")) { + if (coreaudio_buf_lock (core, "audioDeviceIOProc")) { inInputTime = 0; return 0; } if (inDevice != core->outputDeviceID) { - coreaudio_unlock (core, "audioDeviceIOProc(old device)"); + coreaudio_buf_unlock (core, "audioDeviceIOProc(old device)"); return 0; } @@ -342,7 +327,7 @@ static OSStatus audioDeviceIOProc( /* if there are not enough samples, set signal and return */ if (pending_frames < frameCount) { inInputTime = 0; - coreaudio_unlock (core, "audioDeviceIOProc(empty)"); + coreaudio_buf_unlock (core, "audioDeviceIOProc(empty)"); return 0; } @@ -364,7 +349,7 @@ static OSStatus audioDeviceIOProc( out += write_len; } - coreaudio_unlock (core, "audioDeviceIOProc"); + coreaudio_buf_unlock (core, "audioDeviceIOProc"); return 0; } @@ -373,6 +358,17 @@ static OSStatus init_out_device(coreaudioVoiceOut *core) OSStatus status; AudioValueRange frameRange; + AudioStreamBasicDescription streamBasicDescription = { + .mBitsPerChannel = core->hw.info.bits, + .mBytesPerFrame = core->hw.info.bytes_per_frame, + .mBytesPerPacket = core->hw.info.bytes_per_frame, + .mChannelsPerFrame = core->hw.info.nchannels, + .mFormatFlags = kLinearPCMFormatFlagIsFloat, + .mFormatID = kAudioFormatLinearPCM, + .mFramesPerPacket = 1, + .mSampleRate = core->hw.info.freq + }; + status = coreaudio_get_voice(&core->outputDeviceID); if (status != kAudioHardwareNoError) { coreaudio_playback_logerr (status, @@ -432,34 +428,30 @@ static OSStatus init_out_device(coreaudioVoiceOut *core) } core->hw.samples = core->bufferCount * core->audioDevicePropertyBufferFrameSize; - /* get StreamFormat */ - status = coreaudio_get_streamformat(core->outputDeviceID, - &core->outputStreamBasicDescription); - if (status == kAudioHardwareBadObjectError) { - return 0; - } - if (status != kAudioHardwareNoError) { - coreaudio_playback_logerr (status, - "Could not get Device Stream properties\n"); - core->outputDeviceID = kAudioDeviceUnknown; - return status; - } - /* set Samplerate */ status = coreaudio_set_streamformat(core->outputDeviceID, - &core->outputStreamBasicDescription); + &streamBasicDescription); if (status == kAudioHardwareBadObjectError) { return 0; } if (status != kAudioHardwareNoError) { coreaudio_playback_logerr (status, "Could not set samplerate %lf\n", - core->outputStreamBasicDescription.mSampleRate); + streamBasicDescription.mSampleRate); core->outputDeviceID = kAudioDeviceUnknown; return status; } - /* set Callback */ + /* + * set Callback. + * + * On macOS 11.3.1, Core Audio calls AudioDeviceIOProc after calling an + * internal function named HALB_Mutex::Lock(), which locks a mutex in + * HALB_IOThread::Entry(void*). HALB_Mutex::Lock() is also called in + * AudioObjectGetPropertyData, which is called by coreaudio driver. + * Therefore, the specified callback must be designed to avoid a deadlock + * with the callers of AudioObjectGetPropertyData. + */ core->ioprocid = NULL; status = AudioDeviceCreateIOProcID(core->outputDeviceID, audioDeviceIOProc, @@ -542,6 +534,7 @@ static void update_device_playback_state(coreaudioVoiceOut *core) } } +/* called without iothread lock. */ static OSStatus handle_voice_change( AudioObjectID in_object_id, UInt32 in_number_addresses, @@ -551,9 +544,7 @@ static OSStatus handle_voice_change( OSStatus status; coreaudioVoiceOut *core = in_client_data; - if (coreaudio_lock(core, __func__)) { - abort(); - } + qemu_mutex_lock_iothread(); if (core->outputDeviceID) { fini_out_device(core); @@ -564,7 +555,7 @@ static OSStatus handle_voice_change( update_device_playback_state(core); } - coreaudio_unlock (core, __func__); + qemu_mutex_unlock_iothread(); return status; } @@ -579,14 +570,10 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as, struct audsettings obt_as; /* create mutex */ - err = pthread_mutex_init(&core->mutex, NULL); + err = pthread_mutex_init(&core->buf_mutex, NULL); if (err) { dolog("Could not create mutex\nReason: %s\n", strerror (err)); - goto mutex_error; - } - - if (coreaudio_lock(core, __func__)) { - goto lock_error; + return -1; } obt_as = *as; @@ -598,7 +585,6 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as, qapi_AudiodevCoreaudioPerDirectionOptions_base(cpdo), as, 11610); core->bufferCount = cpdo->has_buffer_count ? cpdo->buffer_count : 4; - core->outputStreamBasicDescription.mSampleRate = (Float64) as->freq; status = AudioObjectAddPropertyListener(kAudioObjectSystemObject, &voice_addr, handle_voice_change, @@ -606,37 +592,21 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as, if (status != kAudioHardwareNoError) { coreaudio_playback_logerr (status, "Could not listen to voice property change\n"); - goto listener_error; + return -1; } if (init_out_device(core)) { - goto device_error; + status = AudioObjectRemovePropertyListener(kAudioObjectSystemObject, + &voice_addr, + handle_voice_change, + core); + if (status != kAudioHardwareNoError) { + coreaudio_playback_logerr(status, + "Could not remove voice property change listener\n"); + } } - coreaudio_unlock(core, __func__); return 0; - -device_error: - status = AudioObjectRemovePropertyListener(kAudioObjectSystemObject, - &voice_addr, - handle_voice_change, - core); - if (status != kAudioHardwareNoError) { - coreaudio_playback_logerr(status, - "Could not remove voice property change listener\n"); - } - -listener_error: - coreaudio_unlock(core, __func__); - -lock_error: - err = pthread_mutex_destroy(&core->mutex); - if (err) { - dolog("Could not destroy mutex\nReason: %s\n", strerror (err)); - } - -mutex_error: - return -1; } static void coreaudio_fini_out (HWVoiceOut *hw) @@ -645,10 +615,6 @@ static void coreaudio_fini_out (HWVoiceOut *hw) int err; coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw; - if (coreaudio_lock(core, __func__)) { - abort(); - } - status = AudioObjectRemovePropertyListener(kAudioObjectSystemObject, &voice_addr, handle_voice_change, @@ -659,10 +625,8 @@ static void coreaudio_fini_out (HWVoiceOut *hw) fini_out_device(core); - coreaudio_unlock(core, __func__); - /* destroy mutex */ - err = pthread_mutex_destroy(&core->mutex); + err = pthread_mutex_destroy(&core->buf_mutex); if (err) { dolog("Could not destroy mutex\nReason: %s\n", strerror (err)); } @@ -672,14 +636,8 @@ static void coreaudio_enable_out(HWVoiceOut *hw, bool enable) { coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw; - if (coreaudio_lock(core, __func__)) { - abort(); - } - core->enabled = enable; update_device_playback_state(core); - - coreaudio_unlock(core, __func__); } static void *coreaudio_audio_init(Audiodev *dev) diff --git a/audio/jackaudio.c b/audio/jackaudio.c index 3031c4e29b..e7de6d5433 100644 --- a/audio/jackaudio.c +++ b/audio/jackaudio.c @@ -26,7 +26,6 @@ #include "qemu/module.h" #include "qemu/atomic.h" #include "qemu/main-loop.h" -#include "qemu-common.h" #include "audio.h" #define AUDIO_CAP "jack" @@ -412,7 +411,7 @@ static int qjack_client_init(QJackClient *c) snprintf(client_name, sizeof(client_name), "%s-%s", c->out ? "out" : "in", - c->opt->client_name ? c->opt->client_name : qemu_get_vm_name()); + c->opt->client_name ? c->opt->client_name : audio_application_name()); if (c->opt->exact_name) { options |= JackUseExactName; diff --git a/audio/paaudio.c b/audio/paaudio.c index c97b22e970..75401d5391 100644 --- a/audio/paaudio.c +++ b/audio/paaudio.c @@ -2,7 +2,6 @@ #include "qemu/osdep.h" #include "qemu/module.h" -#include "qemu-common.h" #include "audio.h" #include "qapi/opts-visitor.h" @@ -463,10 +462,7 @@ static pa_stream *qpa_simple_new ( pa_stream_set_state_callback(stream, stream_state_cb, c); - flags = - PA_STREAM_INTERPOLATE_TIMING - | PA_STREAM_AUTO_TIMING_UPDATE - | PA_STREAM_EARLY_REQUESTS; + flags = PA_STREAM_EARLY_REQUESTS; if (dev) { /* don't move the stream if the user specified a sink/source */ @@ -756,7 +752,6 @@ static int qpa_validate_per_direction_opts(Audiodev *dev, /* common */ static void *qpa_conn_init(const char *server) { - const char *vm_name; PAConnection *c = g_malloc0(sizeof(PAConnection)); QTAILQ_INSERT_TAIL(&pa_conns, c, list); @@ -765,9 +760,8 @@ static void *qpa_conn_init(const char *server) goto fail; } - vm_name = qemu_get_vm_name(); c->context = pa_context_new(pa_threaded_mainloop_get_api(c->mainloop), - vm_name ? vm_name : "qemu"); + audio_application_name()); if (!c->context) { goto fail; } diff --git a/audio/spiceaudio.c b/audio/spiceaudio.c index 999bfbde47..a8d370fe6f 100644 --- a/audio/spiceaudio.c +++ b/audio/spiceaudio.c @@ -317,3 +317,5 @@ static void register_audio_spice(void) audio_driver_register(&spice_audio_driver); } type_init(register_audio_spice); + +module_dep("ui-spice-core"); diff --git a/audio/trace-events b/audio/trace-events index 6aec535763..957c92337b 100644 --- a/audio/trace-events +++ b/audio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # alsaaudio.c alsa_revents(int revents) "revents = %d" diff --git a/authz/meson.build b/authz/meson.build index 88fa7769cb..42a1ec0ff6 100644 --- a/authz/meson.build +++ b/authz/meson.build @@ -6,4 +6,4 @@ authz_ss.add(files( 'simple.c', )) -authz_ss.add(when: ['CONFIG_AUTH_PAM', pam], if_true: files('pamacct.c')) +authz_ss.add(when: pam, if_true: files('pamacct.c')) diff --git a/authz/trace-events b/authz/trace-events index e62ebb36b7..9c255dafb6 100644 --- a/authz/trace-events +++ b/authz/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # base.c qauthz_is_allowed(void *authz, const char *identity, bool allowed) "AuthZ %p check identity=%s allowed=%d" diff --git a/backends/cryptodev-vhost.c b/backends/cryptodev-vhost.c index 8231e7f1bc..bc13e466b4 100644 --- a/backends/cryptodev-vhost.c +++ b/backends/cryptodev-vhost.c @@ -52,6 +52,7 @@ cryptodev_vhost_init( { int r; CryptoDevBackendVhost *crypto; + Error *local_err = NULL; crypto = g_new(CryptoDevBackendVhost, 1); crypto->dev.max_queues = 1; @@ -66,8 +67,10 @@ cryptodev_vhost_init( /* vhost-user needs vq_index to initiate a specific queue pair */ crypto->dev.vq_index = crypto->cc->queue_index * crypto->dev.nvqs; - r = vhost_dev_init(&crypto->dev, options->opaque, options->backend_type, 0); + r = vhost_dev_init(&crypto->dev, options->opaque, options->backend_type, 0, + &local_err); if (r < 0) { + error_report_err(local_err); goto fail; } diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c index b683da9daf..cd038024fa 100644 --- a/backends/hostmem-file.c +++ b/backends/hostmem-file.c @@ -15,7 +15,6 @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "sysemu/hostmem.h" -#include "sysemu/sysemu.h" #include "qom/object_interfaces.h" #include "qom/object.h" @@ -40,6 +39,7 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) object_get_typename(OBJECT(backend))); #else HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(backend); + uint32_t ram_flags; gchar *name; if (!backend->size) { @@ -52,11 +52,11 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) } name = host_memory_backend_get_name(backend); - memory_region_init_ram_from_file(&backend->mr, OBJECT(backend), - name, - backend->size, fb->align, - (backend->share ? RAM_SHARED : 0) | - (fb->is_pmem ? RAM_PMEM : 0), + ram_flags = backend->share ? RAM_SHARED : 0; + ram_flags |= backend->reserve ? 0 : RAM_NORESERVE; + ram_flags |= fb->is_pmem ? RAM_PMEM : 0; + memory_region_init_ram_from_file(&backend->mr, OBJECT(backend), name, + backend->size, fb->align, ram_flags, fb->mem_path, fb->readonly, errp); g_free(name); #endif diff --git a/backends/hostmem-memfd.c b/backends/hostmem-memfd.c index 69b0ae30bb..3fc85c3db8 100644 --- a/backends/hostmem-memfd.c +++ b/backends/hostmem-memfd.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" #include "sysemu/hostmem.h" -#include "sysemu/sysemu.h" #include "qom/object_interfaces.h" #include "qemu/memfd.h" #include "qemu/module.h" @@ -36,6 +35,7 @@ static void memfd_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) { HostMemoryBackendMemfd *m = MEMORY_BACKEND_MEMFD(backend); + uint32_t ram_flags; char *name; int fd; @@ -53,9 +53,10 @@ memfd_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) } name = host_memory_backend_get_name(backend); - memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend), - name, backend->size, - backend->share, fd, 0, errp); + ram_flags = backend->share ? RAM_SHARED : 0; + ram_flags |= backend->reserve ? 0 : RAM_NORESERVE; + memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend), name, + backend->size, ram_flags, fd, 0, errp); g_free(name); } diff --git a/backends/hostmem-ram.c b/backends/hostmem-ram.c index 5cc53e76c9..b8e55cdbd0 100644 --- a/backends/hostmem-ram.c +++ b/backends/hostmem-ram.c @@ -19,6 +19,7 @@ static void ram_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) { + uint32_t ram_flags; char *name; if (!backend->size) { @@ -27,8 +28,10 @@ ram_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) } name = host_memory_backend_get_name(backend); - memory_region_init_ram_shared_nomigrate(&backend->mr, OBJECT(backend), name, - backend->size, backend->share, errp); + ram_flags = backend->share ? RAM_SHARED : 0; + ram_flags |= backend->reserve ? 0 : RAM_NORESERVE; + memory_region_init_ram_flags_nomigrate(&backend->mr, OBJECT(backend), name, + backend->size, ram_flags, errp); g_free(name); } diff --git a/backends/hostmem.c b/backends/hostmem.c index c6c1ff5b99..4c05862ed5 100644 --- a/backends/hostmem.c +++ b/backends/hostmem.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" #include "sysemu/hostmem.h" -#include "sysemu/sysemu.h" #include "hw/boards.h" #include "qapi/error.h" #include "qapi/qapi-builtin-visit.h" @@ -217,6 +216,11 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value, Error *local_err = NULL; HostMemoryBackend *backend = MEMORY_BACKEND(obj); + if (!backend->reserve && value) { + error_setg(errp, "'prealloc=on' and 'reserve=off' are incompatible"); + return; + } + if (!host_memory_backend_mr_inited(backend)) { backend->prealloc = value; return; @@ -268,6 +272,7 @@ static void host_memory_backend_init(Object *obj) /* TODO: convert access to globals to compat properties */ backend->merge = machine_mem_merge(machine); backend->dump = machine_dump_guest_core(machine); + backend->reserve = true; backend->prealloc_threads = 1; } @@ -426,6 +431,30 @@ static void host_memory_backend_set_share(Object *o, bool value, Error **errp) backend->share = value; } +#ifdef CONFIG_LINUX +static bool host_memory_backend_get_reserve(Object *o, Error **errp) +{ + HostMemoryBackend *backend = MEMORY_BACKEND(o); + + return backend->reserve; +} + +static void host_memory_backend_set_reserve(Object *o, bool value, Error **errp) +{ + HostMemoryBackend *backend = MEMORY_BACKEND(o); + + if (host_memory_backend_mr_inited(backend)) { + error_setg(errp, "cannot change property value"); + return; + } + if (backend->prealloc && !value) { + error_setg(errp, "'prealloc=on' and 'reserve=off' are incompatible"); + return; + } + backend->reserve = value; +} +#endif /* CONFIG_LINUX */ + static bool host_memory_backend_get_use_canonical_path(Object *obj, Error **errp) { @@ -494,6 +523,12 @@ host_memory_backend_class_init(ObjectClass *oc, void *data) host_memory_backend_get_share, host_memory_backend_set_share); object_class_property_set_description(oc, "share", "Mark the memory as private to QEMU or shared"); +#ifdef CONFIG_LINUX + object_class_property_add_bool(oc, "reserve", + host_memory_backend_get_reserve, host_memory_backend_set_reserve); + object_class_property_set_description(oc, "reserve", + "Reserve swap space (or huge pages) if applicable"); +#endif /* CONFIG_LINUX */ /* * Do not delete/rename option. This option must be considered stable * (as if it didn't have the 'x-' prefix including deprecation period) as diff --git a/backends/tpm/tpm_emulator.c b/backends/tpm/tpm_emulator.c index a012adc193..e5f1063ab6 100644 --- a/backends/tpm/tpm_emulator.c +++ b/backends/tpm/tpm_emulator.c @@ -30,6 +30,7 @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "qemu/sockets.h" +#include "qemu/lockable.h" #include "io/channel-socket.h" #include "sysemu/tpm_backend.h" #include "sysemu/tpm_util.h" @@ -124,31 +125,26 @@ static int tpm_emulator_ctrlcmd(TPMEmulator *tpm, unsigned long cmd, void *msg, uint32_t cmd_no = cpu_to_be32(cmd); ssize_t n = sizeof(uint32_t) + msg_len_in; uint8_t *buf = NULL; - int ret = -1; - qemu_mutex_lock(&tpm->mutex); + WITH_QEMU_LOCK_GUARD(&tpm->mutex) { + buf = g_alloca(n); + memcpy(buf, &cmd_no, sizeof(cmd_no)); + memcpy(buf + sizeof(cmd_no), msg, msg_len_in); - buf = g_alloca(n); - memcpy(buf, &cmd_no, sizeof(cmd_no)); - memcpy(buf + sizeof(cmd_no), msg, msg_len_in); - - n = qemu_chr_fe_write_all(dev, buf, n); - if (n <= 0) { - goto end; - } - - if (msg_len_out != 0) { - n = qemu_chr_fe_read_all(dev, msg, msg_len_out); + n = qemu_chr_fe_write_all(dev, buf, n); if (n <= 0) { - goto end; + return -1; + } + + if (msg_len_out != 0) { + n = qemu_chr_fe_read_all(dev, msg, msg_len_out); + if (n <= 0) { + return -1; + } } } - ret = 0; - -end: - qemu_mutex_unlock(&tpm->mutex); - return ret; + return 0; } static int tpm_emulator_unix_tx_bufs(TPMEmulator *tpm_emu, diff --git a/backends/tpm/trace-events b/backends/tpm/trace-events index 0a2591fb2d..3298766dd7 100644 --- a/backends/tpm/trace-events +++ b/backends/tpm/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # tpm_passthrough.c tpm_passthrough_handle_request(void *cmd) "processing command %p" diff --git a/backends/trace-events b/backends/trace-events index 59058f7630..652eb76a57 100644 --- a/backends/trace-events +++ b/backends/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # dbus-vmstate.c dbus_vmstate_pre_save(void) diff --git a/backends/vhost-user.c b/backends/vhost-user.c index b366610e16..10b39992d2 100644 --- a/backends/vhost-user.c +++ b/backends/vhost-user.c @@ -48,9 +48,9 @@ vhost_user_backend_dev_init(VhostUserBackend *b, VirtIODevice *vdev, b->dev.nvqs = nvqs; b->dev.vqs = g_new0(struct vhost_virtqueue, nvqs); - ret = vhost_dev_init(&b->dev, &b->vhost_user, VHOST_BACKEND_TYPE_USER, 0); + ret = vhost_dev_init(&b->dev, &b->vhost_user, VHOST_BACKEND_TYPE_USER, 0, + errp); if (ret < 0) { - error_setg_errno(errp, -ret, "vhost initialization failed"); return -1; } diff --git a/block.c b/block.c index c5b887cec1..e97ce0b1c8 100644 --- a/block.c +++ b/block.c @@ -2,6 +2,7 @@ * QEMU System Emulator block driver * * Copyright (c) 2003 Fabrice Bellard + * Copyright (c) 2020 Virtuozzo International GmbH. * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -41,7 +42,6 @@ #include "qapi/qobject-output-visitor.h" #include "qapi/qapi-visit-block-core.h" #include "sysemu/block-backend.h" -#include "sysemu/sysemu.h" #include "qemu/notify.h" #include "qemu/option.h" #include "qemu/coroutine.h" @@ -54,7 +54,7 @@ #ifdef CONFIG_BSD #include #include -#ifndef __DragonFly__ +#if defined(HAVE_SYS_DISK_H) #include #endif #endif @@ -82,6 +82,20 @@ static BlockDriverState *bdrv_open_inherit(const char *filename, BdrvChildRole child_role, Error **errp); +static void bdrv_replace_child_noperm(BdrvChild *child, + BlockDriverState *new_bs); +static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, + BdrvChild *child, + Transaction *tran); +static void bdrv_remove_filter_or_cow_child(BlockDriverState *bs, + Transaction *tran); + +static int bdrv_reopen_prepare(BDRVReopenState *reopen_state, + BlockReopenQueue *queue, + Transaction *change_child_tran, Error **errp); +static void bdrv_reopen_commit(BDRVReopenState *reopen_state); +static void bdrv_reopen_abort(BDRVReopenState *reopen_state); + /* If non-zero, use only whitelisted block drivers */ static int use_bdrv_whitelist; @@ -246,7 +260,7 @@ void bdrv_parse_filename_strip_prefix(const char *filename, const char *prefix, * image is inactivated. */ bool bdrv_is_read_only(BlockDriverState *bs) { - return bs->read_only; + return !(bs->open_flags & BDRV_O_RDWR); } int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, @@ -298,7 +312,6 @@ int bdrv_apply_auto_read_only(BlockDriverState *bs, const char *errmsg, goto fail; } - bs->read_only = true; bs->open_flags &= ~BDRV_O_RDWR; return 0; @@ -381,7 +394,6 @@ BlockDriverState *bdrv_new(void) for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) { QLIST_INIT(&bs->op_blockers[i]); } - notifier_with_return_list_init(&bs->before_write_notifiers); qemu_co_mutex_init(&bs->reqs_lock); qemu_mutex_init(&bs->dirty_bitmap_mutex); bs->refcnt = 1; @@ -1140,7 +1152,7 @@ int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough) static char *bdrv_child_get_parent_desc(BdrvChild *c) { BlockDriverState *parent = c->opaque; - return g_strdup(bdrv_get_device_or_node_name(parent)); + return g_strdup_printf("node '%s'", bdrv_get_node_name(parent)); } static void bdrv_child_cb_drained_begin(BdrvChild *child) @@ -1394,6 +1406,13 @@ static int bdrv_child_cb_update_filename(BdrvChild *c, BlockDriverState *base, return 0; } +AioContext *child_of_bds_get_parent_aio_context(BdrvChild *c) +{ + BlockDriverState *bs = c->opaque; + + return bdrv_get_aio_context(bs); +} + const BdrvChildClass child_of_bds = { .parent_is_bds = true, .get_parent_desc = bdrv_child_get_parent_desc, @@ -1407,8 +1426,14 @@ const BdrvChildClass child_of_bds = { .can_set_aio_ctx = bdrv_child_cb_can_set_aio_ctx, .set_aio_ctx = bdrv_child_cb_set_aio_ctx, .update_filename = bdrv_child_cb_update_filename, + .get_parent_aio_context = child_of_bds_get_parent_aio_context, }; +AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c) +{ + return c->klass->get_parent_aio_context(c); +} + static int bdrv_open_flags(BlockDriverState *bs, int flags) { int open_flags = flags; @@ -1518,7 +1543,6 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv, } bs->drv = drv; - bs->read_only = !(bs->open_flags & BDRV_O_RDWR); bs->opaque = g_malloc0(drv->instance_size); if (drv->bdrv_file_open) { @@ -1547,7 +1571,7 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv, return ret; } - bdrv_refresh_limits(bs, &local_err); + bdrv_refresh_limits(bs, NULL, &local_err); if (local_err) { error_propagate(errp, local_err); return -EINVAL; @@ -1689,6 +1713,7 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, QemuOpts *opts; BlockDriver *drv; Error *local_err = NULL; + bool ro; assert(bs->file == NULL); assert(options != NULL && bs->options != options); @@ -1739,17 +1764,17 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, trace_bdrv_open_common(bs, filename ?: "", bs->open_flags, drv->format_name); - bs->read_only = !(bs->open_flags & BDRV_O_RDWR); + ro = bdrv_is_read_only(bs); - if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) { - if (!bs->read_only && bdrv_is_whitelisted(drv, true)) { + if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, ro)) { + if (!ro && bdrv_is_whitelisted(drv, true)) { ret = bdrv_apply_auto_read_only(bs, NULL, NULL); } else { ret = -ENOTSUP; } if (ret < 0) { error_setg(errp, - !bs->read_only && bdrv_is_whitelisted(drv, true) + !ro && bdrv_is_whitelisted(drv, true) ? "Driver '%s' can only be used for read-only devices" : "Driver '%s' is not whitelisted", drv->format_name); @@ -1761,7 +1786,7 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, assert(qatomic_read(&bs->copy_on_read) == 0); if (bs->open_flags & BDRV_O_COPY_ON_READ) { - if (!bs->read_only) { + if (!ro) { bdrv_enable_copy_on_read(bs); } else { error_setg(errp, "Can't use copy-on-read on read-only device"); @@ -1955,12 +1980,6 @@ static int bdrv_fill_options(QDict **options, const char *filename, return 0; } -static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q, - uint64_t perm, uint64_t shared, - GSList *ignore_children, Error **errp); -static void bdrv_child_abort_perm_update(BdrvChild *c); -static void bdrv_child_set_perm(BdrvChild *c); - typedef struct BlockReopenQueueEntry { bool prepared; bool perms_checked; @@ -2008,6 +2027,68 @@ bool bdrv_is_writable(BlockDriverState *bs) return bdrv_is_writable_after_reopen(bs, NULL); } +static char *bdrv_child_user_desc(BdrvChild *c) +{ + return c->klass->get_parent_desc(c); +} + +/* + * Check that @a allows everything that @b needs. @a and @b must reference same + * child node. + */ +static bool bdrv_a_allow_b(BdrvChild *a, BdrvChild *b, Error **errp) +{ + const char *child_bs_name; + g_autofree char *a_user = NULL; + g_autofree char *b_user = NULL; + g_autofree char *perms = NULL; + + assert(a->bs); + assert(a->bs == b->bs); + + if ((b->perm & a->shared_perm) == b->perm) { + return true; + } + + child_bs_name = bdrv_get_node_name(b->bs); + a_user = bdrv_child_user_desc(a); + b_user = bdrv_child_user_desc(b); + perms = bdrv_perm_names(b->perm & ~a->shared_perm); + + error_setg(errp, "Permission conflict on node '%s': permissions '%s' are " + "both required by %s (uses node '%s' as '%s' child) and " + "unshared by %s (uses node '%s' as '%s' child).", + child_bs_name, perms, + b_user, child_bs_name, b->name, + a_user, child_bs_name, a->name); + + return false; +} + +static bool bdrv_parent_perms_conflict(BlockDriverState *bs, Error **errp) +{ + BdrvChild *a, *b; + + /* + * During the loop we'll look at each pair twice. That's correct because + * bdrv_a_allow_b() is asymmetric and we should check each pair in both + * directions. + */ + QLIST_FOREACH(a, &bs->parents, next_parent) { + QLIST_FOREACH(b, &bs->parents, next_parent) { + if (a == b) { + continue; + } + + if (!bdrv_a_allow_b(a, b, errp)) { + return true; + } + } + } + + return false; +} + static void bdrv_child_perm(BlockDriverState *bs, BlockDriverState *child_bs, BdrvChild *c, BdrvChildRole role, BlockReopenQueue *reopen_queue, @@ -2025,22 +2106,188 @@ static void bdrv_child_perm(BlockDriverState *bs, BlockDriverState *child_bs, } /* - * Check whether permissions on this node can be changed in a way that - * @cumulative_perms and @cumulative_shared_perms are the new cumulative - * permissions of all its parents. This involves checking whether all necessary - * permission changes to child nodes can be performed. + * Adds the whole subtree of @bs (including @bs itself) to the @list (except for + * nodes that are already in the @list, of course) so that final list is + * topologically sorted. Return the result (GSList @list object is updated, so + * don't use old reference after function call). * - * A call to this function must always be followed by a call to bdrv_set_perm() - * or bdrv_abort_perm_update(). + * On function start @list must be already topologically sorted and for any node + * in the @list the whole subtree of the node must be in the @list as well. The + * simplest way to satisfy this criteria: use only result of + * bdrv_topological_dfs() or NULL as @list parameter. */ -static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q, - uint64_t cumulative_perms, - uint64_t cumulative_shared_perms, - GSList *ignore_children, Error **errp) +static GSList *bdrv_topological_dfs(GSList *list, GHashTable *found, + BlockDriverState *bs) +{ + BdrvChild *child; + g_autoptr(GHashTable) local_found = NULL; + + if (!found) { + assert(!list); + found = local_found = g_hash_table_new(NULL, NULL); + } + + if (g_hash_table_contains(found, bs)) { + return list; + } + g_hash_table_add(found, bs); + + QLIST_FOREACH(child, &bs->children, next) { + list = bdrv_topological_dfs(list, found, child->bs); + } + + return g_slist_prepend(list, bs); +} + +typedef struct BdrvChildSetPermState { + BdrvChild *child; + uint64_t old_perm; + uint64_t old_shared_perm; +} BdrvChildSetPermState; + +static void bdrv_child_set_perm_abort(void *opaque) +{ + BdrvChildSetPermState *s = opaque; + + s->child->perm = s->old_perm; + s->child->shared_perm = s->old_shared_perm; +} + +static TransactionActionDrv bdrv_child_set_pem_drv = { + .abort = bdrv_child_set_perm_abort, + .clean = g_free, +}; + +static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, + uint64_t shared, Transaction *tran) +{ + BdrvChildSetPermState *s = g_new(BdrvChildSetPermState, 1); + + *s = (BdrvChildSetPermState) { + .child = c, + .old_perm = c->perm, + .old_shared_perm = c->shared_perm, + }; + + c->perm = perm; + c->shared_perm = shared; + + tran_add(tran, &bdrv_child_set_pem_drv, s); +} + +static void bdrv_drv_set_perm_commit(void *opaque) +{ + BlockDriverState *bs = opaque; + uint64_t cumulative_perms, cumulative_shared_perms; + + if (bs->drv->bdrv_set_perm) { + bdrv_get_cumulative_perm(bs, &cumulative_perms, + &cumulative_shared_perms); + bs->drv->bdrv_set_perm(bs, cumulative_perms, cumulative_shared_perms); + } +} + +static void bdrv_drv_set_perm_abort(void *opaque) +{ + BlockDriverState *bs = opaque; + + if (bs->drv->bdrv_abort_perm_update) { + bs->drv->bdrv_abort_perm_update(bs); + } +} + +TransactionActionDrv bdrv_drv_set_perm_drv = { + .abort = bdrv_drv_set_perm_abort, + .commit = bdrv_drv_set_perm_commit, +}; + +static int bdrv_drv_set_perm(BlockDriverState *bs, uint64_t perm, + uint64_t shared_perm, Transaction *tran, + Error **errp) +{ + if (!bs->drv) { + return 0; + } + + if (bs->drv->bdrv_check_perm) { + int ret = bs->drv->bdrv_check_perm(bs, perm, shared_perm, errp); + if (ret < 0) { + return ret; + } + } + + if (tran) { + tran_add(tran, &bdrv_drv_set_perm_drv, bs); + } + + return 0; +} + +typedef struct BdrvReplaceChildState { + BdrvChild *child; + BlockDriverState *old_bs; +} BdrvReplaceChildState; + +static void bdrv_replace_child_commit(void *opaque) +{ + BdrvReplaceChildState *s = opaque; + + bdrv_unref(s->old_bs); +} + +static void bdrv_replace_child_abort(void *opaque) +{ + BdrvReplaceChildState *s = opaque; + BlockDriverState *new_bs = s->child->bs; + + /* old_bs reference is transparently moved from @s to @s->child */ + bdrv_replace_child_noperm(s->child, s->old_bs); + bdrv_unref(new_bs); +} + +static TransactionActionDrv bdrv_replace_child_drv = { + .commit = bdrv_replace_child_commit, + .abort = bdrv_replace_child_abort, + .clean = g_free, +}; + +/* + * bdrv_replace_child_tran + * + * Note: real unref of old_bs is done only on commit. + * + * The function doesn't update permissions, caller is responsible for this. + */ +static void bdrv_replace_child_tran(BdrvChild *child, BlockDriverState *new_bs, + Transaction *tran) +{ + BdrvReplaceChildState *s = g_new(BdrvReplaceChildState, 1); + *s = (BdrvReplaceChildState) { + .child = child, + .old_bs = child->bs, + }; + tran_add(tran, &bdrv_replace_child_drv, s); + + if (new_bs) { + bdrv_ref(new_bs); + } + bdrv_replace_child_noperm(child, new_bs); + /* old_bs reference is transparently moved from @child to @s */ +} + +/* + * Refresh permissions in @bs subtree. The function is intended to be called + * after some graph modification that was done without permission update. + */ +static int bdrv_node_refresh_perm(BlockDriverState *bs, BlockReopenQueue *q, + Transaction *tran, Error **errp) { BlockDriver *drv = bs->drv; BdrvChild *c; int ret; + uint64_t cumulative_perms, cumulative_shared_perms; + + bdrv_get_cumulative_perm(bs, &cumulative_perms, &cumulative_shared_perms); /* Write permissions never work with read-only images */ if ((cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) && @@ -2049,15 +2296,8 @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q, if (!bdrv_is_writable_after_reopen(bs, NULL)) { error_setg(errp, "Block node is read-only"); } else { - uint64_t current_perms, current_shared; - bdrv_get_cumulative_perm(bs, ¤t_perms, ¤t_shared); - if (current_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) { - error_setg(errp, "Cannot make block node read-only, there is " - "a writer on it"); - } else { - error_setg(errp, "Cannot make block node read-only and create " - "a writer on it"); - } + error_setg(errp, "Read-only block node '%s' cannot support " + "read-write users", bdrv_get_node_name(bs)); } return -EPERM; @@ -2084,12 +2324,10 @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q, return 0; } - if (drv->bdrv_check_perm) { - ret = drv->bdrv_check_perm(bs, cumulative_perms, - cumulative_shared_perms, errp); - if (ret < 0) { - return ret; - } + ret = bdrv_drv_set_perm(bs, cumulative_perms, cumulative_shared_perms, tran, + errp); + if (ret < 0) { + return ret; } /* Drivers that never have children can omit .bdrv_child_perm() */ @@ -2105,8 +2343,26 @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q, bdrv_child_perm(bs, c->bs, c, c->role, q, cumulative_perms, cumulative_shared_perms, &cur_perm, &cur_shared); - ret = bdrv_child_check_perm(c, q, cur_perm, cur_shared, ignore_children, - errp); + bdrv_child_set_perm(c, cur_perm, cur_shared, tran); + } + + return 0; +} + +static int bdrv_list_refresh_perms(GSList *list, BlockReopenQueue *q, + Transaction *tran, Error **errp) +{ + int ret; + BlockDriverState *bs; + + for ( ; list; list = list->next) { + bs = list->data; + + if (bdrv_parent_perms_conflict(bs, errp)) { + return -EINVAL; + } + + ret = bdrv_node_refresh_perm(bs, q, tran, errp); if (ret < 0) { return ret; } @@ -2115,60 +2371,6 @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q, return 0; } -/* - * Notifies drivers that after a previous bdrv_check_perm() call, the - * permission update is not performed and any preparations made for it (e.g. - * taken file locks) need to be undone. - * - * This function recursively notifies all child nodes. - */ -static void bdrv_abort_perm_update(BlockDriverState *bs) -{ - BlockDriver *drv = bs->drv; - BdrvChild *c; - - if (!drv) { - return; - } - - if (drv->bdrv_abort_perm_update) { - drv->bdrv_abort_perm_update(bs); - } - - QLIST_FOREACH(c, &bs->children, next) { - bdrv_child_abort_perm_update(c); - } -} - -static void bdrv_set_perm(BlockDriverState *bs) -{ - uint64_t cumulative_perms, cumulative_shared_perms; - BlockDriver *drv = bs->drv; - BdrvChild *c; - - if (!drv) { - return; - } - - bdrv_get_cumulative_perm(bs, &cumulative_perms, &cumulative_shared_perms); - - /* Update this node */ - if (drv->bdrv_set_perm) { - drv->bdrv_set_perm(bs, cumulative_perms, cumulative_shared_perms); - } - - /* Drivers that never have children can omit .bdrv_child_perm() */ - if (!drv->bdrv_child_perm) { - assert(QLIST_EMPTY(&bs->children)); - return; - } - - /* Update all children */ - QLIST_FOREACH(c, &bs->children, next) { - bdrv_child_set_perm(c); - } -} - void bdrv_get_cumulative_perm(BlockDriverState *bs, uint64_t *perm, uint64_t *shared_perm) { @@ -2185,15 +2387,6 @@ void bdrv_get_cumulative_perm(BlockDriverState *bs, uint64_t *perm, *shared_perm = cumulative_shared_perms; } -static char *bdrv_child_user_desc(BdrvChild *c) -{ - if (c->klass->get_parent_desc) { - return c->klass->get_parent_desc(c); - } - - return g_strdup("another user"); -} - char *bdrv_perm_names(uint64_t perm) { struct perm_name { @@ -2223,140 +2416,33 @@ char *bdrv_perm_names(uint64_t perm) return g_string_free(result, FALSE); } -/* - * Checks whether a new reference to @bs can be added if the new user requires - * @new_used_perm/@new_shared_perm as its permissions. If @ignore_children is - * set, the BdrvChild objects in this list are ignored in the calculations; - * this allows checking permission updates for an existing reference. - * - * Needs to be followed by a call to either bdrv_set_perm() or - * bdrv_abort_perm_update(). */ -static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q, - uint64_t new_used_perm, - uint64_t new_shared_perm, - GSList *ignore_children, - Error **errp) -{ - BdrvChild *c; - uint64_t cumulative_perms = new_used_perm; - uint64_t cumulative_shared_perms = new_shared_perm; - - - /* There is no reason why anyone couldn't tolerate write_unchanged */ - assert(new_shared_perm & BLK_PERM_WRITE_UNCHANGED); - - QLIST_FOREACH(c, &bs->parents, next_parent) { - if (g_slist_find(ignore_children, c)) { - continue; - } - - if ((new_used_perm & c->shared_perm) != new_used_perm) { - char *user = bdrv_child_user_desc(c); - char *perm_names = bdrv_perm_names(new_used_perm & ~c->shared_perm); - - error_setg(errp, "Conflicts with use by %s as '%s', which does not " - "allow '%s' on %s", - user, c->name, perm_names, bdrv_get_node_name(c->bs)); - g_free(user); - g_free(perm_names); - return -EPERM; - } - - if ((c->perm & new_shared_perm) != c->perm) { - char *user = bdrv_child_user_desc(c); - char *perm_names = bdrv_perm_names(c->perm & ~new_shared_perm); - - error_setg(errp, "Conflicts with use by %s as '%s', which uses " - "'%s' on %s", - user, c->name, perm_names, bdrv_get_node_name(c->bs)); - g_free(user); - g_free(perm_names); - return -EPERM; - } - - cumulative_perms |= c->perm; - cumulative_shared_perms &= c->shared_perm; - } - - return bdrv_check_perm(bs, q, cumulative_perms, cumulative_shared_perms, - ignore_children, errp); -} - -/* Needs to be followed by a call to either bdrv_child_set_perm() or - * bdrv_child_abort_perm_update(). */ -static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q, - uint64_t perm, uint64_t shared, - GSList *ignore_children, Error **errp) -{ - int ret; - - ignore_children = g_slist_prepend(g_slist_copy(ignore_children), c); - ret = bdrv_check_update_perm(c->bs, q, perm, shared, ignore_children, errp); - g_slist_free(ignore_children); - - if (ret < 0) { - return ret; - } - - if (!c->has_backup_perm) { - c->has_backup_perm = true; - c->backup_perm = c->perm; - c->backup_shared_perm = c->shared_perm; - } - /* - * Note: it's OK if c->has_backup_perm was already set, as we can find the - * same child twice during check_perm procedure - */ - - c->perm = perm; - c->shared_perm = shared; - - return 0; -} - -static void bdrv_child_set_perm(BdrvChild *c) -{ - c->has_backup_perm = false; - - bdrv_set_perm(c->bs); -} - -static void bdrv_child_abort_perm_update(BdrvChild *c) -{ - if (c->has_backup_perm) { - c->perm = c->backup_perm; - c->shared_perm = c->backup_shared_perm; - c->has_backup_perm = false; - } - - bdrv_abort_perm_update(c->bs); -} static int bdrv_refresh_perms(BlockDriverState *bs, Error **errp) { int ret; - uint64_t perm, shared_perm; + Transaction *tran = tran_new(); + g_autoptr(GSList) list = bdrv_topological_dfs(NULL, NULL, bs); - bdrv_get_cumulative_perm(bs, &perm, &shared_perm); - ret = bdrv_check_perm(bs, NULL, perm, shared_perm, NULL, errp); - if (ret < 0) { - bdrv_abort_perm_update(bs); - return ret; - } - bdrv_set_perm(bs); + ret = bdrv_list_refresh_perms(list, NULL, tran, errp); + tran_finalize(tran, ret); - return 0; + return ret; } int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared, Error **errp) { Error *local_err = NULL; + Transaction *tran = tran_new(); int ret; - ret = bdrv_child_check_perm(c, NULL, perm, shared, NULL, &local_err); + bdrv_child_set_perm(c, perm, shared, tran); + + ret = bdrv_refresh_perms(c->bs, &local_err); + + tran_finalize(tran, ret); + if (ret < 0) { - bdrv_child_abort_perm_update(c); if ((perm & ~c->perm) || (c->shared_perm & ~shared)) { /* tighten permissions */ error_propagate(errp, local_err); @@ -2370,12 +2456,9 @@ int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared, error_free(local_err); ret = 0; } - return ret; } - bdrv_child_set_perm(c); - - return 0; + return ret; } int bdrv_child_refresh_perms(BlockDriverState *bs, BdrvChild *c, Error **errp) @@ -2627,37 +2710,192 @@ static void bdrv_replace_child_noperm(BdrvChild *child, } } +static void bdrv_child_free(void *opaque) +{ + BdrvChild *c = opaque; + + g_free(c->name); + g_free(c); +} + +static void bdrv_remove_empty_child(BdrvChild *child) +{ + assert(!child->bs); + QLIST_SAFE_REMOVE(child, next); + bdrv_child_free(child); +} + +typedef struct BdrvAttachChildCommonState { + BdrvChild **child; + AioContext *old_parent_ctx; + AioContext *old_child_ctx; +} BdrvAttachChildCommonState; + +static void bdrv_attach_child_common_abort(void *opaque) +{ + BdrvAttachChildCommonState *s = opaque; + BdrvChild *child = *s->child; + BlockDriverState *bs = child->bs; + + bdrv_replace_child_noperm(child, NULL); + + if (bdrv_get_aio_context(bs) != s->old_child_ctx) { + bdrv_try_set_aio_context(bs, s->old_child_ctx, &error_abort); + } + + if (bdrv_child_get_parent_aio_context(child) != s->old_parent_ctx) { + GSList *ignore = g_slist_prepend(NULL, child); + + child->klass->can_set_aio_ctx(child, s->old_parent_ctx, &ignore, + &error_abort); + g_slist_free(ignore); + ignore = g_slist_prepend(NULL, child); + child->klass->set_aio_ctx(child, s->old_parent_ctx, &ignore); + + g_slist_free(ignore); + } + + bdrv_unref(bs); + bdrv_remove_empty_child(child); + *s->child = NULL; +} + +static TransactionActionDrv bdrv_attach_child_common_drv = { + .abort = bdrv_attach_child_common_abort, + .clean = g_free, +}; + /* - * Updates @child to change its reference to point to @new_bs, including - * checking and applying the necessary permission updates both to the old node - * and to @new_bs. + * Common part of attaching bdrv child to bs or to blk or to job * - * NULL is passed as @new_bs for removing the reference before freeing @child. + * Resulting new child is returned through @child. + * At start *@child must be NULL. + * @child is saved to a new entry of @tran, so that *@child could be reverted to + * NULL on abort(). So referenced variable must live at least until transaction + * end. * - * If @new_bs is not NULL, bdrv_check_perm() must be called beforehand, as this - * function uses bdrv_set_perm() to update the permissions according to the new - * reference that @new_bs gets. - * - * Callers must ensure that child->frozen is false. + * Function doesn't update permissions, caller is responsible for this. */ -static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs) +static int bdrv_attach_child_common(BlockDriverState *child_bs, + const char *child_name, + const BdrvChildClass *child_class, + BdrvChildRole child_role, + uint64_t perm, uint64_t shared_perm, + void *opaque, BdrvChild **child, + Transaction *tran, Error **errp) +{ + BdrvChild *new_child; + AioContext *parent_ctx; + AioContext *child_ctx = bdrv_get_aio_context(child_bs); + + assert(child); + assert(*child == NULL); + assert(child_class->get_parent_desc); + + new_child = g_new(BdrvChild, 1); + *new_child = (BdrvChild) { + .bs = NULL, + .name = g_strdup(child_name), + .klass = child_class, + .role = child_role, + .perm = perm, + .shared_perm = shared_perm, + .opaque = opaque, + }; + + /* + * If the AioContexts don't match, first try to move the subtree of + * child_bs into the AioContext of the new parent. If this doesn't work, + * try moving the parent into the AioContext of child_bs instead. + */ + parent_ctx = bdrv_child_get_parent_aio_context(new_child); + if (child_ctx != parent_ctx) { + Error *local_err = NULL; + int ret = bdrv_try_set_aio_context(child_bs, parent_ctx, &local_err); + + if (ret < 0 && child_class->can_set_aio_ctx) { + GSList *ignore = g_slist_prepend(NULL, new_child); + if (child_class->can_set_aio_ctx(new_child, child_ctx, &ignore, + NULL)) + { + error_free(local_err); + ret = 0; + g_slist_free(ignore); + ignore = g_slist_prepend(NULL, new_child); + child_class->set_aio_ctx(new_child, child_ctx, &ignore); + } + g_slist_free(ignore); + } + + if (ret < 0) { + error_propagate(errp, local_err); + bdrv_remove_empty_child(new_child); + return ret; + } + } + + bdrv_ref(child_bs); + bdrv_replace_child_noperm(new_child, child_bs); + + *child = new_child; + + BdrvAttachChildCommonState *s = g_new(BdrvAttachChildCommonState, 1); + *s = (BdrvAttachChildCommonState) { + .child = child, + .old_parent_ctx = parent_ctx, + .old_child_ctx = child_ctx, + }; + tran_add(tran, &bdrv_attach_child_common_drv, s); + + return 0; +} + +/* + * Variable referenced by @child must live at least until transaction end. + * (see bdrv_attach_child_common() doc for details) + * + * Function doesn't update permissions, caller is responsible for this. + */ +static int bdrv_attach_child_noperm(BlockDriverState *parent_bs, + BlockDriverState *child_bs, + const char *child_name, + const BdrvChildClass *child_class, + BdrvChildRole child_role, + BdrvChild **child, + Transaction *tran, + Error **errp) +{ + int ret; + uint64_t perm, shared_perm; + + assert(parent_bs->drv); + + bdrv_get_cumulative_perm(parent_bs, &perm, &shared_perm); + bdrv_child_perm(parent_bs, child_bs, NULL, child_role, NULL, + perm, shared_perm, &perm, &shared_perm); + + ret = bdrv_attach_child_common(child_bs, child_name, child_class, + child_role, perm, shared_perm, parent_bs, + child, tran, errp); + if (ret < 0) { + return ret; + } + + QLIST_INSERT_HEAD(&parent_bs->children, *child, next); + /* + * child is removed in bdrv_attach_child_common_abort(), so don't care to + * abort this change separately. + */ + + return 0; +} + +static void bdrv_detach_child(BdrvChild *child) { BlockDriverState *old_bs = child->bs; - /* Asserts that child->frozen == false */ - bdrv_replace_child_noperm(child, new_bs); - - /* - * Start with the new node's permissions. If @new_bs is a (direct - * or indirect) child of @old_bs, we must complete the permission - * update on @new_bs before we loosen the restrictions on @old_bs. - * Otherwise, bdrv_check_perm() on @old_bs would re-initiate - * updating the permissions of @new_bs, and thus not purely loosen - * restrictions. - */ - if (new_bs) { - bdrv_set_perm(new_bs); - } + bdrv_replace_child_noperm(child, NULL); + bdrv_remove_empty_child(child); if (old_bs) { /* @@ -2667,8 +2905,10 @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs) */ bdrv_refresh_perms(old_bs, NULL); - /* When the parent requiring a non-default AioContext is removed, the - * node moves back to the main AioContext */ + /* + * When the parent requiring a non-default AioContext is removed, the + * node moves back to the main AioContext + */ bdrv_try_set_aio_context(old_bs, qemu_get_aio_context(), NULL); } } @@ -2687,61 +2927,28 @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, const char *child_name, const BdrvChildClass *child_class, BdrvChildRole child_role, - AioContext *ctx, uint64_t perm, uint64_t shared_perm, void *opaque, Error **errp) { - BdrvChild *child; - Error *local_err = NULL; int ret; + BdrvChild *child = NULL; + Transaction *tran = tran_new(); - ret = bdrv_check_update_perm(child_bs, NULL, perm, shared_perm, NULL, errp); + ret = bdrv_attach_child_common(child_bs, child_name, child_class, + child_role, perm, shared_perm, opaque, + &child, tran, errp); if (ret < 0) { - bdrv_abort_perm_update(child_bs); - bdrv_unref(child_bs); - return NULL; + goto out; } - child = g_new(BdrvChild, 1); - *child = (BdrvChild) { - .bs = NULL, - .name = g_strdup(child_name), - .klass = child_class, - .role = child_role, - .perm = perm, - .shared_perm = shared_perm, - .opaque = opaque, - }; + ret = bdrv_refresh_perms(child_bs, errp); - /* If the AioContexts don't match, first try to move the subtree of - * child_bs into the AioContext of the new parent. If this doesn't work, - * try moving the parent into the AioContext of child_bs instead. */ - if (bdrv_get_aio_context(child_bs) != ctx) { - ret = bdrv_try_set_aio_context(child_bs, ctx, &local_err); - if (ret < 0 && child_class->can_set_aio_ctx) { - GSList *ignore = g_slist_prepend(NULL, child); - ctx = bdrv_get_aio_context(child_bs); - if (child_class->can_set_aio_ctx(child, ctx, &ignore, NULL)) { - error_free(local_err); - ret = 0; - g_slist_free(ignore); - ignore = g_slist_prepend(NULL, child); - child_class->set_aio_ctx(child, ctx, &ignore); - } - g_slist_free(ignore); - } - if (ret < 0) { - error_propagate(errp, local_err); - g_free(child); - bdrv_abort_perm_update(child_bs); - bdrv_unref(child_bs); - return NULL; - } - } - - /* This performs the matching bdrv_set_perm() for the above check. */ - bdrv_replace_child(child, child_bs); +out: + tran_finalize(tran, ret); + /* child is unset on failure by bdrv_attach_child_common_abort() */ + assert((ret < 0) == !child); + bdrv_unref(child_bs); return child; } @@ -2763,36 +2970,31 @@ BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs, BdrvChildRole child_role, Error **errp) { - BdrvChild *child; - uint64_t perm, shared_perm; + int ret; + BdrvChild *child = NULL; + Transaction *tran = tran_new(); - bdrv_get_cumulative_perm(parent_bs, &perm, &shared_perm); - - assert(parent_bs->drv); - bdrv_child_perm(parent_bs, child_bs, NULL, child_role, NULL, - perm, shared_perm, &perm, &shared_perm); - - child = bdrv_root_attach_child(child_bs, child_name, child_class, - child_role, bdrv_get_aio_context(parent_bs), - perm, shared_perm, parent_bs, errp); - if (child == NULL) { - return NULL; + ret = bdrv_attach_child_noperm(parent_bs, child_bs, child_name, child_class, + child_role, &child, tran, errp); + if (ret < 0) { + goto out; } - QLIST_INSERT_HEAD(&parent_bs->children, child, next); + ret = bdrv_refresh_perms(parent_bs, errp); + if (ret < 0) { + goto out; + } + +out: + tran_finalize(tran, ret); + /* child is unset on failure by bdrv_attach_child_common_abort() */ + assert((ret < 0) == !child); + + bdrv_unref(child_bs); + return child; } -static void bdrv_detach_child(BdrvChild *child) -{ - QLIST_SAFE_REMOVE(child, next); - - bdrv_replace_child(child, NULL); - - g_free(child->name); - g_free(child); -} - /* Callers must ensure that child->frozen is false. */ void bdrv_root_unref_child(BdrvChild *child) { @@ -2803,11 +3005,49 @@ void bdrv_root_unref_child(BdrvChild *child) bdrv_unref(child_bs); } +typedef struct BdrvSetInheritsFrom { + BlockDriverState *bs; + BlockDriverState *old_inherits_from; +} BdrvSetInheritsFrom; + +static void bdrv_set_inherits_from_abort(void *opaque) +{ + BdrvSetInheritsFrom *s = opaque; + + s->bs->inherits_from = s->old_inherits_from; +} + +static TransactionActionDrv bdrv_set_inherits_from_drv = { + .abort = bdrv_set_inherits_from_abort, + .clean = g_free, +}; + +/* @tran is allowed to be NULL. In this case no rollback is possible */ +static void bdrv_set_inherits_from(BlockDriverState *bs, + BlockDriverState *new_inherits_from, + Transaction *tran) +{ + if (tran) { + BdrvSetInheritsFrom *s = g_new(BdrvSetInheritsFrom, 1); + + *s = (BdrvSetInheritsFrom) { + .bs = bs, + .old_inherits_from = bs->inherits_from, + }; + + tran_add(tran, &bdrv_set_inherits_from_drv, s); + } + + bs->inherits_from = new_inherits_from; +} + /** * Clear all inherits_from pointers from children and grandchildren of * @root that point to @root, where necessary. + * @tran is allowed to be NULL. In this case no rollback is possible */ -static void bdrv_unset_inherits_from(BlockDriverState *root, BdrvChild *child) +static void bdrv_unset_inherits_from(BlockDriverState *root, BdrvChild *child, + Transaction *tran) { BdrvChild *c; @@ -2822,12 +3062,12 @@ static void bdrv_unset_inherits_from(BlockDriverState *root, BdrvChild *child) } } if (c == NULL) { - child->bs->inherits_from = NULL; + bdrv_set_inherits_from(child->bs, NULL, tran); } } QLIST_FOREACH(c, &child->bs->children, next) { - bdrv_unset_inherits_from(root, c); + bdrv_unset_inherits_from(root, c, tran); } } @@ -2838,7 +3078,7 @@ void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child) return; } - bdrv_unset_inherits_from(parent, child); + bdrv_unset_inherits_from(parent, child, NULL); bdrv_root_unref_child(child); } @@ -2880,50 +3120,118 @@ static BdrvChildRole bdrv_backing_role(BlockDriverState *bs) } /* - * Sets the bs->backing link of a BDS. A new reference is created; callers - * which don't need their own reference any more must call bdrv_unref(). + * Sets the bs->backing or bs->file link of a BDS. A new reference is created; + * callers which don't need their own reference any more must call bdrv_unref(). + * + * Function doesn't update permissions, caller is responsible for this. */ -int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd, - Error **errp) +static int bdrv_set_file_or_backing_noperm(BlockDriverState *parent_bs, + BlockDriverState *child_bs, + bool is_backing, + Transaction *tran, Error **errp) { int ret = 0; - bool update_inherits_from = bdrv_chain_contains(bs, backing_hd) && - bdrv_inherits_from_recursive(backing_hd, bs); + bool update_inherits_from = + bdrv_inherits_from_recursive(child_bs, parent_bs); + BdrvChild *child = is_backing ? parent_bs->backing : parent_bs->file; + BdrvChildRole role; - if (bdrv_is_backing_chain_frozen(bs, child_bs(bs->backing), errp)) { + if (!parent_bs->drv) { + /* + * Node without drv is an object without a class :/. TODO: finally fix + * qcow2 driver to never clear bs->drv and implement format corruption + * handling in other way. + */ + error_setg(errp, "Node corrupted"); + return -EINVAL; + } + + if (child && child->frozen) { + error_setg(errp, "Cannot change frozen '%s' link from '%s' to '%s'", + child->name, parent_bs->node_name, child->bs->node_name); return -EPERM; } - if (backing_hd) { - bdrv_ref(backing_hd); + if (is_backing && !parent_bs->drv->is_filter && + !parent_bs->drv->supports_backing) + { + error_setg(errp, "Driver '%s' of node '%s' does not support backing " + "files", parent_bs->drv->format_name, parent_bs->node_name); + return -EINVAL; } - if (bs->backing) { - /* Cannot be frozen, we checked that above */ - bdrv_unref_child(bs, bs->backing); - bs->backing = NULL; + if (parent_bs->drv->is_filter) { + role = BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY; + } else if (is_backing) { + role = BDRV_CHILD_COW; + } else { + /* + * We only can use same role as it is in existing child. We don't have + * infrastructure to determine role of file child in generic way + */ + if (!child) { + error_setg(errp, "Cannot set file child to format node without " + "file child"); + return -EINVAL; + } + role = child->role; } - if (!backing_hd) { + if (child) { + bdrv_unset_inherits_from(parent_bs, child, tran); + bdrv_remove_file_or_backing_child(parent_bs, child, tran); + } + + if (!child_bs) { goto out; } - bs->backing = bdrv_attach_child(bs, backing_hd, "backing", &child_of_bds, - bdrv_backing_role(bs), errp); - if (!bs->backing) { - ret = -EPERM; - goto out; + ret = bdrv_attach_child_noperm(parent_bs, child_bs, + is_backing ? "backing" : "file", + &child_of_bds, role, + is_backing ? &parent_bs->backing : + &parent_bs->file, + tran, errp); + if (ret < 0) { + return ret; } - /* If backing_hd was already part of bs's backing chain, and - * inherits_from pointed recursively to bs then let's update it to - * point directly to bs (else it will become NULL). */ + + /* + * If inherits_from pointed recursively to bs then let's update it to + * point directly to bs (else it will become NULL). + */ if (update_inherits_from) { - backing_hd->inherits_from = bs; + bdrv_set_inherits_from(child_bs, parent_bs, tran); } out: - bdrv_refresh_limits(bs, NULL); + bdrv_refresh_limits(parent_bs, tran, NULL); + + return 0; +} + +static int bdrv_set_backing_noperm(BlockDriverState *bs, + BlockDriverState *backing_hd, + Transaction *tran, Error **errp) +{ + return bdrv_set_file_or_backing_noperm(bs, backing_hd, true, tran, errp); +} + +int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd, + Error **errp) +{ + int ret; + Transaction *tran = tran_new(); + + ret = bdrv_set_backing_noperm(bs, backing_hd, tran, errp); + if (ret < 0) { + goto out; + } + + ret = bdrv_refresh_perms(bs, errp); +out: + tran_finalize(tran, ret); return ret; } @@ -3213,11 +3521,6 @@ static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs, goto out; } - /* bdrv_append() consumes a strong reference to bs_snapshot - * (i.e. it will call bdrv_unref() on it) even on error, so in - * order to be able to return one, we have to increase - * bs_snapshot's refcount here */ - bdrv_ref(bs_snapshot); ret = bdrv_append(bs_snapshot, bs, errp); if (ret < 0) { bs_snapshot = NULL; @@ -3729,10 +4032,6 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, bs_entry->state.explicit_options = explicit_options; bs_entry->state.flags = flags; - /* This needs to be overwritten in bdrv_reopen_prepare() */ - bs_entry->state.perm = UINT64_MAX; - bs_entry->state.shared_perm = 0; - /* * If keep_old_opts is false then it means that unspecified * options must be reset to their original value. We don't allow @@ -3796,6 +4095,19 @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, NULL, 0, keep_old_opts); } +void bdrv_reopen_queue_free(BlockReopenQueue *bs_queue) +{ + if (bs_queue) { + BlockReopenQueueEntry *bs_entry, *next; + QTAILQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) { + qobject_unref(bs_entry->state.explicit_options); + qobject_unref(bs_entry->state.options); + g_free(bs_entry); + } + g_free(bs_queue); + } +} + /* * Reopen multiple BlockDriverStates atomically & transactionally. * @@ -3812,43 +4124,68 @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, * * All affected nodes must be drained between bdrv_reopen_queue() and * bdrv_reopen_multiple(). + * + * To be called from the main thread, with all other AioContexts unlocked. */ int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp) { int ret = -1; BlockReopenQueueEntry *bs_entry, *next; + AioContext *ctx; + Transaction *tran = tran_new(); + g_autoptr(GHashTable) found = NULL; + g_autoptr(GSList) refresh_list = NULL; + assert(qemu_get_current_aio_context() == qemu_get_aio_context()); assert(bs_queue != NULL); + QTAILQ_FOREACH(bs_entry, bs_queue, entry) { + ctx = bdrv_get_aio_context(bs_entry->state.bs); + aio_context_acquire(ctx); + ret = bdrv_flush(bs_entry->state.bs); + aio_context_release(ctx); + if (ret < 0) { + error_setg_errno(errp, -ret, "Error flushing drive"); + goto abort; + } + } + QTAILQ_FOREACH(bs_entry, bs_queue, entry) { assert(bs_entry->state.bs->quiesce_counter > 0); - if (bdrv_reopen_prepare(&bs_entry->state, bs_queue, errp)) { - goto cleanup; + ctx = bdrv_get_aio_context(bs_entry->state.bs); + aio_context_acquire(ctx); + ret = bdrv_reopen_prepare(&bs_entry->state, bs_queue, tran, errp); + aio_context_release(ctx); + if (ret < 0) { + goto abort; } bs_entry->prepared = true; } + found = g_hash_table_new(NULL, NULL); QTAILQ_FOREACH(bs_entry, bs_queue, entry) { BDRVReopenState *state = &bs_entry->state; - ret = bdrv_check_perm(state->bs, bs_queue, state->perm, - state->shared_perm, NULL, errp); - if (ret < 0) { - goto cleanup_perm; + + refresh_list = bdrv_topological_dfs(refresh_list, found, state->bs); + if (state->old_backing_bs) { + refresh_list = bdrv_topological_dfs(refresh_list, found, + state->old_backing_bs); } - /* Check if new_backing_bs would accept the new permissions */ - if (state->replace_backing_bs && state->new_backing_bs) { - uint64_t nperm, nshared; - bdrv_child_perm(state->bs, state->new_backing_bs, - NULL, bdrv_backing_role(state->bs), - bs_queue, state->perm, state->shared_perm, - &nperm, &nshared); - ret = bdrv_check_update_perm(state->new_backing_bs, NULL, - nperm, nshared, NULL, errp); - if (ret < 0) { - goto cleanup_perm; - } + if (state->old_file_bs) { + refresh_list = bdrv_topological_dfs(refresh_list, found, + state->old_file_bs); } - bs_entry->perms_checked = true; + } + + /* + * Note that file-posix driver rely on permission update done during reopen + * (even if no permission changed), because it wants "new" permissions for + * reconfiguring the fd and that's why it does it in raw_check_perm(), not + * in raw_reopen_prepare() which is called with "old" permissions. + */ + ret = bdrv_list_refresh_perms(refresh_list, bs_queue, tran, errp); + if (ret < 0) { + goto abort; } /* @@ -3861,57 +4198,64 @@ int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp) * to first element. */ QTAILQ_FOREACH_REVERSE(bs_entry, bs_queue, entry) { + ctx = bdrv_get_aio_context(bs_entry->state.bs); + aio_context_acquire(ctx); bdrv_reopen_commit(&bs_entry->state); + aio_context_release(ctx); + } + + tran_commit(tran); + + QTAILQ_FOREACH_REVERSE(bs_entry, bs_queue, entry) { + BlockDriverState *bs = bs_entry->state.bs; + + if (bs->drv->bdrv_reopen_commit_post) { + ctx = bdrv_get_aio_context(bs); + aio_context_acquire(ctx); + bs->drv->bdrv_reopen_commit_post(&bs_entry->state); + aio_context_release(ctx); + } } ret = 0; -cleanup_perm: + goto cleanup; + +abort: + tran_abort(tran); QTAILQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) { - BDRVReopenState *state = &bs_entry->state; - - if (!bs_entry->perms_checked) { - continue; - } - - if (ret == 0) { - uint64_t perm, shared; - - bdrv_get_cumulative_perm(state->bs, &perm, &shared); - assert(perm == state->perm); - assert(shared == state->shared_perm); - - bdrv_set_perm(state->bs); - } else { - bdrv_abort_perm_update(state->bs); - if (state->replace_backing_bs && state->new_backing_bs) { - bdrv_abort_perm_update(state->new_backing_bs); - } + if (bs_entry->prepared) { + ctx = bdrv_get_aio_context(bs_entry->state.bs); + aio_context_acquire(ctx); + bdrv_reopen_abort(&bs_entry->state); + aio_context_release(ctx); } } - if (ret == 0) { - QTAILQ_FOREACH_REVERSE(bs_entry, bs_queue, entry) { - BlockDriverState *bs = bs_entry->state.bs; - - if (bs->drv->bdrv_reopen_commit_post) - bs->drv->bdrv_reopen_commit_post(&bs_entry->state); - } - } cleanup: - QTAILQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) { - if (ret) { - if (bs_entry->prepared) { - bdrv_reopen_abort(&bs_entry->state); - } - qobject_unref(bs_entry->state.explicit_options); - qobject_unref(bs_entry->state.options); - } - if (bs_entry->state.new_backing_bs) { - bdrv_unref(bs_entry->state.new_backing_bs); - } - g_free(bs_entry); + bdrv_reopen_queue_free(bs_queue); + + return ret; +} + +int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts, + Error **errp) +{ + AioContext *ctx = bdrv_get_aio_context(bs); + BlockReopenQueue *queue; + int ret; + + bdrv_subtree_drained_begin(bs); + if (ctx != qemu_get_aio_context()) { + aio_context_release(ctx); } - g_free(bs_queue); + + queue = bdrv_reopen_queue(NULL, bs, opts, keep_old_opts); + ret = bdrv_reopen_multiple(queue, errp); + + if (ctx != qemu_get_aio_context()) { + aio_context_acquire(ctx); + } + bdrv_subtree_drained_end(bs); return ret; } @@ -3919,88 +4263,11 @@ cleanup: int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only, Error **errp) { - int ret; - BlockReopenQueue *queue; QDict *opts = qdict_new(); qdict_put_bool(opts, BDRV_OPT_READ_ONLY, read_only); - bdrv_subtree_drained_begin(bs); - queue = bdrv_reopen_queue(NULL, bs, opts, true); - ret = bdrv_reopen_multiple(queue, errp); - bdrv_subtree_drained_end(bs); - - return ret; -} - -static BlockReopenQueueEntry *find_parent_in_reopen_queue(BlockReopenQueue *q, - BdrvChild *c) -{ - BlockReopenQueueEntry *entry; - - QTAILQ_FOREACH(entry, q, entry) { - BlockDriverState *bs = entry->state.bs; - BdrvChild *child; - - QLIST_FOREACH(child, &bs->children, next) { - if (child == c) { - return entry; - } - } - } - - return NULL; -} - -static void bdrv_reopen_perm(BlockReopenQueue *q, BlockDriverState *bs, - uint64_t *perm, uint64_t *shared) -{ - BdrvChild *c; - BlockReopenQueueEntry *parent; - uint64_t cumulative_perms = 0; - uint64_t cumulative_shared_perms = BLK_PERM_ALL; - - QLIST_FOREACH(c, &bs->parents, next_parent) { - parent = find_parent_in_reopen_queue(q, c); - if (!parent) { - cumulative_perms |= c->perm; - cumulative_shared_perms &= c->shared_perm; - } else { - uint64_t nperm, nshared; - - bdrv_child_perm(parent->state.bs, bs, c, c->role, q, - parent->state.perm, parent->state.shared_perm, - &nperm, &nshared); - - cumulative_perms |= nperm; - cumulative_shared_perms &= nshared; - } - } - *perm = cumulative_perms; - *shared = cumulative_shared_perms; -} - -static bool bdrv_reopen_can_attach(BlockDriverState *parent, - BdrvChild *child, - BlockDriverState *new_child, - Error **errp) -{ - AioContext *parent_ctx = bdrv_get_aio_context(parent); - AioContext *child_ctx = bdrv_get_aio_context(new_child); - GSList *ignore; - bool ret; - - ignore = g_slist_prepend(NULL, child); - ret = bdrv_can_set_aio_context(new_child, parent_ctx, &ignore, NULL); - g_slist_free(ignore); - if (ret) { - return ret; - } - - ignore = g_slist_prepend(NULL, child); - ret = bdrv_can_set_aio_context(parent, child_ctx, &ignore, errp); - g_slist_free(ignore); - return ret; + return bdrv_reopen(bs, opts, true, errp); } /* @@ -4020,110 +4287,81 @@ static bool bdrv_reopen_can_attach(BlockDriverState *parent, * * Return 0 on success, otherwise return < 0 and set @errp. */ -static int bdrv_reopen_parse_backing(BDRVReopenState *reopen_state, - Error **errp) +static int bdrv_reopen_parse_file_or_backing(BDRVReopenState *reopen_state, + bool is_backing, Transaction *tran, + Error **errp) { BlockDriverState *bs = reopen_state->bs; - BlockDriverState *overlay_bs, *below_bs, *new_backing_bs; + BlockDriverState *new_child_bs; + BlockDriverState *old_child_bs = is_backing ? child_bs(bs->backing) : + child_bs(bs->file); + const char *child_name = is_backing ? "backing" : "file"; QObject *value; const char *str; - value = qdict_get(reopen_state->options, "backing"); + value = qdict_get(reopen_state->options, child_name); if (value == NULL) { return 0; } switch (qobject_type(value)) { case QTYPE_QNULL: - new_backing_bs = NULL; + assert(is_backing); /* The 'file' option does not allow a null value */ + new_child_bs = NULL; break; case QTYPE_QSTRING: str = qstring_get_str(qobject_to(QString, value)); - new_backing_bs = bdrv_lookup_bs(NULL, str, errp); - if (new_backing_bs == NULL) { + new_child_bs = bdrv_lookup_bs(NULL, str, errp); + if (new_child_bs == NULL) { return -EINVAL; - } else if (bdrv_recurse_has_child(new_backing_bs, bs)) { - error_setg(errp, "Making '%s' a backing file of '%s' " - "would create a cycle", str, bs->node_name); + } else if (bdrv_recurse_has_child(new_child_bs, bs)) { + error_setg(errp, "Making '%s' a %s child of '%s' would create a " + "cycle", str, child_name, bs->node_name); return -EINVAL; } break; default: - /* 'backing' does not allow any other data type */ + /* + * The options QDict has been flattened, so 'backing' and 'file' + * do not allow any other data type here. + */ g_assert_not_reached(); } - /* - * Check AioContext compatibility so that the bdrv_set_backing_hd() call in - * bdrv_reopen_commit() won't fail. - */ - if (new_backing_bs) { - if (!bdrv_reopen_can_attach(bs, bs->backing, new_backing_bs, errp)) { - return -EINVAL; + if (old_child_bs == new_child_bs) { + return 0; + } + + if (old_child_bs) { + if (bdrv_skip_implicit_filters(old_child_bs) == new_child_bs) { + return 0; + } + + if (old_child_bs->implicit) { + error_setg(errp, "Cannot replace implicit %s child of %s", + child_name, bs->node_name); + return -EPERM; } } - /* - * Ensure that @bs can really handle backing files, because we are - * about to give it one (or swap the existing one) - */ - if (bs->drv->is_filter) { - /* Filters always have a file or a backing child */ - if (!bs->backing) { - error_setg(errp, "'%s' is a %s filter node that does not support a " - "backing child", bs->node_name, bs->drv->format_name); - return -EINVAL; - } - } else if (!bs->drv->supports_backing) { - error_setg(errp, "Driver '%s' of node '%s' does not support backing " - "files", bs->drv->format_name, bs->node_name); + if (bs->drv->is_filter && !old_child_bs) { + /* + * Filters always have a file or a backing child, so we are trying to + * change wrong child + */ + error_setg(errp, "'%s' is a %s filter node that does not support a " + "%s child", bs->node_name, bs->drv->format_name, child_name); return -EINVAL; } - /* - * Find the "actual" backing file by skipping all links that point - * to an implicit node, if any (e.g. a commit filter node). - * We cannot use any of the bdrv_skip_*() functions here because - * those return the first explicit node, while we are looking for - * its overlay here. - */ - overlay_bs = bs; - for (below_bs = bdrv_filter_or_cow_bs(overlay_bs); - below_bs && below_bs->implicit; - below_bs = bdrv_filter_or_cow_bs(overlay_bs)) - { - overlay_bs = below_bs; + if (is_backing) { + reopen_state->old_backing_bs = old_child_bs; + } else { + reopen_state->old_file_bs = old_child_bs; } - /* If we want to replace the backing file we need some extra checks */ - if (new_backing_bs != bdrv_filter_or_cow_bs(overlay_bs)) { - /* Check for implicit nodes between bs and its backing file */ - if (bs != overlay_bs) { - error_setg(errp, "Cannot change backing link if '%s' has " - "an implicit backing file", bs->node_name); - return -EPERM; - } - /* - * Check if the backing link that we want to replace is frozen. - * Note that - * bdrv_filter_or_cow_child(overlay_bs) == overlay_bs->backing, - * because we know that overlay_bs == bs, and that @bs - * either is a filter that uses ->backing or a COW format BDS - * with bs->drv->supports_backing == true. - */ - if (bdrv_is_backing_chain_frozen(overlay_bs, - child_bs(overlay_bs->backing), errp)) - { - return -EPERM; - } - reopen_state->replace_backing_bs = true; - if (new_backing_bs) { - bdrv_ref(new_backing_bs); - reopen_state->new_backing_bs = new_backing_bs; - } - } - - return 0; + return bdrv_set_file_or_backing_noperm(bs, new_child_bs, is_backing, + tran, errp); } /* @@ -4143,8 +4381,9 @@ static int bdrv_reopen_parse_backing(BDRVReopenState *reopen_state, * commit() for any other BDS that have been left in a prepare() state * */ -int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, - Error **errp) +static int bdrv_reopen_prepare(BDRVReopenState *reopen_state, + BlockReopenQueue *queue, + Transaction *change_child_tran, Error **errp) { int ret = -1; int old_flags; @@ -4211,16 +4450,6 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, goto error; } - /* Calculate required permissions after reopening */ - bdrv_reopen_perm(queue, reopen_state->bs, - &reopen_state->perm, &reopen_state->shared_perm); - - ret = bdrv_flush(reopen_state->bs); - if (ret) { - error_setg_errno(errp, -ret, "Error flushing drive"); - goto error; - } - if (drv->bdrv_reopen_prepare) { /* * If a driver-specific option is missing, it means that we @@ -4274,12 +4503,21 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, * either a reference to an existing node (using its node name) * or NULL to simply detach the current backing file. */ - ret = bdrv_reopen_parse_backing(reopen_state, errp); + ret = bdrv_reopen_parse_file_or_backing(reopen_state, true, + change_child_tran, errp); if (ret < 0) { goto error; } qdict_del(reopen_state->options, "backing"); + /* Allow changing the 'file' option. In this case NULL is not allowed */ + ret = bdrv_reopen_parse_file_or_backing(reopen_state, false, + change_child_tran, errp); + if (ret < 0) { + goto error; + } + qdict_del(reopen_state->options, "file"); + /* Options that are not handled are only okay if they are unchanged * compared to the old state. It is expected that some options are only * used for the initial open, but not reopen (e.g. filename) */ @@ -4359,7 +4597,7 @@ error: * makes them final by swapping the staging BlockDriverState contents into * the active BlockDriverState contents. */ -void bdrv_reopen_commit(BDRVReopenState *reopen_state) +static void bdrv_reopen_commit(BDRVReopenState *reopen_state) { BlockDriver *drv; BlockDriverState *bs; @@ -4378,48 +4616,32 @@ void bdrv_reopen_commit(BDRVReopenState *reopen_state) /* set BDS specific flags now */ qobject_unref(bs->explicit_options); qobject_unref(bs->options); + qobject_ref(reopen_state->explicit_options); + qobject_ref(reopen_state->options); bs->explicit_options = reopen_state->explicit_options; bs->options = reopen_state->options; bs->open_flags = reopen_state->flags; - bs->read_only = !(reopen_state->flags & BDRV_O_RDWR); bs->detect_zeroes = reopen_state->detect_zeroes; - if (reopen_state->replace_backing_bs) { - qdict_del(bs->explicit_options, "backing"); - qdict_del(bs->options, "backing"); - } - /* Remove child references from bs->options and bs->explicit_options. * Child options were already removed in bdrv_reopen_queue_child() */ QLIST_FOREACH(child, &bs->children, next) { qdict_del(bs->explicit_options, child->name); qdict_del(bs->options, child->name); } + /* backing is probably removed, so it's not handled by previous loop */ + qdict_del(bs->explicit_options, "backing"); + qdict_del(bs->options, "backing"); - /* - * Change the backing file if a new one was specified. We do this - * after updating bs->options, so bdrv_refresh_filename() (called - * from bdrv_set_backing_hd()) has the new values. - */ - if (reopen_state->replace_backing_bs) { - BlockDriverState *old_backing_bs = child_bs(bs->backing); - assert(!old_backing_bs || !old_backing_bs->implicit); - /* Abort the permission update on the backing bs we're detaching */ - if (old_backing_bs) { - bdrv_abort_perm_update(old_backing_bs); - } - bdrv_set_backing_hd(bs, reopen_state->new_backing_bs, &error_abort); - } - - bdrv_refresh_limits(bs, NULL); + bdrv_refresh_limits(bs, NULL, NULL); } /* * Abort the reopen, and delete and free the staged changes in * reopen_state */ -void bdrv_reopen_abort(BDRVReopenState *reopen_state) +static void bdrv_reopen_abort(BDRVReopenState *reopen_state) { BlockDriver *drv; @@ -4585,22 +4807,150 @@ static bool should_update_child(BdrvChild *c, BlockDriverState *to) return ret; } +typedef struct BdrvRemoveFilterOrCowChild { + BdrvChild *child; + bool is_backing; +} BdrvRemoveFilterOrCowChild; + +static void bdrv_remove_filter_or_cow_child_abort(void *opaque) +{ + BdrvRemoveFilterOrCowChild *s = opaque; + BlockDriverState *parent_bs = s->child->opaque; + + QLIST_INSERT_HEAD(&parent_bs->children, s->child, next); + if (s->is_backing) { + parent_bs->backing = s->child; + } else { + parent_bs->file = s->child; + } + + /* + * We don't have to restore child->bs here to undo bdrv_replace_child_tran() + * because that function is transactionable and it registered own completion + * entries in @tran, so .abort() for bdrv_replace_child_safe() will be + * called automatically. + */ +} + +static void bdrv_remove_filter_or_cow_child_commit(void *opaque) +{ + BdrvRemoveFilterOrCowChild *s = opaque; + + bdrv_child_free(s->child); +} + +static TransactionActionDrv bdrv_remove_filter_or_cow_child_drv = { + .abort = bdrv_remove_filter_or_cow_child_abort, + .commit = bdrv_remove_filter_or_cow_child_commit, + .clean = g_free, +}; + +/* + * A function to remove backing or file child of @bs. + * Function doesn't update permissions, caller is responsible for this. + */ +static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, + BdrvChild *child, + Transaction *tran) +{ + BdrvRemoveFilterOrCowChild *s; + + assert(child == bs->backing || child == bs->file); + + if (!child) { + return; + } + + if (child->bs) { + bdrv_replace_child_tran(child, NULL, tran); + } + + s = g_new(BdrvRemoveFilterOrCowChild, 1); + *s = (BdrvRemoveFilterOrCowChild) { + .child = child, + .is_backing = (child == bs->backing), + }; + tran_add(tran, &bdrv_remove_filter_or_cow_child_drv, s); + + QLIST_SAFE_REMOVE(child, next); + if (s->is_backing) { + bs->backing = NULL; + } else { + bs->file = NULL; + } +} + +/* + * A function to remove backing-chain child of @bs if exists: cow child for + * format nodes (always .backing) and filter child for filters (may be .file or + * .backing) + */ +static void bdrv_remove_filter_or_cow_child(BlockDriverState *bs, + Transaction *tran) +{ + bdrv_remove_file_or_backing_child(bs, bdrv_filter_or_cow_child(bs), tran); +} + +static int bdrv_replace_node_noperm(BlockDriverState *from, + BlockDriverState *to, + bool auto_skip, Transaction *tran, + Error **errp) +{ + BdrvChild *c, *next; + + QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) { + assert(c->bs == from); + if (!should_update_child(c, to)) { + if (auto_skip) { + continue; + } + error_setg(errp, "Should not change '%s' link to '%s'", + c->name, from->node_name); + return -EINVAL; + } + if (c->frozen) { + error_setg(errp, "Cannot change '%s' link to '%s'", + c->name, from->node_name); + return -EPERM; + } + bdrv_replace_child_tran(c, to, tran); + } + + return 0; +} + /* * With auto_skip=true bdrv_replace_node_common skips updating from parents * if it creates a parent-child relation loop or if parent is block-job. * * With auto_skip=false the error is returned if from has a parent which should * not be updated. + * + * With @detach_subchain=true @to must be in a backing chain of @from. In this + * case backing link of the cow-parent of @to is removed. */ static int bdrv_replace_node_common(BlockDriverState *from, BlockDriverState *to, - bool auto_skip, Error **errp) + bool auto_skip, bool detach_subchain, + Error **errp) { - BdrvChild *c, *next; - GSList *list = NULL, *p; - uint64_t perm = 0, shared = BLK_PERM_ALL; + Transaction *tran = tran_new(); + g_autoptr(GHashTable) found = NULL; + g_autoptr(GSList) refresh_list = NULL; + BlockDriverState *to_cow_parent = NULL; int ret; + if (detach_subchain) { + assert(bdrv_chain_contains(from, to)); + assert(from != to); + for (to_cow_parent = from; + bdrv_filter_or_cow_bs(to_cow_parent) != to; + to_cow_parent = bdrv_filter_or_cow_bs(to_cow_parent)) + { + ; + } + } + /* Make sure that @from doesn't go away until we have successfully attached * all of its parents to @to. */ bdrv_ref(from); @@ -4609,54 +4959,36 @@ static int bdrv_replace_node_common(BlockDriverState *from, assert(bdrv_get_aio_context(from) == bdrv_get_aio_context(to)); bdrv_drained_begin(from); - /* Put all parents into @list and calculate their cumulative permissions */ - QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) { - assert(c->bs == from); - if (!should_update_child(c, to)) { - if (auto_skip) { - continue; - } - ret = -EINVAL; - error_setg(errp, "Should not change '%s' link to '%s'", - c->name, from->node_name); - goto out; - } - if (c->frozen) { - ret = -EPERM; - error_setg(errp, "Cannot change '%s' link to '%s'", - c->name, from->node_name); - goto out; - } - list = g_slist_prepend(list, c); - perm |= c->perm; - shared &= c->shared_perm; - } - - /* Check whether the required permissions can be granted on @to, ignoring - * all BdrvChild in @list so that they can't block themselves. */ - ret = bdrv_check_update_perm(to, NULL, perm, shared, list, errp); + /* + * Do the replacement without permission update. + * Replacement may influence the permissions, we should calculate new + * permissions based on new graph. If we fail, we'll roll-back the + * replacement. + */ + ret = bdrv_replace_node_noperm(from, to, auto_skip, tran, errp); if (ret < 0) { - bdrv_abort_perm_update(to); goto out; } - /* Now actually perform the change. We performed the permission check for - * all elements of @list at once, so set the permissions all at once at the - * very end. */ - for (p = list; p != NULL; p = p->next) { - c = p->data; - - bdrv_ref(to); - bdrv_replace_child_noperm(c, to); - bdrv_unref(from); + if (detach_subchain) { + bdrv_remove_filter_or_cow_child(to_cow_parent, tran); } - bdrv_set_perm(to); + found = g_hash_table_new(NULL, NULL); + + refresh_list = bdrv_topological_dfs(refresh_list, found, to); + refresh_list = bdrv_topological_dfs(refresh_list, found, from); + + ret = bdrv_list_refresh_perms(refresh_list, NULL, tran, errp); + if (ret < 0) { + goto out; + } ret = 0; out: - g_slist_free(list); + tran_finalize(tran, ret); + bdrv_drained_end(from); bdrv_unref(from); @@ -4666,7 +4998,13 @@ out: int bdrv_replace_node(BlockDriverState *from, BlockDriverState *to, Error **errp) { - return bdrv_replace_node_common(from, to, true, errp); + return bdrv_replace_node_common(from, to, true, false, errp); +} + +int bdrv_drop_filter(BlockDriverState *bs, Error **errp) +{ + return bdrv_replace_node_common(bs, bdrv_filter_or_cow_bs(bs), true, true, + errp); } /* @@ -4676,37 +5014,36 @@ int bdrv_replace_node(BlockDriverState *from, BlockDriverState *to, * This will modify the BlockDriverState fields, and swap contents * between bs_new and bs_top. Both bs_new and bs_top are modified. * - * bs_new must not be attached to a BlockBackend. + * bs_new must not be attached to a BlockBackend and must not have backing + * child. * * This function does not create any image files. - * - * bdrv_append() takes ownership of a bs_new reference and unrefs it because - * that's what the callers commonly need. bs_new will be referenced by the old - * parents of bs_top after bdrv_append() returns. If the caller needs to keep a - * reference of its own, it must call bdrv_ref(). */ int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top, Error **errp) { - int ret = bdrv_set_backing_hd(bs_new, bs_top, errp); + int ret; + Transaction *tran = tran_new(); + + assert(!bs_new->backing); + + ret = bdrv_attach_child_noperm(bs_new, bs_top, "backing", + &child_of_bds, bdrv_backing_role(bs_new), + &bs_new->backing, tran, errp); if (ret < 0) { goto out; } - ret = bdrv_replace_node(bs_top, bs_new, errp); + ret = bdrv_replace_node_noperm(bs_top, bs_new, true, tran, errp); if (ret < 0) { - bdrv_set_backing_hd(bs_new, NULL, &error_abort); goto out; } - ret = 0; - + ret = bdrv_refresh_perms(bs_new, errp); out: - /* - * bs_new is now referenced by its new parents, we don't need the - * additional reference any more. - */ - bdrv_unref(bs_new); + tran_finalize(tran, ret); + + bdrv_refresh_limits(bs_top, NULL, NULL); return ret; } @@ -4782,7 +5119,7 @@ int coroutine_fn bdrv_co_check(BlockDriverState *bs, * -ENOTSUP - format driver doesn't support changing the backing file */ int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file, - const char *backing_fmt, bool warn) + const char *backing_fmt, bool require) { BlockDriver *drv = bs->drv; int ret; @@ -4796,10 +5133,8 @@ int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file, return -EINVAL; } - if (warn && backing_file && !backing_fmt) { - warn_report("Deprecated use of backing file without explicit " - "backing format, use of this image requires " - "potentially unsafe format probing"); + if (require && backing_file && !backing_fmt) { + return -EINVAL; } if (drv->bdrv_change_backing_file != NULL) { @@ -5002,7 +5337,17 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base, updated_children = g_slist_prepend(updated_children, c); } - bdrv_replace_node_common(top, base, false, &local_err); + /* + * It seems correct to pass detach_subchain=true here, but it triggers + * one more yet not fixed bug, when due to nested aio_poll loop we switch to + * another drained section, which modify the graph (for example, removing + * the child, which we keep in updated_children list). So, it's a TODO. + * + * Note, bug triggered if pass detach_subchain=true here and run + * test-bdrv-drain. test_drop_intermediate_poll() test-case will crash. + * That's a FIXME. + */ + bdrv_replace_node_common(top, base, false, false, &local_err); if (local_err) { error_report_err(local_err); goto exit; @@ -5817,6 +6162,9 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs, void bdrv_init(void) { +#ifdef CONFIG_BDRV_WHITELIST_TOOLS + use_bdrv_whitelist = 1; +#endif module_call_init(MODULE_INIT_BLOCK); } @@ -6277,9 +6625,13 @@ void bdrv_img_create(const char *filename, const char *fmt, } assert(full_backing); - /* backing files always opened read-only */ + /* + * No need to do I/O here, which allows us to open encrypted + * backing images without needing the secret + */ back_flags = flags; back_flags &= ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING); + back_flags |= BDRV_O_NO_IO; backing_options = qdict_new(); if (backing_fmt) { @@ -6295,24 +6647,11 @@ void bdrv_img_create(const char *filename, const char *fmt, goto out; } else { if (!backing_fmt) { - warn_report("Deprecated use of backing file without explicit " - "backing format (detected format of %s)", - bs->drv->format_name); - if (bs->drv != &bdrv_raw) { - /* - * A probe of raw deserves the most attention: - * leaving the backing format out of the image - * will ensure bs->probed is set (ensuring we - * don't accidentally commit into the backing - * file), and allow more spots to warn the users - * to fix their toolchain when opening this image - * later. For other images, we can safely record - * the format that we probed. - */ - backing_fmt = bs->drv->format_name; - qemu_opt_set(opts, BLOCK_OPT_BACKING_FMT, backing_fmt, - NULL); - } + error_setg(&local_err, + "Backing file specified without backing format"); + error_append_hint(&local_err, "Detected format of %s.", + bs->drv->format_name); + goto out; } if (size == -1) { /* Opened BS, have no size */ @@ -6329,9 +6668,9 @@ void bdrv_img_create(const char *filename, const char *fmt, } /* (backing_file && !(flags & BDRV_O_NO_BACKING)) */ } else if (backing_file && !backing_fmt) { - warn_report("Deprecated use of unopened backing file without " - "explicit backing format, use of this image requires " - "potentially unsafe format probing"); + error_setg(&local_err, + "Backing file specified without backing format"); + goto out; } if (size == -1) { diff --git a/block/backup-top.c b/block/backup-top.c index 589e8b651d..425e3778be 100644 --- a/block/backup-top.c +++ b/block/backup-top.c @@ -37,7 +37,6 @@ typedef struct BDRVBackupTopState { BlockCopyState *bcs; BdrvChild *target; - bool active; int64_t cluster_size; } BDRVBackupTopState; @@ -45,12 +44,6 @@ static coroutine_fn int backup_top_co_preadv( BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags) { - BDRVBackupTopState *s = bs->opaque; - - if (!s->active) { - return -EIO; - } - return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags); } @@ -60,10 +53,6 @@ static coroutine_fn int backup_top_cbw(BlockDriverState *bs, uint64_t offset, BDRVBackupTopState *s = bs->opaque; uint64_t off, end; - if (!s->active) { - return -EIO; - } - if (flags & BDRV_REQ_WRITE_UNCHANGED) { return 0; } @@ -137,21 +126,6 @@ static void backup_top_child_perm(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared) { - BDRVBackupTopState *s = bs->opaque; - - if (!s->active) { - /* - * The filter node may be in process of bdrv_append(), which firstly do - * bdrv_set_backing_hd() and then bdrv_replace_node(). This means that - * we can't unshare BLK_PERM_WRITE during bdrv_append() operation. So, - * let's require nothing during bdrv_append() and refresh permissions - * after it (see bdrv_backup_top_append()). - */ - *nperm = 0; - *nshared = BLK_PERM_ALL; - return; - } - if (!(role & BDRV_CHILD_FILTERED)) { /* * Target child @@ -234,7 +208,6 @@ BlockDriverState *bdrv_backup_top_append(BlockDriverState *source, bdrv_drained_begin(source); - bdrv_ref(top); ret = bdrv_append(top, source, errp); if (ret < 0) { error_prepend(errp, "Cannot append backup-top filter: "); @@ -242,17 +215,6 @@ BlockDriverState *bdrv_backup_top_append(BlockDriverState *source, } appended = true; - /* - * bdrv_append() finished successfully, now we can require permissions - * we want. - */ - state->active = true; - ret = bdrv_child_refresh_perms(top, top->backing, errp); - if (ret < 0) { - error_prepend(errp, "Cannot set permissions for backup-top filter: "); - goto fail; - } - state->cluster_size = cluster_size; state->bcs = block_copy_state_new(top->backing, state->target, cluster_size, perf->use_copy_range, @@ -269,7 +231,6 @@ BlockDriverState *bdrv_backup_top_append(BlockDriverState *source, fail: if (appended) { - state->active = false; bdrv_backup_top_drop(top); } else { bdrv_unref(top); @@ -284,16 +245,9 @@ void bdrv_backup_top_drop(BlockDriverState *bs) { BDRVBackupTopState *s = bs->opaque; - bdrv_drained_begin(bs); + bdrv_drop_filter(bs, &error_abort); block_copy_state_free(s->bcs); - s->active = false; - bdrv_child_refresh_perms(bs, bs->backing, &error_abort); - bdrv_replace_node(bs, bs->backing->bs, &error_abort); - bdrv_set_backing_hd(bs, NULL, &error_abort); - - bdrv_drained_end(bs); - bdrv_unref(bs); } diff --git a/block/backup.c b/block/backup.c index 6cf2f974aa..bd3614ce70 100644 --- a/block/backup.c +++ b/block/backup.c @@ -331,7 +331,7 @@ static void coroutine_fn backup_set_speed(BlockJob *job, int64_t speed) } } -static void backup_cancel(Job *job) +static void backup_cancel(Job *job, bool force) { BackupBlockJob *s = container_of(job, BackupBlockJob, common.job); diff --git a/block/blkdebug.c b/block/blkdebug.c index 2c0b9b0ee8..8b67554bec 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -38,25 +38,27 @@ #include "qapi/qobject-input-visitor.h" #include "sysemu/qtest.h" +/* All APIs are thread-safe */ + typedef struct BDRVBlkdebugState { - int state; - int new_state; + /* IN: initialized in blkdebug_open() and never changed */ uint64_t align; uint64_t max_transfer; uint64_t opt_write_zero; uint64_t max_write_zero; uint64_t opt_discard; uint64_t max_discard; - + char *config_file; /* For blkdebug_refresh_filename() */ + /* initialized in blkdebug_parse_perms() */ uint64_t take_child_perms; uint64_t unshare_child_perms; - /* For blkdebug_refresh_filename() */ - char *config_file; - + /* State. Protected by lock */ + int state; QLIST_HEAD(, BlkdebugRule) rules[BLKDBG__MAX]; QSIMPLEQ_HEAD(, BlkdebugRule) active_rules; QLIST_HEAD(, BlkdebugSuspendedReq) suspended_reqs; + QemuMutex lock; } BDRVBlkdebugState; typedef struct BlkdebugAIOCB { @@ -65,8 +67,11 @@ typedef struct BlkdebugAIOCB { } BlkdebugAIOCB; typedef struct BlkdebugSuspendedReq { + /* IN: initialized in suspend_request() */ Coroutine *co; char *tag; + + /* List entry protected BDRVBlkdebugState's lock */ QLIST_ENTRY(BlkdebugSuspendedReq) next; } BlkdebugSuspendedReq; @@ -74,9 +79,11 @@ enum { ACTION_INJECT_ERROR, ACTION_SET_STATE, ACTION_SUSPEND, + ACTION__MAX, }; typedef struct BlkdebugRule { + /* IN: initialized in add_rule() or blkdebug_debug_breakpoint() */ BlkdebugEvent event; int action; int state; @@ -95,6 +102,8 @@ typedef struct BlkdebugRule { char *tag; } suspend; } options; + + /* List entries protected BDRVBlkdebugState's lock */ QLIST_ENTRY(BlkdebugRule) next; QSIMPLEQ_ENTRY(BlkdebugRule) active_next; } BlkdebugRule; @@ -244,11 +253,14 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp) }; /* Add the rule */ + qemu_mutex_lock(&s->lock); QLIST_INSERT_HEAD(&s->rules[event], rule, next); + qemu_mutex_unlock(&s->lock); return 0; } +/* Called with lock held or from .bdrv_close */ static void remove_rule(BlkdebugRule *rule) { switch (rule->action) { @@ -467,6 +479,7 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags, int ret; uint64_t align; + qemu_mutex_init(&s->lock); opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort); if (!qemu_opts_absorb_qdict(opts, options, errp)) { ret = -EINVAL; @@ -567,6 +580,7 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags, ret = 0; out: if (ret < 0) { + qemu_mutex_destroy(&s->lock); g_free(s->config_file); } qemu_opts_del(opts); @@ -581,6 +595,7 @@ static int rule_check(BlockDriverState *bs, uint64_t offset, uint64_t bytes, int error; bool immediately; + qemu_mutex_lock(&s->lock); QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) { uint64_t inject_offset = rule->options.inject.offset; @@ -594,6 +609,7 @@ static int rule_check(BlockDriverState *bs, uint64_t offset, uint64_t bytes, } if (!rule || !rule->options.inject.error) { + qemu_mutex_unlock(&s->lock); return 0; } @@ -605,6 +621,7 @@ static int rule_check(BlockDriverState *bs, uint64_t offset, uint64_t bytes, remove_rule(rule); } + qemu_mutex_unlock(&s->lock); if (!immediately) { aio_co_schedule(qemu_get_current_aio_context(), qemu_coroutine_self()); qemu_coroutine_yield(); @@ -770,78 +787,80 @@ static void blkdebug_close(BlockDriverState *bs) } g_free(s->config_file); + qemu_mutex_destroy(&s->lock); } +/* Called with lock held. */ static void suspend_request(BlockDriverState *bs, BlkdebugRule *rule) { BDRVBlkdebugState *s = bs->opaque; - BlkdebugSuspendedReq r; + BlkdebugSuspendedReq *r; - r = (BlkdebugSuspendedReq) { - .co = qemu_coroutine_self(), - .tag = g_strdup(rule->options.suspend.tag), - }; + r = g_new(BlkdebugSuspendedReq, 1); + + r->co = qemu_coroutine_self(); + r->tag = g_strdup(rule->options.suspend.tag); remove_rule(rule); - QLIST_INSERT_HEAD(&s->suspended_reqs, &r, next); + QLIST_INSERT_HEAD(&s->suspended_reqs, r, next); if (!qtest_enabled()) { - printf("blkdebug: Suspended request '%s'\n", r.tag); + printf("blkdebug: Suspended request '%s'\n", r->tag); } - qemu_coroutine_yield(); - if (!qtest_enabled()) { - printf("blkdebug: Resuming request '%s'\n", r.tag); - } - - QLIST_REMOVE(&r, next); - g_free(r.tag); } -static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule, - bool injected) +/* Called with lock held. */ +static void process_rule(BlockDriverState *bs, struct BlkdebugRule *rule, + int *action_count, int *new_state) { BDRVBlkdebugState *s = bs->opaque; /* Only process rules for the current state */ if (rule->state && rule->state != s->state) { - return injected; + return; } /* Take the action */ + action_count[rule->action]++; switch (rule->action) { case ACTION_INJECT_ERROR: - if (!injected) { + if (action_count[ACTION_INJECT_ERROR] == 1) { QSIMPLEQ_INIT(&s->active_rules); - injected = true; } QSIMPLEQ_INSERT_HEAD(&s->active_rules, rule, active_next); break; case ACTION_SET_STATE: - s->new_state = rule->options.set_state.new_state; + *new_state = rule->options.set_state.new_state; break; case ACTION_SUSPEND: suspend_request(bs, rule); break; } - return injected; } static void blkdebug_debug_event(BlockDriverState *bs, BlkdebugEvent event) { BDRVBlkdebugState *s = bs->opaque; struct BlkdebugRule *rule, *next; - bool injected; + int new_state; + int actions_count[ACTION__MAX] = { 0 }; assert((int)event >= 0 && event < BLKDBG__MAX); - injected = false; - s->new_state = s->state; - QLIST_FOREACH_SAFE(rule, &s->rules[event], next, next) { - injected = process_rule(bs, rule, injected); + WITH_QEMU_LOCK_GUARD(&s->lock) { + new_state = s->state; + QLIST_FOREACH_SAFE(rule, &s->rules[event], next, next) { + process_rule(bs, rule, actions_count, &new_state); + } + s->state = new_state; + } + + while (actions_count[ACTION_SUSPEND] > 0) { + qemu_coroutine_yield(); + actions_count[ACTION_SUSPEND]--; } - s->state = s->new_state; } static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event, @@ -864,33 +883,64 @@ static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event, .options.suspend.tag = g_strdup(tag), }; + qemu_mutex_lock(&s->lock); QLIST_INSERT_HEAD(&s->rules[blkdebug_event], rule, next); + qemu_mutex_unlock(&s->lock); return 0; } -static int blkdebug_debug_resume(BlockDriverState *bs, const char *tag) +/* Called with lock held. May temporarily release lock. */ +static int resume_req_by_tag(BDRVBlkdebugState *s, const char *tag, bool all) { - BDRVBlkdebugState *s = bs->opaque; - BlkdebugSuspendedReq *r, *next; + BlkdebugSuspendedReq *r; - QLIST_FOREACH_SAFE(r, &s->suspended_reqs, next, next) { +retry: + /* + * No need for _SAFE, since a different coroutine can remove another node + * (not the current one) in this list, and when the current one is removed + * the iteration starts back from beginning anyways. + */ + QLIST_FOREACH(r, &s->suspended_reqs, next) { if (!strcmp(r->tag, tag)) { - qemu_coroutine_enter(r->co); + Coroutine *co = r->co; + + if (!qtest_enabled()) { + printf("blkdebug: Resuming request '%s'\n", r->tag); + } + + QLIST_REMOVE(r, next); + g_free(r->tag); + g_free(r); + + qemu_mutex_unlock(&s->lock); + qemu_coroutine_enter(co); + qemu_mutex_lock(&s->lock); + + if (all) { + goto retry; + } return 0; } } return -ENOENT; } +static int blkdebug_debug_resume(BlockDriverState *bs, const char *tag) +{ + BDRVBlkdebugState *s = bs->opaque; + QEMU_LOCK_GUARD(&s->lock); + return resume_req_by_tag(s, tag, false); +} + static int blkdebug_debug_remove_breakpoint(BlockDriverState *bs, const char *tag) { BDRVBlkdebugState *s = bs->opaque; - BlkdebugSuspendedReq *r, *r_next; BlkdebugRule *rule, *next; int i, ret = -ENOENT; + QEMU_LOCK_GUARD(&s->lock); for (i = 0; i < BLKDBG__MAX; i++) { QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) { if (rule->action == ACTION_SUSPEND && @@ -900,11 +950,8 @@ static int blkdebug_debug_remove_breakpoint(BlockDriverState *bs, } } } - QLIST_FOREACH_SAFE(r, &s->suspended_reqs, next, r_next) { - if (!strcmp(r->tag, tag)) { - qemu_coroutine_enter(r->co); - ret = 0; - } + if (resume_req_by_tag(s, tag, true) == 0) { + ret = 0; } return ret; } @@ -914,6 +961,7 @@ static bool blkdebug_debug_is_suspended(BlockDriverState *bs, const char *tag) BDRVBlkdebugState *s = bs->opaque; BlkdebugSuspendedReq *r; + QEMU_LOCK_GUARD(&s->lock); QLIST_FOREACH(r, &s->suspended_reqs, next) { if (!strcmp(r->tag, tag)) { return true; diff --git a/block/block-backend.c b/block/block-backend.c index 413af51f3b..deb55c272e 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -18,7 +18,6 @@ #include "hw/qdev-core.h" #include "sysemu/blockdev.h" #include "sysemu/runstate.h" -#include "sysemu/sysemu.h" #include "sysemu/replay.h" #include "qapi/error.h" #include "qapi/qapi-events-block.h" @@ -142,19 +141,18 @@ static void blk_root_set_aio_ctx(BdrvChild *child, AioContext *ctx, static char *blk_root_get_parent_desc(BdrvChild *child) { BlockBackend *blk = child->opaque; - char *dev_id; + g_autofree char *dev_id = NULL; if (blk->name) { - return g_strdup(blk->name); + return g_strdup_printf("block device '%s'", blk->name); } dev_id = blk_get_attached_dev_id(blk); if (*dev_id) { - return dev_id; + return g_strdup_printf("block device '%s'", dev_id); } else { /* TODO Callback into the BB owner for something more detailed */ - g_free(dev_id); - return g_strdup("a block device"); + return g_strdup("an unnamed block device"); } } @@ -298,6 +296,13 @@ static void blk_root_detach(BdrvChild *child) } } +static AioContext *blk_root_get_parent_aio_context(BdrvChild *c) +{ + BlockBackend *blk = c->opaque; + + return blk_get_aio_context(blk); +} + static const BdrvChildClass child_root = { .inherit_options = blk_root_inherit_options, @@ -318,6 +323,8 @@ static const BdrvChildClass child_root = { .can_set_aio_ctx = blk_root_can_set_aio_ctx, .set_aio_ctx = blk_root_set_aio_ctx, + + .get_parent_aio_context = blk_root_get_parent_aio_context, }; /* @@ -398,15 +405,19 @@ BlockBackend *blk_new_open(const char *filename, const char *reference, BlockBackend *blk; BlockDriverState *bs; uint64_t perm = 0; + uint64_t shared = BLK_PERM_ALL; - /* blk_new_open() is mainly used in .bdrv_create implementations and the - * tools where sharing isn't a concern because the BDS stays private, so we - * just request permission according to the flags. + /* + * blk_new_open() is mainly used in .bdrv_create implementations and the + * tools where sharing isn't a major concern because the BDS stays private + * and the file is generally not supposed to be used by a second process, + * so we just request permission according to the flags. * * The exceptions are xen_disk and blockdev_init(); in these cases, the * caller of blk_new_open() doesn't make use of the permissions, but they * shouldn't hurt either. We can still share everything here because the - * guest devices will add their own blockers if they can't share. */ + * guest devices will add their own blockers if they can't share. + */ if ((flags & BDRV_O_NO_IO) == 0) { perm |= BLK_PERM_CONSISTENT_READ; if (flags & BDRV_O_RDWR) { @@ -416,8 +427,11 @@ BlockBackend *blk_new_open(const char *filename, const char *reference, if (flags & BDRV_O_RESIZE) { perm |= BLK_PERM_RESIZE; } + if (flags & BDRV_O_NO_SHARE) { + shared = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED; + } - blk = blk_new(qemu_get_aio_context(), perm, BLK_PERM_ALL); + blk = blk_new(qemu_get_aio_context(), perm, shared); bs = bdrv_open(filename, reference, options, flags, errp); if (!bs) { blk_unref(blk); @@ -426,7 +440,7 @@ BlockBackend *blk_new_open(const char *filename, const char *reference, blk->root = bdrv_root_attach_child(bs, "root", &child_root, BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - blk->ctx, perm, BLK_PERM_ALL, blk, errp); + perm, shared, blk, errp); if (!blk->root) { blk_unref(blk); return NULL; @@ -840,7 +854,7 @@ int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp) bdrv_ref(bs); blk->root = bdrv_root_attach_child(bs, "root", &child_root, BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - blk->ctx, blk->perm, blk->shared_perm, + blk->perm, blk->shared_perm, blk, errp); if (blk->root == NULL) { return -EPERM; @@ -1837,7 +1851,7 @@ bool blk_supports_write_perm(BlockBackend *blk) if (bs) { return !bdrv_is_read_only(bs); } else { - return !blk->root_state.read_only; + return blk->root_state.open_flags & BDRV_O_RDWR; } } @@ -1939,16 +1953,29 @@ uint32_t blk_get_request_alignment(BlockBackend *blk) return bs ? bs->bl.request_alignment : BDRV_SECTOR_SIZE; } +/* Returns the maximum hardware transfer length, in bytes; guaranteed nonzero */ +uint64_t blk_get_max_hw_transfer(BlockBackend *blk) +{ + BlockDriverState *bs = blk_bs(blk); + uint64_t max = INT_MAX; + + if (bs) { + max = MIN_NON_ZERO(max, bs->bl.max_hw_transfer); + max = MIN_NON_ZERO(max, bs->bl.max_transfer); + } + return ROUND_DOWN(max, blk_get_request_alignment(blk)); +} + /* Returns the maximum transfer length, in bytes; guaranteed nonzero */ uint32_t blk_get_max_transfer(BlockBackend *blk) { BlockDriverState *bs = blk_bs(blk); - uint32_t max = 0; + uint32_t max = INT_MAX; if (bs) { - max = bs->bl.max_transfer; + max = MIN_NON_ZERO(max, bs->bl.max_transfer); } - return MIN_NON_ZERO(max, INT_MAX); + return ROUND_DOWN(max, blk_get_request_alignment(blk)); } int blk_get_max_iov(BlockBackend *blk) @@ -2254,7 +2281,6 @@ void blk_update_root_state(BlockBackend *blk) assert(blk->root); blk->root_state.open_flags = blk->root->bs->open_flags; - blk->root_state.read_only = blk->root->bs->read_only; blk->root_state.detect_zeroes = blk->root->bs->detect_zeroes; } @@ -2273,12 +2299,7 @@ bool blk_get_detect_zeroes_from_root_state(BlockBackend *blk) */ int blk_get_open_flags_from_root_state(BlockBackend *blk) { - int bs_flags; - - bs_flags = blk->root_state.read_only ? 0 : BDRV_O_RDWR; - bs_flags |= blk->root_state.open_flags & ~BDRV_O_RDWR; - - return bs_flags; + return blk->root_state.open_flags; } BlockBackendRootState *blk_get_root_state(BlockBackend *blk) @@ -2378,8 +2399,13 @@ static void blk_root_drained_begin(BdrvChild *child) static bool blk_root_drained_poll(BdrvChild *child) { BlockBackend *blk = child->opaque; + bool busy = false; assert(blk->quiesce_counter); - return !!blk->in_flight; + + if (blk->dev_ops && blk->dev_ops->drained_poll) { + busy = blk->dev_ops->drained_poll(blk->dev_opaque); + } + return busy || !!blk->in_flight; } static void blk_root_drained_end(BdrvChild *child, int *drained_end_counter) diff --git a/block/block-copy.c b/block/block-copy.c index 39ae481c8b..0becad52da 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -28,10 +28,18 @@ #define BLOCK_COPY_MAX_WORKERS 64 #define BLOCK_COPY_SLICE_TIME 100000000ULL /* ns */ +typedef enum { + COPY_READ_WRITE_CLUSTER, + COPY_READ_WRITE, + COPY_WRITE_ZEROES, + COPY_RANGE_SMALL, + COPY_RANGE_FULL +} BlockCopyMethod; + static coroutine_fn int block_copy_task_entry(AioTask *task); typedef struct BlockCopyCallState { - /* IN parameters. Initialized in block_copy_async() and never changed. */ + /* Fields initialized in block_copy_async() and never changed. */ BlockCopyState *s; int64_t offset; int64_t bytes; @@ -40,33 +48,60 @@ typedef struct BlockCopyCallState { bool ignore_ratelimit; BlockCopyAsyncCallbackFunc cb; void *cb_opaque; - /* Coroutine where async block-copy is running */ Coroutine *co; + /* Fields whose state changes throughout the execution */ + bool finished; /* atomic */ + QemuCoSleep sleep; /* TODO: protect API with a lock */ + bool cancelled; /* atomic */ /* To reference all call states from BlockCopyState */ QLIST_ENTRY(BlockCopyCallState) list; - /* State */ - int ret; - bool finished; - QemuCoSleepState *sleep_state; - bool cancelled; - - /* OUT parameters */ + /* + * Fields that report information about return values and erros. + * Protected by lock in BlockCopyState. + */ bool error_is_read; + /* + * @ret is set concurrently by tasks under mutex. Only set once by first + * failed task (and untouched if no task failed). + * After finishing (call_state->finished is true), it is not modified + * anymore and may be safely read without mutex. + */ + int ret; } BlockCopyCallState; typedef struct BlockCopyTask { AioTask task; + /* + * Fields initialized in block_copy_task_create() + * and never changed. + */ BlockCopyState *s; BlockCopyCallState *call_state; int64_t offset; - int64_t bytes; - bool zeroes; - QLIST_ENTRY(BlockCopyTask) list; + /* + * @method can also be set again in the while loop of + * block_copy_dirty_clusters(), but it is never accessed concurrently + * because the only other function that reads it is + * block_copy_task_entry() and it is invoked afterwards in the same + * iteration. + */ + BlockCopyMethod method; + + /* + * Fields whose state changes throughout the execution + * Protected by lock in BlockCopyState. + */ CoQueue wait_queue; /* coroutines blocked on this task */ + /* + * Only protect the case of parallel read while updating @bytes + * value in block_copy_task_shrink(). + */ + int64_t bytes; + QLIST_ENTRY(BlockCopyTask) list; } BlockCopyTask; static int64_t task_end(BlockCopyTask *task) @@ -82,17 +117,25 @@ typedef struct BlockCopyState { */ BdrvChild *source; BdrvChild *target; - BdrvDirtyBitmap *copy_bitmap; - int64_t in_flight_bytes; - int64_t cluster_size; - bool use_copy_range; - int64_t copy_size; - uint64_t len; - QLIST_HEAD(, BlockCopyTask) tasks; /* All tasks from all block-copy calls */ - QLIST_HEAD(, BlockCopyCallState) calls; + /* + * Fields initialized in block_copy_state_new() + * and never changed. + */ + int64_t cluster_size; + int64_t max_transfer; + uint64_t len; BdrvRequestFlags write_flags; + /* + * Fields whose state changes throughout the execution + * Protected by lock. + */ + CoMutex lock; + int64_t in_flight_bytes; + BlockCopyMethod method; + QLIST_HEAD(, BlockCopyTask) tasks; /* All tasks from all block-copy calls */ + QLIST_HEAD(, BlockCopyCallState) calls; /* * skip_unallocated: * @@ -107,16 +150,15 @@ typedef struct BlockCopyState { * skip unallocated regions, clear them in the copy_bitmap, and invoke * block_copy_reset_unallocated() every time it does. */ - bool skip_unallocated; - + bool skip_unallocated; /* atomic */ + /* State fields that use a thread-safe API */ + BdrvDirtyBitmap *copy_bitmap; ProgressMeter *progress; - SharedResource *mem; - - uint64_t speed; RateLimit rate_limit; } BlockCopyState; +/* Called with lock held */ static BlockCopyTask *find_conflicting_task(BlockCopyState *s, int64_t offset, int64_t bytes) { @@ -134,6 +176,9 @@ static BlockCopyTask *find_conflicting_task(BlockCopyState *s, /* * If there are no intersecting tasks return false. Otherwise, wait for the * first found intersecting tasks to finish and return true. + * + * Called with lock held. May temporary release the lock. + * Return value of 0 proves that lock was NOT released. */ static bool coroutine_fn block_copy_wait_one(BlockCopyState *s, int64_t offset, int64_t bytes) @@ -144,22 +189,43 @@ static bool coroutine_fn block_copy_wait_one(BlockCopyState *s, int64_t offset, return false; } - qemu_co_queue_wait(&task->wait_queue, NULL); + qemu_co_queue_wait(&task->wait_queue, &s->lock); return true; } +/* Called with lock held */ +static int64_t block_copy_chunk_size(BlockCopyState *s) +{ + switch (s->method) { + case COPY_READ_WRITE_CLUSTER: + return s->cluster_size; + case COPY_READ_WRITE: + case COPY_RANGE_SMALL: + return MIN(MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER), + s->max_transfer); + case COPY_RANGE_FULL: + return MIN(MAX(s->cluster_size, BLOCK_COPY_MAX_COPY_RANGE), + s->max_transfer); + default: + /* Cannot have COPY_WRITE_ZEROES here. */ + abort(); + } +} + /* * Search for the first dirty area in offset/bytes range and create task at * the beginning of it. */ -static BlockCopyTask *block_copy_task_create(BlockCopyState *s, - BlockCopyCallState *call_state, - int64_t offset, int64_t bytes) +static coroutine_fn BlockCopyTask * +block_copy_task_create(BlockCopyState *s, BlockCopyCallState *call_state, + int64_t offset, int64_t bytes) { BlockCopyTask *task; - int64_t max_chunk = MIN_NON_ZERO(s->copy_size, call_state->max_chunk); + int64_t max_chunk; + QEMU_LOCK_GUARD(&s->lock); + max_chunk = MIN_NON_ZERO(block_copy_chunk_size(s), call_state->max_chunk); if (!bdrv_dirty_bitmap_next_dirty_area(s->copy_bitmap, offset, offset + bytes, max_chunk, &offset, &bytes)) @@ -183,6 +249,7 @@ static BlockCopyTask *block_copy_task_create(BlockCopyState *s, .call_state = call_state, .offset = offset, .bytes = bytes, + .method = s->method, }; qemu_co_queue_init(&task->wait_queue); QLIST_INSERT_HEAD(&s->tasks, task, list); @@ -200,6 +267,7 @@ static BlockCopyTask *block_copy_task_create(BlockCopyState *s, static void coroutine_fn block_copy_task_shrink(BlockCopyTask *task, int64_t new_bytes) { + QEMU_LOCK_GUARD(&task->s->lock); if (new_bytes == task->bytes) { return; } @@ -216,11 +284,15 @@ static void coroutine_fn block_copy_task_shrink(BlockCopyTask *task, static void coroutine_fn block_copy_task_end(BlockCopyTask *task, int ret) { + QEMU_LOCK_GUARD(&task->s->lock); task->s->in_flight_bytes -= task->bytes; if (ret < 0) { bdrv_set_dirty_bitmap(task->s->copy_bitmap, task->offset, task->bytes); } QLIST_REMOVE(task, list); + progress_set_remaining(task->s->progress, + bdrv_get_dirty_count(task->s->copy_bitmap) + + task->s->in_flight_bytes); qemu_co_queue_restart_all(&task->wait_queue); } @@ -230,6 +302,7 @@ void block_copy_state_free(BlockCopyState *s) return; } + ratelimit_destroy(&s->rate_limit); bdrv_release_dirty_bitmap(s->copy_bitmap); shres_destroy(s->mem); g_free(s); @@ -265,36 +338,39 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, .len = bdrv_dirty_bitmap_size(copy_bitmap), .write_flags = write_flags, .mem = shres_create(BLOCK_COPY_MAX_MEM), + .max_transfer = QEMU_ALIGN_DOWN( + block_copy_max_transfer(source, target), + cluster_size), }; - if (block_copy_max_transfer(source, target) < cluster_size) { + if (s->max_transfer < cluster_size) { /* * copy_range does not respect max_transfer. We don't want to bother * with requests smaller than block-copy cluster size, so fallback to * buffered copying (read and write respect max_transfer on their * behalf). */ - s->use_copy_range = false; - s->copy_size = cluster_size; + s->method = COPY_READ_WRITE_CLUSTER; } else if (write_flags & BDRV_REQ_WRITE_COMPRESSED) { /* Compression supports only cluster-size writes and no copy-range. */ - s->use_copy_range = false; - s->copy_size = cluster_size; + s->method = COPY_READ_WRITE_CLUSTER; } else { /* - * We enable copy-range, but keep small copy_size, until first + * If copy range enabled, start with COPY_RANGE_SMALL, until first * successful copy_range (look at block_copy_do_copy). */ - s->use_copy_range = use_copy_range; - s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER); + s->method = use_copy_range ? COPY_RANGE_SMALL : COPY_READ_WRITE; } + ratelimit_init(&s->rate_limit); + qemu_co_mutex_init(&s->lock); QLIST_INIT(&s->tasks); QLIST_INIT(&s->calls); return s; } +/* Only set before running the job, no need for locking. */ void block_copy_set_progress_meter(BlockCopyState *s, ProgressMeter *pm) { s->progress = pm; @@ -340,11 +416,15 @@ static coroutine_fn int block_copy_task_run(AioTaskPool *pool, * * No sync here: nor bitmap neighter intersecting requests handling, only copy. * + * @method is an in-out argument, so that copy_range can be either extended to + * a full-size buffer or disabled if the copy_range attempt fails. The output + * value of @method should be used for subsequent tasks. * Returns 0 on success. */ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, int64_t offset, int64_t bytes, - bool zeroes, bool *error_is_read) + BlockCopyMethod *method, + bool *error_is_read) { int ret; int64_t nbytes = MIN(offset + bytes, s->len) - offset; @@ -358,7 +438,8 @@ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, offset + bytes == QEMU_ALIGN_UP(s->len, s->cluster_size)); assert(nbytes < INT_MAX); - if (zeroes) { + switch (*method) { + case COPY_WRITE_ZEROES: ret = bdrv_co_pwrite_zeroes(s->target, offset, nbytes, s->write_flags & ~BDRV_REQ_WRITE_COMPRESSED); if (ret < 0) { @@ -366,84 +447,86 @@ static int coroutine_fn block_copy_do_copy(BlockCopyState *s, *error_is_read = false; } return ret; - } - if (s->use_copy_range) { + case COPY_RANGE_SMALL: + case COPY_RANGE_FULL: ret = bdrv_co_copy_range(s->source, offset, s->target, offset, nbytes, 0, s->write_flags); + if (ret >= 0) { + /* Successful copy-range, increase chunk size. */ + *method = COPY_RANGE_FULL; + return 0; + } + + trace_block_copy_copy_range_fail(s, offset, ret); + *method = COPY_READ_WRITE; + /* Fall through to read+write with allocated buffer */ + + case COPY_READ_WRITE_CLUSTER: + case COPY_READ_WRITE: + /* + * In case of failed copy_range request above, we may proceed with + * buffered request larger than BLOCK_COPY_MAX_BUFFER. + * Still, further requests will be properly limited, so don't care too + * much. Moreover the most likely case (copy_range is unsupported for + * the configuration, so the very first copy_range request fails) + * is handled by setting large copy_size only after first successful + * copy_range. + */ + + bounce_buffer = qemu_blockalign(s->source->bs, nbytes); + + ret = bdrv_co_pread(s->source, offset, nbytes, bounce_buffer, 0); if (ret < 0) { - trace_block_copy_copy_range_fail(s, offset, ret); - s->use_copy_range = false; - s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER); - /* Fallback to read+write with allocated buffer */ - } else { - if (s->use_copy_range) { - /* - * Successful copy-range. Now increase copy_size. copy_range - * does not respect max_transfer (it's a TODO), so we factor - * that in here. - * - * Note: we double-check s->use_copy_range for the case when - * parallel block-copy request unsets it during previous - * bdrv_co_copy_range call. - */ - s->copy_size = - MIN(MAX(s->cluster_size, BLOCK_COPY_MAX_COPY_RANGE), - QEMU_ALIGN_DOWN(block_copy_max_transfer(s->source, - s->target), - s->cluster_size)); - } + trace_block_copy_read_fail(s, offset, ret); + *error_is_read = true; goto out; } + + ret = bdrv_co_pwrite(s->target, offset, nbytes, bounce_buffer, + s->write_flags); + if (ret < 0) { + trace_block_copy_write_fail(s, offset, ret); + *error_is_read = false; + goto out; + } + + out: + qemu_vfree(bounce_buffer); + break; + + default: + abort(); } - /* - * In case of failed copy_range request above, we may proceed with buffered - * request larger than BLOCK_COPY_MAX_BUFFER. Still, further requests will - * be properly limited, so don't care too much. Moreover the most likely - * case (copy_range is unsupported for the configuration, so the very first - * copy_range request fails) is handled by setting large copy_size only - * after first successful copy_range. - */ - - bounce_buffer = qemu_blockalign(s->source->bs, nbytes); - - ret = bdrv_co_pread(s->source, offset, nbytes, bounce_buffer, 0); - if (ret < 0) { - trace_block_copy_read_fail(s, offset, ret); - *error_is_read = true; - goto out; - } - - ret = bdrv_co_pwrite(s->target, offset, nbytes, bounce_buffer, - s->write_flags); - if (ret < 0) { - trace_block_copy_write_fail(s, offset, ret); - *error_is_read = false; - goto out; - } - -out: - qemu_vfree(bounce_buffer); - return ret; } static coroutine_fn int block_copy_task_entry(AioTask *task) { BlockCopyTask *t = container_of(task, BlockCopyTask, task); + BlockCopyState *s = t->s; bool error_is_read = false; + BlockCopyMethod method = t->method; int ret; - ret = block_copy_do_copy(t->s, t->offset, t->bytes, t->zeroes, - &error_is_read); - if (ret < 0 && !t->call_state->ret) { - t->call_state->ret = ret; - t->call_state->error_is_read = error_is_read; - } else { - progress_work_done(t->s->progress, t->bytes); + ret = block_copy_do_copy(s, t->offset, t->bytes, &method, &error_is_read); + + WITH_QEMU_LOCK_GUARD(&s->lock) { + if (s->method == t->method) { + s->method = method; + } + + if (ret < 0) { + if (!t->call_state->ret) { + t->call_state->ret = ret; + t->call_state->error_is_read = error_is_read; + } + } else { + progress_work_done(s->progress, t->bytes); + } } - co_put_to_shres(t->s->mem, t->bytes); + co_put_to_shres(s->mem, t->bytes); block_copy_task_end(t, ret); return ret; @@ -456,7 +539,7 @@ static int block_copy_block_status(BlockCopyState *s, int64_t offset, BlockDriverState *base; int ret; - if (s->skip_unallocated) { + if (qatomic_read(&s->skip_unallocated)) { base = bdrv_backing_chain_next(s->source->bs); } else { base = NULL; @@ -543,10 +626,12 @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, bytes = clusters * s->cluster_size; if (!ret) { + qemu_co_mutex_lock(&s->lock); bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes); progress_set_remaining(s->progress, bdrv_get_dirty_count(s->copy_bitmap) + s->in_flight_bytes); + qemu_co_mutex_unlock(&s->lock); } *count = bytes; @@ -582,7 +667,8 @@ block_copy_dirty_clusters(BlockCopyCallState *call_state) assert(QEMU_IS_ALIGNED(offset, s->cluster_size)); assert(QEMU_IS_ALIGNED(bytes, s->cluster_size)); - while (bytes && aio_task_pool_status(aio) == 0 && !call_state->cancelled) { + while (bytes && aio_task_pool_status(aio) == 0 && + !qatomic_read(&call_state->cancelled)) { BlockCopyTask *task; int64_t status_bytes; @@ -604,34 +690,32 @@ block_copy_dirty_clusters(BlockCopyCallState *call_state) if (status_bytes < task->bytes) { block_copy_task_shrink(task, status_bytes); } - if (s->skip_unallocated && !(ret & BDRV_BLOCK_ALLOCATED)) { + if (qatomic_read(&s->skip_unallocated) && + !(ret & BDRV_BLOCK_ALLOCATED)) { block_copy_task_end(task, 0); - progress_set_remaining(s->progress, - bdrv_get_dirty_count(s->copy_bitmap) + - s->in_flight_bytes); trace_block_copy_skip_range(s, task->offset, task->bytes); offset = task_end(task); bytes = end - offset; g_free(task); continue; } - task->zeroes = ret & BDRV_BLOCK_ZERO; - - if (s->speed) { - if (!call_state->ignore_ratelimit) { - uint64_t ns = ratelimit_calculate_delay(&s->rate_limit, 0); - if (ns > 0) { - block_copy_task_end(task, -EAGAIN); - g_free(task); - qemu_co_sleep_ns_wakeable(QEMU_CLOCK_REALTIME, ns, - &call_state->sleep_state); - continue; - } - } - - ratelimit_calculate_delay(&s->rate_limit, task->bytes); + if (ret & BDRV_BLOCK_ZERO) { + task->method = COPY_WRITE_ZEROES; } + if (!call_state->ignore_ratelimit) { + uint64_t ns = ratelimit_calculate_delay(&s->rate_limit, 0); + if (ns > 0) { + block_copy_task_end(task, -EAGAIN); + g_free(task); + qemu_co_sleep_ns_wakeable(&call_state->sleep, + QEMU_CLOCK_REALTIME, ns); + continue; + } + } + + ratelimit_calculate_delay(&s->rate_limit, task->bytes); + trace_block_copy_process(s, task->offset); co_get_from_shres(s->mem, task->bytes); @@ -672,9 +756,7 @@ out: void block_copy_kick(BlockCopyCallState *call_state) { - if (call_state->sleep_state) { - qemu_co_sleep_wake(call_state->sleep_state); - } + qemu_co_sleep_wake(&call_state->sleep); } /* @@ -689,15 +771,40 @@ void block_copy_kick(BlockCopyCallState *call_state) static int coroutine_fn block_copy_common(BlockCopyCallState *call_state) { int ret; + BlockCopyState *s = call_state->s; - QLIST_INSERT_HEAD(&call_state->s->calls, call_state, list); + qemu_co_mutex_lock(&s->lock); + QLIST_INSERT_HEAD(&s->calls, call_state, list); + qemu_co_mutex_unlock(&s->lock); do { ret = block_copy_dirty_clusters(call_state); - if (ret == 0 && !call_state->cancelled) { - ret = block_copy_wait_one(call_state->s, call_state->offset, - call_state->bytes); + if (ret == 0 && !qatomic_read(&call_state->cancelled)) { + WITH_QEMU_LOCK_GUARD(&s->lock) { + /* + * Check that there is no task we still need to + * wait to complete + */ + ret = block_copy_wait_one(s, call_state->offset, + call_state->bytes); + if (ret == 0) { + /* + * No pending tasks, but check again the bitmap in this + * same critical section, since a task might have failed + * between this and the critical section in + * block_copy_dirty_clusters(). + * + * block_copy_wait_one return value 0 also means that it + * didn't release the lock. So, we are still in the same + * critical section, not interrupted by any concurrent + * access to state. + */ + ret = bdrv_dirty_bitmap_next_dirty(s->copy_bitmap, + call_state->offset, + call_state->bytes) >= 0; + } + } } /* @@ -709,15 +816,17 @@ static int coroutine_fn block_copy_common(BlockCopyCallState *call_state) * 2. We have waited for some intersecting block-copy request * It may have failed and produced new dirty bits. */ - } while (ret > 0 && !call_state->cancelled); + } while (ret > 0 && !qatomic_read(&call_state->cancelled)); - call_state->finished = true; + qatomic_store_release(&call_state->finished, true); if (call_state->cb) { call_state->cb(call_state->cb_opaque); } + qemu_co_mutex_lock(&s->lock); QLIST_REMOVE(call_state, list); + qemu_co_mutex_unlock(&s->lock); return ret; } @@ -772,44 +881,50 @@ void block_copy_call_free(BlockCopyCallState *call_state) return; } - assert(call_state->finished); + assert(qatomic_read(&call_state->finished)); g_free(call_state); } bool block_copy_call_finished(BlockCopyCallState *call_state) { - return call_state->finished; + return qatomic_read(&call_state->finished); } bool block_copy_call_succeeded(BlockCopyCallState *call_state) { - return call_state->finished && !call_state->cancelled && - call_state->ret == 0; + return qatomic_load_acquire(&call_state->finished) && + !qatomic_read(&call_state->cancelled) && + call_state->ret == 0; } bool block_copy_call_failed(BlockCopyCallState *call_state) { - return call_state->finished && !call_state->cancelled && - call_state->ret < 0; + return qatomic_load_acquire(&call_state->finished) && + !qatomic_read(&call_state->cancelled) && + call_state->ret < 0; } bool block_copy_call_cancelled(BlockCopyCallState *call_state) { - return call_state->cancelled; + return qatomic_read(&call_state->cancelled); } int block_copy_call_status(BlockCopyCallState *call_state, bool *error_is_read) { - assert(call_state->finished); + assert(qatomic_load_acquire(&call_state->finished)); if (error_is_read) { *error_is_read = call_state->error_is_read; } return call_state->ret; } +/* + * Note that cancelling and finishing are racy. + * User can cancel a block-copy that is already finished. + */ void block_copy_call_cancel(BlockCopyCallState *call_state) { - call_state->cancelled = true; + qatomic_set(&call_state->cancelled, true); block_copy_kick(call_state); } @@ -820,15 +935,12 @@ BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s) void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip) { - s->skip_unallocated = skip; + qatomic_set(&s->skip_unallocated, skip); } void block_copy_set_speed(BlockCopyState *s, uint64_t speed) { - s->speed = speed; - if (speed > 0) { - ratelimit_set_speed(&s->rate_limit, speed, BLOCK_COPY_SLICE_TIME); - } + ratelimit_set_speed(&s->rate_limit, speed, BLOCK_COPY_SLICE_TIME); /* * Note: it's good to kick all call states from here, but it should be done diff --git a/block/commit.c b/block/commit.c index dd9ba87349..42792b4556 100644 --- a/block/commit.c +++ b/block/commit.c @@ -119,24 +119,24 @@ static int coroutine_fn commit_run(Job *job, Error **errp) uint64_t delay_ns = 0; int ret = 0; int64_t n = 0; /* bytes */ - void *buf = NULL; + QEMU_AUTO_VFREE void *buf = NULL; int64_t len, base_len; - ret = len = blk_getlength(s->top); + len = blk_getlength(s->top); if (len < 0) { - goto out; + return len; } job_progress_set_remaining(&s->common.job, len); - ret = base_len = blk_getlength(s->base); + base_len = blk_getlength(s->base); if (base_len < 0) { - goto out; + return base_len; } if (base_len < len) { ret = blk_truncate(s->base, len, false, PREALLOC_MODE_OFF, 0, NULL); if (ret) { - goto out; + return ret; } } @@ -174,7 +174,7 @@ static int coroutine_fn commit_run(Job *job, Error **errp) block_job_error_action(&s->common, s->on_error, error_in_source, -ret); if (action == BLOCK_ERROR_ACTION_REPORT) { - goto out; + return ret; } else { n = 0; continue; @@ -190,12 +190,7 @@ static int coroutine_fn commit_run(Job *job, Error **errp) } } - ret = 0; - -out: - qemu_vfree(buf); - - return ret; + return 0; } static const BlockJobDriver commit_job_driver = { @@ -312,6 +307,7 @@ void commit_start(const char *job_id, BlockDriverState *bs, commit_top_bs->total_sectors = top->total_sectors; ret = bdrv_append(commit_top_bs, top, errp); + bdrv_unref(commit_top_bs); /* referenced by new parents or failed */ if (ret < 0) { commit_top_bs = NULL; goto fail; @@ -434,7 +430,7 @@ int bdrv_commit(BlockDriverState *bs) int ro; int64_t n; int ret = 0; - uint8_t *buf = NULL; + QEMU_AUTO_VFREE uint8_t *buf = NULL; Error *local_err = NULL; if (!drv) @@ -452,7 +448,7 @@ int bdrv_commit(BlockDriverState *bs) return -EBUSY; } - ro = backing_file_bs->read_only; + ro = bdrv_is_read_only(backing_file_bs); if (ro) { if (bdrv_reopen_set_read_only(backing_file_bs, false, NULL)) { @@ -555,8 +551,6 @@ int bdrv_commit(BlockDriverState *bs) ret = 0; ro_cleanup: - qemu_vfree(buf); - blk_unref(backing); if (bdrv_cow_bs(bs) != backing_file_bs) { bdrv_set_backing_hd(bs, backing_file_bs, &error_abort); diff --git a/block/copy-on-read.c b/block/copy-on-read.c index 9cad9e1b8c..c428682272 100644 --- a/block/copy-on-read.c +++ b/block/copy-on-read.c @@ -29,7 +29,6 @@ typedef struct BDRVStateCOR { - bool active; BlockDriverState *bottom_bs; bool chain_frozen; } BDRVStateCOR; @@ -89,7 +88,6 @@ static int cor_open(BlockDriverState *bs, QDict *options, int flags, */ bdrv_ref(bottom_bs); } - state->active = true; state->bottom_bs = bottom_bs; /* @@ -112,17 +110,6 @@ static void cor_child_perm(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared) { - BDRVStateCOR *s = bs->opaque; - - if (!s->active) { - /* - * While the filter is being removed - */ - *nperm = 0; - *nshared = BLK_PERM_ALL; - return; - } - *nperm = perm & PERM_PASSTHROUGH; *nshared = (shared & PERM_PASSTHROUGH) | PERM_UNCHANGED; @@ -280,32 +267,14 @@ static BlockDriver bdrv_copy_on_read = { void bdrv_cor_filter_drop(BlockDriverState *cor_filter_bs) { - BdrvChild *child; - BlockDriverState *bs; BDRVStateCOR *s = cor_filter_bs->opaque; - child = bdrv_filter_child(cor_filter_bs); - if (!child) { - return; - } - bs = child->bs; - - /* Retain the BDS until we complete the graph change. */ - bdrv_ref(bs); - /* Hold a guest back from writing while permissions are being reset. */ - bdrv_drained_begin(bs); - /* Drop permissions before the graph change. */ - s->active = false; /* unfreeze, as otherwise bdrv_replace_node() will fail */ if (s->chain_frozen) { s->chain_frozen = false; bdrv_unfreeze_backing_chain(cor_filter_bs, s->bottom_bs); } - bdrv_child_refresh_perms(cor_filter_bs, child, &error_abort); - bdrv_replace_node(cor_filter_bs, bs, &error_abort); - - bdrv_drained_end(bs); - bdrv_unref(bs); + bdrv_drop_filter(cor_filter_bs, &error_abort); bdrv_unref(cor_filter_bs); } diff --git a/block/coroutines.h b/block/coroutines.h index 4cfb4946e6..514d169d23 100644 --- a/block/coroutines.h +++ b/block/coroutines.h @@ -66,4 +66,10 @@ int coroutine_fn bdrv_co_readv_vmstate(BlockDriverState *bs, int coroutine_fn bdrv_co_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos); +int generated_co_wrapper +nbd_do_establish_connection(BlockDriverState *bs, Error **errp); +int coroutine_fn +nbd_co_do_establish_connection(BlockDriverState *bs, Error **errp); + + #endif /* BLOCK_COROUTINES_INT_H */ diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index 68d295d6e3..0ef46163e3 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -193,7 +193,7 @@ int bdrv_dirty_bitmap_check(const BdrvDirtyBitmap *bitmap, uint32_t flags, error_setg(errp, "Bitmap '%s' is inconsistent and cannot be used", bitmap->name); error_append_hint(errp, "Try block-dirty-bitmap-remove to delete" - " this bitmap from disk"); + " this bitmap from disk\n"); return -1; } diff --git a/block/export/export.c b/block/export/export.c index fec7d9f738..6d3b9964c8 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -111,6 +111,7 @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) if (export->has_iothread) { IOThread *iothread; AioContext *new_ctx; + Error **set_context_errp; iothread = iothread_by_id(export->iothread); if (!iothread) { @@ -120,7 +121,9 @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) new_ctx = iothread_get_aio_context(iothread); - ret = bdrv_try_set_aio_context(bs, new_ctx, errp); + /* Ignore errors with fixed-iothread=false */ + set_context_errp = fixed_iothread ? errp : NULL; + ret = bdrv_try_set_aio_context(bs, new_ctx, set_context_errp); if (ret == 0) { aio_context_release(ctx); aio_context_acquire(new_ctx); diff --git a/block/export/fuse.c b/block/export/fuse.c index 38f74c94da..fc7b07d2b5 100644 --- a/block/export/fuse.c +++ b/block/export/fuse.c @@ -46,6 +46,12 @@ typedef struct FuseExport { char *mountpoint; bool writable; bool growable; + /* Whether allow_other was used as a mount option or not */ + bool allow_other; + + mode_t st_mode; + uid_t st_uid; + gid_t st_gid; } FuseExport; static GHashTable *exports; @@ -57,7 +63,7 @@ static void fuse_export_delete(BlockExport *exp); static void init_exports_table(void); static int setup_fuse_export(FuseExport *exp, const char *mountpoint, - Error **errp); + bool allow_other, Error **errp); static void read_from_fuse_export(void *opaque); static bool is_regular_file(const char *path, Error **errp); @@ -118,7 +124,29 @@ static int fuse_export_create(BlockExport *blk_exp, exp->writable = blk_exp_args->writable; exp->growable = args->growable; - ret = setup_fuse_export(exp, args->mountpoint, errp); + /* set default */ + if (!args->has_allow_other) { + args->allow_other = FUSE_EXPORT_ALLOW_OTHER_AUTO; + } + + exp->st_mode = S_IFREG | S_IRUSR; + if (exp->writable) { + exp->st_mode |= S_IWUSR; + } + exp->st_uid = getuid(); + exp->st_gid = getgid(); + + if (args->allow_other == FUSE_EXPORT_ALLOW_OTHER_AUTO) { + /* Ignore errors on our first attempt */ + ret = setup_fuse_export(exp, args->mountpoint, true, NULL); + exp->allow_other = ret == 0; + if (ret < 0) { + ret = setup_fuse_export(exp, args->mountpoint, false, errp); + } + } else { + exp->allow_other = args->allow_other == FUSE_EXPORT_ALLOW_OTHER_ON; + ret = setup_fuse_export(exp, args->mountpoint, exp->allow_other, errp); + } if (ret < 0) { goto fail; } @@ -146,15 +174,20 @@ static void init_exports_table(void) * Create exp->fuse_session and mount it. */ static int setup_fuse_export(FuseExport *exp, const char *mountpoint, - Error **errp) + bool allow_other, Error **errp) { const char *fuse_argv[4]; char *mount_opts; struct fuse_args fuse_args; int ret; - /* Needs to match what fuse_init() sets. Only max_read must be supplied. */ - mount_opts = g_strdup_printf("max_read=%zu", FUSE_MAX_BOUNCE_BYTES); + /* + * max_read needs to match what fuse_init() sets. + * max_write need not be supplied. + */ + mount_opts = g_strdup_printf("max_read=%zu,default_permissions%s", + FUSE_MAX_BOUNCE_BYTES, + allow_other ? ",allow_other" : ""); fuse_argv[0] = ""; /* Dummy program name */ fuse_argv[1] = "-o"; @@ -316,7 +349,6 @@ static void fuse_getattr(fuse_req_t req, fuse_ino_t inode, int64_t length, allocated_blocks; time_t now = time(NULL); FuseExport *exp = fuse_req_userdata(req); - mode_t mode; length = blk_getlength(exp->common.blk); if (length < 0) { @@ -331,17 +363,12 @@ static void fuse_getattr(fuse_req_t req, fuse_ino_t inode, allocated_blocks = DIV_ROUND_UP(allocated_blocks, 512); } - mode = S_IFREG | S_IRUSR; - if (exp->writable) { - mode |= S_IWUSR; - } - statbuf = (struct stat) { .st_ino = inode, - .st_mode = mode, + .st_mode = exp->st_mode, .st_nlink = 1, - .st_uid = getuid(), - .st_gid = getgid(), + .st_uid = exp->st_uid, + .st_gid = exp->st_gid, .st_size = length, .st_blksize = blk_bs(exp->common.blk)->bl.request_alignment, .st_blocks = allocated_blocks, @@ -387,28 +414,76 @@ static int fuse_do_truncate(const FuseExport *exp, int64_t size, } /** - * Let clients set file attributes. Only resizing is supported. + * Let clients set file attributes. Only resizing and changing + * permissions (st_mode, st_uid, st_gid) is allowed. + * Changing permissions is only allowed as far as it will actually + * permit access: Read-only exports cannot be given +w, and exports + * without allow_other cannot be given a different UID or GID, and + * they cannot be given non-owner access. */ static void fuse_setattr(fuse_req_t req, fuse_ino_t inode, struct stat *statbuf, int to_set, struct fuse_file_info *fi) { FuseExport *exp = fuse_req_userdata(req); + int supported_attrs; int ret; - if (!exp->writable) { - fuse_reply_err(req, EACCES); - return; + supported_attrs = FUSE_SET_ATTR_SIZE | FUSE_SET_ATTR_MODE; + if (exp->allow_other) { + supported_attrs |= FUSE_SET_ATTR_UID | FUSE_SET_ATTR_GID; } - if (to_set & ~FUSE_SET_ATTR_SIZE) { + if (to_set & ~supported_attrs) { fuse_reply_err(req, ENOTSUP); return; } - ret = fuse_do_truncate(exp, statbuf->st_size, true, PREALLOC_MODE_OFF); - if (ret < 0) { - fuse_reply_err(req, -ret); - return; + /* Do some argument checks first before committing to anything */ + if (to_set & FUSE_SET_ATTR_MODE) { + /* + * Without allow_other, non-owners can never access the export, so do + * not allow setting permissions for them + */ + if (!exp->allow_other && + (statbuf->st_mode & (S_IRWXG | S_IRWXO)) != 0) + { + fuse_reply_err(req, EPERM); + return; + } + + /* +w for read-only exports makes no sense, disallow it */ + if (!exp->writable && + (statbuf->st_mode & (S_IWUSR | S_IWGRP | S_IWOTH)) != 0) + { + fuse_reply_err(req, EROFS); + return; + } + } + + if (to_set & FUSE_SET_ATTR_SIZE) { + if (!exp->writable) { + fuse_reply_err(req, EACCES); + return; + } + + ret = fuse_do_truncate(exp, statbuf->st_size, true, PREALLOC_MODE_OFF); + if (ret < 0) { + fuse_reply_err(req, -ret); + return; + } + } + + if (to_set & FUSE_SET_ATTR_MODE) { + /* Ignore FUSE-supplied file type, only change the mode */ + exp->st_mode = (statbuf->st_mode & 07777) | S_IFREG; + } + + if (to_set & FUSE_SET_ATTR_UID) { + exp->st_uid = statbuf->st_uid; + } + + if (to_set & FUSE_SET_ATTR_GID) { + exp->st_gid = statbuf->st_gid; } fuse_getattr(req, inode, fi); @@ -560,7 +635,9 @@ static void fuse_fallocate(fuse_req_t req, fuse_ino_t inode, int mode, offset += size; length -= size; } while (ret == 0 && length > 0); - } else if (mode & FALLOC_FL_ZERO_RANGE) { + } +#ifdef CONFIG_FALLOCATE_ZERO_RANGE + else if (mode & FALLOC_FL_ZERO_RANGE) { if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + length > blk_len) { /* No need for zeroes, we are going to write them ourselves */ ret = fuse_do_truncate(exp, offset + length, false, @@ -579,7 +656,9 @@ static void fuse_fallocate(fuse_req_t req, fuse_ino_t inode, int mode, offset += size; length -= size; } while (ret == 0 && length > 0); - } else if (!mode) { + } +#endif /* CONFIG_FALLOCATE_ZERO_RANGE */ + else if (!mode) { /* We can only fallocate at the EOF with a truncate */ if (offset < blk_len) { fuse_reply_err(req, EOPNOTSUPP); diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index fa06996d37..1862563336 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -70,9 +70,16 @@ static void vu_blk_req_complete(VuBlkReq *req) static bool vu_blk_sect_range_ok(VuBlkExport *vexp, uint64_t sector, size_t size) { - uint64_t nb_sectors = size >> BDRV_SECTOR_BITS; + uint64_t nb_sectors; uint64_t total_sectors; + if (size % VIRTIO_BLK_SECTOR_SIZE) { + return false; + } + + nb_sectors = size >> VIRTIO_BLK_SECTOR_BITS; + + QEMU_BUILD_BUG_ON(BDRV_SECTOR_SIZE != VIRTIO_BLK_SECTOR_SIZE); if (nb_sectors > BDRV_REQUEST_MAX_SECTORS) { return false; } diff --git a/block/file-posix.c b/block/file-posix.c index 20e14f8e96..cb9bffe047 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -42,8 +42,11 @@ #include "scsi/constants.h" #if defined(__APPLE__) && (__MACH__) +#include +#if defined(HAVE_HOST_BLOCK_DEVICE) #include #include +#include #include #include #include @@ -52,6 +55,7 @@ //#include #include #include +#endif /* defined(HAVE_HOST_BLOCK_DEVICE) */ #endif #ifdef __sun__ @@ -106,8 +110,6 @@ #include #endif -#include "trace.h" - /* OS X does not have O_DSYNC */ #ifndef O_DSYNC #ifdef O_SYNC @@ -160,7 +162,7 @@ typedef struct BDRVRawState { bool discard_zeroes:1; bool use_linux_aio:1; bool use_linux_io_uring:1; - bool page_cache_inconsistent:1; + int page_cache_inconsistent; /* errno from fdatasync failure */ bool has_fallocate; bool needs_alignment; bool drop_cache; @@ -175,13 +177,22 @@ typedef struct BDRVRawState { } BDRVRawState; typedef struct BDRVRawReopenState { - int fd; int open_flags; bool drop_cache; bool check_cache_dropped; } BDRVRawReopenState; -static int fd_open(BlockDriverState *bs); +static int fd_open(BlockDriverState *bs) +{ + BDRVRawState *s = bs->opaque; + + /* this is just to ensure s->fd is sane (its called by io ops) */ + if (s->fd >= 0) { + return 0; + } + return -EIO; +} + static int64_t raw_getlength(BlockDriverState *bs); typedef struct RawPosixAIOData { @@ -1075,7 +1086,6 @@ static int raw_reopen_prepare(BDRVReopenState *state, BDRVRawReopenState *rs; QemuOpts *opts; int ret; - Error *local_err = NULL; assert(state != NULL); assert(state->bs != NULL); @@ -1101,32 +1111,18 @@ static int raw_reopen_prepare(BDRVReopenState *state, * bdrv_reopen_prepare() will detect changes and complain. */ qemu_opts_to_qdict(opts, state->options); - rs->fd = raw_reconfigure_getfd(state->bs, state->flags, &rs->open_flags, - state->perm, true, &local_err); - if (local_err) { - error_propagate(errp, local_err); - ret = -1; - goto out; - } - - /* Fail already reopen_prepare() if we can't get a working O_DIRECT - * alignment with the new fd. */ - if (rs->fd != -1) { - raw_probe_alignment(state->bs, rs->fd, &local_err); - if (local_err) { - error_propagate(errp, local_err); - ret = -EINVAL; - goto out_fd; - } - } + /* + * As part of reopen prepare we also want to create new fd by + * raw_reconfigure_getfd(). But it wants updated "perm", when in + * bdrv_reopen_multiple() .bdrv_reopen_prepare() callback called prior to + * permission update. Happily, permission update is always a part (a seprate + * stage) of bdrv_reopen_multiple() so we can rely on this fact and + * reconfigure fd in raw_check_perm(). + */ s->reopen_state = state; ret = 0; -out_fd: - if (ret < 0) { - qemu_close(rs->fd); - rs->fd = -1; - } + out: qemu_opts_del(opts); return ret; @@ -1140,10 +1136,6 @@ static void raw_reopen_commit(BDRVReopenState *state) s->drop_cache = rs->drop_cache; s->check_cache_dropped = rs->check_cache_dropped; s->open_flags = rs->open_flags; - - qemu_close(s->fd); - s->fd = rs->fd; - g_free(state->opaque); state->opaque = NULL; @@ -1162,10 +1154,6 @@ static void raw_reopen_abort(BDRVReopenState *state) return; } - if (rs->fd >= 0) { - qemu_close(rs->fd); - rs->fd = -1; - } g_free(state->opaque); state->opaque = NULL; @@ -1173,22 +1161,27 @@ static void raw_reopen_abort(BDRVReopenState *state) s->reopen_state = NULL; } -static int sg_get_max_transfer_length(int fd) +static int hdev_get_max_hw_transfer(int fd, struct stat *st) { #ifdef BLKSECTGET - int max_bytes = 0; - - if (ioctl(fd, BLKSECTGET, &max_bytes) == 0) { - return max_bytes; + if (S_ISBLK(st->st_mode)) { + unsigned short max_sectors = 0; + if (ioctl(fd, BLKSECTGET, &max_sectors) == 0) { + return max_sectors * 512; + } } else { - return -errno; + int max_bytes = 0; + if (ioctl(fd, BLKSECTGET, &max_bytes) == 0) { + return max_bytes; + } } + return -errno; #else return -ENOSYS; #endif } -static int sg_get_max_segments(int fd) +static int hdev_get_max_segments(int fd, struct stat *st) { #ifdef CONFIG_LINUX char buf[32]; @@ -1197,15 +1190,20 @@ static int sg_get_max_segments(int fd) int ret; int sysfd = -1; long max_segments; - struct stat st; - if (fstat(fd, &st)) { - ret = -errno; - goto out; + if (S_ISCHR(st->st_mode)) { + if (ioctl(fd, SG_GET_SG_TABLESIZE, &ret) == 0) { + return ret; + } + return -ENOTSUP; + } + + if (!S_ISBLK(st->st_mode)) { + return -ENOTSUP; } sysfspath = g_strdup_printf("/sys/dev/block/%u:%u/queue/max_segments", - major(st.st_rdev), minor(st.st_rdev)); + major(st->st_rdev), minor(st->st_rdev)); sysfd = open(sysfspath, O_RDONLY); if (sysfd == -1) { ret = -errno; @@ -1242,24 +1240,42 @@ out: static void raw_refresh_limits(BlockDriverState *bs, Error **errp) { BDRVRawState *s = bs->opaque; - - if (bs->sg) { - int ret = sg_get_max_transfer_length(s->fd); - - if (ret > 0 && ret <= BDRV_REQUEST_MAX_BYTES) { - bs->bl.max_transfer = pow2floor(ret); - } - - ret = sg_get_max_segments(s->fd); - if (ret > 0) { - bs->bl.max_transfer = MIN(bs->bl.max_transfer, - ret * qemu_real_host_page_size); - } - } + struct stat st; raw_probe_alignment(bs, s->fd, errp); bs->bl.min_mem_alignment = s->buf_align; bs->bl.opt_mem_alignment = MAX(s->buf_align, qemu_real_host_page_size); + + /* + * Maximum transfers are best effort, so it is okay to ignore any + * errors. That said, based on the man page errors in fstat would be + * very much unexpected; the only possible case seems to be ENOMEM. + */ + if (fstat(s->fd, &st)) { + return; + } + +#if defined(__APPLE__) && (__MACH__) + struct statfs buf; + + if (!fstatfs(s->fd, &buf)) { + bs->bl.opt_transfer = buf.f_iosize; + bs->bl.pdiscard_alignment = buf.f_bsize; + } +#endif + + if (bs->sg || S_ISBLK(st.st_mode)) { + int ret = hdev_get_max_hw_transfer(s->fd, &st); + + if (ret > 0 && ret <= BDRV_REQUEST_MAX_BYTES) { + bs->bl.max_hw_transfer = ret; + } + + ret = hdev_get_max_segments(s->fd, &st); + if (ret > 0) { + bs->bl.max_iov = ret; + } + } } static int check_for_dasd(int fd) @@ -1341,7 +1357,9 @@ static int handle_aiocb_ioctl(void *opaque) RawPosixAIOData *aiocb = opaque; int ret; - ret = ioctl(aiocb->aio_fildes, aiocb->ioctl.cmd, aiocb->ioctl.buf); + do { + ret = ioctl(aiocb->aio_fildes, aiocb->ioctl.cmd, aiocb->ioctl.buf); + } while (ret == -1 && errno == EINTR); if (ret == -1) { return -errno; } @@ -1357,11 +1375,13 @@ static int handle_aiocb_flush(void *opaque) int ret; if (s->page_cache_inconsistent) { - return -EIO; + return -s->page_cache_inconsistent; } ret = qemu_fdatasync(aiocb->aio_fildes); if (ret == -1) { + trace_file_flush_fdatasync_failed(errno); + /* There is no clear definition of the semantics of a failing fsync(), * so we may have to assume the worst. The sad truth is that this * assumption is correct for Linux. Some pages are now probably marked @@ -1376,7 +1396,7 @@ static int handle_aiocb_flush(void *opaque) * Obviously, this doesn't affect O_DIRECT, which bypasses the page * cache. */ if ((s->open_flags & O_DIRECT) == 0) { - s->page_cache_inconsistent = true; + s->page_cache_inconsistent = errno; } return -errno; } @@ -1581,6 +1601,7 @@ out: } } +#if defined(CONFIG_FALLOCATE) || defined(BLKZEROOUT) || defined(BLKDISCARD) static int translate_err(int err) { if (err == -ENODEV || err == -ENOSYS || err == -EOPNOTSUPP || @@ -1589,6 +1610,7 @@ static int translate_err(int err) } return err; } +#endif #ifdef CONFIG_FALLOCATE static int do_fallocate(int fd, int mode, off_t offset, off_t len) @@ -1649,17 +1671,17 @@ static int handle_aiocb_write_zeroes(void *opaque) if (s->has_write_zeroes) { int ret = do_fallocate(s->fd, FALLOC_FL_ZERO_RANGE, aiocb->aio_offset, aiocb->aio_nbytes); - if (ret == -EINVAL) { - /* - * Allow falling back to pwrite for file systems that - * do not support fallocate() for an unaligned byte range. - */ - return -ENOTSUP; - } - if (ret == 0 || ret != -ENOTSUP) { + if (ret == -ENOTSUP) { + s->has_write_zeroes = false; + } else if (ret == 0 || ret != -EINVAL) { return ret; } - s->has_write_zeroes = false; + /* + * Note: Some file systems do not like unaligned byte ranges, and + * return EINVAL in such a case, though they should not do it according + * to the man-page of fallocate(). Thus we simply ignore this return + * value and try the other fallbacks instead. + */ } #endif @@ -1674,6 +1696,17 @@ static int handle_aiocb_write_zeroes(void *opaque) return ret; } s->has_fallocate = false; + } else if (ret == -EINVAL) { + /* + * Some file systems like older versions of GPFS do not like un- + * aligned byte ranges, and return EINVAL in such a case, though + * they should not do it according to the man-page of fallocate(). + * Warn about the bad filesystem and try the final fallback instead. + */ + warn_report_once("Your file system is misbehaving: " + "fallocate(FALLOC_FL_PUNCH_HOLE) returned EINVAL. " + "Please report this bug to your file sytem " + "vendor."); } else if (ret != -ENOTSUP) { return ret; } else { @@ -1790,16 +1823,27 @@ static int handle_aiocb_discard(void *opaque) } } while (errno == EINTR); - ret = -errno; + ret = translate_err(-errno); #endif } else { #ifdef CONFIG_FALLOCATE_PUNCH_HOLE ret = do_fallocate(s->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, aiocb->aio_offset, aiocb->aio_nbytes); + ret = translate_err(-errno); +#elif defined(__APPLE__) && (__MACH__) + fpunchhole_t fpunchhole; + fpunchhole.fp_flags = 0; + fpunchhole.reserved = 0; + fpunchhole.fp_offset = aiocb->aio_offset; + fpunchhole.fp_length = aiocb->aio_nbytes; + if (fcntl(s->fd, F_PUNCHHOLE, &fpunchhole) == -1) { + ret = errno == ENODEV ? -ENOTSUP : -errno; + } else { + ret = 0; + } #endif } - ret = translate_err(ret); if (ret == -ENOTSUP) { s->has_discard = false; } @@ -2308,39 +2352,37 @@ static int64_t raw_getlength(BlockDriverState *bs) again: #endif if (!fstat(fd, &sb) && (S_IFCHR & sb.st_mode)) { + size = 0; #ifdef DIOCGMEDIASIZE - if (ioctl(fd, DIOCGMEDIASIZE, (off_t *)&size)) -#elif defined(DIOCGPART) - { - struct partinfo pi; - if (ioctl(fd, DIOCGPART, &pi) == 0) - size = pi.media_size; - else - size = 0; + if (ioctl(fd, DIOCGMEDIASIZE, (off_t *)&size)) { + size = 0; } - if (size == 0) #endif -#if defined(__APPLE__) && defined(__MACH__) - { +#ifdef DIOCGPART + if (size == 0) { + struct partinfo pi; + if (ioctl(fd, DIOCGPART, &pi) == 0) { + size = pi.media_size; + } + } +#endif +#if defined(DKIOCGETBLOCKCOUNT) && defined(DKIOCGETBLOCKSIZE) + if (size == 0) { uint64_t sectors = 0; uint32_t sector_size = 0; if (ioctl(fd, DKIOCGETBLOCKCOUNT, §ors) == 0 && ioctl(fd, DKIOCGETBLOCKSIZE, §or_size) == 0) { size = sectors * sector_size; - } else { - size = lseek(fd, 0LL, SEEK_END); - if (size < 0) { - return -errno; - } } } -#else - size = lseek(fd, 0LL, SEEK_END); +#endif + if (size == 0) { + size = lseek(fd, 0LL, SEEK_END); + } if (size < 0) { return -errno; } -#endif #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__) switch(s->type) { case FTYPE_CD: @@ -3027,6 +3069,7 @@ static BlockStatsSpecific *raw_get_specific_stats(BlockDriverState *bs) return stats; } +#if defined(HAVE_HOST_BLOCK_DEVICE) static BlockStatsSpecific *hdev_get_specific_stats(BlockDriverState *bs) { BlockStatsSpecific *stats = g_new(BlockStatsSpecific, 1); @@ -3036,6 +3079,7 @@ static BlockStatsSpecific *hdev_get_specific_stats(BlockDriverState *bs) return stats; } +#endif /* HAVE_HOST_BLOCK_DEVICE */ static QemuOptsList raw_create_opts = { .name = "raw-create-opts", @@ -3073,39 +3117,30 @@ static int raw_check_perm(BlockDriverState *bs, uint64_t perm, uint64_t shared, Error **errp) { BDRVRawState *s = bs->opaque; - BDRVRawReopenState *rs = NULL; + int input_flags = s->reopen_state ? s->reopen_state->flags : bs->open_flags; int open_flags; int ret; - if (s->perm_change_fd) { - /* - * In the context of reopen, this function may be called several times - * (directly and recursively while change permissions of the parent). - * This is even true for children that don't inherit from the original - * reopen node, so s->reopen_state is not set. - * - * Ignore all but the first call. - */ - return 0; - } + /* We may need a new fd if auto-read-only switches the mode */ + ret = raw_reconfigure_getfd(bs, input_flags, &open_flags, perm, + false, errp); + if (ret < 0) { + return ret; + } else if (ret != s->fd) { + Error *local_err = NULL; - if (s->reopen_state) { - /* We already have a new file descriptor to set permissions for */ - assert(s->reopen_state->perm == perm); - assert(s->reopen_state->shared_perm == shared); - rs = s->reopen_state->opaque; - s->perm_change_fd = rs->fd; - s->perm_change_flags = rs->open_flags; - } else { - /* We may need a new fd if auto-read-only switches the mode */ - ret = raw_reconfigure_getfd(bs, bs->open_flags, &open_flags, perm, - false, errp); - if (ret < 0) { - return ret; - } else if (ret != s->fd) { - s->perm_change_fd = ret; - s->perm_change_flags = open_flags; + /* + * Fail already check_perm() if we can't get a working O_DIRECT + * alignment with the new fd. + */ + raw_probe_alignment(bs, ret, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return -EINVAL; } + + s->perm_change_fd = ret; + s->perm_change_flags = open_flags; } /* Prepare permissions on old fd to avoid conflicts between old and new, @@ -3127,7 +3162,7 @@ static int raw_check_perm(BlockDriverState *bs, uint64_t perm, uint64_t shared, return 0; fail: - if (s->perm_change_fd && !s->reopen_state) { + if (s->perm_change_fd) { qemu_close(s->perm_change_fd); } s->perm_change_fd = 0; @@ -3158,7 +3193,7 @@ static void raw_abort_perm_update(BlockDriverState *bs) /* For reopen, .bdrv_reopen_abort is called afterwards and will close * the file descriptor. */ - if (s->perm_change_fd && !s->reopen_state) { + if (s->perm_change_fd) { qemu_close(s->perm_change_fd); } s->perm_change_fd = 0; @@ -3260,6 +3295,8 @@ BlockDriver bdrv_file = { /***********************************************/ /* host device */ +#if defined(HAVE_HOST_BLOCK_DEVICE) + #if defined(__APPLE__) && defined(__MACH__) static kern_return_t GetBSDPath(io_iterator_t mediaIterator, char *bsdPath, CFIndex maxPathSize, int flags); @@ -3552,16 +3589,6 @@ hdev_co_ioctl(BlockDriverState *bs, unsigned long int req, void *buf) } #endif /* linux */ -static int fd_open(BlockDriverState *bs) -{ - BDRVRawState *s = bs->opaque; - - /* this is just to ensure s->fd is sane (its called by io ops) */ - if (s->fd >= 0) - return 0; - return -EIO; -} - static coroutine_fn int hdev_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes) { @@ -3885,6 +3912,8 @@ static BlockDriver bdrv_host_cdrom = { }; #endif /* __FreeBSD__ */ +#endif /* HAVE_HOST_BLOCK_DEVICE */ + static void bdrv_file_init(void) { /* @@ -3892,6 +3921,7 @@ static void bdrv_file_init(void) * registered last will get probed first. */ bdrv_register(&bdrv_file); +#if defined(HAVE_HOST_BLOCK_DEVICE) bdrv_register(&bdrv_host_device); #ifdef __linux__ bdrv_register(&bdrv_host_cdrom); @@ -3899,6 +3929,7 @@ static void bdrv_file_init(void) #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__) bdrv_register(&bdrv_host_cdrom); #endif +#endif /* HAVE_HOST_BLOCK_DEVICE */ } block_init(bdrv_file_init); diff --git a/block/io.c b/block/io.c index ca2dca3007..a19942718b 100644 --- a/block/io.c +++ b/block/io.c @@ -30,6 +30,7 @@ #include "block/blockjob_int.h" #include "block/block_int.h" #include "block/coroutines.h" +#include "block/write-threshold.h" #include "qemu/cutils.h" #include "qapi/error.h" #include "qemu/error-report.h" @@ -124,8 +125,12 @@ void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll) static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src) { + dst->pdiscard_alignment = MAX(dst->pdiscard_alignment, + src->pdiscard_alignment); dst->opt_transfer = MAX(dst->opt_transfer, src->opt_transfer); dst->max_transfer = MIN_NON_ZERO(dst->max_transfer, src->max_transfer); + dst->max_hw_transfer = MIN_NON_ZERO(dst->max_hw_transfer, + src->max_hw_transfer); dst->opt_mem_alignment = MAX(dst->opt_mem_alignment, src->opt_mem_alignment); dst->min_mem_alignment = MAX(dst->min_mem_alignment, @@ -133,13 +138,40 @@ static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src) dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov); } -void bdrv_refresh_limits(BlockDriverState *bs, Error **errp) +typedef struct BdrvRefreshLimitsState { + BlockDriverState *bs; + BlockLimits old_bl; +} BdrvRefreshLimitsState; + +static void bdrv_refresh_limits_abort(void *opaque) +{ + BdrvRefreshLimitsState *s = opaque; + + s->bs->bl = s->old_bl; +} + +static TransactionActionDrv bdrv_refresh_limits_drv = { + .abort = bdrv_refresh_limits_abort, + .clean = g_free, +}; + +/* @tran is allowed to be NULL, in this case no rollback is possible. */ +void bdrv_refresh_limits(BlockDriverState *bs, Transaction *tran, Error **errp) { ERRP_GUARD(); BlockDriver *drv = bs->drv; BdrvChild *c; bool have_limits; + if (tran) { + BdrvRefreshLimitsState *s = g_new(BdrvRefreshLimitsState, 1); + *s = (BdrvRefreshLimitsState) { + .bs = bs, + .old_bl = bs->bl, + }; + tran_add(tran, &bdrv_refresh_limits_drv, s); + } + memset(&bs->bl, 0, sizeof(bs->bl)); if (!drv) { @@ -156,7 +188,7 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp) QLIST_FOREACH(c, &bs->children, next) { if (c->role & (BDRV_CHILD_DATA | BDRV_CHILD_FILTERED | BDRV_CHILD_COW)) { - bdrv_refresh_limits(c->bs, errp); + bdrv_refresh_limits(c->bs, tran, errp); if (*errp) { return; } @@ -1809,7 +1841,7 @@ int coroutine_fn bdrv_co_preadv_part(BdrvChild *child, ret = bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad, NULL); if (ret < 0) { - return ret; + goto fail; } tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_READ); @@ -1817,10 +1849,11 @@ int coroutine_fn bdrv_co_preadv_part(BdrvChild *child, bs->bl.request_alignment, qiov, qiov_offset, flags); tracked_request_end(&req); - bdrv_dec_in_flight(bs); - bdrv_padding_destroy(&pad); +fail: + bdrv_dec_in_flight(bs); + return ret; } @@ -1945,7 +1978,7 @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, int64_t bytes, bdrv_check_request(offset, bytes, &error_abort); - if (bs->read_only) { + if (bdrv_is_read_only(bs)) { return -EPERM; } @@ -1981,8 +2014,8 @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, int64_t bytes, } else { assert(child->perm & BLK_PERM_WRITE); } - return notifier_with_return_list_notify(&bs->before_write_notifiers, - req); + bdrv_write_threshold_check_write(bs, offset, bytes); + return 0; case BDRV_TRACKED_TRUNCATE: assert(child->perm & BLK_PERM_RESIZE); return 0; @@ -3137,12 +3170,6 @@ bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov) return true; } -void bdrv_add_before_write_notifier(BlockDriverState *bs, - NotifierWithReturn *notifier) -{ - notifier_with_return_list_add(&bs->before_write_notifiers, notifier); -} - void bdrv_io_plug(BlockDriverState *bs) { BdrvChild *child; @@ -3368,6 +3395,11 @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, return old_size; } + if (bdrv_is_read_only(bs)) { + error_setg(errp, "Image is read-only"); + return -EACCES; + } + if (offset > old_size) { new_bytes = offset - old_size; } else { @@ -3384,11 +3416,6 @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, if (new_bytes) { bdrv_make_request_serialising(&req, 1); } - if (bs->read_only) { - error_setg(errp, "Image is read-only"); - ret = -EACCES; - goto out; - } ret = bdrv_co_write_req_prepare(child, offset - new_bytes, new_bytes, &req, 0); if (ret < 0) { diff --git a/block/io_uring.c b/block/io_uring.c index 00a3ee9fb8..dfa475cc87 100644 --- a/block/io_uring.c +++ b/block/io_uring.c @@ -165,7 +165,21 @@ static void luring_process_completions(LuringState *s) total_bytes = ret + luringcb->total_read; if (ret < 0) { - if (ret == -EINTR) { + /* + * Only writev/readv/fsync requests on regular files or host block + * devices are submitted. Therefore -EAGAIN is not expected but it's + * known to happen sometimes with Linux SCSI. Submit again and hope + * the request completes successfully. + * + * For more information, see: + * https://lore.kernel.org/io-uring/20210727165811.284510-3-axboe@kernel.dk/T/#u + * + * If the code is changed to submit other types of requests in the + * future, then this workaround may need to be extended to deal with + * genuine -EAGAIN results that should not be resubmitted + * immediately. + */ + if (ret == -EINTR || ret == -EAGAIN) { luring_resubmit(s, luringcb); continue; } diff --git a/block/iscsi-opts.c b/block/iscsi-opts.c index afaf8837d6..4f2da405e6 100644 --- a/block/iscsi-opts.c +++ b/block/iscsi-opts.c @@ -68,3 +68,4 @@ static void iscsi_block_opts_init(void) } block_init(iscsi_block_opts_init); +module_opts("iscsi"); diff --git a/block/linux-aio.c b/block/linux-aio.c index 3c0527c2bf..0dab507b71 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c @@ -28,6 +28,9 @@ */ #define MAX_EVENTS 1024 +/* Maximum number of requests in a batch. (default value) */ +#define DEFAULT_MAX_BATCH 32 + struct qemu_laiocb { Coroutine *co; LinuxAioState *ctx; @@ -351,6 +354,10 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset, LinuxAioState *s = laiocb->ctx; struct iocb *iocbs = &laiocb->iocb; QEMUIOVector *qiov = laiocb->qiov; + int64_t max_batch = s->aio_context->aio_max_batch ?: DEFAULT_MAX_BATCH; + + /* limit the batch with the number of available events */ + max_batch = MIN_NON_ZERO(MAX_EVENTS - s->io_q.in_flight, max_batch); switch (type) { case QEMU_AIO_WRITE: @@ -371,7 +378,7 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset, s->io_q.in_queue++; if (!s->io_q.blocked && (!s->io_q.plugged || - s->io_q.in_flight + s->io_q.in_queue >= MAX_EVENTS)) { + s->io_q.in_queue >= max_batch)) { ioq_submit(s); } diff --git a/block/meson.build b/block/meson.build index d21990ec95..0450914c7a 100644 --- a/block/meson.build +++ b/block/meson.build @@ -13,6 +13,7 @@ block_ss.add(files( 'commit.c', 'copy-on-read.c', 'preallocate.c', + 'progress_meter.c', 'create.c', 'crypto.c', 'dirty-bitmap.c', @@ -64,27 +65,26 @@ block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit block_ss.add(when: libiscsi, if_true: files('iscsi-opts.c')) block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c')) block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c')) -block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c')) block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c')) -block_ss.add(when: ['CONFIG_LINUX_IO_URING', linux_io_uring], if_true: files('io_uring.c')) +block_ss.add(when: linux_io_uring, if_true: files('io_uring.c')) block_modules = {} modsrc = [] foreach m : [ - [curl, 'curl', [curl, glib], 'curl.c'], - [glusterfs, 'gluster', glusterfs, 'gluster.c'], - [libiscsi, 'iscsi', libiscsi, 'iscsi.c'], - [libnfs, 'nfs', libnfs, 'nfs.c'], - [libssh, 'ssh', libssh, 'ssh.c'], - [rbd, 'rbd', rbd, 'rbd.c'], + [curl, 'curl', files('curl.c')], + [glusterfs, 'gluster', files('gluster.c')], + [libiscsi, 'iscsi', [files('iscsi.c'), libm]], + [libnfs, 'nfs', files('nfs.c')], + [libssh, 'ssh', files('ssh.c')], + [rbd, 'rbd', files('rbd.c')], ] if m[0].found() - if enable_modules - modsrc += files(m[3]) - endif module_ss = ss.source_set() - module_ss.add(when: m[2], if_true: files(m[3])) + module_ss.add(when: m[0], if_true: m[2]) + if enable_modules + modsrc += module_ss.all_sources() + endif block_modules += {m[1] : module_ss} endif endforeach diff --git a/block/mirror.c b/block/mirror.c index 5a71bd8bbc..98fc66eabf 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -107,6 +107,7 @@ struct MirrorOp { bool is_in_flight; CoQueue waiting_requests; Coroutine *co; + MirrorOp *waiting_for_op; QTAILQ_ENTRY(MirrorOp) next; }; @@ -159,7 +160,18 @@ static void coroutine_fn mirror_wait_on_conflicts(MirrorOp *self, if (ranges_overlap(self_start_chunk, self_nb_chunks, op_start_chunk, op_nb_chunks)) { + /* + * If the operation is already (indirectly) waiting for us, or + * will wait for us as soon as it wakes up, then just go on + * (instead of producing a deadlock in the former case). + */ + if (op->waiting_for_op) { + continue; + } + + self->waiting_for_op = op; qemu_co_queue_wait(&op->waiting_requests, NULL); + self->waiting_for_op = NULL; break; } } @@ -1178,12 +1190,14 @@ static bool mirror_drained_poll(BlockJob *job) return !!s->in_flight; } -static void mirror_cancel(Job *job) +static void mirror_cancel(Job *job, bool force) { MirrorBlockJob *s = container_of(job, MirrorBlockJob, common.job); BlockDriverState *target = blk_bs(s->target); - bdrv_cancel_in_flight(target); + if (force || !job_is_ready(job)) { + bdrv_cancel_in_flight(target); + } } static const BlockJobDriver mirror_job_driver = { @@ -1341,6 +1355,7 @@ static MirrorOp *coroutine_fn active_write_prepare(MirrorBlockJob *s, .bytes = bytes, .is_active_write = true, .is_in_flight = true, + .co = qemu_coroutine_self(), }; qemu_co_queue_init(&op->waiting_requests); QTAILQ_INSERT_TAIL(&s->ops_in_flight, op, next); @@ -1630,9 +1645,6 @@ static BlockJob *mirror_start_job( bs_opaque->is_commit = target_is_backing; - /* bdrv_append takes ownership of the mirror_top_bs reference, need to keep - * it alive until block_job_create() succeeds even if bs has no parent. */ - bdrv_ref(mirror_top_bs); bdrv_drained_begin(bs); ret = bdrv_append(mirror_top_bs, bs, errp); bdrv_drained_end(bs); diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c index ebf1033f31..3e6670c963 100644 --- a/block/monitor/block-hmp-cmds.c +++ b/block/monitor/block-hmp-cmds.c @@ -557,8 +557,10 @@ void hmp_eject(Monitor *mon, const QDict *qdict) void hmp_qemu_io(Monitor *mon, const QDict *qdict) { - BlockBackend *blk; + BlockBackend *blk = NULL; + BlockDriverState *bs = NULL; BlockBackend *local_blk = NULL; + AioContext *ctx = NULL; bool qdev = qdict_get_try_bool(qdict, "qdev", false); const char *device = qdict_get_str(qdict, "device"); const char *command = qdict_get_str(qdict, "command"); @@ -573,20 +575,24 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) } else { blk = blk_by_name(device); if (!blk) { - BlockDriverState *bs = bdrv_lookup_bs(NULL, device, &err); - if (bs) { - blk = local_blk = blk_new(bdrv_get_aio_context(bs), - 0, BLK_PERM_ALL); - ret = blk_insert_bs(blk, bs, &err); - if (ret < 0) { - goto fail; - } - } else { + bs = bdrv_lookup_bs(NULL, device, &err); + if (!bs) { goto fail; } } } + ctx = blk ? blk_get_aio_context(blk) : bdrv_get_aio_context(bs); + aio_context_acquire(ctx); + + if (bs) { + blk = local_blk = blk_new(bdrv_get_aio_context(bs), 0, BLK_PERM_ALL); + ret = blk_insert_bs(blk, bs, &err); + if (ret < 0) { + goto fail; + } + } + /* * Notably absent: Proper permission management. This is sad, but it seems * almost impossible to achieve without changing the semantics and thereby @@ -616,6 +622,11 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) fail: blk_unref(local_blk); + + if (ctx) { + aio_context_release(ctx); + } + hmp_handle_error(mon, err); } diff --git a/block/nbd.c b/block/nbd.c index 1d4668d42d..f6ff1c4fb4 100644 --- a/block/nbd.c +++ b/block/nbd.c @@ -44,6 +44,7 @@ #include "block/qdict.h" #include "block/nbd.h" #include "block/block_int.h" +#include "block/coroutines.h" #include "qemu/yank.h" @@ -66,63 +67,19 @@ typedef enum NBDClientState { NBD_CLIENT_QUIT } NBDClientState; -typedef enum NBDConnectThreadState { - /* No thread, no pending results */ - CONNECT_THREAD_NONE, - - /* Thread is running, no results for now */ - CONNECT_THREAD_RUNNING, - - /* - * Thread is running, but requestor exited. Thread should close - * the new socket and free the connect state on exit. - */ - CONNECT_THREAD_RUNNING_DETACHED, - - /* Thread finished, results are stored in a state */ - CONNECT_THREAD_FAIL, - CONNECT_THREAD_SUCCESS -} NBDConnectThreadState; - -typedef struct NBDConnectThread { - /* Initialization constants */ - SocketAddress *saddr; /* address to connect to */ - /* - * Bottom half to schedule on completion. Scheduled only if bh_ctx is not - * NULL - */ - QEMUBHFunc *bh_func; - void *bh_opaque; - - /* - * Result of last attempt. Valid in FAIL and SUCCESS states. - * If you want to steal error, don't forget to set pointer to NULL. - */ - QIOChannelSocket *sioc; - Error *err; - - /* state and bh_ctx are protected by mutex */ - QemuMutex mutex; - NBDConnectThreadState state; /* current state of the thread */ - AioContext *bh_ctx; /* where to schedule bh (NULL means don't schedule) */ -} NBDConnectThread; - typedef struct BDRVNBDState { - QIOChannelSocket *sioc; /* The master data channel */ - QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */ + QIOChannel *ioc; /* The current I/O channel */ NBDExportInfo info; CoMutex send_mutex; CoQueue free_sema; Coroutine *connection_co; Coroutine *teardown_co; - QemuCoSleepState *connection_co_sleep_ns_state; + QemuCoSleep reconnect_sleep; bool drained; bool wait_drained_end; int in_flight; NBDClientState state; - int connect_status; - Error *connect_err; bool wait_in_flight; QEMUTimer *reconnect_delay_timer; @@ -140,20 +97,20 @@ typedef struct BDRVNBDState { char *x_dirty_bitmap; bool alloc_depth; - bool wait_connect; - NBDConnectThread *connect_thread; + NBDClientConnection *conn; } BDRVNBDState; -static int nbd_establish_connection(BlockDriverState *bs, SocketAddress *saddr, - Error **errp); -static int nbd_co_establish_connection(BlockDriverState *bs, Error **errp); -static void nbd_co_establish_connection_cancel(BlockDriverState *bs, - bool detach); -static int nbd_client_handshake(BlockDriverState *bs, Error **errp); static void nbd_yank(void *opaque); -static void nbd_clear_bdrvstate(BDRVNBDState *s) +static void nbd_clear_bdrvstate(BlockDriverState *bs) { + BDRVNBDState *s = (BDRVNBDState *)bs->opaque; + + nbd_client_connection_release(s->conn); + s->conn = NULL; + + yank_unregister_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name)); + object_unref(OBJECT(s->tlscreds)); qapi_free_SocketAddress(s->saddr); s->saddr = NULL; @@ -165,15 +122,20 @@ static void nbd_clear_bdrvstate(BDRVNBDState *s) s->x_dirty_bitmap = NULL; } +static bool nbd_client_connected(BDRVNBDState *s) +{ + return qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED; +} + static void nbd_channel_error(BDRVNBDState *s, int ret) { if (ret == -EIO) { - if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED) { + if (nbd_client_connected(s)) { s->state = s->reconnect_delay ? NBD_CLIENT_CONNECTING_WAIT : NBD_CLIENT_CONNECTING_NOWAIT; } } else { - if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED) { + if (nbd_client_connected(s)) { qio_channel_shutdown(s->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); } s->state = NBD_CLIENT_QUIT; @@ -188,6 +150,7 @@ static void nbd_recv_coroutines_wake_all(BDRVNBDState *s) NBDClientRequest *req = &s->requests[i]; if (req->coroutine && req->receiving) { + req->receiving = false; aio_co_wake(req->coroutine); } } @@ -271,7 +234,7 @@ static void nbd_client_attach_aio_context(BlockDriverState *bs, * s->connection_co is either yielded from nbd_receive_reply or from * nbd_co_reconnect_loop() */ - if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED) { + if (nbd_client_connected(s)) { qio_channel_attach_aio_context(QIO_CHANNEL(s->ioc), new_context); } @@ -289,11 +252,9 @@ static void coroutine_fn nbd_client_co_drain_begin(BlockDriverState *bs) BDRVNBDState *s = (BDRVNBDState *)bs->opaque; s->drained = true; - if (s->connection_co_sleep_ns_state) { - qemu_co_sleep_wake(s->connection_co_sleep_ns_state); - } + qemu_co_sleep_wake(&s->reconnect_sleep); - nbd_co_establish_connection_cancel(bs, false); + nbd_co_establish_connection_cancel(s->conn); reconnect_delay_timer_del(s); @@ -322,18 +283,12 @@ static void nbd_teardown_connection(BlockDriverState *bs) if (s->ioc) { /* finish any pending coroutines */ qio_channel_shutdown(s->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); - } else if (s->sioc) { - /* abort negotiation */ - qio_channel_shutdown(QIO_CHANNEL(s->sioc), QIO_CHANNEL_SHUTDOWN_BOTH, - NULL); } s->state = NBD_CLIENT_QUIT; if (s->connection_co) { - if (s->connection_co_sleep_ns_state) { - qemu_co_sleep_wake(s->connection_co_sleep_ns_state); - } - nbd_co_establish_connection_cancel(bs, true); + qemu_co_sleep_wake(&s->reconnect_sleep); + nbd_co_establish_connection_cancel(s->conn); } if (qemu_in_coroutine()) { s->teardown_co = qemu_coroutine_self(); @@ -358,239 +313,97 @@ static bool nbd_client_connecting_wait(BDRVNBDState *s) return qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTING_WAIT; } -static void connect_bh(void *opaque) -{ - BDRVNBDState *state = opaque; - - assert(state->wait_connect); - state->wait_connect = false; - aio_co_wake(state->connection_co); -} - -static void nbd_init_connect_thread(BDRVNBDState *s) -{ - s->connect_thread = g_new(NBDConnectThread, 1); - - *s->connect_thread = (NBDConnectThread) { - .saddr = QAPI_CLONE(SocketAddress, s->saddr), - .state = CONNECT_THREAD_NONE, - .bh_func = connect_bh, - .bh_opaque = s, - }; - - qemu_mutex_init(&s->connect_thread->mutex); -} - -static void nbd_free_connect_thread(NBDConnectThread *thr) -{ - if (thr->sioc) { - qio_channel_close(QIO_CHANNEL(thr->sioc), NULL); - } - error_free(thr->err); - qapi_free_SocketAddress(thr->saddr); - g_free(thr); -} - -static void *connect_thread_func(void *opaque) -{ - NBDConnectThread *thr = opaque; - int ret; - bool do_free = false; - - thr->sioc = qio_channel_socket_new(); - - error_free(thr->err); - thr->err = NULL; - ret = qio_channel_socket_connect_sync(thr->sioc, thr->saddr, &thr->err); - if (ret < 0) { - object_unref(OBJECT(thr->sioc)); - thr->sioc = NULL; - } - - qemu_mutex_lock(&thr->mutex); - - switch (thr->state) { - case CONNECT_THREAD_RUNNING: - thr->state = ret < 0 ? CONNECT_THREAD_FAIL : CONNECT_THREAD_SUCCESS; - if (thr->bh_ctx) { - aio_bh_schedule_oneshot(thr->bh_ctx, thr->bh_func, thr->bh_opaque); - - /* play safe, don't reuse bh_ctx on further connection attempts */ - thr->bh_ctx = NULL; - } - break; - case CONNECT_THREAD_RUNNING_DETACHED: - do_free = true; - break; - default: - abort(); - } - - qemu_mutex_unlock(&thr->mutex); - - if (do_free) { - nbd_free_connect_thread(thr); - } - - return NULL; -} - -static int coroutine_fn -nbd_co_establish_connection(BlockDriverState *bs, Error **errp) -{ - int ret; - QemuThread thread; - BDRVNBDState *s = bs->opaque; - NBDConnectThread *thr = s->connect_thread; - - if (!thr) { - /* detached */ - return -1; - } - - qemu_mutex_lock(&thr->mutex); - - switch (thr->state) { - case CONNECT_THREAD_FAIL: - case CONNECT_THREAD_NONE: - error_free(thr->err); - thr->err = NULL; - thr->state = CONNECT_THREAD_RUNNING; - qemu_thread_create(&thread, "nbd-connect", - connect_thread_func, thr, QEMU_THREAD_DETACHED); - break; - case CONNECT_THREAD_SUCCESS: - /* Previous attempt finally succeeded in background */ - thr->state = CONNECT_THREAD_NONE; - s->sioc = thr->sioc; - thr->sioc = NULL; - yank_register_function(BLOCKDEV_YANK_INSTANCE(bs->node_name), - nbd_yank, bs); - qemu_mutex_unlock(&thr->mutex); - return 0; - case CONNECT_THREAD_RUNNING: - /* Already running, will wait */ - break; - default: - abort(); - } - - thr->bh_ctx = qemu_get_current_aio_context(); - - qemu_mutex_unlock(&thr->mutex); - - - /* - * We are going to wait for connect-thread finish, but - * nbd_client_co_drain_begin() can interrupt. - * - * Note that wait_connect variable is not visible for connect-thread. It - * doesn't need mutex protection, it used only inside home aio context of - * bs. - */ - s->wait_connect = true; - qemu_coroutine_yield(); - - if (!s->connect_thread) { - /* detached */ - return -1; - } - assert(thr == s->connect_thread); - - qemu_mutex_lock(&thr->mutex); - - switch (thr->state) { - case CONNECT_THREAD_SUCCESS: - case CONNECT_THREAD_FAIL: - thr->state = CONNECT_THREAD_NONE; - error_propagate(errp, thr->err); - thr->err = NULL; - s->sioc = thr->sioc; - thr->sioc = NULL; - if (s->sioc) { - yank_register_function(BLOCKDEV_YANK_INSTANCE(bs->node_name), - nbd_yank, bs); - } - ret = (s->sioc ? 0 : -1); - break; - case CONNECT_THREAD_RUNNING: - case CONNECT_THREAD_RUNNING_DETACHED: - /* - * Obviously, drained section wants to start. Report the attempt as - * failed. Still connect thread is executing in background, and its - * result may be used for next connection attempt. - */ - ret = -1; - error_setg(errp, "Connection attempt cancelled by other operation"); - break; - - case CONNECT_THREAD_NONE: - /* - * Impossible. We've seen this thread running. So it should be - * running or at least give some results. - */ - abort(); - - default: - abort(); - } - - qemu_mutex_unlock(&thr->mutex); - - return ret; -} - /* - * nbd_co_establish_connection_cancel - * Cancel nbd_co_establish_connection asynchronously: it will finish soon, to - * allow drained section to begin. - * - * If detach is true, also cleanup the state (or if thread is running, move it - * to CONNECT_THREAD_RUNNING_DETACHED state). s->connect_thread becomes NULL if - * detach is true. + * Update @bs with information learned during a completed negotiation process. + * Return failure if the server's advertised options are incompatible with the + * client's needs. */ -static void nbd_co_establish_connection_cancel(BlockDriverState *bs, - bool detach) +static int nbd_handle_updated_info(BlockDriverState *bs, Error **errp) { - BDRVNBDState *s = bs->opaque; - NBDConnectThread *thr = s->connect_thread; - bool wake = false; - bool do_free = false; + BDRVNBDState *s = (BDRVNBDState *)bs->opaque; + int ret; - qemu_mutex_lock(&thr->mutex); - - if (thr->state == CONNECT_THREAD_RUNNING) { - /* We can cancel only in running state, when bh is not yet scheduled */ - thr->bh_ctx = NULL; - if (s->wait_connect) { - s->wait_connect = false; - wake = true; + if (s->x_dirty_bitmap) { + if (!s->info.base_allocation) { + error_setg(errp, "requested x-dirty-bitmap %s not found", + s->x_dirty_bitmap); + return -EINVAL; } - if (detach) { - thr->state = CONNECT_THREAD_RUNNING_DETACHED; - s->connect_thread = NULL; + if (strcmp(s->x_dirty_bitmap, "qemu:allocation-depth") == 0) { + s->alloc_depth = true; } - } else if (detach) { - do_free = true; } - qemu_mutex_unlock(&thr->mutex); - - if (do_free) { - nbd_free_connect_thread(thr); - s->connect_thread = NULL; + if (s->info.flags & NBD_FLAG_READ_ONLY) { + ret = bdrv_apply_auto_read_only(bs, "NBD export is read-only", errp); + if (ret < 0) { + return ret; + } } - if (wake) { - aio_co_wake(s->connection_co); + if (s->info.flags & NBD_FLAG_SEND_FUA) { + bs->supported_write_flags = BDRV_REQ_FUA; + bs->supported_zero_flags |= BDRV_REQ_FUA; } + + if (s->info.flags & NBD_FLAG_SEND_WRITE_ZEROES) { + bs->supported_zero_flags |= BDRV_REQ_MAY_UNMAP; + if (s->info.flags & NBD_FLAG_SEND_FAST_ZERO) { + bs->supported_zero_flags |= BDRV_REQ_NO_FALLBACK; + } + } + + trace_nbd_client_handshake_success(s->export); + + return 0; +} + +int coroutine_fn nbd_co_do_establish_connection(BlockDriverState *bs, + Error **errp) +{ + BDRVNBDState *s = (BDRVNBDState *)bs->opaque; + int ret; + + assert(!s->ioc); + + s->ioc = nbd_co_establish_connection(s->conn, &s->info, true, errp); + if (!s->ioc) { + return -ECONNREFUSED; + } + + yank_register_function(BLOCKDEV_YANK_INSTANCE(s->bs->node_name), nbd_yank, + bs); + + ret = nbd_handle_updated_info(s->bs, NULL); + if (ret < 0) { + /* + * We have connected, but must fail for other reasons. + * Send NBD_CMD_DISC as a courtesy to the server. + */ + NBDRequest request = { .type = NBD_CMD_DISC }; + + nbd_send_request(s->ioc, &request); + + yank_unregister_function(BLOCKDEV_YANK_INSTANCE(s->bs->node_name), + nbd_yank, bs); + object_unref(OBJECT(s->ioc)); + s->ioc = NULL; + + return ret; + } + + qio_channel_set_blocking(s->ioc, false, NULL); + qio_channel_attach_aio_context(s->ioc, bdrv_get_aio_context(bs)); + + /* successfully connected */ + s->state = NBD_CLIENT_CONNECTED; + qemu_co_queue_restart_all(&s->free_sema); + + return 0; } static coroutine_fn void nbd_reconnect_attempt(BDRVNBDState *s) { - int ret; - Error *local_err = NULL; - if (!nbd_client_connecting(s)) { return; } @@ -624,44 +437,11 @@ static coroutine_fn void nbd_reconnect_attempt(BDRVNBDState *s) qio_channel_detach_aio_context(QIO_CHANNEL(s->ioc)); yank_unregister_function(BLOCKDEV_YANK_INSTANCE(s->bs->node_name), nbd_yank, s->bs); - object_unref(OBJECT(s->sioc)); - s->sioc = NULL; object_unref(OBJECT(s->ioc)); s->ioc = NULL; } - if (nbd_co_establish_connection(s->bs, &local_err) < 0) { - ret = -ECONNREFUSED; - goto out; - } - - bdrv_dec_in_flight(s->bs); - - ret = nbd_client_handshake(s->bs, &local_err); - - if (s->drained) { - s->wait_drained_end = true; - while (s->drained) { - /* - * We may be entered once from nbd_client_attach_aio_context_bh - * and then from nbd_client_co_drain_end. So here is a loop. - */ - qemu_coroutine_yield(); - } - } - bdrv_inc_in_flight(s->bs); - -out: - s->connect_status = ret; - error_free(s->connect_err); - s->connect_err = NULL; - error_propagate(&s->connect_err, local_err); - - if (ret >= 0) { - /* successfully connected */ - s->state = NBD_CLIENT_CONNECTED; - qemu_co_queue_restart_all(&s->free_sema); - } + nbd_co_do_establish_connection(s->bs, NULL); } static coroutine_fn void nbd_co_reconnect_loop(BDRVNBDState *s) @@ -689,8 +469,8 @@ static coroutine_fn void nbd_co_reconnect_loop(BDRVNBDState *s) } bdrv_inc_in_flight(s->bs); } else { - qemu_co_sleep_ns_wakeable(QEMU_CLOCK_REALTIME, timeout, - &s->connection_co_sleep_ns_state); + qemu_co_sleep_ns_wakeable(&s->reconnect_sleep, + QEMU_CLOCK_REALTIME, timeout); if (s->drained) { continue; } @@ -727,7 +507,7 @@ static coroutine_fn void nbd_connection_entry(void *opaque) nbd_co_reconnect_loop(s); } - if (qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) { + if (!nbd_client_connected(s)) { continue; } @@ -771,6 +551,7 @@ static coroutine_fn void nbd_connection_entry(void *opaque) * connection_co happens through a bottom half, which can only * run after we yield. */ + s->requests[i].receiving = false; aio_co_wake(s->requests[i].coroutine); qemu_coroutine_yield(); } @@ -784,8 +565,6 @@ static coroutine_fn void nbd_connection_entry(void *opaque) qio_channel_detach_aio_context(QIO_CHANNEL(s->ioc)); yank_unregister_function(BLOCKDEV_YANK_INSTANCE(s->bs->node_name), nbd_yank, s->bs); - object_unref(OBJECT(s->sioc)); - s->sioc = NULL; object_unref(OBJECT(s->ioc)); s->ioc = NULL; } @@ -808,7 +587,7 @@ static int nbd_co_send_request(BlockDriverState *bs, qemu_co_queue_wait(&s->free_sema, &s->send_mutex); } - if (qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) { + if (!nbd_client_connected(s)) { rc = -EIO; goto err; } @@ -835,8 +614,7 @@ static int nbd_co_send_request(BlockDriverState *bs, if (qiov) { qio_channel_set_cork(s->ioc, true); rc = nbd_send_request(s->ioc, request); - if (qatomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED && - rc >= 0) { + if (nbd_client_connected(s) && rc >= 0) { if (qio_channel_writev_all(s->ioc, qiov->iov, qiov->niov, NULL) < 0) { rc = -EIO; @@ -1160,8 +938,8 @@ static coroutine_fn int nbd_co_do_receive_one_chunk( /* Wait until we're woken up by nbd_connection_entry. */ s->requests[i].receiving = true; qemu_coroutine_yield(); - s->requests[i].receiving = false; - if (qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) { + assert(!s->requests[i].receiving); + if (!nbd_client_connected(s)) { error_setg(errp, "Connection closed"); return -EIO; } @@ -1320,7 +1098,7 @@ static bool nbd_reply_chunk_iter_receive(BDRVNBDState *s, NBDReply local_reply; NBDStructuredReplyChunk *chunk; Error *local_err = NULL; - if (qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) { + if (!nbd_client_connected(s)) { error_setg(&local_err, "Connection closed"); nbd_iter_channel_error(iter, -EIO, &local_err); goto break_loop; @@ -1345,8 +1123,7 @@ static bool nbd_reply_chunk_iter_receive(BDRVNBDState *s, } /* Do not execute the body of NBD_FOREACH_REPLY_CHUNK for simple reply. */ - if (nbd_reply_is_simple(reply) || - qatomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) { + if (nbd_reply_is_simple(reply) || !nbd_client_connected(s)) { goto break_loop; } @@ -1784,7 +1561,7 @@ static void nbd_yank(void *opaque) BDRVNBDState *s = (BDRVNBDState *)bs->opaque; qatomic_store_release(&s->state, NBD_CLIENT_QUIT); - qio_channel_shutdown(QIO_CHANNEL(s->sioc), QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + qio_channel_shutdown(QIO_CHANNEL(s->ioc), QIO_CHANNEL_SHUTDOWN_BOTH, NULL); } static void nbd_client_close(BlockDriverState *bs) @@ -1799,111 +1576,6 @@ static void nbd_client_close(BlockDriverState *bs) nbd_teardown_connection(bs); } -static int nbd_establish_connection(BlockDriverState *bs, - SocketAddress *saddr, - Error **errp) -{ - ERRP_GUARD(); - BDRVNBDState *s = (BDRVNBDState *)bs->opaque; - - s->sioc = qio_channel_socket_new(); - qio_channel_set_name(QIO_CHANNEL(s->sioc), "nbd-client"); - - qio_channel_socket_connect_sync(s->sioc, saddr, errp); - if (*errp) { - object_unref(OBJECT(s->sioc)); - s->sioc = NULL; - return -1; - } - - yank_register_function(BLOCKDEV_YANK_INSTANCE(bs->node_name), nbd_yank, bs); - qio_channel_set_delay(QIO_CHANNEL(s->sioc), false); - - return 0; -} - -/* nbd_client_handshake takes ownership on s->sioc. On failure it's unref'ed. */ -static int nbd_client_handshake(BlockDriverState *bs, Error **errp) -{ - BDRVNBDState *s = (BDRVNBDState *)bs->opaque; - AioContext *aio_context = bdrv_get_aio_context(bs); - int ret; - - trace_nbd_client_handshake(s->export); - qio_channel_set_blocking(QIO_CHANNEL(s->sioc), false, NULL); - qio_channel_attach_aio_context(QIO_CHANNEL(s->sioc), aio_context); - - s->info.request_sizes = true; - s->info.structured_reply = true; - s->info.base_allocation = true; - s->info.x_dirty_bitmap = g_strdup(s->x_dirty_bitmap); - s->info.name = g_strdup(s->export ?: ""); - ret = nbd_receive_negotiate(aio_context, QIO_CHANNEL(s->sioc), s->tlscreds, - s->hostname, &s->ioc, &s->info, errp); - g_free(s->info.x_dirty_bitmap); - g_free(s->info.name); - if (ret < 0) { - yank_unregister_function(BLOCKDEV_YANK_INSTANCE(bs->node_name), - nbd_yank, bs); - object_unref(OBJECT(s->sioc)); - s->sioc = NULL; - return ret; - } - if (s->x_dirty_bitmap) { - if (!s->info.base_allocation) { - error_setg(errp, "requested x-dirty-bitmap %s not found", - s->x_dirty_bitmap); - ret = -EINVAL; - goto fail; - } - if (strcmp(s->x_dirty_bitmap, "qemu:allocation-depth") == 0) { - s->alloc_depth = true; - } - } - if (s->info.flags & NBD_FLAG_READ_ONLY) { - ret = bdrv_apply_auto_read_only(bs, "NBD export is read-only", errp); - if (ret < 0) { - goto fail; - } - } - if (s->info.flags & NBD_FLAG_SEND_FUA) { - bs->supported_write_flags = BDRV_REQ_FUA; - bs->supported_zero_flags |= BDRV_REQ_FUA; - } - if (s->info.flags & NBD_FLAG_SEND_WRITE_ZEROES) { - bs->supported_zero_flags |= BDRV_REQ_MAY_UNMAP; - if (s->info.flags & NBD_FLAG_SEND_FAST_ZERO) { - bs->supported_zero_flags |= BDRV_REQ_NO_FALLBACK; - } - } - - if (!s->ioc) { - s->ioc = QIO_CHANNEL(s->sioc); - object_ref(OBJECT(s->ioc)); - } - - trace_nbd_client_handshake_success(s->export); - - return 0; - - fail: - /* - * We have connected, but must fail for other reasons. - * Send NBD_CMD_DISC as a courtesy to the server. - */ - { - NBDRequest request = { .type = NBD_CMD_DISC }; - - nbd_send_request(s->ioc ?: QIO_CHANNEL(s->sioc), &request); - - yank_unregister_function(BLOCKDEV_YANK_INSTANCE(bs->node_name), - nbd_yank, bs); - object_unref(OBJECT(s->sioc)); - s->sioc = NULL; - - return ret; - } -} /* * Parse nbd_open options @@ -2137,6 +1809,12 @@ static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options, goto done; } + if (socket_address_parse_named_fd(saddr, errp) < 0) { + qapi_free_SocketAddress(saddr); + saddr = NULL; + goto done; + } + done: qobject_unref(addr); visit_free(iv); @@ -2163,9 +1841,9 @@ static QCryptoTLSCreds *nbd_get_tls_creds(const char *id, Error **errp) return NULL; } - if (creds->endpoint != QCRYPTO_TLS_CREDS_ENDPOINT_CLIENT) { - error_setg(errp, - "Expecting TLS credentials with a client endpoint"); + if (!qcrypto_tls_creds_check_endpoint(creds, + QCRYPTO_TLS_CREDS_ENDPOINT_CLIENT, + errp)) { return NULL; } object_ref(obj); @@ -2278,9 +1956,6 @@ static int nbd_process_options(BlockDriverState *bs, QDict *options, ret = 0; error: - if (ret < 0) { - nbd_clear_bdrvstate(s); - } qemu_opts_del(opts); return ret; } @@ -2291,11 +1966,6 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags, int ret; BDRVNBDState *s = (BDRVNBDState *)bs->opaque; - ret = nbd_process_options(bs, options, errp); - if (ret < 0) { - return ret; - } - s->bs = bs; qemu_co_mutex_init(&s->send_mutex); qemu_co_queue_init(&s->free_sema); @@ -2304,31 +1974,29 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags, return -EEXIST; } - /* - * establish TCP connection, return error if it fails - * TODO: Configurable retry-until-timeout behaviour. - */ - if (nbd_establish_connection(bs, s->saddr, errp) < 0) { - yank_unregister_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name)); - return -ECONNREFUSED; - } - - ret = nbd_client_handshake(bs, errp); + ret = nbd_process_options(bs, options, errp); if (ret < 0) { - yank_unregister_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name)); - nbd_clear_bdrvstate(s); - return ret; + goto fail; } - /* successfully connected */ - s->state = NBD_CLIENT_CONNECTED; - nbd_init_connect_thread(s); + s->conn = nbd_client_connection_new(s->saddr, true, s->export, + s->x_dirty_bitmap, s->tlscreds); + + /* TODO: Configurable retry-until-timeout behaviour. */ + ret = nbd_do_establish_connection(bs, errp); + if (ret < 0) { + goto fail; + } s->connection_co = qemu_coroutine_create(nbd_connection_entry, s); bdrv_inc_in_flight(bs); aio_co_schedule(bdrv_get_aio_context(bs), s->connection_co); return 0; + +fail: + nbd_clear_bdrvstate(bs); + return ret; } static int nbd_co_flush(BlockDriverState *bs) @@ -2372,11 +2040,8 @@ static void nbd_refresh_limits(BlockDriverState *bs, Error **errp) static void nbd_close(BlockDriverState *bs) { - BDRVNBDState *s = bs->opaque; - nbd_client_close(bs); - yank_unregister_instance(BLOCKDEV_YANK_INSTANCE(bs->node_name)); - nbd_clear_bdrvstate(s); + nbd_clear_bdrvstate(bs); } /* diff --git a/block/nfs.c b/block/nfs.c index 8c1968bb41..9aeaefb364 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -39,7 +39,6 @@ #include "qemu/option.h" #include "qemu/uri.h" #include "qemu/cutils.h" -#include "sysemu/sysemu.h" #include "sysemu/replay.h" #include "qapi/qapi-visit-block-core.h" #include "qapi/qmp/qdict.h" @@ -148,9 +147,7 @@ out: if (qp) { query_params_free(qp); } - if (uri) { - uri_free(uri); - } + uri_free(uri); return ret; } diff --git a/block/nvme.c b/block/nvme.c index 2b5421e7aa..e8dbbc2317 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -1030,7 +1030,29 @@ try_map: r = qemu_vfio_dma_map(s->vfio, qiov->iov[i].iov_base, len, true, &iova); + if (r == -ENOSPC) { + /* + * In addition to the -ENOMEM error, the VFIO_IOMMU_MAP_DMA + * ioctl returns -ENOSPC to signal the user exhausted the DMA + * mappings available for a container since Linux kernel commit + * 492855939bdb ("vfio/type1: Limit DMA mappings per container", + * April 2019, see CVE-2019-3882). + * + * This block driver already handles this error path by checking + * for the -ENOMEM error, so we directly replace -ENOSPC by + * -ENOMEM. Beside, -ENOSPC has a specific meaning for blockdev + * coroutines: it triggers BLOCKDEV_ON_ERROR_ENOSPC and + * BLOCK_ERROR_ACTION_STOP which stops the VM, asking the operator + * to add more storage to the blockdev. Not something we can do + * easily with an IOMMU :) + */ + r = -ENOMEM; + } if (r == -ENOMEM && retry) { + /* + * We exhausted the DMA mappings available for our container: + * recycle the volatile IOVA mappings. + */ retry = false; trace_nvme_dma_flush_queue_wait(s); if (s->dma_map_count) { diff --git a/block/progress_meter.c b/block/progress_meter.c new file mode 100644 index 0000000000..aa2e60248c --- /dev/null +++ b/block/progress_meter.c @@ -0,0 +1,64 @@ +/* + * Helper functionality for some process progress tracking. + * + * Copyright (c) 2011 IBM Corp. + * Copyright (c) 2012, 2018 Red Hat, Inc. + * Copyright (c) 2020 Virtuozzo International GmbH + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#include "qemu/osdep.h" +#include "qemu/progress_meter.h" + +void progress_init(ProgressMeter *pm) +{ + qemu_mutex_init(&pm->lock); +} + +void progress_destroy(ProgressMeter *pm) +{ + qemu_mutex_destroy(&pm->lock); +} + +void progress_get_snapshot(ProgressMeter *pm, uint64_t *current, + uint64_t *total) +{ + QEMU_LOCK_GUARD(&pm->lock); + + *current = pm->current; + *total = pm->total; +} + +void progress_work_done(ProgressMeter *pm, uint64_t done) +{ + QEMU_LOCK_GUARD(&pm->lock); + pm->current += done; +} + +void progress_set_remaining(ProgressMeter *pm, uint64_t remaining) +{ + QEMU_LOCK_GUARD(&pm->lock); + pm->total = pm->current + remaining; +} + +void progress_increase_remaining(ProgressMeter *pm, uint64_t delta) +{ + QEMU_LOCK_GUARD(&pm->lock); + pm->total += delta; +} diff --git a/block/qapi.c b/block/qapi.c index 943e7b15ad..cf557e3aea 100644 --- a/block/qapi.c +++ b/block/qapi.c @@ -59,7 +59,7 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk, info = g_malloc0(sizeof(*info)); info->file = g_strdup(bs->filename); - info->ro = bs->read_only; + info->ro = bdrv_is_read_only(bs); info->drv = g_strdup(bs->drv->format_name); info->encrypted = bs->encrypted; @@ -663,10 +663,8 @@ BlockStatsList *qmp_query_blockstats(bool has_query_nodes, void bdrv_snapshot_dump(QEMUSnapshotInfo *sn) { - char date_buf[128], clock_buf[128]; + char clock_buf[128]; char icount_buf[128] = {0}; - struct tm tm; - time_t ti; int64_t secs; char *sizing = NULL; @@ -674,10 +672,9 @@ void bdrv_snapshot_dump(QEMUSnapshotInfo *sn) qemu_printf("%-10s%-17s%8s%20s%13s%11s", "ID", "TAG", "VM SIZE", "DATE", "VM CLOCK", "ICOUNT"); } else { - ti = sn->date_sec; - localtime_r(&ti, &tm); - strftime(date_buf, sizeof(date_buf), - "%Y-%m-%d %H:%M:%S", &tm); + g_autoptr(GDateTime) date = g_date_time_new_from_unix_local(sn->date_sec); + g_autofree char *date_buf = g_date_time_format(date, "%Y-%m-%d %H:%M:%S"); + secs = sn->vm_clock_nsec / 1000000000; snprintf(clock_buf, sizeof(clock_buf), "%02d:%02d:%02d.%03d", diff --git a/block/qcow2-snapshot.c b/block/qcow2-snapshot.c index 2e98c7f4b6..71ddb08c21 100644 --- a/block/qcow2-snapshot.c +++ b/block/qcow2-snapshot.c @@ -1026,7 +1026,7 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs, int new_l1_bytes; int ret; - assert(bs->read_only); + assert(bdrv_is_read_only(bs)); /* Search the snapshot */ snapshot_index = find_snapshot_by_id_and_name(bs, snapshot_id, name); diff --git a/block/qcow2.c b/block/qcow2.c index 9727ae8fe3..9f1b6461c8 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -1723,8 +1723,7 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, /* Clear unknown autoclear feature bits */ update_header |= s->autoclear_features & ~QCOW2_AUTOCLEAR_MASK; - update_header = - update_header && !bs->read_only && !(flags & BDRV_O_INACTIVE); + update_header = update_header && bdrv_is_writable(bs); if (update_header) { s->autoclear_features &= QCOW2_AUTOCLEAR_MASK; } @@ -1811,7 +1810,7 @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, bs->supported_truncate_flags = BDRV_REQ_ZERO_WRITE; /* Repair image if dirty */ - if (!(flags & (BDRV_O_CHECK | BDRV_O_INACTIVE)) && !bs->read_only && + if (!(flags & BDRV_O_CHECK) && bdrv_is_writable(bs) && (s->incompatible_features & QCOW2_INCOMPAT_DIRTY)) { BdrvCheckResult result = {0}; @@ -1927,6 +1926,7 @@ static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp) static int qcow2_reopen_prepare(BDRVReopenState *state, BlockReopenQueue *queue, Error **errp) { + BDRVQcow2State *s = state->bs->opaque; Qcow2ReopenState *r; int ret; @@ -1957,6 +1957,16 @@ static int qcow2_reopen_prepare(BDRVReopenState *state, } } + /* + * Without an external data file, s->data_file points to the same BdrvChild + * as bs->file. It needs to be resynced after reopen because bs->file may + * be changed. We can't use it in the meantime. + */ + if (!has_data_file(state->bs)) { + assert(s->data_file == state->bs->file); + s->data_file = NULL; + } + return 0; fail: @@ -1967,7 +1977,16 @@ fail: static void qcow2_reopen_commit(BDRVReopenState *state) { + BDRVQcow2State *s = state->bs->opaque; + qcow2_update_options_commit(state->bs, state->opaque); + if (!s->data_file) { + /* + * If we don't have an external data file, s->data_file was cleared by + * qcow2_reopen_prepare() and needs to be updated. + */ + s->data_file = state->bs->file; + } g_free(state->opaque); } @@ -1991,6 +2010,15 @@ static void qcow2_reopen_commit_post(BDRVReopenState *state) static void qcow2_reopen_abort(BDRVReopenState *state) { + BDRVQcow2State *s = state->bs->opaque; + + if (!s->data_file) { + /* + * If we don't have an external data file, s->data_file was cleared by + * qcow2_reopen_prepare() and needs to be restored. + */ + s->data_file = state->bs->file; + } qcow2_update_options_abort(state->bs, state->opaque); g_free(state->opaque); } @@ -5089,6 +5117,7 @@ static int qcow2_get_info(BlockDriverState *bs, BlockDriverInfo *bdi) BDRVQcow2State *s = bs->opaque; bdi->cluster_size = s->cluster_size; bdi->vm_state_offset = qcow2_vm_state_offset(s); + bdi->is_dirty = s->incompatible_features & QCOW2_INCOMPAT_DIRTY; return 0; } @@ -5620,15 +5649,10 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, if (backing_file || backing_format) { if (g_strcmp0(backing_file, s->image_backing_file) || g_strcmp0(backing_format, s->image_backing_format)) { - warn_report("Deprecated use of amend to alter the backing file; " - "use qemu-img rebase instead"); - } - ret = qcow2_change_backing_file(bs, - backing_file ?: s->image_backing_file, - backing_format ?: s->image_backing_format); - if (ret < 0) { - error_setg_errno(errp, -ret, "Failed to change the backing file"); - return ret; + error_setg(errp, "Cannot amend the backing file"); + error_append_hint(errp, + "You can use 'qemu-img rebase' instead.\n"); + return -EINVAL; } } diff --git a/block/quorum.c b/block/quorum.c index cfc1436abb..f2c0805000 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -1279,7 +1279,7 @@ static BlockDriver bdrv_quorum = { .bdrv_dirname = quorum_dirname, .bdrv_co_block_status = quorum_co_block_status, - .bdrv_co_flush_to_disk = quorum_co_flush, + .bdrv_co_flush = quorum_co_flush, .bdrv_getlength = quorum_getlength, diff --git a/block/rbd.c b/block/rbd.c index f098a89c7b..dcf82b15b8 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -55,49 +55,30 @@ * leading "\". */ -/* rbd_aio_discard added in 0.1.2 */ -#if LIBRBD_VERSION_CODE >= LIBRBD_VERSION(0, 1, 2) -#define LIBRBD_SUPPORTS_DISCARD -#else -#undef LIBRBD_SUPPORTS_DISCARD -#endif - #define OBJ_MAX_SIZE (1UL << OBJ_DEFAULT_OBJ_ORDER) #define RBD_MAX_SNAPS 100 -/* The LIBRBD_SUPPORTS_IOVEC is defined in librbd.h */ -#ifdef LIBRBD_SUPPORTS_IOVEC -#define LIBRBD_USE_IOVEC 1 -#else -#define LIBRBD_USE_IOVEC 0 -#endif +#define RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN 8 + +static const char rbd_luks_header_verification[ + RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN] = { + 'L', 'U', 'K', 'S', 0xBA, 0xBE, 0, 1 +}; + +static const char rbd_luks2_header_verification[ + RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN] = { + 'L', 'U', 'K', 'S', 0xBA, 0xBE, 0, 2 +}; typedef enum { RBD_AIO_READ, RBD_AIO_WRITE, RBD_AIO_DISCARD, - RBD_AIO_FLUSH + RBD_AIO_FLUSH, + RBD_AIO_WRITE_ZEROES } RBDAIOCmd; -typedef struct RBDAIOCB { - BlockAIOCB common; - int64_t ret; - QEMUIOVector *qiov; - char *bounce; - RBDAIOCmd cmd; - int error; - struct BDRVRBDState *s; -} RBDAIOCB; - -typedef struct RADOSCB { - RBDAIOCB *acb; - struct BDRVRBDState *s; - int64_t size; - char *buf; - int64_t ret; -} RADOSCB; - typedef struct BDRVRBDState { rados_t cluster; rados_ioctx_t io_ctx; @@ -106,28 +87,46 @@ typedef struct BDRVRBDState { char *snap; char *namespace; uint64_t image_size; + uint64_t object_size; } BDRVRBDState; +typedef struct RBDTask { + BlockDriverState *bs; + Coroutine *co; + bool complete; + int64_t ret; +} RBDTask; + static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx, BlockdevOptionsRbd *opts, bool cache, const char *keypairs, const char *secretid, Error **errp); +static char *qemu_rbd_strchr(char *src, char delim) +{ + char *p; + + for (p = src; *p; ++p) { + if (*p == delim) { + return p; + } + if (*p == '\\' && p[1] != '\0') { + ++p; + } + } + + return NULL; +} + + static char *qemu_rbd_next_tok(char *src, char delim, char **p) { char *end; *p = NULL; - for (end = src; *end; ++end) { - if (*end == delim) { - break; - } - if (*end == '\\' && end[1] != '\0') { - end++; - } - } - if (*end == delim) { + end = qemu_rbd_strchr(src, delim); + if (end) { *p = end + 1; *end = '\0'; } @@ -171,7 +170,7 @@ static void qemu_rbd_parse_filename(const char *filename, QDict *options, qemu_rbd_unescape(found_str); qdict_put_str(options, "pool", found_str); - if (strchr(p, '@')) { + if (qemu_rbd_strchr(p, '@')) { image_name = qemu_rbd_next_tok(p, '@', &p); found_str = qemu_rbd_next_tok(p, ':', &p); @@ -181,7 +180,7 @@ static void qemu_rbd_parse_filename(const char *filename, QDict *options, image_name = qemu_rbd_next_tok(p, ':', &p); } /* Check for namespace in the image_name */ - if (strchr(image_name, '/')) { + if (qemu_rbd_strchr(image_name, '/')) { found_str = qemu_rbd_next_tok(image_name, '/', &image_name); qemu_rbd_unescape(found_str); qdict_put_str(options, "namespace", found_str); @@ -241,14 +240,6 @@ done: return; } - -static void qemu_rbd_refresh_limits(BlockDriverState *bs, Error **errp) -{ - /* XXX Does RBD support AIO on less than 512-byte alignment? */ - bs->bl.request_alignment = 512; -} - - static int qemu_rbd_set_auth(rados_t cluster, BlockdevOptionsRbd *opts, Error **errp) { @@ -330,17 +321,203 @@ static int qemu_rbd_set_keypairs(rados_t cluster, const char *keypairs_json, return ret; } -static void qemu_rbd_memset(RADOSCB *rcb, int64_t offs) +#ifdef LIBRBD_SUPPORTS_ENCRYPTION +static int qemu_rbd_convert_luks_options( + RbdEncryptionOptionsLUKSBase *luks_opts, + char **passphrase, + size_t *passphrase_len, + Error **errp) { - if (LIBRBD_USE_IOVEC) { - RBDAIOCB *acb = rcb->acb; - iov_memset(acb->qiov->iov, acb->qiov->niov, offs, 0, - acb->qiov->size - offs); - } else { - memset(rcb->buf + offs, 0, rcb->size - offs); - } + return qcrypto_secret_lookup(luks_opts->key_secret, (uint8_t **)passphrase, + passphrase_len, errp); } +static int qemu_rbd_convert_luks_create_options( + RbdEncryptionCreateOptionsLUKSBase *luks_opts, + rbd_encryption_algorithm_t *alg, + char **passphrase, + size_t *passphrase_len, + Error **errp) +{ + int r = 0; + + r = qemu_rbd_convert_luks_options( + qapi_RbdEncryptionCreateOptionsLUKSBase_base(luks_opts), + passphrase, passphrase_len, errp); + if (r < 0) { + return r; + } + + if (luks_opts->has_cipher_alg) { + switch (luks_opts->cipher_alg) { + case QCRYPTO_CIPHER_ALG_AES_128: { + *alg = RBD_ENCRYPTION_ALGORITHM_AES128; + break; + } + case QCRYPTO_CIPHER_ALG_AES_256: { + *alg = RBD_ENCRYPTION_ALGORITHM_AES256; + break; + } + default: { + r = -ENOTSUP; + error_setg_errno(errp, -r, "unknown encryption algorithm: %u", + luks_opts->cipher_alg); + return r; + } + } + } else { + /* default alg */ + *alg = RBD_ENCRYPTION_ALGORITHM_AES256; + } + + return 0; +} + +static int qemu_rbd_encryption_format(rbd_image_t image, + RbdEncryptionCreateOptions *encrypt, + Error **errp) +{ + int r = 0; + g_autofree char *passphrase = NULL; + size_t passphrase_len; + rbd_encryption_format_t format; + rbd_encryption_options_t opts; + rbd_encryption_luks1_format_options_t luks_opts; + rbd_encryption_luks2_format_options_t luks2_opts; + size_t opts_size; + uint64_t raw_size, effective_size; + + r = rbd_get_size(image, &raw_size); + if (r < 0) { + error_setg_errno(errp, -r, "cannot get raw image size"); + return r; + } + + switch (encrypt->format) { + case RBD_IMAGE_ENCRYPTION_FORMAT_LUKS: { + memset(&luks_opts, 0, sizeof(luks_opts)); + format = RBD_ENCRYPTION_FORMAT_LUKS1; + opts = &luks_opts; + opts_size = sizeof(luks_opts); + r = qemu_rbd_convert_luks_create_options( + qapi_RbdEncryptionCreateOptionsLUKS_base(&encrypt->u.luks), + &luks_opts.alg, &passphrase, &passphrase_len, errp); + if (r < 0) { + return r; + } + luks_opts.passphrase = passphrase; + luks_opts.passphrase_size = passphrase_len; + break; + } + case RBD_IMAGE_ENCRYPTION_FORMAT_LUKS2: { + memset(&luks2_opts, 0, sizeof(luks2_opts)); + format = RBD_ENCRYPTION_FORMAT_LUKS2; + opts = &luks2_opts; + opts_size = sizeof(luks2_opts); + r = qemu_rbd_convert_luks_create_options( + qapi_RbdEncryptionCreateOptionsLUKS2_base( + &encrypt->u.luks2), + &luks2_opts.alg, &passphrase, &passphrase_len, errp); + if (r < 0) { + return r; + } + luks2_opts.passphrase = passphrase; + luks2_opts.passphrase_size = passphrase_len; + break; + } + default: { + r = -ENOTSUP; + error_setg_errno( + errp, -r, "unknown image encryption format: %u", + encrypt->format); + return r; + } + } + + r = rbd_encryption_format(image, format, opts, opts_size); + if (r < 0) { + error_setg_errno(errp, -r, "encryption format fail"); + return r; + } + + r = rbd_get_size(image, &effective_size); + if (r < 0) { + error_setg_errno(errp, -r, "cannot get effective image size"); + return r; + } + + r = rbd_resize(image, raw_size + (raw_size - effective_size)); + if (r < 0) { + error_setg_errno(errp, -r, "cannot resize image after format"); + return r; + } + + return 0; +} + +static int qemu_rbd_encryption_load(rbd_image_t image, + RbdEncryptionOptions *encrypt, + Error **errp) +{ + int r = 0; + g_autofree char *passphrase = NULL; + size_t passphrase_len; + rbd_encryption_luks1_format_options_t luks_opts; + rbd_encryption_luks2_format_options_t luks2_opts; + rbd_encryption_format_t format; + rbd_encryption_options_t opts; + size_t opts_size; + + switch (encrypt->format) { + case RBD_IMAGE_ENCRYPTION_FORMAT_LUKS: { + memset(&luks_opts, 0, sizeof(luks_opts)); + format = RBD_ENCRYPTION_FORMAT_LUKS1; + opts = &luks_opts; + opts_size = sizeof(luks_opts); + r = qemu_rbd_convert_luks_options( + qapi_RbdEncryptionOptionsLUKS_base(&encrypt->u.luks), + &passphrase, &passphrase_len, errp); + if (r < 0) { + return r; + } + luks_opts.passphrase = passphrase; + luks_opts.passphrase_size = passphrase_len; + break; + } + case RBD_IMAGE_ENCRYPTION_FORMAT_LUKS2: { + memset(&luks2_opts, 0, sizeof(luks2_opts)); + format = RBD_ENCRYPTION_FORMAT_LUKS2; + opts = &luks2_opts; + opts_size = sizeof(luks2_opts); + r = qemu_rbd_convert_luks_options( + qapi_RbdEncryptionOptionsLUKS2_base(&encrypt->u.luks2), + &passphrase, &passphrase_len, errp); + if (r < 0) { + return r; + } + luks2_opts.passphrase = passphrase; + luks2_opts.passphrase_size = passphrase_len; + break; + } + default: { + r = -ENOTSUP; + error_setg_errno( + errp, -r, "unknown image encryption format: %u", + encrypt->format); + return r; + } + } + + r = rbd_encryption_load(image, format, opts, opts_size); + if (r < 0) { + error_setg_errno(errp, -r, "encryption load fail"); + return r; + } + + return 0; +} +#endif + /* FIXME Deprecate and remove keypairs or make it available in QMP. */ static int qemu_rbd_do_create(BlockdevCreateOptions *options, const char *keypairs, const char *password_secret, @@ -358,6 +535,13 @@ static int qemu_rbd_do_create(BlockdevCreateOptions *options, return -EINVAL; } +#ifndef LIBRBD_SUPPORTS_ENCRYPTION + if (opts->has_encrypt) { + error_setg(errp, "RBD library does not support image encryption"); + return -ENOTSUP; + } +#endif + if (opts->has_cluster_size) { int64_t objsize = opts->cluster_size; if ((objsize - 1) & objsize) { /* not a power of 2? */ @@ -383,6 +567,28 @@ static int qemu_rbd_do_create(BlockdevCreateOptions *options, goto out; } +#ifdef LIBRBD_SUPPORTS_ENCRYPTION + if (opts->has_encrypt) { + rbd_image_t image; + + ret = rbd_open(io_ctx, opts->location->image, &image, NULL); + if (ret < 0) { + error_setg_errno(errp, -ret, + "error opening image '%s' for encryption format", + opts->location->image); + goto out; + } + + ret = qemu_rbd_encryption_format(image, opts->encrypt, errp); + rbd_close(image); + if (ret < 0) { + /* encryption format fail, try removing the image */ + rbd_remove(io_ctx, opts->location->image); + goto out; + } + } +#endif + ret = 0; out: rados_ioctx_destroy(io_ctx); @@ -395,6 +601,43 @@ static int qemu_rbd_co_create(BlockdevCreateOptions *options, Error **errp) return qemu_rbd_do_create(options, NULL, NULL, errp); } +static int qemu_rbd_extract_encryption_create_options( + QemuOpts *opts, + RbdEncryptionCreateOptions **spec, + Error **errp) +{ + QDict *opts_qdict; + QDict *encrypt_qdict; + Visitor *v; + int ret = 0; + + opts_qdict = qemu_opts_to_qdict(opts, NULL); + qdict_extract_subqdict(opts_qdict, &encrypt_qdict, "encrypt."); + qobject_unref(opts_qdict); + if (!qdict_size(encrypt_qdict)) { + *spec = NULL; + goto exit; + } + + /* Convert options into a QAPI object */ + v = qobject_input_visitor_new_flat_confused(encrypt_qdict, errp); + if (!v) { + ret = -EINVAL; + goto exit; + } + + visit_type_RbdEncryptionCreateOptions(v, NULL, spec, errp); + visit_free(v); + if (!*spec) { + ret = -EINVAL; + goto exit; + } + +exit: + qobject_unref(encrypt_qdict); + return ret; +} + static int coroutine_fn qemu_rbd_co_create_opts(BlockDriver *drv, const char *filename, QemuOpts *opts, @@ -403,6 +646,7 @@ static int coroutine_fn qemu_rbd_co_create_opts(BlockDriver *drv, BlockdevCreateOptions *create_options; BlockdevCreateOptionsRbd *rbd_opts; BlockdevOptionsRbd *loc; + RbdEncryptionCreateOptions *encrypt = NULL; Error *local_err = NULL; const char *keypairs, *password_secret; QDict *options = NULL; @@ -431,6 +675,13 @@ static int coroutine_fn qemu_rbd_co_create_opts(BlockDriver *drv, goto exit; } + ret = qemu_rbd_extract_encryption_create_options(opts, &encrypt, errp); + if (ret < 0) { + goto exit; + } + rbd_opts->encrypt = encrypt; + rbd_opts->has_encrypt = !!encrypt; + /* * Caution: while qdict_get_try_str() is fine, getting non-string * types would require more care. When @options come from -blockdev @@ -459,53 +710,6 @@ exit: return ret; } -/* - * This aio completion is being called from rbd_finish_bh() and runs in qemu - * BH context. - */ -static void qemu_rbd_complete_aio(RADOSCB *rcb) -{ - RBDAIOCB *acb = rcb->acb; - int64_t r; - - r = rcb->ret; - - if (acb->cmd != RBD_AIO_READ) { - if (r < 0) { - acb->ret = r; - acb->error = 1; - } else if (!acb->error) { - acb->ret = rcb->size; - } - } else { - if (r < 0) { - qemu_rbd_memset(rcb, 0); - acb->ret = r; - acb->error = 1; - } else if (r < rcb->size) { - qemu_rbd_memset(rcb, r); - if (!acb->error) { - acb->ret = rcb->size; - } - } else if (!acb->error) { - acb->ret = r; - } - } - - g_free(rcb); - - if (!LIBRBD_USE_IOVEC) { - if (acb->cmd == RBD_AIO_READ) { - qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size); - } - qemu_vfree(acb->bounce); - } - - acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret)); - - qemu_aio_unref(acb); -} - static char *qemu_rbd_mon_host(BlockdevOptionsRbd *opts, Error **errp) { const char **vals; @@ -692,6 +896,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags, const QDictEntry *e; Error *local_err = NULL; char *keypairs, *secretid; + rbd_image_info_t info; int r; keypairs = g_strdup(qdict_get_try_str(options, "=keyvalue-pairs")); @@ -756,30 +961,49 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags, goto failed_open; } - r = rbd_get_size(s->image, &s->image_size); - if (r < 0) { - error_setg_errno(errp, -r, "error getting image size from %s", - s->image_name); - rbd_close(s->image); - goto failed_open; + if (opts->has_encrypt) { +#ifdef LIBRBD_SUPPORTS_ENCRYPTION + r = qemu_rbd_encryption_load(s->image, opts->encrypt, errp); + if (r < 0) { + goto failed_post_open; + } +#else + r = -ENOTSUP; + error_setg(errp, "RBD library does not support image encryption"); + goto failed_post_open; +#endif } + r = rbd_stat(s->image, &info, sizeof(info)); + if (r < 0) { + error_setg_errno(errp, -r, "error getting image info from %s", + s->image_name); + goto failed_post_open; + } + s->image_size = info.size; + s->object_size = info.obj_size; + /* If we are using an rbd snapshot, we must be r/o, otherwise * leave as-is */ if (s->snap != NULL) { r = bdrv_apply_auto_read_only(bs, "rbd snapshots are read-only", errp); if (r < 0) { - rbd_close(s->image); - goto failed_open; + goto failed_post_open; } } +#ifdef LIBRBD_SUPPORTS_WRITE_ZEROES + bs->supported_zero_flags = BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK; +#endif + /* When extending regular files, we get zeros from the OS */ bs->supported_truncate_flags = BDRV_REQ_ZERO_WRITE; r = 0; goto out; +failed_post_open: + rbd_close(s->image); failed_open: rados_ioctx_destroy(s->io_ctx); g_free(s->snap); @@ -839,229 +1063,213 @@ static int qemu_rbd_resize(BlockDriverState *bs, uint64_t size) return 0; } -static const AIOCBInfo rbd_aiocb_info = { - .aiocb_size = sizeof(RBDAIOCB), -}; - -static void rbd_finish_bh(void *opaque) +static void qemu_rbd_finish_bh(void *opaque) { - RADOSCB *rcb = opaque; - qemu_rbd_complete_aio(rcb); + RBDTask *task = opaque; + task->complete = true; + aio_co_wake(task->co); } /* - * This is the callback function for rbd_aio_read and _write + * This is the completion callback function for all rbd aio calls + * started from qemu_rbd_start_co(). * * Note: this function is being called from a non qemu thread so * we need to be careful about what we do here. Generally we only * schedule a BH, and do the rest of the io completion handling - * from rbd_finish_bh() which runs in a qemu context. + * from qemu_rbd_finish_bh() which runs in a qemu context. */ -static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb) +static void qemu_rbd_completion_cb(rbd_completion_t c, RBDTask *task) { - RBDAIOCB *acb = rcb->acb; - - rcb->ret = rbd_aio_get_return_value(c); + task->ret = rbd_aio_get_return_value(c); rbd_aio_release(c); - - replay_bh_schedule_oneshot_event(bdrv_get_aio_context(acb->common.bs), - rbd_finish_bh, rcb); + aio_bh_schedule_oneshot(bdrv_get_aio_context(task->bs), + qemu_rbd_finish_bh, task); } -static int rbd_aio_discard_wrapper(rbd_image_t image, - uint64_t off, - uint64_t len, - rbd_completion_t comp) +static int coroutine_fn qemu_rbd_start_co(BlockDriverState *bs, + uint64_t offset, + uint64_t bytes, + QEMUIOVector *qiov, + int flags, + RBDAIOCmd cmd) { -#ifdef LIBRBD_SUPPORTS_DISCARD - return rbd_aio_discard(image, off, len, comp); -#else - return -ENOTSUP; -#endif -} - -static int rbd_aio_flush_wrapper(rbd_image_t image, - rbd_completion_t comp) -{ -#ifdef LIBRBD_SUPPORTS_AIO_FLUSH - return rbd_aio_flush(image, comp); -#else - return -ENOTSUP; -#endif -} - -static BlockAIOCB *rbd_start_aio(BlockDriverState *bs, - int64_t off, - QEMUIOVector *qiov, - int64_t size, - BlockCompletionFunc *cb, - void *opaque, - RBDAIOCmd cmd) -{ - RBDAIOCB *acb; - RADOSCB *rcb = NULL; + BDRVRBDState *s = bs->opaque; + RBDTask task = { .bs = bs, .co = qemu_coroutine_self() }; rbd_completion_t c; int r; - BDRVRBDState *s = bs->opaque; + assert(!qiov || qiov->size == bytes); - acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque); - acb->cmd = cmd; - acb->qiov = qiov; - assert(!qiov || qiov->size == size); - - rcb = g_new(RADOSCB, 1); - - if (!LIBRBD_USE_IOVEC) { - if (cmd == RBD_AIO_DISCARD || cmd == RBD_AIO_FLUSH) { - acb->bounce = NULL; - } else { - acb->bounce = qemu_try_blockalign(bs, qiov->size); - if (acb->bounce == NULL) { - goto failed; - } - } - if (cmd == RBD_AIO_WRITE) { - qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size); - } - rcb->buf = acb->bounce; - } - - acb->ret = 0; - acb->error = 0; - acb->s = s; - - rcb->acb = acb; - rcb->s = acb->s; - rcb->size = size; - r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c); + r = rbd_aio_create_completion(&task, + (rbd_callback_t) qemu_rbd_completion_cb, &c); if (r < 0) { - goto failed; + return r; } switch (cmd) { - case RBD_AIO_WRITE: { - /* - * RBD APIs don't allow us to write more than actual size, so in order - * to support growing images, we resize the image before write - * operations that exceed the current size. - */ - if (off + size > s->image_size) { - r = qemu_rbd_resize(bs, off + size); - if (r < 0) { - goto failed_completion; - } - } -#ifdef LIBRBD_SUPPORTS_IOVEC - r = rbd_aio_writev(s->image, qiov->iov, qiov->niov, off, c); -#else - r = rbd_aio_write(s->image, off, size, rcb->buf, c); -#endif - break; - } case RBD_AIO_READ: -#ifdef LIBRBD_SUPPORTS_IOVEC - r = rbd_aio_readv(s->image, qiov->iov, qiov->niov, off, c); -#else - r = rbd_aio_read(s->image, off, size, rcb->buf, c); -#endif + r = rbd_aio_readv(s->image, qiov->iov, qiov->niov, offset, c); + break; + case RBD_AIO_WRITE: + r = rbd_aio_writev(s->image, qiov->iov, qiov->niov, offset, c); break; case RBD_AIO_DISCARD: - r = rbd_aio_discard_wrapper(s->image, off, size, c); + r = rbd_aio_discard(s->image, offset, bytes, c); break; case RBD_AIO_FLUSH: - r = rbd_aio_flush_wrapper(s->image, c); + r = rbd_aio_flush(s->image, c); break; +#ifdef LIBRBD_SUPPORTS_WRITE_ZEROES + case RBD_AIO_WRITE_ZEROES: { + int zero_flags = 0; +#ifdef RBD_WRITE_ZEROES_FLAG_THICK_PROVISION + if (!(flags & BDRV_REQ_MAY_UNMAP)) { + zero_flags = RBD_WRITE_ZEROES_FLAG_THICK_PROVISION; + } +#endif + r = rbd_aio_write_zeroes(s->image, offset, bytes, c, zero_flags, 0); + break; + } +#endif default: r = -EINVAL; } if (r < 0) { - goto failed_completion; - } - return &acb->common; - -failed_completion: - rbd_aio_release(c); -failed: - g_free(rcb); - if (!LIBRBD_USE_IOVEC) { - qemu_vfree(acb->bounce); + error_report("rbd request failed early: cmd %d offset %" PRIu64 + " bytes %" PRIu64 " flags %d r %d (%s)", cmd, offset, + bytes, flags, r, strerror(-r)); + rbd_aio_release(c); + return r; } - qemu_aio_unref(acb); - return NULL; -} + while (!task.complete) { + qemu_coroutine_yield(); + } -static BlockAIOCB *qemu_rbd_aio_preadv(BlockDriverState *bs, - uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags, - BlockCompletionFunc *cb, - void *opaque) -{ - return rbd_start_aio(bs, offset, qiov, bytes, cb, opaque, - RBD_AIO_READ); -} + if (task.ret < 0) { + error_report("rbd request failed: cmd %d offset %" PRIu64 " bytes %" + PRIu64 " flags %d task.ret %" PRIi64 " (%s)", cmd, offset, + bytes, flags, task.ret, strerror(-task.ret)); + return task.ret; + } -static BlockAIOCB *qemu_rbd_aio_pwritev(BlockDriverState *bs, - uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags, - BlockCompletionFunc *cb, - void *opaque) -{ - return rbd_start_aio(bs, offset, qiov, bytes, cb, opaque, - RBD_AIO_WRITE); -} + /* zero pad short reads */ + if (cmd == RBD_AIO_READ && task.ret < qiov->size) { + qemu_iovec_memset(qiov, task.ret, 0, qiov->size - task.ret); + } -#ifdef LIBRBD_SUPPORTS_AIO_FLUSH -static BlockAIOCB *qemu_rbd_aio_flush(BlockDriverState *bs, - BlockCompletionFunc *cb, - void *opaque) -{ - return rbd_start_aio(bs, 0, NULL, 0, cb, opaque, RBD_AIO_FLUSH); -} - -#else - -static int qemu_rbd_co_flush(BlockDriverState *bs) -{ -#if LIBRBD_VERSION_CODE >= LIBRBD_VERSION(0, 1, 1) - /* rbd_flush added in 0.1.1 */ - BDRVRBDState *s = bs->opaque; - return rbd_flush(s->image); -#else return 0; -#endif +} + +static int +coroutine_fn qemu_rbd_co_preadv(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, + int flags) +{ + return qemu_rbd_start_co(bs, offset, bytes, qiov, flags, RBD_AIO_READ); +} + +static int +coroutine_fn qemu_rbd_co_pwritev(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, + int flags) +{ + BDRVRBDState *s = bs->opaque; + /* + * RBD APIs don't allow us to write more than actual size, so in order + * to support growing images, we resize the image before write + * operations that exceed the current size. + */ + if (offset + bytes > s->image_size) { + int r = qemu_rbd_resize(bs, offset + bytes); + if (r < 0) { + return r; + } + } + return qemu_rbd_start_co(bs, offset, bytes, qiov, flags, RBD_AIO_WRITE); +} + +static int coroutine_fn qemu_rbd_co_flush(BlockDriverState *bs) +{ + return qemu_rbd_start_co(bs, 0, 0, NULL, 0, RBD_AIO_FLUSH); +} + +static int coroutine_fn qemu_rbd_co_pdiscard(BlockDriverState *bs, + int64_t offset, int count) +{ + return qemu_rbd_start_co(bs, offset, count, NULL, 0, RBD_AIO_DISCARD); +} + +#ifdef LIBRBD_SUPPORTS_WRITE_ZEROES +static int +coroutine_fn qemu_rbd_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, + int count, BdrvRequestFlags flags) +{ + return qemu_rbd_start_co(bs, offset, count, NULL, flags, + RBD_AIO_WRITE_ZEROES); } #endif static int qemu_rbd_getinfo(BlockDriverState *bs, BlockDriverInfo *bdi) { BDRVRBDState *s = bs->opaque; - rbd_image_info_t info; + bdi->cluster_size = s->object_size; + return 0; +} + +static ImageInfoSpecific *qemu_rbd_get_specific_info(BlockDriverState *bs, + Error **errp) +{ + BDRVRBDState *s = bs->opaque; + ImageInfoSpecific *spec_info; + char buf[RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN] = {0}; int r; - r = rbd_stat(s->image, &info, sizeof(info)); - if (r < 0) { - return r; + if (s->image_size >= RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN) { + r = rbd_read(s->image, 0, + RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN, buf); + if (r < 0) { + error_setg_errno(errp, -r, "cannot read image start for probe"); + return NULL; + } } - bdi->cluster_size = info.obj_size; - return 0; + spec_info = g_new(ImageInfoSpecific, 1); + *spec_info = (ImageInfoSpecific){ + .type = IMAGE_INFO_SPECIFIC_KIND_RBD, + .u.rbd.data = g_new0(ImageInfoSpecificRbd, 1), + }; + + if (memcmp(buf, rbd_luks_header_verification, + RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN) == 0) { + spec_info->u.rbd.data->encryption_format = + RBD_IMAGE_ENCRYPTION_FORMAT_LUKS; + spec_info->u.rbd.data->has_encryption_format = true; + } else if (memcmp(buf, rbd_luks2_header_verification, + RBD_ENCRYPTION_LUKS_HEADER_VERIFICATION_LEN) == 0) { + spec_info->u.rbd.data->encryption_format = + RBD_IMAGE_ENCRYPTION_FORMAT_LUKS2; + spec_info->u.rbd.data->has_encryption_format = true; + } else { + spec_info->u.rbd.data->has_encryption_format = false; + } + + return spec_info; } static int64_t qemu_rbd_getlength(BlockDriverState *bs) { BDRVRBDState *s = bs->opaque; - rbd_image_info_t info; int r; - r = rbd_stat(s->image, &info, sizeof(info)); + r = rbd_get_size(s->image, &s->image_size); if (r < 0) { return r; } - return info.size; + return s->image_size; } static int coroutine_fn qemu_rbd_co_truncate(BlockDriverState *bs, @@ -1200,19 +1408,6 @@ static int qemu_rbd_snap_list(BlockDriverState *bs, return snap_count; } -#ifdef LIBRBD_SUPPORTS_DISCARD -static BlockAIOCB *qemu_rbd_aio_pdiscard(BlockDriverState *bs, - int64_t offset, - int bytes, - BlockCompletionFunc *cb, - void *opaque) -{ - return rbd_start_aio(bs, offset, NULL, bytes, cb, opaque, - RBD_AIO_DISCARD); -} -#endif - -#ifdef LIBRBD_SUPPORTS_INVALIDATE static void coroutine_fn qemu_rbd_co_invalidate_cache(BlockDriverState *bs, Error **errp) { @@ -1222,7 +1417,6 @@ static void coroutine_fn qemu_rbd_co_invalidate_cache(BlockDriverState *bs, error_setg_errno(errp, -r, "Failed to invalidate the cache"); } } -#endif static QemuOptsList qemu_rbd_create_opts = { .name = "rbd-create-opts", @@ -1243,6 +1437,22 @@ static QemuOptsList qemu_rbd_create_opts = { .type = QEMU_OPT_STRING, .help = "ID of secret providing the password", }, + { + .name = "encrypt.format", + .type = QEMU_OPT_STRING, + .help = "Encrypt the image, format choices: 'luks', 'luks2'", + }, + { + .name = "encrypt.cipher-alg", + .type = QEMU_OPT_STRING, + .help = "Name of encryption cipher algorithm" + " (allowed values: aes-128, aes-256)", + }, + { + .name = "encrypt.key-secret", + .type = QEMU_OPT_STRING, + .help = "ID of secret providing LUKS passphrase", + }, { /* end of list */ } } }; @@ -1264,7 +1474,6 @@ static BlockDriver bdrv_rbd = { .format_name = "rbd", .instance_size = sizeof(BDRVRBDState), .bdrv_parse_filename = qemu_rbd_parse_filename, - .bdrv_refresh_limits = qemu_rbd_refresh_limits, .bdrv_file_open = qemu_rbd_open, .bdrv_close = qemu_rbd_close, .bdrv_reopen_prepare = qemu_rbd_reopen_prepare, @@ -1272,31 +1481,25 @@ static BlockDriver bdrv_rbd = { .bdrv_co_create_opts = qemu_rbd_co_create_opts, .bdrv_has_zero_init = bdrv_has_zero_init_1, .bdrv_get_info = qemu_rbd_getinfo, + .bdrv_get_specific_info = qemu_rbd_get_specific_info, .create_opts = &qemu_rbd_create_opts, .bdrv_getlength = qemu_rbd_getlength, .bdrv_co_truncate = qemu_rbd_co_truncate, .protocol_name = "rbd", - .bdrv_aio_preadv = qemu_rbd_aio_preadv, - .bdrv_aio_pwritev = qemu_rbd_aio_pwritev, - -#ifdef LIBRBD_SUPPORTS_AIO_FLUSH - .bdrv_aio_flush = qemu_rbd_aio_flush, -#else + .bdrv_co_preadv = qemu_rbd_co_preadv, + .bdrv_co_pwritev = qemu_rbd_co_pwritev, .bdrv_co_flush_to_disk = qemu_rbd_co_flush, -#endif - -#ifdef LIBRBD_SUPPORTS_DISCARD - .bdrv_aio_pdiscard = qemu_rbd_aio_pdiscard, + .bdrv_co_pdiscard = qemu_rbd_co_pdiscard, +#ifdef LIBRBD_SUPPORTS_WRITE_ZEROES + .bdrv_co_pwrite_zeroes = qemu_rbd_co_pwrite_zeroes, #endif .bdrv_snapshot_create = qemu_rbd_snap_create, .bdrv_snapshot_delete = qemu_rbd_snap_remove, .bdrv_snapshot_list = qemu_rbd_snap_list, .bdrv_snapshot_goto = qemu_rbd_snap_rollback, -#ifdef LIBRBD_SUPPORTS_INVALIDATE .bdrv_co_invalidate_cache = qemu_rbd_co_invalidate_cache, -#endif .strong_runtime_opts = qemu_rbd_strong_runtime_opts, }; diff --git a/block/replication.c b/block/replication.c index 97be7ef4de..32444b9a8f 100644 --- a/block/replication.c +++ b/block/replication.c @@ -22,7 +22,7 @@ #include "sysemu/block-backend.h" #include "qapi/error.h" #include "qapi/qmp/qdict.h" -#include "replication.h" +#include "block/replication.h" typedef enum { BLOCK_REPLICATION_NONE, /* block replication is not started */ @@ -35,7 +35,6 @@ typedef enum { typedef struct BDRVReplicationState { ReplicationMode mode; ReplicationStage stage; - BdrvChild *active_disk; BlockJob *commit_job; BdrvChild *hidden_disk; BdrvChild *secondary_disk; @@ -166,7 +165,12 @@ static void replication_child_perm(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared) { - *nperm = BLK_PERM_CONSISTENT_READ; + if (role & BDRV_CHILD_PRIMARY) { + *nperm = BLK_PERM_CONSISTENT_READ; + } else { + *nperm = 0; + } + if ((bs->open_flags & (BDRV_O_INACTIVE | BDRV_O_RDWR)) == BDRV_O_RDWR) { *nperm |= BLK_PERM_WRITE; } @@ -307,8 +311,10 @@ out: return ret; } -static void secondary_do_checkpoint(BDRVReplicationState *s, Error **errp) +static void secondary_do_checkpoint(BlockDriverState *bs, Error **errp) { + BDRVReplicationState *s = bs->opaque; + BdrvChild *active_disk = bs->file; Error *local_err = NULL; int ret; @@ -323,13 +329,13 @@ static void secondary_do_checkpoint(BDRVReplicationState *s, Error **errp) return; } - if (!s->active_disk->bs->drv) { + if (!active_disk->bs->drv) { error_setg(errp, "Active disk %s is ejected", - s->active_disk->bs->node_name); + active_disk->bs->node_name); return; } - ret = bdrv_make_empty(s->active_disk, errp); + ret = bdrv_make_empty(active_disk, errp); if (ret < 0) { return; } @@ -340,17 +346,7 @@ static void secondary_do_checkpoint(BDRVReplicationState *s, Error **errp) return; } - BlockBackend *blk = blk_new(qemu_get_current_aio_context(), - BLK_PERM_WRITE, BLK_PERM_ALL); - blk_insert_bs(blk, s->hidden_disk->bs, &local_err); - if (local_err) { - error_propagate(errp, local_err); - blk_unref(blk); - return; - } - - ret = blk_make_empty(blk, errp); - blk_unref(blk); + ret = bdrv_make_empty(s->hidden_disk, errp); if (ret < 0) { return; } @@ -365,36 +361,51 @@ static void reopen_backing_file(BlockDriverState *bs, bool writable, Error **errp) { BDRVReplicationState *s = bs->opaque; + BdrvChild *hidden_disk, *secondary_disk; BlockReopenQueue *reopen_queue = NULL; + /* + * s->hidden_disk and s->secondary_disk may not be set yet, as they will + * only be set after the children are writable. + */ + hidden_disk = bs->file->bs->backing; + secondary_disk = hidden_disk->bs->backing; + if (writable) { - s->orig_hidden_read_only = bdrv_is_read_only(s->hidden_disk->bs); - s->orig_secondary_read_only = bdrv_is_read_only(s->secondary_disk->bs); + s->orig_hidden_read_only = bdrv_is_read_only(hidden_disk->bs); + s->orig_secondary_read_only = bdrv_is_read_only(secondary_disk->bs); } - bdrv_subtree_drained_begin(s->hidden_disk->bs); - bdrv_subtree_drained_begin(s->secondary_disk->bs); + bdrv_subtree_drained_begin(hidden_disk->bs); + bdrv_subtree_drained_begin(secondary_disk->bs); if (s->orig_hidden_read_only) { QDict *opts = qdict_new(); qdict_put_bool(opts, BDRV_OPT_READ_ONLY, !writable); - reopen_queue = bdrv_reopen_queue(reopen_queue, s->hidden_disk->bs, + reopen_queue = bdrv_reopen_queue(reopen_queue, hidden_disk->bs, opts, true); } if (s->orig_secondary_read_only) { QDict *opts = qdict_new(); qdict_put_bool(opts, BDRV_OPT_READ_ONLY, !writable); - reopen_queue = bdrv_reopen_queue(reopen_queue, s->secondary_disk->bs, + reopen_queue = bdrv_reopen_queue(reopen_queue, secondary_disk->bs, opts, true); } if (reopen_queue) { + AioContext *ctx = bdrv_get_aio_context(bs); + if (ctx != qemu_get_aio_context()) { + aio_context_release(ctx); + } bdrv_reopen_multiple(reopen_queue, errp); + if (ctx != qemu_get_aio_context()) { + aio_context_acquire(ctx); + } } - bdrv_subtree_drained_end(s->hidden_disk->bs); - bdrv_subtree_drained_end(s->secondary_disk->bs); + bdrv_subtree_drained_end(hidden_disk->bs); + bdrv_subtree_drained_end(secondary_disk->bs); } static void backup_job_cleanup(BlockDriverState *bs) @@ -451,6 +462,7 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, BlockDriverState *bs = rs->opaque; BDRVReplicationState *s; BlockDriverState *top_bs; + BdrvChild *active_disk, *hidden_disk, *secondary_disk; int64_t active_length, hidden_length, disk_length; AioContext *aio_context; Error *local_err = NULL; @@ -488,32 +500,31 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, case REPLICATION_MODE_PRIMARY: break; case REPLICATION_MODE_SECONDARY: - s->active_disk = bs->file; - if (!s->active_disk || !s->active_disk->bs || - !s->active_disk->bs->backing) { + active_disk = bs->file; + if (!active_disk || !active_disk->bs || !active_disk->bs->backing) { error_setg(errp, "Active disk doesn't have backing file"); aio_context_release(aio_context); return; } - s->hidden_disk = s->active_disk->bs->backing; - if (!s->hidden_disk->bs || !s->hidden_disk->bs->backing) { + hidden_disk = active_disk->bs->backing; + if (!hidden_disk->bs || !hidden_disk->bs->backing) { error_setg(errp, "Hidden disk doesn't have backing file"); aio_context_release(aio_context); return; } - s->secondary_disk = s->hidden_disk->bs->backing; - if (!s->secondary_disk->bs || !bdrv_has_blk(s->secondary_disk->bs)) { + secondary_disk = hidden_disk->bs->backing; + if (!secondary_disk->bs || !bdrv_has_blk(secondary_disk->bs)) { error_setg(errp, "The secondary disk doesn't have block backend"); aio_context_release(aio_context); return; } /* verify the length */ - active_length = bdrv_getlength(s->active_disk->bs); - hidden_length = bdrv_getlength(s->hidden_disk->bs); - disk_length = bdrv_getlength(s->secondary_disk->bs); + active_length = bdrv_getlength(active_disk->bs); + hidden_length = bdrv_getlength(hidden_disk->bs); + disk_length = bdrv_getlength(secondary_disk->bs); if (active_length < 0 || hidden_length < 0 || disk_length < 0 || active_length != hidden_length || hidden_length != disk_length) { error_setg(errp, "Active disk, hidden disk, secondary disk's length" @@ -523,10 +534,10 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, } /* Must be true, or the bdrv_getlength() calls would have failed */ - assert(s->active_disk->bs->drv && s->hidden_disk->bs->drv); + assert(active_disk->bs->drv && hidden_disk->bs->drv); - if (!s->active_disk->bs->drv->bdrv_make_empty || - !s->hidden_disk->bs->drv->bdrv_make_empty) { + if (!active_disk->bs->drv->bdrv_make_empty || + !hidden_disk->bs->drv->bdrv_make_empty) { error_setg(errp, "Active disk or hidden disk doesn't support make_empty"); aio_context_release(aio_context); @@ -541,6 +552,26 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, return; } + bdrv_ref(hidden_disk->bs); + s->hidden_disk = bdrv_attach_child(bs, hidden_disk->bs, "hidden disk", + &child_of_bds, BDRV_CHILD_DATA, + &local_err); + if (local_err) { + error_propagate(errp, local_err); + aio_context_release(aio_context); + return; + } + + bdrv_ref(secondary_disk->bs); + s->secondary_disk = bdrv_attach_child(bs, secondary_disk->bs, + "secondary disk", &child_of_bds, + BDRV_CHILD_DATA, &local_err); + if (local_err) { + error_propagate(errp, local_err); + aio_context_release(aio_context); + return; + } + /* start backup job now */ error_setg(&s->blocker, "Block device is in use by internal backup job"); @@ -579,7 +610,7 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, s->stage = BLOCK_REPLICATION_RUNNING; if (s->mode == REPLICATION_MODE_SECONDARY) { - secondary_do_checkpoint(s, errp); + secondary_do_checkpoint(bs, errp); } s->error = 0; @@ -608,7 +639,7 @@ static void replication_do_checkpoint(ReplicationState *rs, Error **errp) } if (s->mode == REPLICATION_MODE_SECONDARY) { - secondary_do_checkpoint(s, errp); + secondary_do_checkpoint(bs, errp); } aio_context_release(aio_context); } @@ -645,8 +676,9 @@ static void replication_done(void *opaque, int ret) if (ret == 0) { s->stage = BLOCK_REPLICATION_DONE; - s->active_disk = NULL; + bdrv_unref_child(bs, s->secondary_disk); s->secondary_disk = NULL; + bdrv_unref_child(bs, s->hidden_disk); s->hidden_disk = NULL; s->error = 0; } else { @@ -698,7 +730,7 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp) } if (!failover) { - secondary_do_checkpoint(s, errp); + secondary_do_checkpoint(bs, errp); s->stage = BLOCK_REPLICATION_DONE; aio_context_release(aio_context); return; @@ -706,7 +738,7 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp) s->stage = BLOCK_REPLICATION_FAILOVER; s->commit_job = commit_active_start( - NULL, s->active_disk->bs, s->secondary_disk->bs, + NULL, bs->file->bs, s->secondary_disk->bs, JOB_INTERNAL, 0, BLOCKDEV_ON_ERROR_REPORT, NULL, replication_done, bs, true, errp); break; diff --git a/block/sheepdog.c b/block/sheepdog.c deleted file mode 100644 index a45c73826d..0000000000 --- a/block/sheepdog.c +++ /dev/null @@ -1,3356 +0,0 @@ -/* - * Copyright (C) 2009-2010 Nippon Telegraph and Telephone Corporation. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see . - * - * Contributions after 2012-01-13 are licensed under the terms of the - * GNU GPL, version 2 or (at your option) any later version. - */ - -#include "qemu/osdep.h" -#include "qemu-common.h" -#include "qapi/error.h" -#include "qapi/qapi-visit-sockets.h" -#include "qapi/qapi-visit-block-core.h" -#include "qapi/qmp/qdict.h" -#include "qapi/qobject-input-visitor.h" -#include "qapi/qobject-output-visitor.h" -#include "qemu/uri.h" -#include "qemu/error-report.h" -#include "qemu/main-loop.h" -#include "qemu/module.h" -#include "qemu/option.h" -#include "qemu/sockets.h" -#include "block/block_int.h" -#include "block/qdict.h" -#include "sysemu/block-backend.h" -#include "qemu/bitops.h" -#include "qemu/cutils.h" -#include "trace.h" - -#define SD_PROTO_VER 0x01 - -#define SD_DEFAULT_ADDR "localhost" -#define SD_DEFAULT_PORT 7000 - -#define SD_OP_CREATE_AND_WRITE_OBJ 0x01 -#define SD_OP_READ_OBJ 0x02 -#define SD_OP_WRITE_OBJ 0x03 -/* 0x04 is used internally by Sheepdog */ - -#define SD_OP_NEW_VDI 0x11 -#define SD_OP_LOCK_VDI 0x12 -#define SD_OP_RELEASE_VDI 0x13 -#define SD_OP_GET_VDI_INFO 0x14 -#define SD_OP_READ_VDIS 0x15 -#define SD_OP_FLUSH_VDI 0x16 -#define SD_OP_DEL_VDI 0x17 -#define SD_OP_GET_CLUSTER_DEFAULT 0x18 - -#define SD_FLAG_CMD_WRITE 0x01 -#define SD_FLAG_CMD_COW 0x02 -#define SD_FLAG_CMD_CACHE 0x04 /* Writeback mode for cache */ -#define SD_FLAG_CMD_DIRECT 0x08 /* Don't use cache */ - -#define SD_RES_SUCCESS 0x00 /* Success */ -#define SD_RES_UNKNOWN 0x01 /* Unknown error */ -#define SD_RES_NO_OBJ 0x02 /* No object found */ -#define SD_RES_EIO 0x03 /* I/O error */ -#define SD_RES_VDI_EXIST 0x04 /* Vdi exists already */ -#define SD_RES_INVALID_PARMS 0x05 /* Invalid parameters */ -#define SD_RES_SYSTEM_ERROR 0x06 /* System error */ -#define SD_RES_VDI_LOCKED 0x07 /* Vdi is locked */ -#define SD_RES_NO_VDI 0x08 /* No vdi found */ -#define SD_RES_NO_BASE_VDI 0x09 /* No base vdi found */ -#define SD_RES_VDI_READ 0x0A /* Cannot read requested vdi */ -#define SD_RES_VDI_WRITE 0x0B /* Cannot write requested vdi */ -#define SD_RES_BASE_VDI_READ 0x0C /* Cannot read base vdi */ -#define SD_RES_BASE_VDI_WRITE 0x0D /* Cannot write base vdi */ -#define SD_RES_NO_TAG 0x0E /* Requested tag is not found */ -#define SD_RES_STARTUP 0x0F /* Sheepdog is on starting up */ -#define SD_RES_VDI_NOT_LOCKED 0x10 /* Vdi is not locked */ -#define SD_RES_SHUTDOWN 0x11 /* Sheepdog is shutting down */ -#define SD_RES_NO_MEM 0x12 /* Cannot allocate memory */ -#define SD_RES_FULL_VDI 0x13 /* we already have the maximum vdis */ -#define SD_RES_VER_MISMATCH 0x14 /* Protocol version mismatch */ -#define SD_RES_NO_SPACE 0x15 /* Server has no room for new objects */ -#define SD_RES_WAIT_FOR_FORMAT 0x16 /* Waiting for a format operation */ -#define SD_RES_WAIT_FOR_JOIN 0x17 /* Waiting for other nodes joining */ -#define SD_RES_JOIN_FAILED 0x18 /* Target node had failed to join sheepdog */ -#define SD_RES_HALT 0x19 /* Sheepdog is stopped serving IO request */ -#define SD_RES_READONLY 0x1A /* Object is read-only */ - -/* - * Object ID rules - * - * 0 - 19 (20 bits): data object space - * 20 - 31 (12 bits): reserved data object space - * 32 - 55 (24 bits): vdi object space - * 56 - 59 ( 4 bits): reserved vdi object space - * 60 - 63 ( 4 bits): object type identifier space - */ - -#define VDI_SPACE_SHIFT 32 -#define VDI_BIT (UINT64_C(1) << 63) -#define VMSTATE_BIT (UINT64_C(1) << 62) -#define MAX_DATA_OBJS (UINT64_C(1) << 20) -#define MAX_CHILDREN 1024 -#define SD_MAX_VDI_LEN 256 -#define SD_MAX_VDI_TAG_LEN 256 -#define SD_NR_VDIS (1U << 24) -#define SD_DATA_OBJ_SIZE (UINT64_C(1) << 22) -#define SD_MAX_VDI_SIZE (SD_DATA_OBJ_SIZE * MAX_DATA_OBJS) -#define SD_DEFAULT_BLOCK_SIZE_SHIFT 22 -/* - * For erasure coding, we use at most SD_EC_MAX_STRIP for data strips and - * (SD_EC_MAX_STRIP - 1) for parity strips - * - * SD_MAX_COPIES is sum of number of data strips and parity strips. - */ -#define SD_EC_MAX_STRIP 16 -#define SD_MAX_COPIES (SD_EC_MAX_STRIP * 2 - 1) - -#define SD_INODE_SIZE (sizeof(SheepdogInode)) -#define CURRENT_VDI_ID 0 - -#define LOCK_TYPE_NORMAL 0 -#define LOCK_TYPE_SHARED 1 /* for iSCSI multipath */ - -typedef struct SheepdogReq { - uint8_t proto_ver; - uint8_t opcode; - uint16_t flags; - uint32_t epoch; - uint32_t id; - uint32_t data_length; - uint32_t opcode_specific[8]; -} SheepdogReq; - -typedef struct SheepdogRsp { - uint8_t proto_ver; - uint8_t opcode; - uint16_t flags; - uint32_t epoch; - uint32_t id; - uint32_t data_length; - uint32_t result; - uint32_t opcode_specific[7]; -} SheepdogRsp; - -typedef struct SheepdogObjReq { - uint8_t proto_ver; - uint8_t opcode; - uint16_t flags; - uint32_t epoch; - uint32_t id; - uint32_t data_length; - uint64_t oid; - uint64_t cow_oid; - uint8_t copies; - uint8_t copy_policy; - uint8_t reserved[6]; - uint64_t offset; -} SheepdogObjReq; - -typedef struct SheepdogObjRsp { - uint8_t proto_ver; - uint8_t opcode; - uint16_t flags; - uint32_t epoch; - uint32_t id; - uint32_t data_length; - uint32_t result; - uint8_t copies; - uint8_t copy_policy; - uint8_t reserved[2]; - uint32_t pad[6]; -} SheepdogObjRsp; - -typedef struct SheepdogVdiReq { - uint8_t proto_ver; - uint8_t opcode; - uint16_t flags; - uint32_t epoch; - uint32_t id; - uint32_t data_length; - uint64_t vdi_size; - uint32_t base_vdi_id; - uint8_t copies; - uint8_t copy_policy; - uint8_t store_policy; - uint8_t block_size_shift; - uint32_t snapid; - uint32_t type; - uint32_t pad[2]; -} SheepdogVdiReq; - -typedef struct SheepdogVdiRsp { - uint8_t proto_ver; - uint8_t opcode; - uint16_t flags; - uint32_t epoch; - uint32_t id; - uint32_t data_length; - uint32_t result; - uint32_t rsvd; - uint32_t vdi_id; - uint32_t pad[5]; -} SheepdogVdiRsp; - -typedef struct SheepdogClusterRsp { - uint8_t proto_ver; - uint8_t opcode; - uint16_t flags; - uint32_t epoch; - uint32_t id; - uint32_t data_length; - uint32_t result; - uint8_t nr_copies; - uint8_t copy_policy; - uint8_t block_size_shift; - uint8_t __pad1; - uint32_t __pad2[6]; -} SheepdogClusterRsp; - -typedef struct SheepdogInode { - char name[SD_MAX_VDI_LEN]; - char tag[SD_MAX_VDI_TAG_LEN]; - uint64_t ctime; - uint64_t snap_ctime; - uint64_t vm_clock_nsec; - uint64_t vdi_size; - uint64_t vm_state_size; - uint16_t copy_policy; - uint8_t nr_copies; - uint8_t block_size_shift; - uint32_t snap_id; - uint32_t vdi_id; - uint32_t parent_vdi_id; - uint32_t child_vdi_id[MAX_CHILDREN]; - uint32_t data_vdi_id[MAX_DATA_OBJS]; -} SheepdogInode; - -#define SD_INODE_HEADER_SIZE offsetof(SheepdogInode, data_vdi_id) - -/* - * 64 bit FNV-1a non-zero initial basis - */ -#define FNV1A_64_INIT ((uint64_t)0xcbf29ce484222325ULL) - -static void deprecation_warning(void) -{ - static bool warned; - - if (!warned) { - warn_report("the sheepdog block driver is deprecated"); - warned = true; - } -} - -/* - * 64 bit Fowler/Noll/Vo FNV-1a hash code - */ -static inline uint64_t fnv_64a_buf(void *buf, size_t len, uint64_t hval) -{ - unsigned char *bp = buf; - unsigned char *be = bp + len; - while (bp < be) { - hval ^= (uint64_t) *bp++; - hval += (hval << 1) + (hval << 4) + (hval << 5) + - (hval << 7) + (hval << 8) + (hval << 40); - } - return hval; -} - -static inline bool is_data_obj_writable(SheepdogInode *inode, unsigned int idx) -{ - return inode->vdi_id == inode->data_vdi_id[idx]; -} - -static inline bool is_data_obj(uint64_t oid) -{ - return !(VDI_BIT & oid); -} - -static inline uint64_t data_oid_to_idx(uint64_t oid) -{ - return oid & (MAX_DATA_OBJS - 1); -} - -static inline uint32_t oid_to_vid(uint64_t oid) -{ - return (oid & ~VDI_BIT) >> VDI_SPACE_SHIFT; -} - -static inline uint64_t vid_to_vdi_oid(uint32_t vid) -{ - return VDI_BIT | ((uint64_t)vid << VDI_SPACE_SHIFT); -} - -static inline uint64_t vid_to_vmstate_oid(uint32_t vid, uint32_t idx) -{ - return VMSTATE_BIT | ((uint64_t)vid << VDI_SPACE_SHIFT) | idx; -} - -static inline uint64_t vid_to_data_oid(uint32_t vid, uint32_t idx) -{ - return ((uint64_t)vid << VDI_SPACE_SHIFT) | idx; -} - -static inline bool is_snapshot(struct SheepdogInode *inode) -{ - return !!inode->snap_ctime; -} - -static inline size_t count_data_objs(const struct SheepdogInode *inode) -{ - return DIV_ROUND_UP(inode->vdi_size, - (1UL << inode->block_size_shift)); -} - -typedef struct SheepdogAIOCB SheepdogAIOCB; -typedef struct BDRVSheepdogState BDRVSheepdogState; - -typedef struct AIOReq { - SheepdogAIOCB *aiocb; - unsigned int iov_offset; - - uint64_t oid; - uint64_t base_oid; - uint64_t offset; - unsigned int data_len; - uint8_t flags; - uint32_t id; - bool create; - - QLIST_ENTRY(AIOReq) aio_siblings; -} AIOReq; - -enum AIOCBState { - AIOCB_WRITE_UDATA, - AIOCB_READ_UDATA, - AIOCB_FLUSH_CACHE, - AIOCB_DISCARD_OBJ, -}; - -#define AIOCBOverlapping(x, y) \ - (!(x->max_affect_data_idx < y->min_affect_data_idx \ - || y->max_affect_data_idx < x->min_affect_data_idx)) - -struct SheepdogAIOCB { - BDRVSheepdogState *s; - - QEMUIOVector *qiov; - - int64_t sector_num; - int nb_sectors; - - int ret; - enum AIOCBState aiocb_type; - - Coroutine *coroutine; - int nr_pending; - - uint32_t min_affect_data_idx; - uint32_t max_affect_data_idx; - - /* - * The difference between affect_data_idx and dirty_data_idx: - * affect_data_idx represents range of index of all request types. - * dirty_data_idx represents range of index updated by COW requests. - * dirty_data_idx is used for updating an inode object. - */ - uint32_t min_dirty_data_idx; - uint32_t max_dirty_data_idx; - - QLIST_ENTRY(SheepdogAIOCB) aiocb_siblings; -}; - -struct BDRVSheepdogState { - BlockDriverState *bs; - AioContext *aio_context; - - SheepdogInode inode; - - char name[SD_MAX_VDI_LEN]; - bool is_snapshot; - uint32_t cache_flags; - bool discard_supported; - - SocketAddress *addr; - int fd; - - CoMutex lock; - Coroutine *co_send; - Coroutine *co_recv; - - uint32_t aioreq_seq_num; - - /* Every aio request must be linked to either of these queues. */ - QLIST_HEAD(, AIOReq) inflight_aio_head; - QLIST_HEAD(, AIOReq) failed_aio_head; - - CoMutex queue_lock; - CoQueue overlapping_queue; - QLIST_HEAD(, SheepdogAIOCB) inflight_aiocb_head; -}; - -typedef struct BDRVSheepdogReopenState { - int fd; - int cache_flags; -} BDRVSheepdogReopenState; - -static const char *sd_strerror(int err) -{ - int i; - - static const struct { - int err; - const char *desc; - } errors[] = { - {SD_RES_SUCCESS, "Success"}, - {SD_RES_UNKNOWN, "Unknown error"}, - {SD_RES_NO_OBJ, "No object found"}, - {SD_RES_EIO, "I/O error"}, - {SD_RES_VDI_EXIST, "VDI exists already"}, - {SD_RES_INVALID_PARMS, "Invalid parameters"}, - {SD_RES_SYSTEM_ERROR, "System error"}, - {SD_RES_VDI_LOCKED, "VDI is already locked"}, - {SD_RES_NO_VDI, "No vdi found"}, - {SD_RES_NO_BASE_VDI, "No base VDI found"}, - {SD_RES_VDI_READ, "Failed read the requested VDI"}, - {SD_RES_VDI_WRITE, "Failed to write the requested VDI"}, - {SD_RES_BASE_VDI_READ, "Failed to read the base VDI"}, - {SD_RES_BASE_VDI_WRITE, "Failed to write the base VDI"}, - {SD_RES_NO_TAG, "Failed to find the requested tag"}, - {SD_RES_STARTUP, "The system is still booting"}, - {SD_RES_VDI_NOT_LOCKED, "VDI isn't locked"}, - {SD_RES_SHUTDOWN, "The system is shutting down"}, - {SD_RES_NO_MEM, "Out of memory on the server"}, - {SD_RES_FULL_VDI, "We already have the maximum vdis"}, - {SD_RES_VER_MISMATCH, "Protocol version mismatch"}, - {SD_RES_NO_SPACE, "Server has no space for new objects"}, - {SD_RES_WAIT_FOR_FORMAT, "Sheepdog is waiting for a format operation"}, - {SD_RES_WAIT_FOR_JOIN, "Sheepdog is waiting for other nodes joining"}, - {SD_RES_JOIN_FAILED, "Target node had failed to join sheepdog"}, - {SD_RES_HALT, "Sheepdog is stopped serving IO request"}, - {SD_RES_READONLY, "Object is read-only"}, - }; - - for (i = 0; i < ARRAY_SIZE(errors); ++i) { - if (errors[i].err == err) { - return errors[i].desc; - } - } - - return "Invalid error code"; -} - -/* - * Sheepdog I/O handling: - * - * 1. In sd_co_rw_vector, we send the I/O requests to the server and - * link the requests to the inflight_list in the - * BDRVSheepdogState. The function yields while waiting for - * receiving the response. - * - * 2. We receive the response in aio_read_response, the fd handler to - * the sheepdog connection. We switch back to sd_co_readv/sd_writev - * after all the requests belonging to the AIOCB are finished. If - * needed, sd_co_writev will send another requests for the vdi object. - */ - -static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb, - uint64_t oid, unsigned int data_len, - uint64_t offset, uint8_t flags, bool create, - uint64_t base_oid, unsigned int iov_offset) -{ - AIOReq *aio_req; - - aio_req = g_malloc(sizeof(*aio_req)); - aio_req->aiocb = acb; - aio_req->iov_offset = iov_offset; - aio_req->oid = oid; - aio_req->base_oid = base_oid; - aio_req->offset = offset; - aio_req->data_len = data_len; - aio_req->flags = flags; - aio_req->id = s->aioreq_seq_num++; - aio_req->create = create; - - acb->nr_pending++; - return aio_req; -} - -static void wait_for_overlapping_aiocb(BDRVSheepdogState *s, SheepdogAIOCB *acb) -{ - SheepdogAIOCB *cb; - -retry: - QLIST_FOREACH(cb, &s->inflight_aiocb_head, aiocb_siblings) { - if (AIOCBOverlapping(acb, cb)) { - qemu_co_queue_wait(&s->overlapping_queue, &s->queue_lock); - goto retry; - } - } -} - -static void sd_aio_setup(SheepdogAIOCB *acb, BDRVSheepdogState *s, - QEMUIOVector *qiov, int64_t sector_num, int nb_sectors, - int type) -{ - uint32_t object_size; - - object_size = (UINT32_C(1) << s->inode.block_size_shift); - - acb->s = s; - - acb->qiov = qiov; - - acb->sector_num = sector_num; - acb->nb_sectors = nb_sectors; - - acb->coroutine = qemu_coroutine_self(); - acb->ret = 0; - acb->nr_pending = 0; - - acb->min_affect_data_idx = acb->sector_num * BDRV_SECTOR_SIZE / object_size; - acb->max_affect_data_idx = (acb->sector_num * BDRV_SECTOR_SIZE + - acb->nb_sectors * BDRV_SECTOR_SIZE) / object_size; - - acb->min_dirty_data_idx = UINT32_MAX; - acb->max_dirty_data_idx = 0; - acb->aiocb_type = type; - - if (type == AIOCB_FLUSH_CACHE) { - return; - } - - qemu_co_mutex_lock(&s->queue_lock); - wait_for_overlapping_aiocb(s, acb); - QLIST_INSERT_HEAD(&s->inflight_aiocb_head, acb, aiocb_siblings); - qemu_co_mutex_unlock(&s->queue_lock); -} - -static SocketAddress *sd_server_config(QDict *options, Error **errp) -{ - QDict *server = NULL; - Visitor *iv = NULL; - SocketAddress *saddr = NULL; - - qdict_extract_subqdict(options, &server, "server."); - - iv = qobject_input_visitor_new_flat_confused(server, errp); - if (!iv) { - goto done; - } - - if (!visit_type_SocketAddress(iv, NULL, &saddr, errp)) { - goto done; - } - -done: - visit_free(iv); - qobject_unref(server); - return saddr; -} - -/* Return -EIO in case of error, file descriptor on success */ -static int connect_to_sdog(BDRVSheepdogState *s, Error **errp) -{ - int fd; - - fd = socket_connect(s->addr, errp); - - if (s->addr->type == SOCKET_ADDRESS_TYPE_INET && fd >= 0) { - int ret = socket_set_nodelay(fd); - if (ret < 0) { - warn_report("can't set TCP_NODELAY: %s", strerror(errno)); - } - } - - if (fd >= 0) { - qemu_set_nonblock(fd); - } else { - fd = -EIO; - } - - return fd; -} - -/* Return 0 on success and -errno in case of error */ -static coroutine_fn int send_co_req(int sockfd, SheepdogReq *hdr, void *data, - unsigned int *wlen) -{ - int ret; - - ret = qemu_co_send(sockfd, hdr, sizeof(*hdr)); - if (ret != sizeof(*hdr)) { - error_report("failed to send a req, %s", strerror(errno)); - return -errno; - } - - ret = qemu_co_send(sockfd, data, *wlen); - if (ret != *wlen) { - error_report("failed to send a req, %s", strerror(errno)); - return -errno; - } - - return ret; -} - -typedef struct SheepdogReqCo { - int sockfd; - BlockDriverState *bs; - AioContext *aio_context; - SheepdogReq *hdr; - void *data; - unsigned int *wlen; - unsigned int *rlen; - int ret; - bool finished; - Coroutine *co; -} SheepdogReqCo; - -static void restart_co_req(void *opaque) -{ - SheepdogReqCo *srco = opaque; - - aio_co_wake(srco->co); -} - -static coroutine_fn void do_co_req(void *opaque) -{ - int ret; - SheepdogReqCo *srco = opaque; - int sockfd = srco->sockfd; - SheepdogReq *hdr = srco->hdr; - void *data = srco->data; - unsigned int *wlen = srco->wlen; - unsigned int *rlen = srco->rlen; - - srco->co = qemu_coroutine_self(); - aio_set_fd_handler(srco->aio_context, sockfd, false, - NULL, restart_co_req, NULL, srco); - - ret = send_co_req(sockfd, hdr, data, wlen); - if (ret < 0) { - goto out; - } - - aio_set_fd_handler(srco->aio_context, sockfd, false, - restart_co_req, NULL, NULL, srco); - - ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr)); - if (ret != sizeof(*hdr)) { - error_report("failed to get a rsp, %s", strerror(errno)); - ret = -errno; - goto out; - } - - if (*rlen > hdr->data_length) { - *rlen = hdr->data_length; - } - - if (*rlen) { - ret = qemu_co_recv(sockfd, data, *rlen); - if (ret != *rlen) { - error_report("failed to get the data, %s", strerror(errno)); - ret = -errno; - goto out; - } - } - ret = 0; -out: - /* there is at most one request for this sockfd, so it is safe to - * set each handler to NULL. */ - aio_set_fd_handler(srco->aio_context, sockfd, false, - NULL, NULL, NULL, NULL); - - srco->co = NULL; - srco->ret = ret; - /* Set srco->finished before reading bs->wakeup. */ - qatomic_mb_set(&srco->finished, true); - if (srco->bs) { - bdrv_wakeup(srco->bs); - } -} - -/* - * Send the request to the sheep in a synchronous manner. - * - * Return 0 on success, -errno in case of error. - */ -static int do_req(int sockfd, BlockDriverState *bs, SheepdogReq *hdr, - void *data, unsigned int *wlen, unsigned int *rlen) -{ - Coroutine *co; - SheepdogReqCo srco = { - .sockfd = sockfd, - .aio_context = bs ? bdrv_get_aio_context(bs) : qemu_get_aio_context(), - .bs = bs, - .hdr = hdr, - .data = data, - .wlen = wlen, - .rlen = rlen, - .ret = 0, - .finished = false, - }; - - if (qemu_in_coroutine()) { - do_co_req(&srco); - } else { - co = qemu_coroutine_create(do_co_req, &srco); - if (bs) { - bdrv_coroutine_enter(bs, co); - BDRV_POLL_WHILE(bs, !srco.finished); - } else { - qemu_coroutine_enter(co); - while (!srco.finished) { - aio_poll(qemu_get_aio_context(), true); - } - } - } - - return srco.ret; -} - -static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req, - struct iovec *iov, int niov, - enum AIOCBState aiocb_type); -static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req); -static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag); -static int get_sheep_fd(BDRVSheepdogState *s, Error **errp); -static void co_write_request(void *opaque); - -static coroutine_fn void reconnect_to_sdog(void *opaque) -{ - BDRVSheepdogState *s = opaque; - AIOReq *aio_req, *next; - - aio_set_fd_handler(s->aio_context, s->fd, false, NULL, - NULL, NULL, NULL); - close(s->fd); - s->fd = -1; - - /* Wait for outstanding write requests to be completed. */ - while (s->co_send != NULL) { - co_write_request(opaque); - } - - /* Try to reconnect the sheepdog server every one second. */ - while (s->fd < 0) { - Error *local_err = NULL; - s->fd = get_sheep_fd(s, &local_err); - if (s->fd < 0) { - trace_sheepdog_reconnect_to_sdog(); - error_report_err(local_err); - qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, NANOSECONDS_PER_SECOND); - } - }; - - /* - * Now we have to resend all the request in the inflight queue. However, - * resend_aioreq() can yield and newly created requests can be added to the - * inflight queue before the coroutine is resumed. To avoid mixing them, we - * have to move all the inflight requests to the failed queue before - * resend_aioreq() is called. - */ - qemu_co_mutex_lock(&s->queue_lock); - QLIST_FOREACH_SAFE(aio_req, &s->inflight_aio_head, aio_siblings, next) { - QLIST_REMOVE(aio_req, aio_siblings); - QLIST_INSERT_HEAD(&s->failed_aio_head, aio_req, aio_siblings); - } - - /* Resend all the failed aio requests. */ - while (!QLIST_EMPTY(&s->failed_aio_head)) { - aio_req = QLIST_FIRST(&s->failed_aio_head); - QLIST_REMOVE(aio_req, aio_siblings); - qemu_co_mutex_unlock(&s->queue_lock); - resend_aioreq(s, aio_req); - qemu_co_mutex_lock(&s->queue_lock); - } - qemu_co_mutex_unlock(&s->queue_lock); -} - -/* - * Receive responses of the I/O requests. - * - * This function is registered as a fd handler, and called from the - * main loop when s->fd is ready for reading responses. - */ -static void coroutine_fn aio_read_response(void *opaque) -{ - SheepdogObjRsp rsp; - BDRVSheepdogState *s = opaque; - int fd = s->fd; - int ret; - AIOReq *aio_req = NULL; - SheepdogAIOCB *acb; - uint64_t idx; - - /* read a header */ - ret = qemu_co_recv(fd, &rsp, sizeof(rsp)); - if (ret != sizeof(rsp)) { - error_report("failed to get the header, %s", strerror(errno)); - goto err; - } - - /* find the right aio_req from the inflight aio list */ - QLIST_FOREACH(aio_req, &s->inflight_aio_head, aio_siblings) { - if (aio_req->id == rsp.id) { - break; - } - } - if (!aio_req) { - error_report("cannot find aio_req %x", rsp.id); - goto err; - } - - acb = aio_req->aiocb; - - switch (acb->aiocb_type) { - case AIOCB_WRITE_UDATA: - if (!is_data_obj(aio_req->oid)) { - break; - } - idx = data_oid_to_idx(aio_req->oid); - - if (aio_req->create) { - /* - * If the object is newly created one, we need to update - * the vdi object (metadata object). min_dirty_data_idx - * and max_dirty_data_idx are changed to include updated - * index between them. - */ - if (rsp.result == SD_RES_SUCCESS) { - s->inode.data_vdi_id[idx] = s->inode.vdi_id; - acb->max_dirty_data_idx = MAX(idx, acb->max_dirty_data_idx); - acb->min_dirty_data_idx = MIN(idx, acb->min_dirty_data_idx); - } - } - break; - case AIOCB_READ_UDATA: - ret = qemu_co_recvv(fd, acb->qiov->iov, acb->qiov->niov, - aio_req->iov_offset, rsp.data_length); - if (ret != rsp.data_length) { - error_report("failed to get the data, %s", strerror(errno)); - goto err; - } - break; - case AIOCB_FLUSH_CACHE: - if (rsp.result == SD_RES_INVALID_PARMS) { - trace_sheepdog_aio_read_response(); - s->cache_flags = SD_FLAG_CMD_DIRECT; - rsp.result = SD_RES_SUCCESS; - } - break; - case AIOCB_DISCARD_OBJ: - switch (rsp.result) { - case SD_RES_INVALID_PARMS: - error_report("server doesn't support discard command"); - rsp.result = SD_RES_SUCCESS; - s->discard_supported = false; - break; - default: - break; - } - } - - /* No more data for this aio_req (reload_inode below uses its own file - * descriptor handler which doesn't use co_recv). - */ - s->co_recv = NULL; - - qemu_co_mutex_lock(&s->queue_lock); - QLIST_REMOVE(aio_req, aio_siblings); - qemu_co_mutex_unlock(&s->queue_lock); - - switch (rsp.result) { - case SD_RES_SUCCESS: - break; - case SD_RES_READONLY: - if (s->inode.vdi_id == oid_to_vid(aio_req->oid)) { - ret = reload_inode(s, 0, ""); - if (ret < 0) { - goto err; - } - } - if (is_data_obj(aio_req->oid)) { - aio_req->oid = vid_to_data_oid(s->inode.vdi_id, - data_oid_to_idx(aio_req->oid)); - } else { - aio_req->oid = vid_to_vdi_oid(s->inode.vdi_id); - } - resend_aioreq(s, aio_req); - return; - default: - acb->ret = -EIO; - error_report("%s", sd_strerror(rsp.result)); - break; - } - - g_free(aio_req); - - if (!--acb->nr_pending) { - /* - * We've finished all requests which belong to the AIOCB, so - * we can switch back to sd_co_readv/writev now. - */ - aio_co_wake(acb->coroutine); - } - - return; - -err: - reconnect_to_sdog(opaque); -} - -static void co_read_response(void *opaque) -{ - BDRVSheepdogState *s = opaque; - - if (!s->co_recv) { - s->co_recv = qemu_coroutine_create(aio_read_response, opaque); - } - - aio_co_enter(s->aio_context, s->co_recv); -} - -static void co_write_request(void *opaque) -{ - BDRVSheepdogState *s = opaque; - - aio_co_wake(s->co_send); -} - -/* - * Return a socket descriptor to read/write objects. - * - * We cannot use this descriptor for other operations because - * the block driver may be on waiting response from the server. - */ -static int get_sheep_fd(BDRVSheepdogState *s, Error **errp) -{ - int fd; - - fd = connect_to_sdog(s, errp); - if (fd < 0) { - return fd; - } - - aio_set_fd_handler(s->aio_context, fd, false, - co_read_response, NULL, NULL, s); - return fd; -} - -/* - * Parse numeric snapshot ID in @str - * If @str can't be parsed as number, return false. - * Else, if the number is zero or too large, set *@snapid to zero and - * return true. - * Else, set *@snapid to the number and return true. - */ -static bool sd_parse_snapid(const char *str, uint32_t *snapid) -{ - unsigned long ul; - int ret; - - ret = qemu_strtoul(str, NULL, 10, &ul); - if (ret == -ERANGE) { - ul = ret = 0; - } - if (ret) { - return false; - } - if (ul > UINT32_MAX) { - ul = 0; - } - - *snapid = ul; - return true; -} - -static bool sd_parse_snapid_or_tag(const char *str, - uint32_t *snapid, char tag[]) -{ - if (!sd_parse_snapid(str, snapid)) { - *snapid = 0; - if (g_strlcpy(tag, str, SD_MAX_VDI_TAG_LEN) >= SD_MAX_VDI_TAG_LEN) { - return false; - } - } else if (!*snapid) { - return false; - } else { - tag[0] = 0; - } - return true; -} - -typedef struct { - const char *path; /* non-null iff transport is tcp */ - const char *host; /* valid when transport is tcp */ - int port; /* valid when transport is tcp */ - char vdi[SD_MAX_VDI_LEN]; - char tag[SD_MAX_VDI_TAG_LEN]; - uint32_t snap_id; - /* Remainder is only for sd_config_done() */ - URI *uri; - QueryParams *qp; -} SheepdogConfig; - -static void sd_config_done(SheepdogConfig *cfg) -{ - if (cfg->qp) { - query_params_free(cfg->qp); - } - uri_free(cfg->uri); -} - -static void sd_parse_uri(SheepdogConfig *cfg, const char *filename, - Error **errp) -{ - Error *err = NULL; - QueryParams *qp = NULL; - bool is_unix; - URI *uri; - - memset(cfg, 0, sizeof(*cfg)); - - cfg->uri = uri = uri_parse(filename); - if (!uri) { - error_setg(&err, "invalid URI '%s'", filename); - goto out; - } - - /* transport */ - if (!g_strcmp0(uri->scheme, "sheepdog")) { - is_unix = false; - } else if (!g_strcmp0(uri->scheme, "sheepdog+tcp")) { - is_unix = false; - } else if (!g_strcmp0(uri->scheme, "sheepdog+unix")) { - is_unix = true; - } else { - error_setg(&err, "URI scheme must be 'sheepdog', 'sheepdog+tcp'," - " or 'sheepdog+unix'"); - goto out; - } - - if (uri->path == NULL || !strcmp(uri->path, "/")) { - error_setg(&err, "missing file path in URI"); - goto out; - } - if (g_strlcpy(cfg->vdi, uri->path + 1, SD_MAX_VDI_LEN) - >= SD_MAX_VDI_LEN) { - error_setg(&err, "VDI name is too long"); - goto out; - } - - cfg->qp = qp = query_params_parse(uri->query); - - if (is_unix) { - /* sheepdog+unix:///vdiname?socket=path */ - if (uri->server || uri->port) { - error_setg(&err, "URI scheme %s doesn't accept a server address", - uri->scheme); - goto out; - } - if (!qp->n) { - error_setg(&err, - "URI scheme %s requires query parameter 'socket'", - uri->scheme); - goto out; - } - if (qp->n != 1 || strcmp(qp->p[0].name, "socket")) { - error_setg(&err, "unexpected query parameters"); - goto out; - } - cfg->path = qp->p[0].value; - } else { - /* sheepdog[+tcp]://[host:port]/vdiname */ - if (qp->n) { - error_setg(&err, "unexpected query parameters"); - goto out; - } - cfg->host = uri->server; - cfg->port = uri->port; - } - - /* snapshot tag */ - if (uri->fragment) { - if (!sd_parse_snapid_or_tag(uri->fragment, - &cfg->snap_id, cfg->tag)) { - error_setg(&err, "'%s' is not a valid snapshot ID", - uri->fragment); - goto out; - } - } else { - cfg->snap_id = CURRENT_VDI_ID; /* search current vdi */ - } - -out: - if (err) { - error_propagate(errp, err); - sd_config_done(cfg); - } -} - -/* - * Parse a filename (old syntax) - * - * filename must be one of the following formats: - * 1. [vdiname] - * 2. [vdiname]:[snapid] - * 3. [vdiname]:[tag] - * 4. [hostname]:[port]:[vdiname] - * 5. [hostname]:[port]:[vdiname]:[snapid] - * 6. [hostname]:[port]:[vdiname]:[tag] - * - * You can boot from the snapshot images by specifying `snapid` or - * `tag'. - * - * You can run VMs outside the Sheepdog cluster by specifying - * `hostname' and `port' (experimental). - */ -static void parse_vdiname(SheepdogConfig *cfg, const char *filename, - Error **errp) -{ - Error *err = NULL; - char *p, *q, *uri; - const char *host_spec, *vdi_spec; - int nr_sep; - - strstart(filename, "sheepdog:", &filename); - p = q = g_strdup(filename); - - /* count the number of separators */ - nr_sep = 0; - while (*p) { - if (*p == ':') { - nr_sep++; - } - p++; - } - p = q; - - /* use the first two tokens as host_spec. */ - if (nr_sep >= 2) { - host_spec = p; - p = strchr(p, ':'); - p++; - p = strchr(p, ':'); - *p++ = '\0'; - } else { - host_spec = ""; - } - - vdi_spec = p; - - p = strchr(vdi_spec, ':'); - if (p) { - *p++ = '#'; - } - - uri = g_strdup_printf("sheepdog://%s/%s", host_spec, vdi_spec); - - /* - * FIXME We to escape URI meta-characters, e.g. "x?y=z" - * produces "sheepdog://x?y=z". Because of that ... - */ - sd_parse_uri(cfg, uri, &err); - if (err) { - /* - * ... this can fail, but the error message is misleading. - * Replace it by the traditional useless one until the - * escaping is fixed. - */ - error_free(err); - error_setg(errp, "Can't parse filename"); - } - - g_free(q); - g_free(uri); -} - -static void sd_parse_filename(const char *filename, QDict *options, - Error **errp) -{ - Error *err = NULL; - SheepdogConfig cfg; - char buf[32]; - - if (strstr(filename, "://")) { - sd_parse_uri(&cfg, filename, &err); - } else { - parse_vdiname(&cfg, filename, &err); - } - if (err) { - error_propagate(errp, err); - return; - } - - if (cfg.path) { - qdict_set_default_str(options, "server.path", cfg.path); - qdict_set_default_str(options, "server.type", "unix"); - } else { - qdict_set_default_str(options, "server.type", "inet"); - qdict_set_default_str(options, "server.host", - cfg.host ?: SD_DEFAULT_ADDR); - snprintf(buf, sizeof(buf), "%d", cfg.port ?: SD_DEFAULT_PORT); - qdict_set_default_str(options, "server.port", buf); - } - qdict_set_default_str(options, "vdi", cfg.vdi); - qdict_set_default_str(options, "tag", cfg.tag); - if (cfg.snap_id) { - snprintf(buf, sizeof(buf), "%d", cfg.snap_id); - qdict_set_default_str(options, "snap-id", buf); - } - - sd_config_done(&cfg); -} - -static int find_vdi_name(BDRVSheepdogState *s, const char *filename, - uint32_t snapid, const char *tag, uint32_t *vid, - bool lock, Error **errp) -{ - int ret, fd; - SheepdogVdiReq hdr; - SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr; - unsigned int wlen, rlen = 0; - char buf[SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN] QEMU_NONSTRING; - - fd = connect_to_sdog(s, errp); - if (fd < 0) { - return fd; - } - - /* This pair of strncpy calls ensures that the buffer is zero-filled, - * which is desirable since we'll soon be sending those bytes, and - * don't want the send_req to read uninitialized data. - */ - strncpy(buf, filename, SD_MAX_VDI_LEN); - strncpy(buf + SD_MAX_VDI_LEN, tag, SD_MAX_VDI_TAG_LEN); - - memset(&hdr, 0, sizeof(hdr)); - if (lock) { - hdr.opcode = SD_OP_LOCK_VDI; - hdr.type = LOCK_TYPE_NORMAL; - } else { - hdr.opcode = SD_OP_GET_VDI_INFO; - } - wlen = SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN; - hdr.proto_ver = SD_PROTO_VER; - hdr.data_length = wlen; - hdr.snapid = snapid; - hdr.flags = SD_FLAG_CMD_WRITE; - - ret = do_req(fd, s->bs, (SheepdogReq *)&hdr, buf, &wlen, &rlen); - if (ret) { - error_setg_errno(errp, -ret, "cannot get vdi info"); - goto out; - } - - if (rsp->result != SD_RES_SUCCESS) { - error_setg(errp, "cannot get vdi info, %s, %s %" PRIu32 " %s", - sd_strerror(rsp->result), filename, snapid, tag); - if (rsp->result == SD_RES_NO_VDI) { - ret = -ENOENT; - } else if (rsp->result == SD_RES_VDI_LOCKED) { - ret = -EBUSY; - } else { - ret = -EIO; - } - goto out; - } - *vid = rsp->vdi_id; - - ret = 0; -out: - closesocket(fd); - return ret; -} - -static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req, - struct iovec *iov, int niov, - enum AIOCBState aiocb_type) -{ - int nr_copies = s->inode.nr_copies; - SheepdogObjReq hdr; - unsigned int wlen = 0; - int ret; - uint64_t oid = aio_req->oid; - unsigned int datalen = aio_req->data_len; - uint64_t offset = aio_req->offset; - uint8_t flags = aio_req->flags; - uint64_t old_oid = aio_req->base_oid; - bool create = aio_req->create; - - qemu_co_mutex_lock(&s->queue_lock); - QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings); - qemu_co_mutex_unlock(&s->queue_lock); - - if (!nr_copies) { - error_report("bug"); - } - - memset(&hdr, 0, sizeof(hdr)); - - switch (aiocb_type) { - case AIOCB_FLUSH_CACHE: - hdr.opcode = SD_OP_FLUSH_VDI; - break; - case AIOCB_READ_UDATA: - hdr.opcode = SD_OP_READ_OBJ; - hdr.flags = flags; - break; - case AIOCB_WRITE_UDATA: - if (create) { - hdr.opcode = SD_OP_CREATE_AND_WRITE_OBJ; - } else { - hdr.opcode = SD_OP_WRITE_OBJ; - } - wlen = datalen; - hdr.flags = SD_FLAG_CMD_WRITE | flags; - break; - case AIOCB_DISCARD_OBJ: - hdr.opcode = SD_OP_WRITE_OBJ; - hdr.flags = SD_FLAG_CMD_WRITE | flags; - s->inode.data_vdi_id[data_oid_to_idx(oid)] = 0; - offset = offsetof(SheepdogInode, - data_vdi_id[data_oid_to_idx(oid)]); - oid = vid_to_vdi_oid(s->inode.vdi_id); - wlen = datalen = sizeof(uint32_t); - break; - } - - if (s->cache_flags) { - hdr.flags |= s->cache_flags; - } - - hdr.oid = oid; - hdr.cow_oid = old_oid; - hdr.copies = s->inode.nr_copies; - - hdr.data_length = datalen; - hdr.offset = offset; - - hdr.id = aio_req->id; - - qemu_co_mutex_lock(&s->lock); - s->co_send = qemu_coroutine_self(); - aio_set_fd_handler(s->aio_context, s->fd, false, - co_read_response, co_write_request, NULL, s); - socket_set_cork(s->fd, 1); - - /* send a header */ - ret = qemu_co_send(s->fd, &hdr, sizeof(hdr)); - if (ret != sizeof(hdr)) { - error_report("failed to send a req, %s", strerror(errno)); - goto out; - } - - if (wlen) { - ret = qemu_co_sendv(s->fd, iov, niov, aio_req->iov_offset, wlen); - if (ret != wlen) { - error_report("failed to send a data, %s", strerror(errno)); - } - } -out: - socket_set_cork(s->fd, 0); - aio_set_fd_handler(s->aio_context, s->fd, false, - co_read_response, NULL, NULL, s); - s->co_send = NULL; - qemu_co_mutex_unlock(&s->lock); -} - -static int read_write_object(int fd, BlockDriverState *bs, char *buf, - uint64_t oid, uint8_t copies, - unsigned int datalen, uint64_t offset, - bool write, bool create, uint32_t cache_flags) -{ - SheepdogObjReq hdr; - SheepdogObjRsp *rsp = (SheepdogObjRsp *)&hdr; - unsigned int wlen, rlen; - int ret; - - memset(&hdr, 0, sizeof(hdr)); - - if (write) { - wlen = datalen; - rlen = 0; - hdr.flags = SD_FLAG_CMD_WRITE; - if (create) { - hdr.opcode = SD_OP_CREATE_AND_WRITE_OBJ; - } else { - hdr.opcode = SD_OP_WRITE_OBJ; - } - } else { - wlen = 0; - rlen = datalen; - hdr.opcode = SD_OP_READ_OBJ; - } - - hdr.flags |= cache_flags; - - hdr.oid = oid; - hdr.data_length = datalen; - hdr.offset = offset; - hdr.copies = copies; - - ret = do_req(fd, bs, (SheepdogReq *)&hdr, buf, &wlen, &rlen); - if (ret) { - error_report("failed to send a request to the sheep"); - return ret; - } - - switch (rsp->result) { - case SD_RES_SUCCESS: - return 0; - default: - error_report("%s", sd_strerror(rsp->result)); - return -EIO; - } -} - -static int read_object(int fd, BlockDriverState *bs, char *buf, - uint64_t oid, uint8_t copies, - unsigned int datalen, uint64_t offset, - uint32_t cache_flags) -{ - return read_write_object(fd, bs, buf, oid, copies, - datalen, offset, false, - false, cache_flags); -} - -static int write_object(int fd, BlockDriverState *bs, char *buf, - uint64_t oid, uint8_t copies, - unsigned int datalen, uint64_t offset, bool create, - uint32_t cache_flags) -{ - return read_write_object(fd, bs, buf, oid, copies, - datalen, offset, true, - create, cache_flags); -} - -/* update inode with the latest state */ -static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag) -{ - Error *local_err = NULL; - SheepdogInode *inode; - int ret = 0, fd; - uint32_t vid = 0; - - fd = connect_to_sdog(s, &local_err); - if (fd < 0) { - error_report_err(local_err); - return -EIO; - } - - inode = g_malloc(SD_INODE_HEADER_SIZE); - - ret = find_vdi_name(s, s->name, snapid, tag, &vid, false, &local_err); - if (ret) { - error_report_err(local_err); - goto out; - } - - ret = read_object(fd, s->bs, (char *)inode, vid_to_vdi_oid(vid), - s->inode.nr_copies, SD_INODE_HEADER_SIZE, 0, - s->cache_flags); - if (ret < 0) { - goto out; - } - - if (inode->vdi_id != s->inode.vdi_id) { - memcpy(&s->inode, inode, SD_INODE_HEADER_SIZE); - } - -out: - g_free(inode); - closesocket(fd); - - return ret; -} - -static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req) -{ - SheepdogAIOCB *acb = aio_req->aiocb; - - aio_req->create = false; - - /* check whether this request becomes a CoW one */ - if (acb->aiocb_type == AIOCB_WRITE_UDATA && is_data_obj(aio_req->oid)) { - int idx = data_oid_to_idx(aio_req->oid); - - if (is_data_obj_writable(&s->inode, idx)) { - goto out; - } - - if (s->inode.data_vdi_id[idx]) { - aio_req->base_oid = vid_to_data_oid(s->inode.data_vdi_id[idx], idx); - aio_req->flags |= SD_FLAG_CMD_COW; - } - aio_req->create = true; - } -out: - if (is_data_obj(aio_req->oid)) { - add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, - acb->aiocb_type); - } else { - struct iovec iov; - iov.iov_base = &s->inode; - iov.iov_len = sizeof(s->inode); - add_aio_request(s, aio_req, &iov, 1, AIOCB_WRITE_UDATA); - } -} - -static void sd_detach_aio_context(BlockDriverState *bs) -{ - BDRVSheepdogState *s = bs->opaque; - - aio_set_fd_handler(s->aio_context, s->fd, false, NULL, - NULL, NULL, NULL); -} - -static void sd_attach_aio_context(BlockDriverState *bs, - AioContext *new_context) -{ - BDRVSheepdogState *s = bs->opaque; - - s->aio_context = new_context; - aio_set_fd_handler(new_context, s->fd, false, - co_read_response, NULL, NULL, s); -} - -static QemuOptsList runtime_opts = { - .name = "sheepdog", - .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head), - .desc = { - { - .name = "vdi", - .type = QEMU_OPT_STRING, - }, - { - .name = "snap-id", - .type = QEMU_OPT_NUMBER, - }, - { - .name = "tag", - .type = QEMU_OPT_STRING, - }, - { /* end of list */ } - }, -}; - -static int sd_open(BlockDriverState *bs, QDict *options, int flags, - Error **errp) -{ - int ret, fd; - uint32_t vid = 0; - BDRVSheepdogState *s = bs->opaque; - const char *vdi, *snap_id_str, *tag; - uint64_t snap_id; - char *buf = NULL; - QemuOpts *opts; - - deprecation_warning(); - - s->bs = bs; - s->aio_context = bdrv_get_aio_context(bs); - - opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort); - if (!qemu_opts_absorb_qdict(opts, options, errp)) { - ret = -EINVAL; - goto err_no_fd; - } - - s->addr = sd_server_config(options, errp); - if (!s->addr) { - ret = -EINVAL; - goto err_no_fd; - } - - vdi = qemu_opt_get(opts, "vdi"); - snap_id_str = qemu_opt_get(opts, "snap-id"); - snap_id = qemu_opt_get_number(opts, "snap-id", CURRENT_VDI_ID); - tag = qemu_opt_get(opts, "tag"); - - if (!vdi) { - error_setg(errp, "parameter 'vdi' is missing"); - ret = -EINVAL; - goto err_no_fd; - } - if (strlen(vdi) >= SD_MAX_VDI_LEN) { - error_setg(errp, "value of parameter 'vdi' is too long"); - ret = -EINVAL; - goto err_no_fd; - } - - if (snap_id > UINT32_MAX) { - snap_id = 0; - } - if (snap_id_str && !snap_id) { - error_setg(errp, "'snap-id=%s' is not a valid snapshot ID", - snap_id_str); - ret = -EINVAL; - goto err_no_fd; - } - - if (!tag) { - tag = ""; - } - if (strlen(tag) >= SD_MAX_VDI_TAG_LEN) { - error_setg(errp, "value of parameter 'tag' is too long"); - ret = -EINVAL; - goto err_no_fd; - } - - QLIST_INIT(&s->inflight_aio_head); - QLIST_INIT(&s->failed_aio_head); - QLIST_INIT(&s->inflight_aiocb_head); - - s->fd = get_sheep_fd(s, errp); - if (s->fd < 0) { - ret = s->fd; - goto err_no_fd; - } - - ret = find_vdi_name(s, vdi, (uint32_t)snap_id, tag, &vid, true, errp); - if (ret) { - goto err; - } - - /* - * QEMU block layer emulates writethrough cache as 'writeback + flush', so - * we always set SD_FLAG_CMD_CACHE (writeback cache) as default. - */ - s->cache_flags = SD_FLAG_CMD_CACHE; - if (flags & BDRV_O_NOCACHE) { - s->cache_flags = SD_FLAG_CMD_DIRECT; - } - s->discard_supported = true; - - if (snap_id || tag[0]) { - trace_sheepdog_open(vid); - s->is_snapshot = true; - } - - fd = connect_to_sdog(s, errp); - if (fd < 0) { - ret = fd; - goto err; - } - - buf = g_malloc(SD_INODE_SIZE); - ret = read_object(fd, s->bs, buf, vid_to_vdi_oid(vid), - 0, SD_INODE_SIZE, 0, s->cache_flags); - - closesocket(fd); - - if (ret) { - error_setg(errp, "Can't read snapshot inode"); - goto err; - } - - memcpy(&s->inode, buf, sizeof(s->inode)); - - bs->total_sectors = s->inode.vdi_size / BDRV_SECTOR_SIZE; - bs->supported_truncate_flags = BDRV_REQ_ZERO_WRITE; - pstrcpy(s->name, sizeof(s->name), vdi); - qemu_co_mutex_init(&s->lock); - qemu_co_mutex_init(&s->queue_lock); - qemu_co_queue_init(&s->overlapping_queue); - qemu_opts_del(opts); - g_free(buf); - return 0; - -err: - aio_set_fd_handler(bdrv_get_aio_context(bs), s->fd, - false, NULL, NULL, NULL, NULL); - closesocket(s->fd); -err_no_fd: - qemu_opts_del(opts); - g_free(buf); - return ret; -} - -static int sd_reopen_prepare(BDRVReopenState *state, BlockReopenQueue *queue, - Error **errp) -{ - BDRVSheepdogState *s = state->bs->opaque; - BDRVSheepdogReopenState *re_s; - int ret = 0; - - re_s = state->opaque = g_new0(BDRVSheepdogReopenState, 1); - - re_s->cache_flags = SD_FLAG_CMD_CACHE; - if (state->flags & BDRV_O_NOCACHE) { - re_s->cache_flags = SD_FLAG_CMD_DIRECT; - } - - re_s->fd = get_sheep_fd(s, errp); - if (re_s->fd < 0) { - ret = re_s->fd; - return ret; - } - - return ret; -} - -static void sd_reopen_commit(BDRVReopenState *state) -{ - BDRVSheepdogReopenState *re_s = state->opaque; - BDRVSheepdogState *s = state->bs->opaque; - - if (s->fd) { - aio_set_fd_handler(s->aio_context, s->fd, false, - NULL, NULL, NULL, NULL); - closesocket(s->fd); - } - - s->fd = re_s->fd; - s->cache_flags = re_s->cache_flags; - - g_free(state->opaque); - state->opaque = NULL; - - return; -} - -static void sd_reopen_abort(BDRVReopenState *state) -{ - BDRVSheepdogReopenState *re_s = state->opaque; - BDRVSheepdogState *s = state->bs->opaque; - - if (re_s == NULL) { - return; - } - - if (re_s->fd) { - aio_set_fd_handler(s->aio_context, re_s->fd, false, - NULL, NULL, NULL, NULL); - closesocket(re_s->fd); - } - - g_free(state->opaque); - state->opaque = NULL; - - return; -} - -static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot, - Error **errp) -{ - SheepdogVdiReq hdr; - SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr; - int fd, ret; - unsigned int wlen, rlen = 0; - char buf[SD_MAX_VDI_LEN]; - - fd = connect_to_sdog(s, errp); - if (fd < 0) { - return fd; - } - - /* FIXME: would it be better to fail (e.g., return -EIO) when filename - * does not fit in buf? For now, just truncate and avoid buffer overrun. - */ - memset(buf, 0, sizeof(buf)); - pstrcpy(buf, sizeof(buf), s->name); - - memset(&hdr, 0, sizeof(hdr)); - hdr.opcode = SD_OP_NEW_VDI; - hdr.base_vdi_id = s->inode.vdi_id; - - wlen = SD_MAX_VDI_LEN; - - hdr.flags = SD_FLAG_CMD_WRITE; - hdr.snapid = snapshot; - - hdr.data_length = wlen; - hdr.vdi_size = s->inode.vdi_size; - hdr.copy_policy = s->inode.copy_policy; - hdr.copies = s->inode.nr_copies; - hdr.block_size_shift = s->inode.block_size_shift; - - ret = do_req(fd, NULL, (SheepdogReq *)&hdr, buf, &wlen, &rlen); - - closesocket(fd); - - if (ret) { - error_setg_errno(errp, -ret, "create failed"); - return ret; - } - - if (rsp->result != SD_RES_SUCCESS) { - error_setg(errp, "%s, %s", sd_strerror(rsp->result), s->inode.name); - return -EIO; - } - - if (vdi_id) { - *vdi_id = rsp->vdi_id; - } - - return 0; -} - -static int sd_prealloc(BlockDriverState *bs, int64_t old_size, int64_t new_size, - Error **errp) -{ - BlockBackend *blk = NULL; - BDRVSheepdogState *base = bs->opaque; - unsigned long buf_size; - uint32_t idx, max_idx; - uint32_t object_size; - void *buf = NULL; - int ret; - - blk = blk_new_with_bs(bs, - BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE | BLK_PERM_RESIZE, - BLK_PERM_ALL, errp); - - if (!blk) { - ret = -EPERM; - goto out_with_err_set; - } - - blk_set_allow_write_beyond_eof(blk, true); - - object_size = (UINT32_C(1) << base->inode.block_size_shift); - buf_size = MIN(object_size, SD_DATA_OBJ_SIZE); - buf = g_malloc0(buf_size); - - max_idx = DIV_ROUND_UP(new_size, buf_size); - - for (idx = old_size / buf_size; idx < max_idx; idx++) { - /* - * The created image can be a cloned image, so we need to read - * a data from the source image. - */ - ret = blk_pread(blk, idx * buf_size, buf, buf_size); - if (ret < 0) { - goto out; - } - ret = blk_pwrite(blk, idx * buf_size, buf, buf_size, 0); - if (ret < 0) { - goto out; - } - } - - ret = 0; -out: - if (ret < 0) { - error_setg_errno(errp, -ret, "Can't pre-allocate"); - } -out_with_err_set: - blk_unref(blk); - g_free(buf); - - return ret; -} - -static int sd_create_prealloc(BlockdevOptionsSheepdog *location, int64_t size, - Error **errp) -{ - BlockDriverState *bs; - Visitor *v; - QObject *obj = NULL; - QDict *qdict; - int ret; - - v = qobject_output_visitor_new(&obj); - visit_type_BlockdevOptionsSheepdog(v, NULL, &location, &error_abort); - visit_free(v); - - qdict = qobject_to(QDict, obj); - qdict_flatten(qdict); - - qdict_put_str(qdict, "driver", "sheepdog"); - - bs = bdrv_open(NULL, NULL, qdict, BDRV_O_PROTOCOL | BDRV_O_RDWR, errp); - if (bs == NULL) { - ret = -EIO; - goto fail; - } - - ret = sd_prealloc(bs, 0, size, errp); -fail: - bdrv_unref(bs); - qobject_unref(qdict); - return ret; -} - -static int parse_redundancy(BDRVSheepdogState *s, SheepdogRedundancy *opt) -{ - struct SheepdogInode *inode = &s->inode; - - switch (opt->type) { - case SHEEPDOG_REDUNDANCY_TYPE_FULL: - if (opt->u.full.copies > SD_MAX_COPIES || opt->u.full.copies < 1) { - return -EINVAL; - } - inode->copy_policy = 0; - inode->nr_copies = opt->u.full.copies; - return 0; - - case SHEEPDOG_REDUNDANCY_TYPE_ERASURE_CODED: - { - int64_t copy = opt->u.erasure_coded.data_strips; - int64_t parity = opt->u.erasure_coded.parity_strips; - - if (copy != 2 && copy != 4 && copy != 8 && copy != 16) { - return -EINVAL; - } - - if (parity >= SD_EC_MAX_STRIP || parity < 1) { - return -EINVAL; - } - - /* - * 4 bits for parity and 4 bits for data. - * We have to compress upper data bits because it can't represent 16 - */ - inode->copy_policy = ((copy / 2) << 4) + parity; - inode->nr_copies = copy + parity; - return 0; - } - - default: - g_assert_not_reached(); - } - - return -EINVAL; -} - -/* - * Sheepdog support two kinds of redundancy, full replication and erasure - * coding. - * - * # create a fully replicated vdi with x copies - * -o redundancy=x (1 <= x <= SD_MAX_COPIES) - * - * # create a erasure coded vdi with x data strips and y parity strips - * -o redundancy=x:y (x must be one of {2,4,8,16} and 1 <= y < SD_EC_MAX_STRIP) - */ -static SheepdogRedundancy *parse_redundancy_str(const char *opt) -{ - SheepdogRedundancy *redundancy; - const char *n1, *n2; - long copy, parity; - char p[10]; - int ret; - - pstrcpy(p, sizeof(p), opt); - n1 = strtok(p, ":"); - n2 = strtok(NULL, ":"); - - if (!n1) { - return NULL; - } - - ret = qemu_strtol(n1, NULL, 10, ©); - if (ret < 0) { - return NULL; - } - - redundancy = g_new0(SheepdogRedundancy, 1); - if (!n2) { - *redundancy = (SheepdogRedundancy) { - .type = SHEEPDOG_REDUNDANCY_TYPE_FULL, - .u.full.copies = copy, - }; - } else { - ret = qemu_strtol(n2, NULL, 10, &parity); - if (ret < 0) { - g_free(redundancy); - return NULL; - } - - *redundancy = (SheepdogRedundancy) { - .type = SHEEPDOG_REDUNDANCY_TYPE_ERASURE_CODED, - .u.erasure_coded = { - .data_strips = copy, - .parity_strips = parity, - }, - }; - } - - return redundancy; -} - -static int parse_block_size_shift(BDRVSheepdogState *s, - BlockdevCreateOptionsSheepdog *opts) -{ - struct SheepdogInode *inode = &s->inode; - uint64_t object_size; - int obj_order; - - if (opts->has_object_size) { - object_size = opts->object_size; - - if ((object_size - 1) & object_size) { /* not a power of 2? */ - return -EINVAL; - } - obj_order = ctz32(object_size); - if (obj_order < 20 || obj_order > 31) { - return -EINVAL; - } - inode->block_size_shift = (uint8_t)obj_order; - } - - return 0; -} - -static int sd_co_create(BlockdevCreateOptions *options, Error **errp) -{ - BlockdevCreateOptionsSheepdog *opts = &options->u.sheepdog; - int ret = 0; - uint32_t vid = 0; - char *backing_file = NULL; - char *buf = NULL; - BDRVSheepdogState *s; - uint64_t max_vdi_size; - bool prealloc = false; - - assert(options->driver == BLOCKDEV_DRIVER_SHEEPDOG); - - deprecation_warning(); - - s = g_new0(BDRVSheepdogState, 1); - - /* Steal SocketAddress from QAPI, set NULL to prevent double free */ - s->addr = opts->location->server; - opts->location->server = NULL; - - if (strlen(opts->location->vdi) >= sizeof(s->name)) { - error_setg(errp, "'vdi' string too long"); - ret = -EINVAL; - goto out; - } - pstrcpy(s->name, sizeof(s->name), opts->location->vdi); - - s->inode.vdi_size = opts->size; - backing_file = opts->backing_file; - - if (!opts->has_preallocation) { - opts->preallocation = PREALLOC_MODE_OFF; - } - switch (opts->preallocation) { - case PREALLOC_MODE_OFF: - prealloc = false; - break; - case PREALLOC_MODE_FULL: - prealloc = true; - break; - default: - error_setg(errp, "Preallocation mode not supported for Sheepdog"); - ret = -EINVAL; - goto out; - } - - if (opts->has_redundancy) { - ret = parse_redundancy(s, opts->redundancy); - if (ret < 0) { - error_setg(errp, "Invalid redundancy mode"); - goto out; - } - } - ret = parse_block_size_shift(s, opts); - if (ret < 0) { - error_setg(errp, "Invalid object_size." - " obect_size needs to be power of 2" - " and be limited from 2^20 to 2^31"); - goto out; - } - - if (opts->has_backing_file) { - BlockBackend *blk; - BDRVSheepdogState *base; - BlockDriver *drv; - - /* Currently, only Sheepdog backing image is supported. */ - drv = bdrv_find_protocol(opts->backing_file, true, NULL); - if (!drv || strcmp(drv->protocol_name, "sheepdog") != 0) { - error_setg(errp, "backing_file must be a sheepdog image"); - ret = -EINVAL; - goto out; - } - - blk = blk_new_open(opts->backing_file, NULL, NULL, - BDRV_O_PROTOCOL, errp); - if (blk == NULL) { - ret = -EIO; - goto out; - } - - base = blk_bs(blk)->opaque; - - if (!is_snapshot(&base->inode)) { - error_setg(errp, "cannot clone from a non snapshot vdi"); - blk_unref(blk); - ret = -EINVAL; - goto out; - } - s->inode.vdi_id = base->inode.vdi_id; - blk_unref(blk); - } - - s->aio_context = qemu_get_aio_context(); - - /* if block_size_shift is not specified, get cluster default value */ - if (s->inode.block_size_shift == 0) { - SheepdogVdiReq hdr; - SheepdogClusterRsp *rsp = (SheepdogClusterRsp *)&hdr; - int fd; - unsigned int wlen = 0, rlen = 0; - - fd = connect_to_sdog(s, errp); - if (fd < 0) { - ret = fd; - goto out; - } - - memset(&hdr, 0, sizeof(hdr)); - hdr.opcode = SD_OP_GET_CLUSTER_DEFAULT; - hdr.proto_ver = SD_PROTO_VER; - - ret = do_req(fd, NULL, (SheepdogReq *)&hdr, - NULL, &wlen, &rlen); - closesocket(fd); - if (ret) { - error_setg_errno(errp, -ret, "failed to get cluster default"); - goto out; - } - if (rsp->result == SD_RES_SUCCESS) { - s->inode.block_size_shift = rsp->block_size_shift; - } else { - s->inode.block_size_shift = SD_DEFAULT_BLOCK_SIZE_SHIFT; - } - } - - max_vdi_size = (UINT64_C(1) << s->inode.block_size_shift) * MAX_DATA_OBJS; - - if (s->inode.vdi_size > max_vdi_size) { - error_setg(errp, "An image is too large." - " The maximum image size is %"PRIu64 "GB", - max_vdi_size / 1024 / 1024 / 1024); - ret = -EINVAL; - goto out; - } - - ret = do_sd_create(s, &vid, 0, errp); - if (ret) { - goto out; - } - - if (prealloc) { - ret = sd_create_prealloc(opts->location, opts->size, errp); - } -out: - g_free(backing_file); - g_free(buf); - g_free(s->addr); - g_free(s); - return ret; -} - -static int coroutine_fn sd_co_create_opts(BlockDriver *drv, - const char *filename, - QemuOpts *opts, - Error **errp) -{ - BlockdevCreateOptions *create_options = NULL; - QDict *qdict = NULL, *location_qdict; - Visitor *v; - char *redundancy = NULL; - Error *local_err = NULL; - int ret; - char *backing_fmt = NULL; - - redundancy = qemu_opt_get_del(opts, BLOCK_OPT_REDUNDANCY); - backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT); - - if (backing_fmt && strcmp(backing_fmt, "sheepdog") != 0) { - error_setg(errp, "backing_file must be a sheepdog image"); - ret = -EINVAL; - goto fail; - } - - qdict = qemu_opts_to_qdict(opts, NULL); - qdict_put_str(qdict, "driver", "sheepdog"); - - location_qdict = qdict_new(); - qdict_put(qdict, "location", location_qdict); - - sd_parse_filename(filename, location_qdict, &local_err); - if (local_err) { - error_propagate(errp, local_err); - ret = -EINVAL; - goto fail; - } - - qdict_flatten(qdict); - - /* Change legacy command line options into QMP ones */ - static const QDictRenames opt_renames[] = { - { BLOCK_OPT_BACKING_FILE, "backing-file" }, - { BLOCK_OPT_OBJECT_SIZE, "object-size" }, - { NULL, NULL }, - }; - - if (!qdict_rename_keys(qdict, opt_renames, errp)) { - ret = -EINVAL; - goto fail; - } - - /* Get the QAPI object */ - v = qobject_input_visitor_new_flat_confused(qdict, errp); - if (!v) { - ret = -EINVAL; - goto fail; - } - - visit_type_BlockdevCreateOptions(v, NULL, &create_options, errp); - visit_free(v); - if (!create_options) { - ret = -EINVAL; - goto fail; - } - - assert(create_options->driver == BLOCKDEV_DRIVER_SHEEPDOG); - create_options->u.sheepdog.size = - ROUND_UP(create_options->u.sheepdog.size, BDRV_SECTOR_SIZE); - - if (redundancy) { - create_options->u.sheepdog.has_redundancy = true; - create_options->u.sheepdog.redundancy = - parse_redundancy_str(redundancy); - if (create_options->u.sheepdog.redundancy == NULL) { - error_setg(errp, "Invalid redundancy mode"); - ret = -EINVAL; - goto fail; - } - } - - ret = sd_co_create(create_options, errp); -fail: - qapi_free_BlockdevCreateOptions(create_options); - qobject_unref(qdict); - g_free(redundancy); - g_free(backing_fmt); - return ret; -} - -static void sd_close(BlockDriverState *bs) -{ - Error *local_err = NULL; - BDRVSheepdogState *s = bs->opaque; - SheepdogVdiReq hdr; - SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr; - unsigned int wlen, rlen = 0; - int fd, ret; - - trace_sheepdog_close(s->name); - - fd = connect_to_sdog(s, &local_err); - if (fd < 0) { - error_report_err(local_err); - return; - } - - memset(&hdr, 0, sizeof(hdr)); - - hdr.opcode = SD_OP_RELEASE_VDI; - hdr.type = LOCK_TYPE_NORMAL; - hdr.base_vdi_id = s->inode.vdi_id; - wlen = strlen(s->name) + 1; - hdr.data_length = wlen; - hdr.flags = SD_FLAG_CMD_WRITE; - - ret = do_req(fd, s->bs, (SheepdogReq *)&hdr, - s->name, &wlen, &rlen); - - closesocket(fd); - - if (!ret && rsp->result != SD_RES_SUCCESS && - rsp->result != SD_RES_VDI_NOT_LOCKED) { - error_report("%s, %s", sd_strerror(rsp->result), s->name); - } - - aio_set_fd_handler(bdrv_get_aio_context(bs), s->fd, - false, NULL, NULL, NULL, NULL); - closesocket(s->fd); - qapi_free_SocketAddress(s->addr); -} - -static int64_t sd_getlength(BlockDriverState *bs) -{ - BDRVSheepdogState *s = bs->opaque; - - return s->inode.vdi_size; -} - -static int coroutine_fn sd_co_truncate(BlockDriverState *bs, int64_t offset, - bool exact, PreallocMode prealloc, - BdrvRequestFlags flags, Error **errp) -{ - BDRVSheepdogState *s = bs->opaque; - int ret, fd; - unsigned int datalen; - uint64_t max_vdi_size; - int64_t old_size = s->inode.vdi_size; - - if (prealloc != PREALLOC_MODE_OFF && prealloc != PREALLOC_MODE_FULL) { - error_setg(errp, "Unsupported preallocation mode '%s'", - PreallocMode_str(prealloc)); - return -ENOTSUP; - } - - max_vdi_size = (UINT64_C(1) << s->inode.block_size_shift) * MAX_DATA_OBJS; - if (offset < old_size) { - error_setg(errp, "shrinking is not supported"); - return -EINVAL; - } else if (offset > max_vdi_size) { - error_setg(errp, "too big image size"); - return -EINVAL; - } - - fd = connect_to_sdog(s, errp); - if (fd < 0) { - return fd; - } - - /* we don't need to update entire object */ - datalen = SD_INODE_HEADER_SIZE; - s->inode.vdi_size = offset; - ret = write_object(fd, s->bs, (char *)&s->inode, - vid_to_vdi_oid(s->inode.vdi_id), s->inode.nr_copies, - datalen, 0, false, s->cache_flags); - close(fd); - - if (ret < 0) { - error_setg_errno(errp, -ret, "failed to update an inode"); - return ret; - } - - if (prealloc == PREALLOC_MODE_FULL) { - ret = sd_prealloc(bs, old_size, offset, errp); - if (ret < 0) { - return ret; - } - } - - return 0; -} - -/* - * This function is called after writing data objects. If we need to - * update metadata, this sends a write request to the vdi object. - */ -static void coroutine_fn sd_write_done(SheepdogAIOCB *acb) -{ - BDRVSheepdogState *s = acb->s; - struct iovec iov; - AIOReq *aio_req; - uint32_t offset, data_len, mn, mx; - - mn = acb->min_dirty_data_idx; - mx = acb->max_dirty_data_idx; - if (mn <= mx) { - /* we need to update the vdi object. */ - ++acb->nr_pending; - offset = sizeof(s->inode) - sizeof(s->inode.data_vdi_id) + - mn * sizeof(s->inode.data_vdi_id[0]); - data_len = (mx - mn + 1) * sizeof(s->inode.data_vdi_id[0]); - - acb->min_dirty_data_idx = UINT32_MAX; - acb->max_dirty_data_idx = 0; - - iov.iov_base = &s->inode; - iov.iov_len = sizeof(s->inode); - aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id), - data_len, offset, 0, false, 0, offset); - add_aio_request(s, aio_req, &iov, 1, AIOCB_WRITE_UDATA); - if (--acb->nr_pending) { - qemu_coroutine_yield(); - } - } -} - -/* Delete current working VDI on the snapshot chain */ -static bool sd_delete(BDRVSheepdogState *s) -{ - Error *local_err = NULL; - unsigned int wlen = SD_MAX_VDI_LEN, rlen = 0; - SheepdogVdiReq hdr = { - .opcode = SD_OP_DEL_VDI, - .base_vdi_id = s->inode.vdi_id, - .data_length = wlen, - .flags = SD_FLAG_CMD_WRITE, - }; - SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr; - int fd, ret; - - fd = connect_to_sdog(s, &local_err); - if (fd < 0) { - error_report_err(local_err); - return false; - } - - ret = do_req(fd, s->bs, (SheepdogReq *)&hdr, - s->name, &wlen, &rlen); - closesocket(fd); - if (ret) { - return false; - } - switch (rsp->result) { - case SD_RES_NO_VDI: - error_report("%s was already deleted", s->name); - /* fall through */ - case SD_RES_SUCCESS: - break; - default: - error_report("%s, %s", sd_strerror(rsp->result), s->name); - return false; - } - - return true; -} - -/* - * Create a writable VDI from a snapshot - */ -static int sd_create_branch(BDRVSheepdogState *s) -{ - Error *local_err = NULL; - int ret, fd; - uint32_t vid; - char *buf; - bool deleted; - - trace_sheepdog_create_branch_snapshot(s->inode.vdi_id); - - buf = g_malloc(SD_INODE_SIZE); - - /* - * Even If deletion fails, we will just create extra snapshot based on - * the working VDI which was supposed to be deleted. So no need to - * false bail out. - */ - deleted = sd_delete(s); - ret = do_sd_create(s, &vid, !deleted, &local_err); - if (ret) { - error_report_err(local_err); - goto out; - } - - trace_sheepdog_create_branch_created(vid); - - fd = connect_to_sdog(s, &local_err); - if (fd < 0) { - error_report_err(local_err); - ret = fd; - goto out; - } - - ret = read_object(fd, s->bs, buf, vid_to_vdi_oid(vid), - s->inode.nr_copies, SD_INODE_SIZE, 0, s->cache_flags); - - closesocket(fd); - - if (ret < 0) { - goto out; - } - - memcpy(&s->inode, buf, sizeof(s->inode)); - - s->is_snapshot = false; - ret = 0; - trace_sheepdog_create_branch_new(s->inode.vdi_id); - -out: - g_free(buf); - - return ret; -} - -/* - * Send I/O requests to the server. - * - * This function sends requests to the server, links the requests to - * the inflight_list in BDRVSheepdogState, and exits without - * waiting the response. The responses are received in the - * `aio_read_response' function which is called from the main loop as - * a fd handler. - * - * Returns 1 when we need to wait a response, 0 when there is no sent - * request and -errno in error cases. - */ -static void coroutine_fn sd_co_rw_vector(SheepdogAIOCB *acb) -{ - int ret = 0; - unsigned long len, done = 0, total = acb->nb_sectors * BDRV_SECTOR_SIZE; - unsigned long idx; - uint32_t object_size; - uint64_t oid; - uint64_t offset; - BDRVSheepdogState *s = acb->s; - SheepdogInode *inode = &s->inode; - AIOReq *aio_req; - - if (acb->aiocb_type == AIOCB_WRITE_UDATA && s->is_snapshot) { - /* - * In the case we open the snapshot VDI, Sheepdog creates the - * writable VDI when we do a write operation first. - */ - ret = sd_create_branch(s); - if (ret) { - acb->ret = -EIO; - return; - } - } - - object_size = (UINT32_C(1) << inode->block_size_shift); - idx = acb->sector_num * BDRV_SECTOR_SIZE / object_size; - offset = (acb->sector_num * BDRV_SECTOR_SIZE) % object_size; - - /* - * Make sure we don't free the aiocb before we are done with all requests. - * This additional reference is dropped at the end of this function. - */ - acb->nr_pending++; - - while (done != total) { - uint8_t flags = 0; - uint64_t old_oid = 0; - bool create = false; - - oid = vid_to_data_oid(inode->data_vdi_id[idx], idx); - - len = MIN(total - done, object_size - offset); - - switch (acb->aiocb_type) { - case AIOCB_READ_UDATA: - if (!inode->data_vdi_id[idx]) { - qemu_iovec_memset(acb->qiov, done, 0, len); - goto done; - } - break; - case AIOCB_WRITE_UDATA: - if (!inode->data_vdi_id[idx]) { - create = true; - } else if (!is_data_obj_writable(inode, idx)) { - /* Copy-On-Write */ - create = true; - old_oid = oid; - flags = SD_FLAG_CMD_COW; - } - break; - case AIOCB_DISCARD_OBJ: - /* - * We discard the object only when the whole object is - * 1) allocated 2) trimmed. Otherwise, simply skip it. - */ - if (len != object_size || inode->data_vdi_id[idx] == 0) { - goto done; - } - break; - default: - break; - } - - if (create) { - trace_sheepdog_co_rw_vector_update(inode->vdi_id, oid, - vid_to_data_oid(inode->data_vdi_id[idx], idx), - idx); - oid = vid_to_data_oid(inode->vdi_id, idx); - trace_sheepdog_co_rw_vector_new(oid); - } - - aio_req = alloc_aio_req(s, acb, oid, len, offset, flags, create, - old_oid, - acb->aiocb_type == AIOCB_DISCARD_OBJ ? - 0 : done); - add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, - acb->aiocb_type); - done: - offset = 0; - idx++; - done += len; - } - if (--acb->nr_pending) { - qemu_coroutine_yield(); - } -} - -static void sd_aio_complete(SheepdogAIOCB *acb) -{ - BDRVSheepdogState *s; - if (acb->aiocb_type == AIOCB_FLUSH_CACHE) { - return; - } - - s = acb->s; - qemu_co_mutex_lock(&s->queue_lock); - QLIST_REMOVE(acb, aiocb_siblings); - qemu_co_queue_restart_all(&s->overlapping_queue); - qemu_co_mutex_unlock(&s->queue_lock); -} - -static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov, - int flags) -{ - SheepdogAIOCB acb; - int ret; - int64_t offset = (sector_num + nb_sectors) * BDRV_SECTOR_SIZE; - BDRVSheepdogState *s = bs->opaque; - - assert(!flags); - if (offset > s->inode.vdi_size) { - ret = sd_co_truncate(bs, offset, false, PREALLOC_MODE_OFF, 0, NULL); - if (ret < 0) { - return ret; - } - } - - sd_aio_setup(&acb, s, qiov, sector_num, nb_sectors, AIOCB_WRITE_UDATA); - sd_co_rw_vector(&acb); - sd_write_done(&acb); - sd_aio_complete(&acb); - - return acb.ret; -} - -static coroutine_fn int sd_co_readv(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov) -{ - SheepdogAIOCB acb; - BDRVSheepdogState *s = bs->opaque; - - sd_aio_setup(&acb, s, qiov, sector_num, nb_sectors, AIOCB_READ_UDATA); - sd_co_rw_vector(&acb); - sd_aio_complete(&acb); - - return acb.ret; -} - -static int coroutine_fn sd_co_flush_to_disk(BlockDriverState *bs) -{ - BDRVSheepdogState *s = bs->opaque; - SheepdogAIOCB acb; - AIOReq *aio_req; - - if (s->cache_flags != SD_FLAG_CMD_CACHE) { - return 0; - } - - sd_aio_setup(&acb, s, NULL, 0, 0, AIOCB_FLUSH_CACHE); - - acb.nr_pending++; - aio_req = alloc_aio_req(s, &acb, vid_to_vdi_oid(s->inode.vdi_id), - 0, 0, 0, false, 0, 0); - add_aio_request(s, aio_req, NULL, 0, acb.aiocb_type); - - if (--acb.nr_pending) { - qemu_coroutine_yield(); - } - - sd_aio_complete(&acb); - return acb.ret; -} - -static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info) -{ - Error *local_err = NULL; - BDRVSheepdogState *s = bs->opaque; - int ret, fd; - uint32_t new_vid; - SheepdogInode *inode; - unsigned int datalen; - - trace_sheepdog_snapshot_create_info(sn_info->name, sn_info->id_str, s->name, - sn_info->vm_state_size, s->is_snapshot); - - if (s->is_snapshot) { - error_report("You can't create a snapshot of a snapshot VDI, " - "%s (%" PRIu32 ").", s->name, s->inode.vdi_id); - - return -EINVAL; - } - - trace_sheepdog_snapshot_create(sn_info->name, sn_info->id_str); - - s->inode.vm_state_size = sn_info->vm_state_size; - s->inode.vm_clock_nsec = sn_info->vm_clock_nsec; - /* It appears that inode.tag does not require a NUL terminator, - * which means this use of strncpy is ok. - */ - strncpy(s->inode.tag, sn_info->name, sizeof(s->inode.tag)); - /* we don't need to update entire object */ - datalen = SD_INODE_HEADER_SIZE; - inode = g_malloc(datalen); - - /* refresh inode. */ - fd = connect_to_sdog(s, &local_err); - if (fd < 0) { - error_report_err(local_err); - ret = fd; - goto cleanup; - } - - ret = write_object(fd, s->bs, (char *)&s->inode, - vid_to_vdi_oid(s->inode.vdi_id), s->inode.nr_copies, - datalen, 0, false, s->cache_flags); - if (ret < 0) { - error_report("failed to write snapshot's inode."); - goto cleanup; - } - - ret = do_sd_create(s, &new_vid, 1, &local_err); - if (ret < 0) { - error_reportf_err(local_err, - "failed to create inode for snapshot: "); - goto cleanup; - } - - ret = read_object(fd, s->bs, (char *)inode, - vid_to_vdi_oid(new_vid), s->inode.nr_copies, datalen, 0, - s->cache_flags); - - if (ret < 0) { - error_report("failed to read new inode info. %s", strerror(errno)); - goto cleanup; - } - - memcpy(&s->inode, inode, datalen); - trace_sheepdog_snapshot_create_inode(s->inode.name, s->inode.snap_id, - s->inode.vdi_id); - -cleanup: - g_free(inode); - closesocket(fd); - return ret; -} - -/* - * We implement rollback(loadvm) operation to the specified snapshot by - * 1) switch to the snapshot - * 2) rely on sd_create_branch to delete working VDI and - * 3) create a new working VDI based on the specified snapshot - */ -static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id) -{ - BDRVSheepdogState *s = bs->opaque; - BDRVSheepdogState *old_s; - char tag[SD_MAX_VDI_TAG_LEN]; - uint32_t snapid = 0; - int ret; - - if (!sd_parse_snapid_or_tag(snapshot_id, &snapid, tag)) { - return -EINVAL; - } - - old_s = g_new(BDRVSheepdogState, 1); - - memcpy(old_s, s, sizeof(BDRVSheepdogState)); - - ret = reload_inode(s, snapid, tag); - if (ret) { - goto out; - } - - ret = sd_create_branch(s); - if (ret) { - goto out; - } - - g_free(old_s); - - return 0; -out: - /* recover bdrv_sd_state */ - memcpy(s, old_s, sizeof(BDRVSheepdogState)); - g_free(old_s); - - error_report("failed to open. recover old bdrv_sd_state."); - - return ret; -} - -#define NR_BATCHED_DISCARD 128 - -static int remove_objects(BDRVSheepdogState *s, Error **errp) -{ - int fd, i = 0, nr_objs = 0; - int ret; - SheepdogInode *inode = &s->inode; - - fd = connect_to_sdog(s, errp); - if (fd < 0) { - return fd; - } - - nr_objs = count_data_objs(inode); - while (i < nr_objs) { - int start_idx, nr_filled_idx; - - while (i < nr_objs && !inode->data_vdi_id[i]) { - i++; - } - start_idx = i; - - nr_filled_idx = 0; - while (i < nr_objs && nr_filled_idx < NR_BATCHED_DISCARD) { - if (inode->data_vdi_id[i]) { - inode->data_vdi_id[i] = 0; - nr_filled_idx++; - } - - i++; - } - - ret = write_object(fd, s->bs, - (char *)&inode->data_vdi_id[start_idx], - vid_to_vdi_oid(s->inode.vdi_id), inode->nr_copies, - (i - start_idx) * sizeof(uint32_t), - offsetof(struct SheepdogInode, - data_vdi_id[start_idx]), - false, s->cache_flags); - if (ret < 0) { - error_setg(errp, "Failed to discard snapshot inode"); - goto out; - } - } - - ret = 0; -out: - closesocket(fd); - return ret; -} - -static int sd_snapshot_delete(BlockDriverState *bs, - const char *snapshot_id, - const char *name, - Error **errp) -{ - /* - * FIXME should delete the snapshot matching both @snapshot_id and - * @name, but @name not used here - */ - unsigned long snap_id = 0; - char snap_tag[SD_MAX_VDI_TAG_LEN]; - int fd, ret; - char buf[SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN]; - BDRVSheepdogState *s = bs->opaque; - unsigned int wlen = SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN, rlen = 0; - uint32_t vid; - SheepdogVdiReq hdr = { - .opcode = SD_OP_DEL_VDI, - .data_length = wlen, - .flags = SD_FLAG_CMD_WRITE, - }; - SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr; - - ret = remove_objects(s, errp); - if (ret) { - return ret; - } - - memset(buf, 0, sizeof(buf)); - memset(snap_tag, 0, sizeof(snap_tag)); - pstrcpy(buf, SD_MAX_VDI_LEN, s->name); - /* TODO Use sd_parse_snapid() once this mess is cleaned up */ - ret = qemu_strtoul(snapshot_id, NULL, 10, &snap_id); - if (ret || snap_id > UINT32_MAX) { - /* - * FIXME Since qemu_strtoul() returns -EINVAL when - * @snapshot_id is null, @snapshot_id is mandatory. Correct - * would be to require at least one of @snapshot_id and @name. - */ - error_setg(errp, "Invalid snapshot ID: %s", - snapshot_id ? snapshot_id : ""); - return -EINVAL; - } - - if (snap_id) { - hdr.snapid = (uint32_t) snap_id; - } else { - /* FIXME I suspect we should use @name here */ - /* FIXME don't truncate silently */ - pstrcpy(snap_tag, sizeof(snap_tag), snapshot_id); - pstrcpy(buf + SD_MAX_VDI_LEN, SD_MAX_VDI_TAG_LEN, snap_tag); - } - - ret = find_vdi_name(s, s->name, snap_id, snap_tag, &vid, true, errp); - if (ret) { - return ret; - } - - fd = connect_to_sdog(s, errp); - if (fd < 0) { - return fd; - } - - ret = do_req(fd, s->bs, (SheepdogReq *)&hdr, - buf, &wlen, &rlen); - closesocket(fd); - if (ret) { - error_setg_errno(errp, -ret, "Couldn't send request to server"); - return ret; - } - - switch (rsp->result) { - case SD_RES_NO_VDI: - error_setg(errp, "Can't find the snapshot"); - return -ENOENT; - case SD_RES_SUCCESS: - break; - default: - error_setg(errp, "%s", sd_strerror(rsp->result)); - return -EIO; - } - - return 0; -} - -static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab) -{ - Error *local_err = NULL; - BDRVSheepdogState *s = bs->opaque; - SheepdogReq req; - int fd, nr = 1024, ret, max = BITS_TO_LONGS(SD_NR_VDIS) * sizeof(long); - QEMUSnapshotInfo *sn_tab = NULL; - unsigned wlen, rlen; - int found = 0; - SheepdogInode *inode; - unsigned long *vdi_inuse; - unsigned int start_nr; - uint64_t hval; - uint32_t vid; - - vdi_inuse = g_malloc(max); - inode = g_malloc(SD_INODE_HEADER_SIZE); - - fd = connect_to_sdog(s, &local_err); - if (fd < 0) { - error_report_err(local_err); - ret = fd; - goto out; - } - - rlen = max; - wlen = 0; - - memset(&req, 0, sizeof(req)); - - req.opcode = SD_OP_READ_VDIS; - req.data_length = max; - - ret = do_req(fd, s->bs, &req, vdi_inuse, &wlen, &rlen); - - closesocket(fd); - if (ret) { - goto out; - } - - sn_tab = g_new0(QEMUSnapshotInfo, nr); - - /* calculate a vdi id with hash function */ - hval = fnv_64a_buf(s->name, strlen(s->name), FNV1A_64_INIT); - start_nr = hval & (SD_NR_VDIS - 1); - - fd = connect_to_sdog(s, &local_err); - if (fd < 0) { - error_report_err(local_err); - ret = fd; - goto out; - } - - for (vid = start_nr; found < nr; vid = (vid + 1) % SD_NR_VDIS) { - if (!test_bit(vid, vdi_inuse)) { - break; - } - - /* we don't need to read entire object */ - ret = read_object(fd, s->bs, (char *)inode, - vid_to_vdi_oid(vid), - 0, SD_INODE_HEADER_SIZE, 0, - s->cache_flags); - - if (ret) { - continue; - } - - if (!strcmp(inode->name, s->name) && is_snapshot(inode)) { - sn_tab[found].date_sec = inode->snap_ctime >> 32; - sn_tab[found].date_nsec = inode->snap_ctime & 0xffffffff; - sn_tab[found].vm_state_size = inode->vm_state_size; - sn_tab[found].vm_clock_nsec = inode->vm_clock_nsec; - - snprintf(sn_tab[found].id_str, sizeof(sn_tab[found].id_str), - "%" PRIu32, inode->snap_id); - pstrcpy(sn_tab[found].name, - MIN(sizeof(sn_tab[found].name), sizeof(inode->tag)), - inode->tag); - found++; - } - } - - closesocket(fd); -out: - *psn_tab = sn_tab; - - g_free(vdi_inuse); - g_free(inode); - - if (ret < 0) { - return ret; - } - - return found; -} - -static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data, - int64_t pos, int size, int load) -{ - Error *local_err = NULL; - bool create; - int fd, ret = 0, remaining = size; - unsigned int data_len; - uint64_t vmstate_oid; - uint64_t offset; - uint32_t vdi_index; - uint32_t vdi_id = load ? s->inode.parent_vdi_id : s->inode.vdi_id; - uint32_t object_size = (UINT32_C(1) << s->inode.block_size_shift); - - fd = connect_to_sdog(s, &local_err); - if (fd < 0) { - error_report_err(local_err); - return fd; - } - - while (remaining) { - vdi_index = pos / object_size; - offset = pos % object_size; - - data_len = MIN(remaining, object_size - offset); - - vmstate_oid = vid_to_vmstate_oid(vdi_id, vdi_index); - - create = (offset == 0); - if (load) { - ret = read_object(fd, s->bs, (char *)data, vmstate_oid, - s->inode.nr_copies, data_len, offset, - s->cache_flags); - } else { - ret = write_object(fd, s->bs, (char *)data, vmstate_oid, - s->inode.nr_copies, data_len, offset, create, - s->cache_flags); - } - - if (ret < 0) { - error_report("failed to save vmstate %s", strerror(errno)); - goto cleanup; - } - - pos += data_len; - data += data_len; - remaining -= data_len; - } - ret = size; -cleanup: - closesocket(fd); - return ret; -} - -static int sd_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, - int64_t pos) -{ - BDRVSheepdogState *s = bs->opaque; - void *buf; - int ret; - - buf = qemu_blockalign(bs, qiov->size); - qemu_iovec_to_buf(qiov, 0, buf, qiov->size); - ret = do_load_save_vmstate(s, (uint8_t *) buf, pos, qiov->size, 0); - qemu_vfree(buf); - - return ret; -} - -static int sd_load_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, - int64_t pos) -{ - BDRVSheepdogState *s = bs->opaque; - void *buf; - int ret; - - buf = qemu_blockalign(bs, qiov->size); - ret = do_load_save_vmstate(s, buf, pos, qiov->size, 1); - qemu_iovec_from_buf(qiov, 0, buf, qiov->size); - qemu_vfree(buf); - - return ret; -} - - -static coroutine_fn int sd_co_pdiscard(BlockDriverState *bs, int64_t offset, - int bytes) -{ - SheepdogAIOCB acb; - BDRVSheepdogState *s = bs->opaque; - QEMUIOVector discard_iov; - struct iovec iov; - uint32_t zero = 0; - - if (!s->discard_supported) { - return 0; - } - - memset(&discard_iov, 0, sizeof(discard_iov)); - memset(&iov, 0, sizeof(iov)); - iov.iov_base = &zero; - iov.iov_len = sizeof(zero); - discard_iov.iov = &iov; - discard_iov.niov = 1; - if (!QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)) { - return -ENOTSUP; - } - sd_aio_setup(&acb, s, &discard_iov, offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, AIOCB_DISCARD_OBJ); - sd_co_rw_vector(&acb); - sd_aio_complete(&acb); - - return acb.ret; -} - -static coroutine_fn int -sd_co_block_status(BlockDriverState *bs, bool want_zero, int64_t offset, - int64_t bytes, int64_t *pnum, int64_t *map, - BlockDriverState **file) -{ - BDRVSheepdogState *s = bs->opaque; - SheepdogInode *inode = &s->inode; - uint32_t object_size = (UINT32_C(1) << inode->block_size_shift); - unsigned long start = offset / object_size, - end = DIV_ROUND_UP(offset + bytes, object_size); - unsigned long idx; - *map = offset; - int ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID; - - for (idx = start; idx < end; idx++) { - if (inode->data_vdi_id[idx] == 0) { - break; - } - } - if (idx == start) { - /* Get the longest length of unallocated sectors */ - ret = 0; - for (idx = start + 1; idx < end; idx++) { - if (inode->data_vdi_id[idx] != 0) { - break; - } - } - } - - *pnum = (idx - start) * object_size; - if (*pnum > bytes) { - *pnum = bytes; - } - if (ret > 0 && ret & BDRV_BLOCK_OFFSET_VALID) { - *file = bs; - } - return ret; -} - -static int64_t sd_get_allocated_file_size(BlockDriverState *bs) -{ - BDRVSheepdogState *s = bs->opaque; - SheepdogInode *inode = &s->inode; - uint32_t object_size = (UINT32_C(1) << inode->block_size_shift); - unsigned long i, last = DIV_ROUND_UP(inode->vdi_size, object_size); - uint64_t size = 0; - - for (i = 0; i < last; i++) { - if (inode->data_vdi_id[i] == 0) { - continue; - } - size += object_size; - } - return size; -} - -static QemuOptsList sd_create_opts = { - .name = "sheepdog-create-opts", - .head = QTAILQ_HEAD_INITIALIZER(sd_create_opts.head), - .desc = { - { - .name = BLOCK_OPT_SIZE, - .type = QEMU_OPT_SIZE, - .help = "Virtual disk size" - }, - { - .name = BLOCK_OPT_BACKING_FILE, - .type = QEMU_OPT_STRING, - .help = "File name of a base image" - }, - { - .name = BLOCK_OPT_BACKING_FMT, - .type = QEMU_OPT_STRING, - .help = "Must be 'sheepdog' if present", - }, - { - .name = BLOCK_OPT_PREALLOC, - .type = QEMU_OPT_STRING, - .help = "Preallocation mode (allowed values: off, full)" - }, - { - .name = BLOCK_OPT_REDUNDANCY, - .type = QEMU_OPT_STRING, - .help = "Redundancy of the image" - }, - { - .name = BLOCK_OPT_OBJECT_SIZE, - .type = QEMU_OPT_SIZE, - .help = "Object size of the image" - }, - { /* end of list */ } - } -}; - -static const char *const sd_strong_runtime_opts[] = { - "vdi", - "snap-id", - "tag", - "server.", - - NULL -}; - -static BlockDriver bdrv_sheepdog = { - .format_name = "sheepdog", - .protocol_name = "sheepdog", - .instance_size = sizeof(BDRVSheepdogState), - .bdrv_parse_filename = sd_parse_filename, - .bdrv_file_open = sd_open, - .bdrv_reopen_prepare = sd_reopen_prepare, - .bdrv_reopen_commit = sd_reopen_commit, - .bdrv_reopen_abort = sd_reopen_abort, - .bdrv_close = sd_close, - .bdrv_co_create = sd_co_create, - .bdrv_co_create_opts = sd_co_create_opts, - .bdrv_has_zero_init = bdrv_has_zero_init_1, - .bdrv_getlength = sd_getlength, - .bdrv_get_allocated_file_size = sd_get_allocated_file_size, - .bdrv_co_truncate = sd_co_truncate, - - .bdrv_co_readv = sd_co_readv, - .bdrv_co_writev = sd_co_writev, - .bdrv_co_flush_to_disk = sd_co_flush_to_disk, - .bdrv_co_pdiscard = sd_co_pdiscard, - .bdrv_co_block_status = sd_co_block_status, - - .bdrv_snapshot_create = sd_snapshot_create, - .bdrv_snapshot_goto = sd_snapshot_goto, - .bdrv_snapshot_delete = sd_snapshot_delete, - .bdrv_snapshot_list = sd_snapshot_list, - - .bdrv_save_vmstate = sd_save_vmstate, - .bdrv_load_vmstate = sd_load_vmstate, - - .bdrv_detach_aio_context = sd_detach_aio_context, - .bdrv_attach_aio_context = sd_attach_aio_context, - - .create_opts = &sd_create_opts, - .strong_runtime_opts = sd_strong_runtime_opts, -}; - -static BlockDriver bdrv_sheepdog_tcp = { - .format_name = "sheepdog", - .protocol_name = "sheepdog+tcp", - .instance_size = sizeof(BDRVSheepdogState), - .bdrv_parse_filename = sd_parse_filename, - .bdrv_file_open = sd_open, - .bdrv_reopen_prepare = sd_reopen_prepare, - .bdrv_reopen_commit = sd_reopen_commit, - .bdrv_reopen_abort = sd_reopen_abort, - .bdrv_close = sd_close, - .bdrv_co_create = sd_co_create, - .bdrv_co_create_opts = sd_co_create_opts, - .bdrv_has_zero_init = bdrv_has_zero_init_1, - .bdrv_getlength = sd_getlength, - .bdrv_get_allocated_file_size = sd_get_allocated_file_size, - .bdrv_co_truncate = sd_co_truncate, - - .bdrv_co_readv = sd_co_readv, - .bdrv_co_writev = sd_co_writev, - .bdrv_co_flush_to_disk = sd_co_flush_to_disk, - .bdrv_co_pdiscard = sd_co_pdiscard, - .bdrv_co_block_status = sd_co_block_status, - - .bdrv_snapshot_create = sd_snapshot_create, - .bdrv_snapshot_goto = sd_snapshot_goto, - .bdrv_snapshot_delete = sd_snapshot_delete, - .bdrv_snapshot_list = sd_snapshot_list, - - .bdrv_save_vmstate = sd_save_vmstate, - .bdrv_load_vmstate = sd_load_vmstate, - - .bdrv_detach_aio_context = sd_detach_aio_context, - .bdrv_attach_aio_context = sd_attach_aio_context, - - .create_opts = &sd_create_opts, - .strong_runtime_opts = sd_strong_runtime_opts, -}; - -static BlockDriver bdrv_sheepdog_unix = { - .format_name = "sheepdog", - .protocol_name = "sheepdog+unix", - .instance_size = sizeof(BDRVSheepdogState), - .bdrv_parse_filename = sd_parse_filename, - .bdrv_file_open = sd_open, - .bdrv_reopen_prepare = sd_reopen_prepare, - .bdrv_reopen_commit = sd_reopen_commit, - .bdrv_reopen_abort = sd_reopen_abort, - .bdrv_close = sd_close, - .bdrv_co_create = sd_co_create, - .bdrv_co_create_opts = sd_co_create_opts, - .bdrv_has_zero_init = bdrv_has_zero_init_1, - .bdrv_getlength = sd_getlength, - .bdrv_get_allocated_file_size = sd_get_allocated_file_size, - .bdrv_co_truncate = sd_co_truncate, - - .bdrv_co_readv = sd_co_readv, - .bdrv_co_writev = sd_co_writev, - .bdrv_co_flush_to_disk = sd_co_flush_to_disk, - .bdrv_co_pdiscard = sd_co_pdiscard, - .bdrv_co_block_status = sd_co_block_status, - - .bdrv_snapshot_create = sd_snapshot_create, - .bdrv_snapshot_goto = sd_snapshot_goto, - .bdrv_snapshot_delete = sd_snapshot_delete, - .bdrv_snapshot_list = sd_snapshot_list, - - .bdrv_save_vmstate = sd_save_vmstate, - .bdrv_load_vmstate = sd_load_vmstate, - - .bdrv_detach_aio_context = sd_detach_aio_context, - .bdrv_attach_aio_context = sd_attach_aio_context, - - .create_opts = &sd_create_opts, - .strong_runtime_opts = sd_strong_runtime_opts, -}; - -static void bdrv_sheepdog_init(void) -{ - bdrv_register(&bdrv_sheepdog); - bdrv_register(&bdrv_sheepdog_tcp); - bdrv_register(&bdrv_sheepdog_unix); -} -block_init(bdrv_sheepdog_init); diff --git a/block/snapshot.c b/block/snapshot.c index e8ae9a28c1..ccacda8bd5 100644 --- a/block/snapshot.c +++ b/block/snapshot.c @@ -275,13 +275,16 @@ int bdrv_snapshot_goto(BlockDriverState *bs, qobject_unref(file_options); g_free(subqdict_prefix); + /* Force .bdrv_open() below to re-attach fallback_bs on *fallback_ptr */ qdict_put_str(options, (*fallback_ptr)->name, bdrv_get_node_name(fallback_bs)); + /* Now close bs, apply the snapshot on fallback_bs, and re-open bs */ if (drv->bdrv_close) { drv->bdrv_close(bs); } + /* .bdrv_open() will re-attach it */ bdrv_unref_child(bs, *fallback_ptr); *fallback_ptr = NULL; @@ -296,7 +299,16 @@ int bdrv_snapshot_goto(BlockDriverState *bs, return ret < 0 ? ret : open_ret; } - assert(fallback_bs == (*fallback_ptr)->bs); + /* + * fallback_ptr is &bs->file or &bs->backing. *fallback_ptr + * was closed above and set to NULL, but the .bdrv_open() call + * has opened it again, because we set the respective option + * (with the qdict_put_str() call above). + * Assert that .bdrv_open() has attached some child on + * *fallback_ptr, and that it has attached the one we wanted + * it to (i.e., fallback_bs). + */ + assert(*fallback_ptr && fallback_bs == (*fallback_ptr)->bs); bdrv_unref(fallback_bs); return ret; } @@ -415,7 +427,7 @@ int bdrv_snapshot_load_tmp(BlockDriverState *bs, error_setg(errp, "snapshot_id and name are both NULL"); return -EINVAL; } - if (!bs->read_only) { + if (!bdrv_is_read_only(bs)) { error_setg(errp, "Device is not readonly"); return -EINVAL; } diff --git a/block/ssh.c b/block/ssh.c index ebe3d8b631..e0fbb4934b 100644 --- a/block/ssh.c +++ b/block/ssh.c @@ -237,9 +237,7 @@ static int parse_uri(const char *filename, QDict *options, Error **errp) return 0; err: - if (uri) { - uri_free(uri); - } + uri_free(uri); return -EINVAL; } @@ -277,7 +275,6 @@ static void ssh_parse_filename(const char *filename, QDict *options, static int check_host_key_knownhosts(BDRVSSHState *s, Error **errp) { int ret; -#ifdef HAVE_LIBSSH_0_8 enum ssh_known_hosts_e state; int r; ssh_key pubkey; @@ -343,46 +340,6 @@ static int check_host_key_knownhosts(BDRVSSHState *s, Error **errp) error_setg(errp, "error while checking for known server (%d)", state); goto out; } -#else /* !HAVE_LIBSSH_0_8 */ - int state; - - state = ssh_is_server_known(s->session); - trace_ssh_server_status(state); - - switch (state) { - case SSH_SERVER_KNOWN_OK: - /* OK */ - trace_ssh_check_host_key_knownhosts(); - break; - case SSH_SERVER_KNOWN_CHANGED: - ret = -EINVAL; - error_setg(errp, - "host key does not match the one in known_hosts; this " - "may be a possible attack"); - goto out; - case SSH_SERVER_FOUND_OTHER: - ret = -EINVAL; - error_setg(errp, - "host key for this server not found, another type exists"); - goto out; - case SSH_SERVER_FILE_NOT_FOUND: - ret = -ENOENT; - error_setg(errp, "known_hosts file not found"); - goto out; - case SSH_SERVER_NOT_KNOWN: - ret = -EINVAL; - error_setg(errp, "no host key was found in known_hosts"); - goto out; - case SSH_SERVER_ERROR: - ret = -EINVAL; - error_setg(errp, "server error"); - goto out; - default: - ret = -EINVAL; - error_setg(errp, "error while checking for known server (%d)", state); - goto out; - } -#endif /* !HAVE_LIBSSH_0_8 */ /* known_hosts checking successful. */ ret = 0; @@ -438,11 +395,7 @@ check_host_key_hash(BDRVSSHState *s, const char *hash, unsigned char *server_hash; size_t server_hash_len; -#ifdef HAVE_LIBSSH_0_8 r = ssh_get_server_publickey(s->session, &pubkey); -#else - r = ssh_get_publickey(s->session, &pubkey); -#endif if (r != SSH_OK) { session_error_setg(errp, s, "failed to read remote host key"); return -EINVAL; @@ -487,6 +440,9 @@ static int check_host_key(BDRVSSHState *s, SshHostKeyCheck *hkc, Error **errp) } else if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_SHA1) { return check_host_key_hash(s, hkc->u.hash.hash, SSH_PUBLICKEY_HASH_SHA1, errp); + } else if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_SHA256) { + return check_host_key_hash(s, hkc->u.hash.hash, + SSH_PUBLICKEY_HASH_SHA256, errp); } g_assert_not_reached(); break; @@ -1233,8 +1189,6 @@ static void unsafe_flush_warning(BDRVSSHState *s, const char *what) } } -#ifdef HAVE_LIBSSH_0_8 - static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs) { int r; @@ -1271,18 +1225,6 @@ static coroutine_fn int ssh_co_flush(BlockDriverState *bs) return ret; } -#else /* !HAVE_LIBSSH_0_8 */ - -static coroutine_fn int ssh_co_flush(BlockDriverState *bs) -{ - BDRVSSHState *s = bs->opaque; - - unsafe_flush_warning(s, "libssh >= 0.8.0"); - return 0; -} - -#endif /* !HAVE_LIBSSH_0_8 */ - static int64_t ssh_getlength(BlockDriverState *bs) { BDRVSSHState *s = bs->opaque; diff --git a/block/trace-events b/block/trace-events index 1a12d634e2..b3d2b1e62c 100644 --- a/block/trace-events +++ b/block/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # ../block.c bdrv_open_common(void *bs, const char *filename, int flags, const char *format_name) "bs %p filename \"%s\" flags 0x%x format_name \"%s\"" @@ -206,20 +206,7 @@ file_copy_file_range(void *bs, int src, int64_t src_off, int dst, int64_t dst_of file_FindEjectableOpticalMedia(const char *media) "Matching using %s" file_setup_cdrom(const char *partition) "Using %s as optical disc" file_hdev_is_sg(int type, int version) "SG device found: type=%d, version=%d" - -# sheepdog.c -sheepdog_reconnect_to_sdog(void) "Wait for connection to be established" -sheepdog_aio_read_response(void) "disable cache since the server doesn't support it" -sheepdog_open(uint32_t vid) "0x%" PRIx32 " snapshot inode was open" -sheepdog_close(const char *name) "%s" -sheepdog_create_branch_snapshot(uint32_t vdi) "0x%" PRIx32 " is snapshot" -sheepdog_create_branch_created(uint32_t vdi) "0x%" PRIx32 " is created" -sheepdog_create_branch_new(uint32_t vdi) "0x%" PRIx32 " was newly created" -sheepdog_co_rw_vector_update(uint32_t vdi, uint64_t oid, uint64_t data, long idx) "update ino (%" PRIu32 ") %" PRIu64 " %" PRIu64 " %ld" -sheepdog_co_rw_vector_new(uint64_t oid) "new oid 0x%" PRIx64 -sheepdog_snapshot_create_info(const char *sn_name, const char *id, const char *name, int64_t size, int is_snapshot) "sn_info: name %s id_str %s s: name %s vm_state_size %" PRId64 " " "is_snapshot %d" -sheepdog_snapshot_create(const char *sn_name, const char *id) "%s %s" -sheepdog_snapshot_create_inode(const char *name, uint32_t snap, uint32_t vdi) "s->inode: name %s snap_id 0x%" PRIx32 " vdi 0x%" PRIx32 +file_flush_fdatasync_failed(int err) "errno %d" # ssh.c sftp_error(const char *op, const char *ssh_err, int ssh_err_code, int sftp_err_code) "%s failed: %s (libssh error code: %d, sftp error code: %d)" diff --git a/block/vhdx-log.c b/block/vhdx-log.c index 404fb5f3cb..7672161d95 100644 --- a/block/vhdx-log.c +++ b/block/vhdx-log.c @@ -801,7 +801,7 @@ int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed, } if (logs.valid) { - if (bs->read_only) { + if (bdrv_is_read_only(bs)) { bdrv_refresh_filename(bs); ret = -EPERM; error_setg(errp, diff --git a/block/vvfat.c b/block/vvfat.c index 54807f82ca..34bf1e3a86 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -3098,26 +3098,6 @@ static int coroutine_fn vvfat_co_block_status(BlockDriverState *bs, return BDRV_BLOCK_DATA; } -static int coroutine_fn -write_target_commit(BlockDriverState *bs, uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags) -{ - int ret; - - BDRVVVFATState* s = *((BDRVVVFATState**) bs->opaque); - qemu_co_mutex_lock(&s->lock); - ret = try_commit(s); - qemu_co_mutex_unlock(&s->lock); - - return ret; -} - -static BlockDriver vvfat_write_target = { - .format_name = "vvfat_write_target", - .instance_size = sizeof(void*), - .bdrv_co_pwritev = write_target_commit, -}; - static void vvfat_qcow_options(BdrvChildRole role, bool parent_is_format, int *child_flags, QDict *child_options, int parent_flags, QDict *parent_options) @@ -3127,16 +3107,12 @@ static void vvfat_qcow_options(BdrvChildRole role, bool parent_is_format, qdict_set_default_str(child_options, BDRV_OPT_CACHE_NO_FLUSH, "on"); } -static const BdrvChildClass child_vvfat_qcow = { - .parent_is_bds = true, - .inherit_options = vvfat_qcow_options, -}; +static BdrvChildClass child_vvfat_qcow; static int enable_write_target(BlockDriverState *bs, Error **errp) { BDRVVVFATState *s = bs->opaque; BlockDriver *bdrv_qcow = NULL; - BlockDriverState *backing; QemuOpts *opts = NULL; int ret; int size = sector2cluster(s, s->sector_count); @@ -3187,13 +3163,6 @@ static int enable_write_target(BlockDriverState *bs, Error **errp) unlink(s->qcow_filename); #endif - backing = bdrv_new_open_driver(&vvfat_write_target, NULL, BDRV_O_ALLOW_RDWR, - &error_abort); - *(void**) backing->opaque = s; - - bdrv_set_backing_hd(s->bs, backing, &error_abort); - bdrv_unref(backing); - return 0; err: @@ -3208,20 +3177,10 @@ static void vvfat_child_perm(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared) { - BDRVVVFATState *s = bs->opaque; - - assert(c == s->qcow || (role & BDRV_CHILD_COW)); - - if (c == s->qcow) { - /* This is a private node, nobody should try to attach to it */ - *nperm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE; - *nshared = BLK_PERM_WRITE_UNCHANGED; - } else { - /* The backing file is there so 'commit' can use it. vvfat doesn't - * access it in any way. */ - *nperm = 0; - *nshared = BLK_PERM_ALL; - } + assert(role & BDRV_CHILD_DATA); + /* This is a private node, nobody should try to attach to it */ + *nperm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE; + *nshared = BLK_PERM_WRITE_UNCHANGED; } static void vvfat_close(BlockDriverState *bs) @@ -3270,6 +3229,8 @@ static BlockDriver bdrv_vvfat = { static void bdrv_vvfat_init(void) { + child_vvfat_qcow = child_of_bds; + child_vvfat_qcow.inherit_options = vvfat_qcow_options; bdrv_register(&bdrv_vvfat); } diff --git a/block/write-threshold.c b/block/write-threshold.c index 85b78dc2a9..35cafbc22d 100644 --- a/block/write-threshold.c +++ b/block/write-threshold.c @@ -12,9 +12,7 @@ #include "qemu/osdep.h" #include "block/block_int.h" -#include "qemu/coroutine.h" #include "block/write-threshold.h" -#include "qemu/notify.h" #include "qapi/error.h" #include "qapi/qapi-commands-block-core.h" #include "qapi/qapi-events-block-core.h" @@ -24,82 +22,9 @@ uint64_t bdrv_write_threshold_get(const BlockDriverState *bs) return bs->write_threshold_offset; } -bool bdrv_write_threshold_is_set(const BlockDriverState *bs) -{ - return bs->write_threshold_offset > 0; -} - -static void write_threshold_disable(BlockDriverState *bs) -{ - if (bdrv_write_threshold_is_set(bs)) { - notifier_with_return_remove(&bs->write_threshold_notifier); - bs->write_threshold_offset = 0; - } -} - -uint64_t bdrv_write_threshold_exceeded(const BlockDriverState *bs, - const BdrvTrackedRequest *req) -{ - if (bdrv_write_threshold_is_set(bs)) { - if (req->offset > bs->write_threshold_offset) { - return (req->offset - bs->write_threshold_offset) + req->bytes; - } - if ((req->offset + req->bytes) > bs->write_threshold_offset) { - return (req->offset + req->bytes) - bs->write_threshold_offset; - } - } - return 0; -} - -static int coroutine_fn before_write_notify(NotifierWithReturn *notifier, - void *opaque) -{ - BdrvTrackedRequest *req = opaque; - BlockDriverState *bs = req->bs; - uint64_t amount = 0; - - amount = bdrv_write_threshold_exceeded(bs, req); - if (amount > 0) { - qapi_event_send_block_write_threshold( - bs->node_name, - amount, - bs->write_threshold_offset); - - /* autodisable to avoid flooding the monitor */ - write_threshold_disable(bs); - } - - return 0; /* should always let other notifiers run */ -} - -static void write_threshold_register_notifier(BlockDriverState *bs) -{ - bs->write_threshold_notifier.notify = before_write_notify; - bdrv_add_before_write_notifier(bs, &bs->write_threshold_notifier); -} - -static void write_threshold_update(BlockDriverState *bs, - int64_t threshold_bytes) -{ - bs->write_threshold_offset = threshold_bytes; -} - void bdrv_write_threshold_set(BlockDriverState *bs, uint64_t threshold_bytes) { - if (bdrv_write_threshold_is_set(bs)) { - if (threshold_bytes > 0) { - write_threshold_update(bs, threshold_bytes); - } else { - write_threshold_disable(bs); - } - } else { - if (threshold_bytes > 0) { - /* avoid multiple registration */ - write_threshold_register_notifier(bs); - write_threshold_update(bs, threshold_bytes); - } - /* discard bogus disable request */ - } + bs->write_threshold_offset = threshold_bytes; } void qmp_block_set_write_threshold(const char *node_name, @@ -122,3 +47,17 @@ void qmp_block_set_write_threshold(const char *node_name, aio_context_release(aio_context); } + +void bdrv_write_threshold_check_write(BlockDriverState *bs, int64_t offset, + int64_t bytes) +{ + int64_t end = offset + bytes; + uint64_t wtr = bs->write_threshold_offset; + + if (wtr > 0 && end > wtr) { + qapi_event_send_block_write_threshold(bs->node_name, end - wtr, wtr); + + /* autodisable to avoid flooding the monitor */ + bdrv_write_threshold_set(bs, 0); + } +} diff --git a/blockdev-nbd.c b/blockdev-nbd.c index b264620b98..bdfa7ed3a5 100644 --- a/blockdev-nbd.c +++ b/blockdev-nbd.c @@ -108,9 +108,9 @@ static QCryptoTLSCreds *nbd_get_tls_creds(const char *id, Error **errp) return NULL; } - if (creds->endpoint != QCRYPTO_TLS_CREDS_ENDPOINT_SERVER) { - error_setg(errp, - "Expecting TLS credentials with a server endpoint"); + if (!qcrypto_tls_creds_check_endpoint(creds, + QCRYPTO_TLS_CREDS_ENDPOINT_SERVER, + errp)) { return NULL; } object_ref(obj); diff --git a/blockdev.c b/blockdev.c index 43663b0c5d..e6d0c0f305 100644 --- a/blockdev.c +++ b/blockdev.c @@ -583,8 +583,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts, blk = blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL); blk_rs = blk_get_root_state(blk); - blk_rs->open_flags = bdrv_flags; - blk_rs->read_only = read_only; + blk_rs->open_flags = bdrv_flags | (read_only ? 0 : BDRV_O_RDWR); blk_rs->detect_zeroes = detect_zeroes; qobject_unref(bs_opts); @@ -1585,10 +1584,6 @@ static void external_snapshot_prepare(BlkActionState *common, goto out; } - /* This removes our old bs and adds the new bs. This is an operation that - * can fail, so we need to do it in .prepare; undoing it for abort is - * always possible. */ - bdrv_ref(state->new_bs); ret = bdrv_append(state->new_bs, state->old_bs, errp); if (ret < 0) { goto out; @@ -1728,6 +1723,7 @@ static void drive_backup_prepare(BlkActionState *common, Error **errp) aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); + state->bs = bs; /* Paired with .clean() */ bdrv_drained_begin(bs); @@ -1827,8 +1823,6 @@ static void drive_backup_prepare(BlkActionState *common, Error **errp) } } - state->bs = bs; - state->job = do_backup_common(qapi_DriveBackup_base(backup), bs, target_bs, aio_context, common->block_job_txn, errp); @@ -3574,46 +3568,60 @@ fail: visit_free(v); } -void qmp_x_blockdev_reopen(BlockdevOptions *options, Error **errp) +void qmp_blockdev_reopen(BlockdevOptionsList *reopen_list, Error **errp) { - BlockDriverState *bs; - AioContext *ctx; - QObject *obj; - Visitor *v = qobject_output_visitor_new(&obj); - BlockReopenQueue *queue; - QDict *qdict; + BlockReopenQueue *queue = NULL; + GSList *drained = NULL; - /* Check for the selected node name */ - if (!options->has_node_name) { - error_setg(errp, "node-name not specified"); - goto fail; + /* Add each one of the BDS that we want to reopen to the queue */ + for (; reopen_list != NULL; reopen_list = reopen_list->next) { + BlockdevOptions *options = reopen_list->value; + BlockDriverState *bs; + AioContext *ctx; + QObject *obj; + Visitor *v; + QDict *qdict; + + /* Check for the selected node name */ + if (!options->has_node_name) { + error_setg(errp, "node-name not specified"); + goto fail; + } + + bs = bdrv_find_node(options->node_name); + if (!bs) { + error_setg(errp, "Failed to find node with node-name='%s'", + options->node_name); + goto fail; + } + + /* Put all options in a QDict and flatten it */ + v = qobject_output_visitor_new(&obj); + visit_type_BlockdevOptions(v, NULL, &options, &error_abort); + visit_complete(v, &obj); + visit_free(v); + + qdict = qobject_to(QDict, obj); + + qdict_flatten(qdict); + + ctx = bdrv_get_aio_context(bs); + aio_context_acquire(ctx); + + bdrv_subtree_drained_begin(bs); + queue = bdrv_reopen_queue(queue, bs, qdict, false); + drained = g_slist_prepend(drained, bs); + + aio_context_release(ctx); } - bs = bdrv_find_node(options->node_name); - if (!bs) { - error_setg(errp, "Failed to find node with node-name='%s'", - options->node_name); - goto fail; - } - - /* Put all options in a QDict and flatten it */ - visit_type_BlockdevOptions(v, NULL, &options, &error_abort); - visit_complete(v, &obj); - qdict = qobject_to(QDict, obj); - - qdict_flatten(qdict); - /* Perform the reopen operation */ - ctx = bdrv_get_aio_context(bs); - aio_context_acquire(ctx); - bdrv_subtree_drained_begin(bs); - queue = bdrv_reopen_queue(NULL, bs, qdict, false); bdrv_reopen_multiple(queue, errp); - bdrv_subtree_drained_end(bs); - aio_context_release(ctx); + queue = NULL; fail: - visit_free(v); + bdrv_reopen_queue_free(queue); + g_slist_free_full(drained, (GDestroyNotify) bdrv_subtree_drained_end); } void qmp_blockdev_del(const char *node_name, Error **errp) diff --git a/blockjob.c b/blockjob.c index 207e8c7fd9..4bad1408cb 100644 --- a/blockjob.c +++ b/blockjob.c @@ -87,6 +87,7 @@ void block_job_free(Job *job) block_job_remove_all_bdrv(bjob); blk_unref(bjob->blk); + ratelimit_destroy(&bjob->limit); error_free(bjob->blocker); } @@ -163,6 +164,13 @@ static void child_job_set_aio_ctx(BdrvChild *c, AioContext *ctx, job->job.aio_context = ctx; } +static AioContext *child_job_get_parent_aio_context(BdrvChild *c) +{ + BlockJob *job = c->opaque; + + return job->job.aio_context; +} + static const BdrvChildClass child_job = { .get_parent_desc = child_job_get_parent_desc, .drained_begin = child_job_drained_begin, @@ -171,6 +179,7 @@ static const BdrvChildClass child_job = { .can_set_aio_ctx = child_job_can_set_aio_ctx, .set_aio_ctx = child_job_set_aio_ctx, .stay_at_node = true, + .get_parent_aio_context = child_job_get_parent_aio_context, }; void block_job_remove_all_bdrv(BlockJob *job) @@ -221,8 +230,7 @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs, if (need_context_ops && job->job.aio_context != qemu_get_aio_context()) { aio_context_release(job->job.aio_context); } - c = bdrv_root_attach_child(bs, name, &child_job, 0, - job->job.aio_context, perm, shared_perm, job, + c = bdrv_root_attach_child(bs, name, &child_job, 0, perm, shared_perm, job, errp); if (need_context_ops && job->job.aio_context != qemu_get_aio_context()) { aio_context_acquire(job->job.aio_context); @@ -292,28 +300,29 @@ bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) int64_t block_job_ratelimit_get_delay(BlockJob *job, uint64_t n) { - if (!job->speed) { - return 0; - } - return ratelimit_calculate_delay(&job->limit, n); } BlockJobInfo *block_job_query(BlockJob *job, Error **errp) { BlockJobInfo *info; + uint64_t progress_current, progress_total; if (block_job_is_internal(job)) { error_setg(errp, "Cannot query QEMU internal jobs"); return NULL; } + + progress_get_snapshot(&job->job.progress, &progress_current, + &progress_total); + info = g_new0(BlockJobInfo, 1); info->type = g_strdup(job_type_str(&job->job)); info->device = g_strdup(job->job.id); info->busy = qatomic_read(&job->job.busy); info->paused = job->job.pause_count > 0; - info->offset = job->job.progress.current; - info->len = job->job.progress.total; + info->offset = progress_current; + info->len = progress_total; info->speed = job->speed; info->io_status = job->iostatus; info->ready = job_is_ready(&job->job), @@ -340,15 +349,19 @@ static void block_job_iostatus_set_err(BlockJob *job, int error) static void block_job_event_cancelled(Notifier *n, void *opaque) { BlockJob *job = opaque; + uint64_t progress_current, progress_total; if (block_job_is_internal(job)) { return; } + progress_get_snapshot(&job->job.progress, &progress_current, + &progress_total); + qapi_event_send_block_job_cancelled(job_type(&job->job), job->job.id, - job->job.progress.total, - job->job.progress.current, + progress_total, + progress_current, job->speed); } @@ -356,6 +369,7 @@ static void block_job_event_completed(Notifier *n, void *opaque) { BlockJob *job = opaque; const char *msg = NULL; + uint64_t progress_current, progress_total; if (block_job_is_internal(job)) { return; @@ -365,10 +379,13 @@ static void block_job_event_completed(Notifier *n, void *opaque) msg = error_get_pretty(job->job.err); } + progress_get_snapshot(&job->job.progress, &progress_current, + &progress_total); + qapi_event_send_block_job_completed(job_type(&job->job), job->job.id, - job->job.progress.total, - job->job.progress.current, + progress_total, + progress_current, job->speed, !!msg, msg); @@ -389,15 +406,19 @@ static void block_job_event_pending(Notifier *n, void *opaque) static void block_job_event_ready(Notifier *n, void *opaque) { BlockJob *job = opaque; + uint64_t progress_current, progress_total; if (block_job_is_internal(job)) { return; } + progress_get_snapshot(&job->job.progress, &progress_current, + &progress_total); + qapi_event_send_block_job_ready(job_type(&job->job), job->job.id, - job->job.progress.total, - job->job.progress.current, + progress_total, + progress_current, job->speed); } @@ -435,6 +456,8 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, assert(job->job.driver->free == &block_job_free); assert(job->job.driver->user_resume == &block_job_user_resume); + ratelimit_init(&job->limit); + job->blk = blk; job->finalize_cancelled_notifier.notify = block_job_event_cancelled; @@ -462,12 +485,9 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, blk_set_disable_request_queuing(blk, true); blk_set_allow_aio_context_change(blk, true); - /* Only set speed when necessary to avoid NotSupported error */ - if (speed != 0) { - if (!block_job_set_speed(job, speed, errp)) { - job_early_fail(&job->job); - return NULL; - } + if (!block_job_set_speed(job, speed, errp)) { + job_early_fail(&job->job); + return NULL; } return job; diff --git a/bsd-user/bsdload.c b/bsd-user/bsdload.c index f38c4faacf..8d83f21eda 100644 --- a/bsd-user/bsdload.c +++ b/bsd-user/bsdload.c @@ -13,47 +13,48 @@ abi_long memcpy_to_target(abi_ulong dest, const void *src, void *host_ptr; host_ptr = lock_user(VERIFY_WRITE, dest, len, 0); - if (!host_ptr) + if (!host_ptr) { return -TARGET_EFAULT; + } memcpy(host_ptr, src, len); unlock_user(host_ptr, dest, 1); return 0; } -static int count(char ** vec) +static int count(char **vec) { int i; - for(i = 0; *vec; i++) { + for (i = 0; *vec; i++) { vec++; } - return(i); + return i; } -static int prepare_binprm(struct linux_binprm *bprm) +static int prepare_binprm(struct bsd_binprm *bprm) { struct stat st; int mode; int retval; - if(fstat(bprm->fd, &st) < 0) { - return(-errno); + if (fstat(bprm->fd, &st) < 0) { + return -errno; } mode = st.st_mode; - if(!S_ISREG(mode)) { /* Must be regular file */ - return(-EACCES); + if (!S_ISREG(mode)) { /* Must be regular file */ + return -EACCES; } - if(!(mode & 0111)) { /* Must have at least one execute bit set */ - return(-EACCES); + if (!(mode & 0111)) { /* Must have at least one execute bit set */ + return -EACCES; } bprm->e_uid = geteuid(); bprm->e_gid = getegid(); /* Set-uid? */ - if(mode & S_ISUID) { + if (mode & S_ISUID) { bprm->e_uid = st.st_uid; } @@ -69,16 +70,14 @@ static int prepare_binprm(struct linux_binprm *bprm) memset(bprm->buf, 0, sizeof(bprm->buf)); retval = lseek(bprm->fd, 0L, SEEK_SET); - if(retval >= 0) { + if (retval >= 0) { retval = read(bprm->fd, bprm->buf, 128); } - if(retval < 0) { + if (retval < 0) { perror("prepare_binprm"); exit(-1); - /* return(-errno); */ - } - else { - return(retval); + } else { + return retval; } } @@ -125,19 +124,21 @@ abi_ulong loader_build_argptr(int envc, int argc, abi_ulong sp, return sp; } -int loader_exec(const char * filename, char ** argv, char ** envp, - struct target_pt_regs * regs, struct image_info *infop) +int loader_exec(const char *filename, char **argv, char **envp, + struct target_pt_regs *regs, struct image_info *infop) { - struct linux_binprm bprm; + struct bsd_binprm bprm; int retval; int i; - bprm.p = TARGET_PAGE_SIZE*MAX_ARG_PAGES-sizeof(unsigned int); - for (i=0 ; i=0) { + if (retval >= 0) { if (bprm.buf[0] == 0x7f && bprm.buf[1] == 'E' && bprm.buf[2] == 'L' && bprm.buf[3] == 'F') { - retval = load_elf_binary(&bprm,regs,infop); + retval = load_elf_binary(&bprm, regs, infop); } else { fprintf(stderr, "Unknown binary format\n"); return -1; } } - if(retval>=0) { + if (retval >= 0) { /* success. Initialize important registers */ do_init_thread(regs, infop); return retval; } /* Something went wrong, return the inode and free the argument pages*/ - for (i=0 ; iARM_cpsr = 0x10; if (infop->entry & 1) - regs->ARM_cpsr |= CPSR_T; + regs->ARM_cpsr |= CPSR_T; regs->ARM_pc = infop->entry & 0xfffffffe; regs->ARM_sp = infop->start_stack; /* FIXME - what to for failure of get_user()? */ @@ -224,9 +224,9 @@ enum #define ELF_START_MMAP 0x80000000 #ifndef TARGET_ABI32 -#define elf_check_arch(x) ( (x) == EM_SPARCV9 || (x) == EM_SPARC32PLUS ) +#define elf_check_arch(x) ((x) == EM_SPARCV9 || (x) == EM_SPARC32PLUS) #else -#define elf_check_arch(x) ( (x) == EM_SPARC32PLUS || (x) == EM_SPARC ) +#define elf_check_arch(x) ((x) == EM_SPARC32PLUS || (x) == EM_SPARC) #endif #define ELF_CLASS ELFCLASS64 @@ -261,7 +261,7 @@ static inline void init_thread(struct target_pt_regs *regs, struct image_info *i #else #define ELF_START_MMAP 0x80000000 -#define elf_check_arch(x) ( (x) == EM_SPARC ) +#define elf_check_arch(x) ((x) == EM_SPARC) #define ELF_CLASS ELFCLASS32 #define ELF_DATA ELFDATA2MSB @@ -285,13 +285,13 @@ static inline void init_thread(struct target_pt_regs *regs, struct image_info *i #if defined(TARGET_PPC64) && !defined(TARGET_ABI32) -#define elf_check_arch(x) ( (x) == EM_PPC64 ) +#define elf_check_arch(x) ((x) == EM_PPC64) #define ELF_CLASS ELFCLASS64 #else -#define elf_check_arch(x) ( (x) == EM_PPC ) +#define elf_check_arch(x) ((x) == EM_PPC) #define ELF_CLASS ELFCLASS32 @@ -376,7 +376,7 @@ static inline void init_thread(struct target_pt_regs *_regs, struct image_info * #define ELF_START_MMAP 0x80000000 -#define elf_check_arch(x) ( (x) == EM_MIPS ) +#define elf_check_arch(x) ((x) == EM_MIPS) #ifdef TARGET_MIPS64 #define ELF_CLASS ELFCLASS64 @@ -406,7 +406,7 @@ static inline void init_thread(struct target_pt_regs *regs, struct image_info *i #define ELF_START_MMAP 0x80000000 -#define elf_check_arch(x) ( (x) == EM_SH ) +#define elf_check_arch(x) ((x) == EM_SH) #define ELF_CLASS ELFCLASS32 #define ELF_DATA ELFDATA2LSB @@ -428,7 +428,7 @@ static inline void init_thread(struct target_pt_regs *regs, struct image_info *i #define ELF_START_MMAP 0x80000000 -#define elf_check_arch(x) ( (x) == EM_CRIS ) +#define elf_check_arch(x) ((x) == EM_CRIS) #define ELF_CLASS ELFCLASS32 #define ELF_DATA ELFDATA2LSB @@ -448,7 +448,7 @@ static inline void init_thread(struct target_pt_regs *regs, struct image_info *i #define ELF_START_MMAP 0x80000000 -#define elf_check_arch(x) ( (x) == EM_68K ) +#define elf_check_arch(x) ((x) == EM_68K) #define ELF_CLASS ELFCLASS32 #define ELF_DATA ELFDATA2MSB @@ -473,7 +473,7 @@ static inline void init_thread(struct target_pt_regs *regs, struct image_info *i #define ELF_START_MMAP (0x30000000000ULL) -#define elf_check_arch(x) ( (x) == ELF_ARCH ) +#define elf_check_arch(x) ((x) == ELF_ARCH) #define ELF_CLASS ELFCLASS64 #define ELF_DATA ELFDATA2MSB @@ -538,8 +538,8 @@ struct exec /* Necessary parameters */ #define TARGET_ELF_EXEC_PAGESIZE TARGET_PAGE_SIZE -#define TARGET_ELF_PAGESTART(_v) ((_v) & ~(unsigned long)(TARGET_ELF_EXEC_PAGESIZE-1)) -#define TARGET_ELF_PAGEOFFSET(_v) ((_v) & (TARGET_ELF_EXEC_PAGESIZE-1)) +#define TARGET_ELF_PAGESTART(_v) ((_v) & ~(unsigned long)(TARGET_ELF_EXEC_PAGESIZE - 1)) +#define TARGET_ELF_PAGEOFFSET(_v) ((_v) & (TARGET_ELF_EXEC_PAGESIZE - 1)) #define INTERPRETER_NONE 0 #define INTERPRETER_AOUT 1 @@ -547,12 +547,12 @@ struct exec #define DLINFO_ITEMS 12 -static inline void memcpy_fromfs(void * to, const void * from, unsigned long n) +static inline void memcpy_fromfs(void *to, const void *from, unsigned long n) { memcpy(to, from, n); } -static int load_aout_interp(void * exptr, int interp_fd); +static int load_aout_interp(void *exptr, int interp_fd); #ifdef BSWAP_NEEDED static void bswap_ehdr(struct elfhdr *ehdr) @@ -613,7 +613,7 @@ static void bswap_sym(struct elf_sym *sym) * to be put directly into the top of new user memory. * */ -static abi_ulong copy_elf_strings(int argc,char ** argv, void **page, +static abi_ulong copy_elf_strings(int argc, char **argv, void **page, abi_ulong p) { char *tmp, *tmp1, *pag = NULL; @@ -638,10 +638,10 @@ static abi_ulong copy_elf_strings(int argc,char ** argv, void **page, --p; --tmp; --len; if (--offset < 0) { offset = p % TARGET_PAGE_SIZE; - pag = (char *)page[p/TARGET_PAGE_SIZE]; + pag = (char *)page[p / TARGET_PAGE_SIZE]; if (!pag) { pag = g_try_malloc0(TARGET_PAGE_SIZE); - page[p/TARGET_PAGE_SIZE] = pag; + page[p / TARGET_PAGE_SIZE] = pag; if (!pag) return 0; } @@ -662,7 +662,7 @@ static abi_ulong copy_elf_strings(int argc,char ** argv, void **page, return p; } -static abi_ulong setup_arg_pages(abi_ulong p, struct linux_binprm *bprm, +static abi_ulong setup_arg_pages(abi_ulong p, struct bsd_binprm *bprm, struct image_info *info) { abi_ulong stack_base, size, error; @@ -672,8 +672,8 @@ static abi_ulong setup_arg_pages(abi_ulong p, struct linux_binprm *bprm, * it for args, we'll use it for something else... */ size = x86_stack_size; - if (size < MAX_ARG_PAGES*TARGET_PAGE_SIZE) - size = MAX_ARG_PAGES*TARGET_PAGE_SIZE; + if (size < MAX_ARG_PAGES * TARGET_PAGE_SIZE) + size = MAX_ARG_PAGES * TARGET_PAGE_SIZE; error = target_mmap(0, size + qemu_host_page_size, PROT_READ | PROT_WRITE, @@ -686,7 +686,7 @@ static abi_ulong setup_arg_pages(abi_ulong p, struct linux_binprm *bprm, /* we reserve one extra page at the top of the stack as guard */ target_mprotect(error + size, qemu_host_page_size, PROT_NONE); - stack_base = error + size - MAX_ARG_PAGES*TARGET_PAGE_SIZE; + stack_base = error + size - MAX_ARG_PAGES * TARGET_PAGE_SIZE; p += stack_base; for (i = 0 ; i < MAX_ARG_PAGES ; i++) { @@ -708,7 +708,7 @@ static void set_brk(abi_ulong start, abi_ulong end) end = HOST_PAGE_ALIGN(end); if (end <= start) return; - if(target_mmap(start, end - start, + if (target_mmap(start, end - start, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_ANON, -1, 0) == -1) { perror("cannot mmap brk"); @@ -738,12 +738,12 @@ static void padzero(abi_ulong elf_bss, abi_ulong last_bss) end_addr = HOST_PAGE_ALIGN(elf_bss); if (end_addr1 < end_addr) { mmap((void *)g2h_untagged(end_addr1), end_addr - end_addr1, - PROT_READ|PROT_WRITE|PROT_EXEC, - MAP_FIXED|MAP_PRIVATE|MAP_ANON, -1, 0); + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_FIXED | MAP_PRIVATE | MAP_ANON, -1, 0); } } - nbyte = elf_bss & (qemu_host_page_size-1); + nbyte = elf_bss & (qemu_host_page_size - 1); if (nbyte) { nbyte = qemu_host_page_size - nbyte; do { @@ -781,10 +781,10 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc, /* * Force 16 byte _final_ alignment here for generality. */ - sp = sp &~ (abi_ulong)15; + sp = sp & ~(abi_ulong)15; size = (DLINFO_ITEMS + 1) * 2; if (k_platform) - size += 2; + size += 2; #ifdef DLINFO_ARCH_ITEMS size += DLINFO_ARCH_ITEMS * 2; #endif @@ -792,7 +792,7 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc, size += (!ibcs ? 3 : 1); /* argc itself */ size *= n; if (size & 15) - sp -= 16 - (size & 15); + sp -= 16 - (size & 15); /* This is correct because Linux defines * elf_addr_t as Elf32_Off / Elf64_Off @@ -800,13 +800,13 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc, #define NEW_AUX_ENT(id, val) do { \ sp -= n; put_user_ual(val, sp); \ sp -= n; put_user_ual(id, sp); \ - } while(0) + } while (0) - NEW_AUX_ENT (AT_NULL, 0); + NEW_AUX_ENT(AT_NULL, 0); /* There must be exactly DLINFO_ITEMS entries here. */ NEW_AUX_ENT(AT_PHDR, (abi_ulong)(load_addr + exec->e_phoff)); - NEW_AUX_ENT(AT_PHENT, (abi_ulong)(sizeof (struct elf_phdr))); + NEW_AUX_ENT(AT_PHENT, (abi_ulong)(sizeof(struct elf_phdr))); NEW_AUX_ENT(AT_PHNUM, (abi_ulong)(exec->e_phnum)); NEW_AUX_ENT(AT_PAGESZ, (abi_ulong)(TARGET_PAGE_SIZE)); NEW_AUX_ENT(AT_BASE, (abi_ulong)(interp_load_addr)); @@ -834,90 +834,90 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc, } -static abi_ulong load_elf_interp(struct elfhdr * interp_elf_ex, +static abi_ulong load_elf_interp(struct elfhdr *interp_elf_ex, int interpreter_fd, abi_ulong *interp_load_addr) { - struct elf_phdr *elf_phdata = NULL; - struct elf_phdr *eppnt; - abi_ulong load_addr = 0; - int load_addr_set = 0; - int retval; - abi_ulong last_bss, elf_bss; - abi_ulong error; - int i; + struct elf_phdr *elf_phdata = NULL; + struct elf_phdr *eppnt; + abi_ulong load_addr = 0; + int load_addr_set = 0; + int retval; + abi_ulong last_bss, elf_bss; + abi_ulong error; + int i; - elf_bss = 0; - last_bss = 0; - error = 0; + elf_bss = 0; + last_bss = 0; + error = 0; #ifdef BSWAP_NEEDED - bswap_ehdr(interp_elf_ex); + bswap_ehdr(interp_elf_ex); #endif - /* First of all, some simple consistency checks */ - if ((interp_elf_ex->e_type != ET_EXEC && - interp_elf_ex->e_type != ET_DYN) || - !elf_check_arch(interp_elf_ex->e_machine)) { - return ~((abi_ulong)0UL); - } + /* First of all, some simple consistency checks */ + if ((interp_elf_ex->e_type != ET_EXEC && + interp_elf_ex->e_type != ET_DYN) || + !elf_check_arch(interp_elf_ex->e_machine)) { + return ~((abi_ulong)0UL); + } - /* Now read in all of the header information */ + /* Now read in all of the header information */ - if (sizeof(struct elf_phdr) * interp_elf_ex->e_phnum > TARGET_PAGE_SIZE) - return ~(abi_ulong)0UL; + if (sizeof(struct elf_phdr) * interp_elf_ex->e_phnum > TARGET_PAGE_SIZE) + return ~(abi_ulong)0UL; - elf_phdata = (struct elf_phdr *) - malloc(sizeof(struct elf_phdr) * interp_elf_ex->e_phnum); + elf_phdata = (struct elf_phdr *) + malloc(sizeof(struct elf_phdr) * interp_elf_ex->e_phnum); - if (!elf_phdata) - return ~((abi_ulong)0UL); + if (!elf_phdata) + return ~((abi_ulong)0UL); - /* - * If the size of this structure has changed, then punt, since - * we will be doing the wrong thing. - */ - if (interp_elf_ex->e_phentsize != sizeof(struct elf_phdr)) { - free(elf_phdata); - return ~((abi_ulong)0UL); - } + /* + * If the size of this structure has changed, then punt, since + * we will be doing the wrong thing. + */ + if (interp_elf_ex->e_phentsize != sizeof(struct elf_phdr)) { + free(elf_phdata); + return ~((abi_ulong)0UL); + } - retval = lseek(interpreter_fd, interp_elf_ex->e_phoff, SEEK_SET); - if(retval >= 0) { - retval = read(interpreter_fd, - (char *) elf_phdata, - sizeof(struct elf_phdr) * interp_elf_ex->e_phnum); - } - if (retval < 0) { - perror("load_elf_interp"); - exit(-1); - free (elf_phdata); - return retval; - } + retval = lseek(interpreter_fd, interp_elf_ex->e_phoff, SEEK_SET); + if (retval >= 0) { + retval = read(interpreter_fd, + (char *) elf_phdata, + sizeof(struct elf_phdr) * interp_elf_ex->e_phnum); + } + if (retval < 0) { + perror("load_elf_interp"); + exit(-1); + free (elf_phdata); + return retval; + } #ifdef BSWAP_NEEDED - eppnt = elf_phdata; - for (i=0; ie_phnum; i++, eppnt++) { - bswap_phdr(eppnt); - } + eppnt = elf_phdata; + for (i = 0; ie_phnum; i++, eppnt++) { + bswap_phdr(eppnt); + } #endif - if (interp_elf_ex->e_type == ET_DYN) { - /* in order to avoid hardcoding the interpreter load - address in qemu, we allocate a big enough memory zone */ - error = target_mmap(0, INTERP_MAP_SIZE, - PROT_NONE, MAP_PRIVATE | MAP_ANON, - -1, 0); - if (error == -1) { - perror("mmap"); - exit(-1); - } - load_addr = error; - load_addr_set = 1; + if (interp_elf_ex->e_type == ET_DYN) { + /* in order to avoid hardcoding the interpreter load + address in qemu, we allocate a big enough memory zone */ + error = target_mmap(0, INTERP_MAP_SIZE, + PROT_NONE, MAP_PRIVATE | MAP_ANON, + -1, 0); + if (error == -1) { + perror("mmap"); + exit(-1); } + load_addr = error; + load_addr_set = 1; + } - eppnt = elf_phdata; - for(i=0; ie_phnum; i++, eppnt++) - if (eppnt->p_type == PT_LOAD) { + eppnt = elf_phdata; + for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) + if (eppnt->p_type == PT_LOAD) { int elf_type = MAP_PRIVATE | MAP_DENYWRITE; int elf_prot = 0; abi_ulong vaddr = 0; @@ -930,23 +930,23 @@ static abi_ulong load_elf_interp(struct elfhdr * interp_elf_ex, elf_type |= MAP_FIXED; vaddr = eppnt->p_vaddr; } - error = target_mmap(load_addr+TARGET_ELF_PAGESTART(vaddr), - eppnt->p_filesz + TARGET_ELF_PAGEOFFSET(eppnt->p_vaddr), - elf_prot, - elf_type, - interpreter_fd, - eppnt->p_offset - TARGET_ELF_PAGEOFFSET(eppnt->p_vaddr)); + error = target_mmap(load_addr + TARGET_ELF_PAGESTART(vaddr), + eppnt->p_filesz + TARGET_ELF_PAGEOFFSET(eppnt->p_vaddr), + elf_prot, + elf_type, + interpreter_fd, + eppnt->p_offset - TARGET_ELF_PAGEOFFSET(eppnt->p_vaddr)); if (error == -1) { - /* Real error */ - close(interpreter_fd); - free(elf_phdata); - return ~((abi_ulong)0UL); + /* Real error */ + close(interpreter_fd); + free(elf_phdata); + return ~((abi_ulong)0UL); } if (!load_addr_set && interp_elf_ex->e_type == ET_DYN) { - load_addr = error; - load_addr_set = 1; + load_addr = error; + load_addr_set = 1; } /* @@ -962,31 +962,31 @@ static abi_ulong load_elf_interp(struct elfhdr * interp_elf_ex, */ k = load_addr + eppnt->p_memsz + eppnt->p_vaddr; if (k > last_bss) last_bss = k; - } - - /* Now use mmap to map the library into memory. */ - - close(interpreter_fd); - - /* - * Now fill out the bss section. First pad the last page up - * to the page boundary, and then perform a mmap to make sure - * that there are zeromapped pages up to and including the last - * bss page. - */ - padzero(elf_bss, last_bss); - elf_bss = TARGET_ELF_PAGESTART(elf_bss + qemu_host_page_size - 1); /* What we have mapped so far */ - - /* Map the last of the bss segment */ - if (last_bss > elf_bss) { - target_mmap(elf_bss, last_bss-elf_bss, - PROT_READ|PROT_WRITE|PROT_EXEC, - MAP_FIXED|MAP_PRIVATE|MAP_ANON, -1, 0); } - free(elf_phdata); - *interp_load_addr = load_addr; - return ((abi_ulong) interp_elf_ex->e_entry) + load_addr; + /* Now use mmap to map the library into memory. */ + + close(interpreter_fd); + + /* + * Now fill out the bss section. First pad the last page up + * to the page boundary, and then perform a mmap to make sure + * that there are zeromapped pages up to and including the last + * bss page. + */ + padzero(elf_bss, last_bss); + elf_bss = TARGET_ELF_PAGESTART(elf_bss + qemu_host_page_size - 1); /* What we have mapped so far */ + + /* Map the last of the bss segment */ + if (last_bss > elf_bss) { + target_mmap(elf_bss, last_bss - elf_bss, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_FIXED | MAP_PRIVATE | MAP_ANON, -1, 0); + } + free(elf_phdata); + + *interp_load_addr = load_addr; + return ((abi_ulong) interp_elf_ex->e_entry) + load_addr; } static int symfind(const void *s0, const void *s1) @@ -1102,7 +1102,7 @@ static void load_symbols(struct elfhdr *hdr, int fd) } continue; } -#if defined(TARGET_ARM) || defined (TARGET_MIPS) +#if defined(TARGET_ARM) || defined(TARGET_MIPS) /* The bottom address bit marks a Thumb or MIPS16 symbol. */ syms[i].st_value &= ~(target_ulong)1; #endif @@ -1143,8 +1143,8 @@ static void load_symbols(struct elfhdr *hdr, int fd) syminfos = s; } -int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, - struct image_info * info) +int load_elf_binary(struct bsd_binprm *bprm, struct target_pt_regs *regs, + struct image_info *info) { struct elfhdr elf_ex; struct elfhdr interp_elf_ex; @@ -1178,13 +1178,13 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, /* First of all, some simple consistency checks */ if ((elf_ex.e_type != ET_EXEC && elf_ex.e_type != ET_DYN) || - (! elf_check_arch(elf_ex.e_machine))) { + (!elf_check_arch(elf_ex.e_machine))) { return -ENOEXEC; } bprm->p = copy_elf_strings(1, &bprm->filename, bprm->page, bprm->p); - bprm->p = copy_elf_strings(bprm->envc,bprm->envp,bprm->page,bprm->p); - bprm->p = copy_elf_strings(bprm->argc,bprm->argv,bprm->page,bprm->p); + bprm->p = copy_elf_strings(bprm->envc, bprm->envp, bprm->page,bprm->p); + bprm->p = copy_elf_strings(bprm->argc, bprm->argv, bprm->page,bprm->p); if (!bprm->p) { retval = -E2BIG; } @@ -1196,21 +1196,21 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, } retval = lseek(bprm->fd, elf_ex.e_phoff, SEEK_SET); - if(retval > 0) { - retval = read(bprm->fd, (char *) elf_phdata, + if (retval > 0) { + retval = read(bprm->fd, (char *)elf_phdata, elf_ex.e_phentsize * elf_ex.e_phnum); } if (retval < 0) { perror("load_elf_binary"); exit(-1); - free (elf_phdata); + free(elf_phdata); return -errno; } #ifdef BSWAP_NEEDED elf_ppnt = elf_phdata; - for (i=0; ip_type == PT_INTERP) { - if ( elf_interpreter != NULL ) + if (elf_interpreter != NULL) { - free (elf_phdata); + free(elf_phdata); free(elf_interpreter); close(bprm->fd); return -EINVAL; @@ -1245,16 +1245,16 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, elf_interpreter = (char *)malloc(elf_ppnt->p_filesz); if (elf_interpreter == NULL) { - free (elf_phdata); + free(elf_phdata); close(bprm->fd); return -ENOMEM; } retval = lseek(bprm->fd, elf_ppnt->p_offset, SEEK_SET); - if(retval >= 0) { + if (retval >= 0) { retval = read(bprm->fd, elf_interpreter, elf_ppnt->p_filesz); } - if(retval < 0) { + if (retval < 0) { perror("load_elf_binary2"); exit(-1); } @@ -1265,8 +1265,8 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, /* JRP - Need to add X86 lib dir stuff here... */ - if (strcmp(elf_interpreter,"/usr/lib/libc.so.1") == 0 || - strcmp(elf_interpreter,"/usr/lib/ld.so.1") == 0) { + if (strcmp(elf_interpreter, "/usr/lib/libc.so.1") == 0 || + strcmp(elf_interpreter, "/usr/lib/ld.so.1") == 0) { ibcs2_interpreter = 1; } @@ -1275,7 +1275,7 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, #endif if (retval >= 0) { retval = open(path(elf_interpreter), O_RDONLY); - if(retval >= 0) { + if (retval >= 0) { interpreter_fd = retval; } else { @@ -1287,8 +1287,8 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, if (retval >= 0) { retval = lseek(interpreter_fd, 0, SEEK_SET); - if(retval >= 0) { - retval = read(interpreter_fd,bprm->buf,128); + if (retval >= 0) { + retval = read(interpreter_fd, bprm->buf, 128); } } if (retval >= 0) { @@ -1298,7 +1298,7 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, if (retval < 0) { perror("load_elf_binary3"); exit(-1); - free (elf_phdata); + free(elf_phdata); free(elf_interpreter); close(bprm->fd); return retval; @@ -1308,17 +1308,17 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, } /* Some simple consistency checks for the interpreter */ - if (elf_interpreter){ + if (elf_interpreter) { interpreter_type = INTERPRETER_ELF | INTERPRETER_AOUT; /* Now figure out which format our binary is */ if ((N_MAGIC(interp_ex) != OMAGIC) && (N_MAGIC(interp_ex) != ZMAGIC) && (N_MAGIC(interp_ex) != QMAGIC)) { - interpreter_type = INTERPRETER_ELF; + interpreter_type = INTERPRETER_ELF; } if (interp_elf_ex.e_ident[0] != 0x7f || - strncmp((char *)&interp_elf_ex.e_ident[1], "ELF",3) != 0) { + strncmp((char *)&interp_elf_ex.e_ident[1], "ELF", 3) != 0) { interpreter_type &= ~INTERPRETER_ELF; } @@ -1334,20 +1334,20 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, and then start this sucker up */ { - char * passed_p; + char *passed_p; if (interpreter_type == INTERPRETER_AOUT) { snprintf(passed_fileno, sizeof(passed_fileno), "%d", bprm->fd); passed_p = passed_fileno; if (elf_interpreter) { - bprm->p = copy_elf_strings(1,&passed_p,bprm->page,bprm->p); + bprm->p = copy_elf_strings(1, &passed_p, bprm->page, bprm->p); bprm->argc++; } } if (!bprm->p) { free(elf_interpreter); - free (elf_phdata); + free(elf_phdata); close(bprm->fd); return -E2BIG; } @@ -1393,7 +1393,7 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, * address. */ - for(i = 0, elf_ppnt = elf_phdata; i < elf_ex.e_phnum; i++, elf_ppnt++) { + for (i = 0, elf_ppnt = elf_phdata; i < elf_ex.e_phnum; i++, elf_ppnt++) { int elf_prot = 0; int elf_flags = 0; abi_ulong error; @@ -1538,7 +1538,7 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, printf("(brk) %x\n" , info->brk); #endif - if ( info->personality == PER_SVR4 ) + if (info->personality == PER_SVR4) { /* Why this, you ask??? Well SVr4 maps page 0 as read-only, and some applications "depend" upon this behavior. @@ -1553,7 +1553,7 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, return 0; } -static int load_aout_interp(void * exptr, int interp_fd) +static int load_aout_interp(void *exptr, int interp_fd) { printf("a.out interpreter not yet supported\n"); return(0); diff --git a/bsd-user/i386/target_signal.h b/bsd-user/i386/target_signal.h deleted file mode 100644 index 2ef36d1f98..0000000000 --- a/bsd-user/i386/target_signal.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef TARGET_SIGNAL_H -#define TARGET_SIGNAL_H - -#include "cpu.h" - -/* this struct defines a stack used during syscall handling */ - -typedef struct target_sigaltstack { - abi_ulong ss_sp; - abi_long ss_flags; - abi_ulong ss_size; -} target_stack_t; - - -static inline abi_ulong get_sp_from_cpustate(CPUX86State *state) -{ - return state->regs[R_ESP]; -} - -#endif /* TARGET_SIGNAL_H */ diff --git a/bsd-user/main.c b/bsd-user/main.c index 798aba512c..fe66204b6b 100644 --- a/bsd-user/main.c +++ b/bsd-user/main.c @@ -32,11 +32,11 @@ #include "qemu/path.h" #include "qemu/help_option.h" #include "qemu/module.h" -#include "cpu.h" #include "exec/exec-all.h" #include "tcg/tcg.h" #include "qemu/timer.h" #include "qemu/envlist.h" +#include "qemu/cutils.h" #include "exec/log.h" #include "trace/control.h" @@ -48,12 +48,13 @@ unsigned long reserved_va; static const char *interp_prefix = CONFIG_QEMU_INTERP_PREFIX; const char *qemu_uname_release; -extern char **environ; enum BSDType bsd_type; -/* XXX: on x86 MAP_GROWSDOWN only works if ESP <= address + 32, so - we allocate a bigger stack. Need a better solution, for example - by remapping the process stack directly at the right place */ +/* + * XXX: on x86 MAP_GROWSDOWN only works if ESP <= address + 32, so + * we allocate a bigger stack. Need a better solution, for example + * by remapping the process stack directly at the right place + */ unsigned long x86_stack_size = 512 * 1024; void gemu_log(const char *fmt, ...) @@ -148,15 +149,15 @@ void cpu_loop(CPUX86State *env) CPUState *cs = env_cpu(env); int trapnr; abi_ulong pc; - //target_siginfo_t info; + /* target_siginfo_t info; */ - for(;;) { + for (;;) { cpu_exec_start(cs); trapnr = cpu_exec(cs); cpu_exec_end(cs); process_queued_cpu_work(cs); - switch(trapnr) { + switch (trapnr) { case 0x80: /* syscall from int $0x80 */ if (bsd_type == target_freebsd) { @@ -197,7 +198,7 @@ void cpu_loop(CPUX86State *env) arg6, arg7, arg8); - } else { //if (bsd_type == target_openbsd) + } else { /* if (bsd_type == target_openbsd) */ env->regs[R_EAX] = do_openbsd_syscall(env, env->regs[R_EAX], env->regs[R_EBX], @@ -217,7 +218,7 @@ void cpu_loop(CPUX86State *env) #ifndef TARGET_ABI32 case EXCP_SYSCALL: /* syscall from syscall instruction */ - if (bsd_type == target_freebsd) + if (bsd_type == target_freebsd) { env->regs[R_EAX] = do_freebsd_syscall(env, env->regs[R_EAX], env->regs[R_EDI], @@ -226,7 +227,7 @@ void cpu_loop(CPUX86State *env) env->regs[R_ECX], env->regs[8], env->regs[9], 0, 0); - else { //if (bsd_type == target_openbsd) + } else { /* if (bsd_type == target_openbsd) */ env->regs[R_EAX] = do_openbsd_syscall(env, env->regs[R_EAX], env->regs[R_EDI], @@ -244,121 +245,14 @@ void cpu_loop(CPUX86State *env) env->eflags &= ~CC_C; } break; -#endif -#if 0 - case EXCP0B_NOSEG: - case EXCP0C_STACK: - info.si_signo = SIGBUS; - info.si_errno = 0; - info.si_code = TARGET_SI_KERNEL; - info._sifields._sigfault._addr = 0; - queue_signal(env, info.si_signo, &info); - break; - case EXCP0D_GPF: - /* XXX: potential problem if ABI32 */ -#ifndef TARGET_X86_64 - if (env->eflags & VM_MASK) { - handle_vm86_fault(env); - } else -#endif - { - info.si_signo = SIGSEGV; - info.si_errno = 0; - info.si_code = TARGET_SI_KERNEL; - info._sifields._sigfault._addr = 0; - queue_signal(env, info.si_signo, &info); - } - break; - case EXCP0E_PAGE: - info.si_signo = SIGSEGV; - info.si_errno = 0; - if (!(env->error_code & 1)) - info.si_code = TARGET_SEGV_MAPERR; - else - info.si_code = TARGET_SEGV_ACCERR; - info._sifields._sigfault._addr = env->cr[2]; - queue_signal(env, info.si_signo, &info); - break; - case EXCP00_DIVZ: -#ifndef TARGET_X86_64 - if (env->eflags & VM_MASK) { - handle_vm86_trap(env, trapnr); - } else -#endif - { - /* division by zero */ - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_code = TARGET_FPE_INTDIV; - info._sifields._sigfault._addr = env->eip; - queue_signal(env, info.si_signo, &info); - } - break; - case EXCP01_DB: - case EXCP03_INT3: -#ifndef TARGET_X86_64 - if (env->eflags & VM_MASK) { - handle_vm86_trap(env, trapnr); - } else -#endif - { - info.si_signo = SIGTRAP; - info.si_errno = 0; - if (trapnr == EXCP01_DB) { - info.si_code = TARGET_TRAP_BRKPT; - info._sifields._sigfault._addr = env->eip; - } else { - info.si_code = TARGET_SI_KERNEL; - info._sifields._sigfault._addr = 0; - } - queue_signal(env, info.si_signo, &info); - } - break; - case EXCP04_INTO: - case EXCP05_BOUND: -#ifndef TARGET_X86_64 - if (env->eflags & VM_MASK) { - handle_vm86_trap(env, trapnr); - } else -#endif - { - info.si_signo = SIGSEGV; - info.si_errno = 0; - info.si_code = TARGET_SI_KERNEL; - info._sifields._sigfault._addr = 0; - queue_signal(env, info.si_signo, &info); - } - break; - case EXCP06_ILLOP: - info.si_signo = SIGILL; - info.si_errno = 0; - info.si_code = TARGET_ILL_ILLOPN; - info._sifields._sigfault._addr = env->eip; - queue_signal(env, info.si_signo, &info); - break; #endif case EXCP_INTERRUPT: /* just indicate that signals should be handled asap */ break; -#if 0 - case EXCP_DEBUG: - { - int sig; - - sig = gdb_handlesig (env, TARGET_SIGTRAP); - if (sig) - { - info.si_signo = sig; - info.si_errno = 0; - info.si_code = TARGET_TRAP_BRKPT; - queue_signal(env, info.si_signo, &info); - } - } - break; -#endif default: pc = env->segs[R_CS].base + env->eip; - fprintf(stderr, "qemu: 0x%08lx: unhandled CPU exception 0x%x - aborting\n", + fprintf(stderr, + "qemu: 0x%08lx: unhandled CPU exception 0x%x - aborting\n", (long)pc, trapnr); abort(); } @@ -370,16 +264,21 @@ void cpu_loop(CPUX86State *env) #ifdef TARGET_SPARC #define SPARC64_STACK_BIAS 2047 -//#define DEBUG_WIN -/* WARNING: dealing with register windows _is_ complicated. More info - can be found at http://www.sics.se/~psm/sparcstack.html */ +/* #define DEBUG_WIN */ +/* + * WARNING: dealing with register windows _is_ complicated. More info + * can be found at http://www.sics.se/~psm/sparcstack.html + */ static inline int get_reg_index(CPUSPARCState *env, int cwp, int index) { index = (index + cwp * 16) % (16 * env->nwindows); - /* wrap handling : if cwp is on the last window, then we use the - registers 'after' the end */ - if (index < 8 && env->cwp == env->nwindows - 1) + /* + * wrap handling : if cwp is on the last window, then we use the + * registers 'after' the end + */ + if (index < 8 && env->cwp == env->nwindows - 1) { index += 16 * env->nwindows; + } return index; } @@ -391,14 +290,15 @@ static inline void save_window_offset(CPUSPARCState *env, int cwp1) sp_ptr = env->regbase[get_reg_index(env, cwp1, 6)]; #ifdef TARGET_SPARC64 - if (sp_ptr & 3) + if (sp_ptr & 3) { sp_ptr += SPARC64_STACK_BIAS; + } #endif #if defined(DEBUG_WIN) printf("win_overflow: sp_ptr=0x" TARGET_ABI_FMT_lx " save_cwp=%d\n", sp_ptr, cwp1); #endif - for(i = 0; i < 16; i++) { + for (i = 0; i < 16; i++) { /* FIXME - what to do if put_user() fails? */ put_user_ual(env->regbase[get_reg_index(env, cwp1, 8 + i)], sp_ptr); sp_ptr += sizeof(abi_ulong); @@ -441,22 +341,24 @@ static void restore_window(CPUSPARCState *env) cwp1 = cpu_cwp_inc(env, env->cwp + 1); sp_ptr = env->regbase[get_reg_index(env, cwp1, 6)]; #ifdef TARGET_SPARC64 - if (sp_ptr & 3) + if (sp_ptr & 3) { sp_ptr += SPARC64_STACK_BIAS; + } #endif #if defined(DEBUG_WIN) printf("win_underflow: sp_ptr=0x" TARGET_ABI_FMT_lx " load_cwp=%d\n", sp_ptr, cwp1); #endif - for(i = 0; i < 16; i++) { + for (i = 0; i < 16; i++) { /* FIXME - what to do if get_user() fails? */ get_user_ual(env->regbase[get_reg_index(env, cwp1, 8 + i)], sp_ptr); sp_ptr += sizeof(abi_ulong); } #ifdef TARGET_SPARC64 env->canrestore++; - if (env->cleanwin < env->nwindows - 1) + if (env->cleanwin < env->nwindows - 1) { env->cleanwin++; + } env->cansave--; #else env->wim = new_wim; @@ -468,15 +370,17 @@ static void flush_windows(CPUSPARCState *env) int offset, cwp1; offset = 1; - for(;;) { + for (;;) { /* if restore would invoke restore_window(), then we can stop */ cwp1 = cpu_cwp_inc(env, env->cwp + offset); #ifndef TARGET_SPARC64 - if (env->wim & (1 << cwp1)) + if (env->wim & (1 << cwp1)) { break; + } #else - if (env->canrestore == 0) + if (env->canrestore == 0) { break; + } env->cansave++; env->canrestore--; #endif @@ -497,7 +401,7 @@ void cpu_loop(CPUSPARCState *env) { CPUState *cs = env_cpu(env); int trapnr, ret, syscall_nr; - //target_siginfo_t info; + /* target_siginfo_t info; */ while (1) { cpu_exec_start(cs); @@ -511,8 +415,9 @@ void cpu_loop(CPUSPARCState *env) #else /* FreeBSD uses 0x141 for syscalls too */ case 0x141: - if (bsd_type != target_freebsd) + if (bsd_type != target_freebsd) { goto badtrap; + } /* fallthrough */ case 0x100: #endif @@ -521,13 +426,14 @@ void cpu_loop(CPUSPARCState *env) ret = do_freebsd_syscall(env, syscall_nr, env->regwptr[0], env->regwptr[1], env->regwptr[2], env->regwptr[3], - env->regwptr[4], env->regwptr[5], 0, 0); + env->regwptr[4], env->regwptr[5], + 0, 0); else if (bsd_type == target_netbsd) ret = do_netbsd_syscall(env, syscall_nr, env->regwptr[0], env->regwptr[1], env->regwptr[2], env->regwptr[3], env->regwptr[4], env->regwptr[5]); - else { //if (bsd_type == target_openbsd) + else { /* if (bsd_type == target_openbsd) */ #if defined(TARGET_SPARC64) syscall_nr &= ~(TARGET_OPENBSD_SYSCALL_G7RFLAG | TARGET_OPENBSD_SYSCALL_G2RFLAG); @@ -589,16 +495,6 @@ void cpu_loop(CPUSPARCState *env) break; case TT_TFAULT: case TT_DFAULT: -#if 0 - { - info.si_signo = SIGSEGV; - info.si_errno = 0; - /* XXX: check env->error_code */ - info.si_code = TARGET_SEGV_MAPERR; - info._sifields._sigfault._addr = env->mmuregs[4]; - queue_signal(env, info.si_signo, &info); - } -#endif break; #else case TT_SPILL: /* window overflow */ @@ -609,19 +505,6 @@ void cpu_loop(CPUSPARCState *env) break; case TT_TFAULT: case TT_DFAULT: -#if 0 - { - info.si_signo = SIGSEGV; - info.si_errno = 0; - /* XXX: check env->error_code */ - info.si_code = TARGET_SEGV_MAPERR; - if (trapnr == TT_DFAULT) - info._sifields._sigfault._addr = env->dmmuregs[4]; - else - info._sifields._sigfault._addr = env->tsptr->tpc; - //queue_signal(env, info.si_signo, &info); - } -#endif break; #endif case EXCP_INTERRUPT: @@ -629,30 +512,18 @@ void cpu_loop(CPUSPARCState *env) break; case EXCP_DEBUG: { -#if 0 - int sig = -#endif gdb_handlesig(cs, TARGET_SIGTRAP); -#if 0 - if (sig) - { - info.si_signo = sig; - info.si_errno = 0; - info.si_code = TARGET_TRAP_BRKPT; - //queue_signal(env, info.si_signo, &info); - } -#endif } break; default: #ifdef TARGET_SPARC64 badtrap: #endif - printf ("Unhandled trap: 0x%x\n", trapnr); + printf("Unhandled trap: 0x%x\n", trapnr); cpu_dump_state(cs, stderr, 0); - exit (1); + exit(1); } - process_pending_signals (env); + process_pending_signals(env); } } @@ -742,15 +613,16 @@ int main(int argc, char **argv) TaskState ts1, *ts = &ts1; CPUArchState *env; CPUState *cpu; - int optind; + int optind, rv; const char *r; const char *gdbstub = NULL; char **target_environ, **wrk; envlist_t *envlist = NULL; bsd_type = target_openbsd; - if (argc <= 1) + if (argc <= 1) { usage(); + } error_init(argv[0]); module_call_init(MODULE_INIT_TRACE); @@ -770,11 +642,13 @@ int main(int argc, char **argv) optind = 1; for (;;) { - if (optind >= argc) + if (optind >= argc) { break; + } r = argv[optind]; - if (r[0] != '-') + if (r[0] != '-') { break; + } optind++; r++; if (!strcmp(r, "-")) { @@ -791,24 +665,28 @@ int main(int argc, char **argv) log_file = argv[optind++]; } else if (!strcmp(r, "E")) { r = argv[optind++]; - if (envlist_setenv(envlist, r) != 0) + if (envlist_setenv(envlist, r) != 0) { usage(); + } } else if (!strcmp(r, "ignore-environment")) { envlist_free(envlist); envlist = envlist_create(); } else if (!strcmp(r, "U")) { r = argv[optind++]; - if (envlist_unsetenv(envlist, r) != 0) + if (envlist_unsetenv(envlist, r) != 0) { usage(); + } } else if (!strcmp(r, "s")) { r = argv[optind++]; - x86_stack_size = strtol(r, (char **)&r, 0); - if (x86_stack_size <= 0) + rv = qemu_strtoul(r, &r, 0, &x86_stack_size); + if (rv < 0 || x86_stack_size <= 0) { usage(); - if (*r == 'M') + } + if (*r == 'M') { x86_stack_size *= MiB; - else if (*r == 'k' || *r == 'K') + } else if (*r == 'k' || *r == 'K') { x86_stack_size *= KiB; + } } else if (!strcmp(r, "L")) { interp_prefix = argv[optind++]; } else if (!strcmp(r, "p")) { @@ -825,15 +703,18 @@ int main(int argc, char **argv) } else if (!strcmp(r, "cpu")) { cpu_model = argv[optind++]; if (is_help_option(cpu_model)) { -/* XXX: implement xxx_cpu_list for targets that still miss it */ + /* XXX: implement xxx_cpu_list for targets that still miss it */ #if defined(cpu_list) - cpu_list(); + cpu_list(); #endif exit(1); } } else if (!strcmp(r, "B")) { - guest_base = strtol(argv[optind++], NULL, 0); - have_guest_base = true; + rv = qemu_strtoul(argv[optind++], NULL, 0, &guest_base); + if (rv < 0) { + usage(); + } + have_guest_base = true; } else if (!strcmp(r, "drop-ld-preload")) { (void) envlist_unsetenv(envlist, "LD_PRELOAD"); } else if (!strcmp(r, "bsd")) { @@ -914,8 +795,8 @@ int main(int argc, char **argv) { AccelClass *ac = ACCEL_GET_CLASS(current_accel()); - ac->init_machine(NULL); accel_init_interfaces(ac); + ac->init_machine(NULL); } cpu = cpu_create(cpu_type); env = cpu->env_ptr; @@ -932,7 +813,7 @@ int main(int argc, char **argv) envlist_free(envlist); /* - * Now that page sizes are configured in tcg_exec_init() we can do + * Now that page sizes are configured we can do * proper page alignment for guest_base. */ guest_base = HOST_PAGE_ALIGN(guest_base); @@ -948,17 +829,19 @@ int main(int argc, char **argv) if (!have_guest_base) { FILE *fp; - if ((fp = fopen("/proc/sys/vm/mmap_min_addr", "r")) != NULL) { + fp = fopen("/proc/sys/vm/mmap_min_addr", "r"); + if (fp != NULL) { unsigned long tmp; if (fscanf(fp, "%lu", &tmp) == 1) { mmap_min_addr = tmp; - qemu_log_mask(CPU_LOG_PAGE, "host mmap_min_addr=0x%lx\n", mmap_min_addr); + qemu_log_mask(CPU_LOG_PAGE, "host mmap_min_addr=0x%lx\n", + mmap_min_addr); } fclose(fp); } } - if (loader_exec(filename, argv+optind, target_environ, regs, info) != 0) { + if (loader_exec(filename, argv + optind, target_environ, regs, info) != 0) { printf("Error loading %s\n", filename); _exit(1); } @@ -990,11 +873,12 @@ int main(int argc, char **argv) syscall_init(); signal_init(); - /* Now that we've loaded the binary, GUEST_BASE is fixed. Delay - generating the prologue until now so that the prologue can take - the real value of GUEST_BASE into account. */ + /* + * Now that we've loaded the binary, GUEST_BASE is fixed. Delay + * generating the prologue until now so that the prologue can take + * the real value of GUEST_BASE into account. + */ tcg_prologue_init(tcg_ctx); - tcg_region_init(); /* build Task State */ memset(ts, 0, sizeof(TaskState)); @@ -1053,8 +937,8 @@ int main(int argc, char **argv) env->idt.limit = 255; #endif env->idt.base = target_mmap(0, sizeof(uint64_t) * (env->idt.limit + 1), - PROT_READ|PROT_WRITE, - MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); idt_table = g2h_untagged(env->idt.base); set_idt(0, 0); set_idt(1, 0); @@ -1082,8 +966,8 @@ int main(int argc, char **argv) { uint64_t *gdt_table; env->gdt.base = target_mmap(0, sizeof(uint64_t) * TARGET_GDT_ENTRIES, - PROT_READ|PROT_WRITE, - MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); env->gdt.limit = sizeof(uint64_t) * TARGET_GDT_ENTRIES - 1; gdt_table = g2h_untagged(env->gdt.base); #ifdef TARGET_ABI32 @@ -1123,10 +1007,12 @@ int main(int argc, char **argv) env->pc = regs->pc; env->npc = regs->npc; env->y = regs->y; - for(i = 0; i < 8; i++) + for (i = 0; i < 8; i++) { env->gregs[i] = regs->u_regs[i]; - for(i = 0; i < 8; i++) + } + for (i = 0; i < 8; i++) { env->regwptr[i] = regs->u_regs[i + 8]; + } } #else #error unsupported target CPU diff --git a/bsd-user/mmap.c b/bsd-user/mmap.c index 01ec808003..0ac1b92706 100644 --- a/bsd-user/mmap.c +++ b/bsd-user/mmap.c @@ -93,11 +93,11 @@ int target_mprotect(abi_ulong start, abi_ulong len, int prot) if (start > host_start) { /* handle host page containing start */ prot1 = prot; - for(addr = host_start; addr < start; addr += TARGET_PAGE_SIZE) { + for (addr = host_start; addr < start; addr += TARGET_PAGE_SIZE) { prot1 |= page_get_flags(addr); } if (host_end == host_start + qemu_host_page_size) { - for(addr = end; addr < host_end; addr += TARGET_PAGE_SIZE) { + for (addr = end; addr < host_end; addr += TARGET_PAGE_SIZE) { prot1 |= page_get_flags(addr); } end = host_end; @@ -110,7 +110,7 @@ int target_mprotect(abi_ulong start, abi_ulong len, int prot) } if (end < host_end) { prot1 = prot; - for(addr = end; addr < host_end; addr += TARGET_PAGE_SIZE) { + for (addr = end; addr < host_end; addr += TARGET_PAGE_SIZE) { prot1 |= page_get_flags(addr); } ret = mprotect(g2h_untagged(host_end - qemu_host_page_size), @@ -148,7 +148,7 @@ static int mmap_frag(abi_ulong real_start, /* get the protection of the target pages outside the mapping */ prot1 = 0; - for(addr = real_start; addr < real_end; addr++) { + for (addr = real_start; addr < real_end; addr++) { if (addr < start || addr >= end) prot1 |= page_get_flags(addr); } @@ -225,9 +225,9 @@ static abi_ulong mmap_find_vma(abi_ulong start, abi_ulong size) if (addr == 0) addr = mmap_next_start; addr_start = addr; - for(;;) { + for (;;) { prot = 0; - for(addr1 = addr; addr1 < (addr + size); addr1 += TARGET_PAGE_SIZE) { + for (addr1 = addr; addr1 < (addr + size); addr1 += TARGET_PAGE_SIZE) { prot |= page_get_flags(addr1); } if (prot == 0) @@ -262,7 +262,7 @@ abi_long target_mmap(abi_ulong start, abi_ulong len, int prot, printf("MAP_FIXED "); if (flags & MAP_ANON) printf("MAP_ANON "); - switch(flags & TARGET_BSD_MAP_FLAGMASK) { + switch (flags & TARGET_BSD_MAP_FLAGMASK) { case MAP_PRIVATE: printf("MAP_PRIVATE "); break; @@ -321,7 +321,7 @@ abi_long target_mmap(abi_ulong start, abi_ulong len, int prot, end = start + len; real_end = HOST_PAGE_ALIGN(end); - for(addr = real_start; addr < real_end; addr += TARGET_PAGE_SIZE) { + for (addr = real_start; addr < real_end; addr += TARGET_PAGE_SIZE) { flg = page_get_flags(addr); if (flg & PAGE_RESERVED) { errno = ENXIO; @@ -433,11 +433,11 @@ int target_munmap(abi_ulong start, abi_ulong len) if (start > real_start) { /* handle host page containing start */ prot = 0; - for(addr = real_start; addr < start; addr += TARGET_PAGE_SIZE) { + for (addr = real_start; addr < start; addr += TARGET_PAGE_SIZE) { prot |= page_get_flags(addr); } if (real_end == real_start + qemu_host_page_size) { - for(addr = end; addr < real_end; addr += TARGET_PAGE_SIZE) { + for (addr = end; addr < real_end; addr += TARGET_PAGE_SIZE) { prot |= page_get_flags(addr); } end = real_end; @@ -447,7 +447,7 @@ int target_munmap(abi_ulong start, abi_ulong len) } if (end < real_end) { prot = 0; - for(addr = end; addr < real_end; addr += TARGET_PAGE_SIZE) { + for (addr = end; addr < real_end; addr += TARGET_PAGE_SIZE) { prot |= page_get_flags(addr); } if (prot != 0) diff --git a/bsd-user/qemu.h b/bsd-user/qemu.h index d2bcaab741..c02e8a5ca1 100644 --- a/bsd-user/qemu.h +++ b/bsd-user/qemu.h @@ -27,6 +27,8 @@ #include "exec/user/abitypes.h" +extern char **environ; + enum BSDType { target_freebsd, target_netbsd, @@ -36,7 +38,6 @@ extern enum BSDType bsd_type; #include "syscall_defs.h" #include "target_syscall.h" -#include "target_signal.h" #include "exec/gdbstub.h" #if defined(CONFIG_USE_NPTL) @@ -45,9 +46,10 @@ extern enum BSDType bsd_type; #define THREAD #endif -/* This struct is used to hold certain information about the image. - * Basically, it replicates in user space what would be certain - * task_struct fields in the kernel +/* + * This struct is used to hold certain information about the image. Basically, + * it replicates in user space what would be certain task_struct fields in the + * kernel */ struct image_info { abi_ulong load_addr; @@ -71,18 +73,18 @@ struct image_info { struct sigqueue { struct sigqueue *next; - //target_siginfo_t info; }; struct emulated_sigtable { int pending; /* true if signal is pending */ struct sigqueue *first; - struct sigqueue info; /* in order to always have memory for the - first signal, we put it here */ + /* in order to always have memory for the first signal, we put it here */ + struct sigqueue info; }; -/* NOTE: we force a big alignment so that the stack stored after is - aligned too */ +/* + * NOTE: we force a big alignment so that the stack stored after is aligned too + */ typedef struct TaskState { pid_t ts_tid; /* tid (or pid) of this task */ @@ -102,7 +104,6 @@ void init_task_state(TaskState *ts); extern const char *qemu_uname_release; extern unsigned long mmap_min_addr; -/* ??? See if we can avoid exposing so much of the loader internals. */ /* * MAX_ARG_PAGES defines the number of pages allocated for arguments * and envelope for the new program. 32 should suffice, this gives @@ -114,7 +115,7 @@ extern unsigned long mmap_min_addr; * This structure is used to hold the arguments that are * used when loading binaries. */ -struct linux_binprm { +struct bsd_binprm { char buf[128]; void *page[MAX_ARG_PAGES]; abi_ulong p; @@ -123,19 +124,19 @@ struct linux_binprm { int argc, envc; char **argv; char **envp; - char * filename; /* Name of binary */ + char *filename; /* Name of binary */ }; void do_init_thread(struct target_pt_regs *regs, struct image_info *infop); abi_ulong loader_build_argptr(int envc, int argc, abi_ulong sp, abi_ulong stringp, int push_ptr); -int loader_exec(const char * filename, char ** argv, char ** envp, - struct target_pt_regs * regs, struct image_info *infop); +int loader_exec(const char *filename, char **argv, char **envp, + struct target_pt_regs *regs, struct image_info *infop); -int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, - struct image_info * info); -int load_flt_binary(struct linux_binprm * bprm, struct target_pt_regs * regs, - struct image_info * info); +int load_elf_binary(struct bsd_binprm *bprm, struct target_pt_regs *regs, + struct image_info *info); +int load_flt_binary(struct bsd_binprm *bprm, struct target_pt_regs *regs, + struct image_info *info); abi_long memcpy_to_target(abi_ulong dest, const void *src, unsigned long len); @@ -193,9 +194,6 @@ extern int do_strace; /* signal.c */ void process_pending_signals(CPUArchState *cpu_env); void signal_init(void); -//int queue_signal(CPUArchState *env, int sig, target_siginfo_t *info); -//void host_to_target_siginfo(target_siginfo_t *tinfo, const siginfo_t *info); -//void target_to_host_siginfo(siginfo_t *info, const target_siginfo_t *tinfo); long do_sigreturn(CPUArchState *env); long do_rt_sigreturn(CPUArchState *env); abi_long do_sigaltstack(abi_ulong uss_addr, abi_ulong uoss_addr, abi_ulong sp); @@ -226,14 +224,16 @@ static inline bool access_ok(int type, abi_ulong addr, abi_ulong size) return page_check_range((target_ulong)addr, size, type) == 0; } -/* NOTE __get_user and __put_user use host pointers and don't check access. */ -/* These are usually used to access struct data members once the - * struct has been locked - usually with lock_user_struct(). +/* + * NOTE __get_user and __put_user use host pointers and don't check access. + * + * These are usually used to access struct data members once the struct has been + * locked - usually with lock_user_struct(). */ #define __put_user(x, hptr)\ ({\ int size = sizeof(*hptr);\ - switch(size) {\ + switch (size) {\ case 1:\ *(uint8_t *)(hptr) = (uint8_t)(typeof(*hptr))(x);\ break;\ @@ -248,14 +248,14 @@ static inline bool access_ok(int type, abi_ulong addr, abi_ulong size) break;\ default:\ abort();\ - }\ + } \ 0;\ }) #define __get_user(x, hptr) \ ({\ int size = sizeof(*hptr);\ - switch(size) {\ + switch (size) {\ case 1:\ x = (typeof(*hptr))*(uint8_t *)(hptr);\ break;\ @@ -269,24 +269,26 @@ static inline bool access_ok(int type, abi_ulong addr, abi_ulong size) x = (typeof(*hptr))tswap64(*(uint64_t *)(hptr));\ break;\ default:\ - /* avoid warning */\ x = 0;\ abort();\ - }\ + } \ 0;\ }) -/* put_user()/get_user() take a guest address and check access */ -/* These are usually used to access an atomic data type, such as an int, - * that has been passed by address. These internally perform locking - * and unlocking on the data type. +/* + * put_user()/get_user() take a guest address and check access + * + * These are usually used to access an atomic data type, such as an int, that + * has been passed by address. These internally perform locking and unlocking + * on the data type. */ #define put_user(x, gaddr, target_type) \ ({ \ abi_ulong __gaddr = (gaddr); \ target_type *__hptr; \ abi_long __ret; \ - if ((__hptr = lock_user(VERIFY_WRITE, __gaddr, sizeof(target_type), 0))) { \ + __hptr = lock_user(VERIFY_WRITE, __gaddr, sizeof(target_type), 0); \ + if (__hptr) { \ __ret = __put_user((x), __hptr); \ unlock_user(__hptr, __gaddr, sizeof(target_type)); \ } else \ @@ -299,11 +301,11 @@ static inline bool access_ok(int type, abi_ulong addr, abi_ulong size) abi_ulong __gaddr = (gaddr); \ target_type *__hptr; \ abi_long __ret; \ - if ((__hptr = lock_user(VERIFY_READ, __gaddr, sizeof(target_type), 1))) { \ + __hptr = lock_user(VERIFY_READ, __gaddr, sizeof(target_type), 1); \ + if (__hptr) { \ __ret = __get_user((x), __hptr); \ unlock_user(__hptr, __gaddr, 0); \ } else { \ - /* avoid warning */ \ (x) = 0; \ __ret = -TARGET_EFAULT; \ } \ @@ -332,33 +334,41 @@ static inline bool access_ok(int type, abi_ulong addr, abi_ulong size) #define get_user_u8(x, gaddr) get_user((x), (gaddr), uint8_t) #define get_user_s8(x, gaddr) get_user((x), (gaddr), int8_t) -/* copy_from_user() and copy_to_user() are usually used to copy data +/* + * copy_from_user() and copy_to_user() are usually used to copy data * buffers between the target and host. These internally perform * locking/unlocking of the memory. */ abi_long copy_from_user(void *hptr, abi_ulong gaddr, size_t len); abi_long copy_to_user(abi_ulong gaddr, void *hptr, size_t len); -/* Functions for accessing guest memory. The tget and tput functions - read/write single values, byteswapping as necessary. The lock_user function - gets a pointer to a contiguous area of guest memory, but does not perform - any byteswapping. lock_user may return either a pointer to the guest - memory, or a temporary buffer. */ +/* + * Functions for accessing guest memory. The tget and tput functions + * read/write single values, byteswapping as necessary. The lock_user function + * gets a pointer to a contiguous area of guest memory, but does not perform + * any byteswapping. lock_user may return either a pointer to the guest + * memory, or a temporary buffer. + */ -/* Lock an area of guest memory into the host. If copy is true then the - host area will have the same contents as the guest. */ -static inline void *lock_user(int type, abi_ulong guest_addr, long len, int copy) +/* + * Lock an area of guest memory into the host. If copy is true then the + * host area will have the same contents as the guest. + */ +static inline void *lock_user(int type, abi_ulong guest_addr, long len, + int copy) { - if (!access_ok(type, guest_addr, len)) + if (!access_ok(type, guest_addr, len)) { return NULL; + } #ifdef DEBUG_REMAP { void *addr; addr = g_malloc(len); - if (copy) + if (copy) { memcpy(addr, g2h_untagged(guest_addr), len); - else + } else { memset(addr, 0, len); + } return addr; } #else @@ -366,26 +376,32 @@ static inline void *lock_user(int type, abi_ulong guest_addr, long len, int copy #endif } -/* Unlock an area of guest memory. The first LEN bytes must be - flushed back to guest memory. host_ptr = NULL is explicitly - allowed and does nothing. */ +/* + * Unlock an area of guest memory. The first LEN bytes must be flushed back to + * guest memory. host_ptr = NULL is explicitly allowed and does nothing. + */ static inline void unlock_user(void *host_ptr, abi_ulong guest_addr, long len) { #ifdef DEBUG_REMAP - if (!host_ptr) + if (!host_ptr) { return; - if (host_ptr == g2h_untagged(guest_addr)) + } + if (host_ptr == g2h_untagged(guest_addr)) { return; - if (len > 0) + } + if (len > 0) { memcpy(g2h_untagged(guest_addr), host_ptr, len); + } g_free(host_ptr); #endif } -/* Return the length of a string in target memory or -TARGET_EFAULT if - access error. */ +/* + * Return the length of a string in target memory or -TARGET_EFAULT if access + * error. + */ abi_long target_strlen(abi_ulong gaddr); /* Like lock_user but for null terminated strings. */ @@ -393,8 +409,9 @@ static inline void *lock_user_string(abi_ulong guest_addr) { abi_long len; len = target_strlen(guest_addr); - if (len < 0) + if (len < 0) { return NULL; + } return lock_user(VERIFY_READ, guest_addr, (long)(len + 1), 1); } diff --git a/bsd-user/signal.c b/bsd-user/signal.c index f6f7aa2427..ad6d935569 100644 --- a/bsd-user/signal.c +++ b/bsd-user/signal.c @@ -19,7 +19,6 @@ #include "qemu/osdep.h" #include "qemu.h" -#include "target_signal.h" void signal_init(void) { diff --git a/bsd-user/sparc/target_signal.h b/bsd-user/sparc/target_signal.h deleted file mode 100644 index 5b2abba40f..0000000000 --- a/bsd-user/sparc/target_signal.h +++ /dev/null @@ -1,27 +0,0 @@ -#ifndef TARGET_SIGNAL_H -#define TARGET_SIGNAL_H - -#include "cpu.h" - -/* this struct defines a stack used during syscall handling */ - -typedef struct target_sigaltstack { - abi_ulong ss_sp; - abi_long ss_flags; - abi_ulong ss_size; -} target_stack_t; - - -#ifndef UREG_I6 -#define UREG_I6 6 -#endif -#ifndef UREG_FP -#define UREG_FP UREG_I6 -#endif - -static inline abi_ulong get_sp_from_cpustate(CPUSPARCState *state) -{ - return state->regwptr[UREG_FP]; -} - -#endif /* TARGET_SIGNAL_H */ diff --git a/bsd-user/sparc64/target_signal.h b/bsd-user/sparc64/target_signal.h deleted file mode 100644 index 5b2abba40f..0000000000 --- a/bsd-user/sparc64/target_signal.h +++ /dev/null @@ -1,27 +0,0 @@ -#ifndef TARGET_SIGNAL_H -#define TARGET_SIGNAL_H - -#include "cpu.h" - -/* this struct defines a stack used during syscall handling */ - -typedef struct target_sigaltstack { - abi_ulong ss_sp; - abi_long ss_flags; - abi_ulong ss_size; -} target_stack_t; - - -#ifndef UREG_I6 -#define UREG_I6 6 -#endif -#ifndef UREG_FP -#define UREG_FP UREG_I6 -#endif - -static inline abi_ulong get_sp_from_cpustate(CPUSPARCState *state) -{ - return state->regwptr[UREG_FP]; -} - -#endif /* TARGET_SIGNAL_H */ diff --git a/bsd-user/strace.c b/bsd-user/strace.c index 2c3b59caf0..be40b8a20c 100644 --- a/bsd-user/strace.c +++ b/bsd-user/strace.c @@ -128,14 +128,6 @@ static void print_syscall_ret_addr(const struct syscallname *name, abi_long ret) } } -#if 0 /* currently unused */ -static void -print_syscall_ret_raw(struct syscallname *name, abi_long ret) -{ - gemu_log(" = 0x" TARGET_ABI_FMT_lx "\n", ret); -} -#endif - /* * An array of all of the syscalls we know about */ diff --git a/bsd-user/syscall.c b/bsd-user/syscall.c index adc3d21b54..3f44311396 100644 --- a/bsd-user/syscall.c +++ b/bsd-user/syscall.c @@ -95,7 +95,7 @@ static abi_long do_freebsd_sysarch(CPUX86State *env, int op, abi_ulong parms) abi_ulong val; int idx; - switch(op) { + switch (op) { #ifdef TARGET_ABI32 case TARGET_FREEBSD_I386_SET_GSBASE: case TARGET_FREEBSD_I386_SET_FSBASE: @@ -199,6 +199,7 @@ static int sysctl_oldcvt(void *holdp, size_t holdlen, uint32_t kind) #else case CTLTYPE_LONG: *(uint64_t *)holdp = tswap64(*(long *)holdp); + break; case CTLTYPE_ULONG: *(uint64_t *)holdp = tswap64(*(unsigned long *)holdp); break; @@ -271,7 +272,7 @@ static abi_long lock_iovec(int type, struct iovec *vec, abi_ulong target_addr, target_vec = lock_user(VERIFY_READ, target_addr, count * sizeof(struct target_iovec), 1); if (!target_vec) return -TARGET_EFAULT; - for(i = 0;i < count; i++) { + for (i = 0;i < count; i++) { base = tswapl(target_vec[i].iov_base); vec[i].iov_len = tswapl(target_vec[i].iov_len); if (vec[i].iov_len != 0) { @@ -297,7 +298,7 @@ static abi_long unlock_iovec(struct iovec *vec, abi_ulong target_addr, target_vec = lock_user(VERIFY_READ, target_addr, count * sizeof(struct target_iovec), 1); if (!target_vec) return -TARGET_EFAULT; - for(i = 0;i < count; i++) { + for (i = 0;i < count; i++) { if (target_vec[i].iov_base) { base = tswapl(target_vec[i].iov_base); unlock_user(vec[i].iov_base, base, copy ? vec[i].iov_len : 0); @@ -325,16 +326,16 @@ abi_long do_freebsd_syscall(void *cpu_env, int num, abi_long arg1, #endif record_syscall_start(cpu, num, arg1, arg2, arg3, arg4, arg5, arg6, 0, 0); - if(do_strace) + if (do_strace) print_freebsd_syscall(num, arg1, arg2, arg3, arg4, arg5, arg6); - switch(num) { + switch (num) { case TARGET_FREEBSD_NR_exit: #ifdef CONFIG_GPROF _mcleanup(); #endif gdb_exit(arg1); - qemu_plugin_atexit_cb(); + qemu_plugin_user_exit(); /* XXX: should free thread stack and CPU env */ _exit(arg1); ret = 0; /* avoid warning */ @@ -427,16 +428,16 @@ abi_long do_netbsd_syscall(void *cpu_env, int num, abi_long arg1, record_syscall_start(cpu, num, arg1, arg2, arg3, arg4, arg5, arg6, 0, 0); - if(do_strace) + if (do_strace) print_netbsd_syscall(num, arg1, arg2, arg3, arg4, arg5, arg6); - switch(num) { + switch (num) { case TARGET_NETBSD_NR_exit: #ifdef CONFIG_GPROF _mcleanup(); #endif gdb_exit(arg1); - qemu_plugin_atexit_cb(); + qemu_plugin_user_exit(); /* XXX: should free thread stack and CPU env */ _exit(arg1); ret = 0; /* avoid warning */ @@ -506,16 +507,16 @@ abi_long do_openbsd_syscall(void *cpu_env, int num, abi_long arg1, record_syscall_start(cpu, num, arg1, arg2, arg3, arg4, arg5, arg6, 0, 0); - if(do_strace) + if (do_strace) print_openbsd_syscall(num, arg1, arg2, arg3, arg4, arg5, arg6); - switch(num) { + switch (num) { case TARGET_OPENBSD_NR_exit: #ifdef CONFIG_GPROF _mcleanup(); #endif gdb_exit(arg1); - qemu_plugin_atexit_cb(); + qemu_plugin_user_exit(); /* XXX: should free thread stack and CPU env */ _exit(arg1); ret = 0; /* avoid warning */ diff --git a/bsd-user/uaccess.c b/bsd-user/uaccess.c index 91e2067933..89163257f4 100644 --- a/bsd-user/uaccess.c +++ b/bsd-user/uaccess.c @@ -46,7 +46,7 @@ abi_long target_strlen(abi_ulong guest_addr1) int max_len, len; guest_addr = guest_addr1; - for(;;) { + for (;;) { max_len = TARGET_PAGE_SIZE - (guest_addr & ~TARGET_PAGE_MASK); ptr = lock_user(VERIFY_READ, guest_addr, max_len, 1); if (!ptr) diff --git a/bsd-user/x86_64/target_signal.h b/bsd-user/x86_64/target_signal.h deleted file mode 100644 index 659cd401b8..0000000000 --- a/bsd-user/x86_64/target_signal.h +++ /dev/null @@ -1,19 +0,0 @@ -#ifndef TARGET_SIGNAL_H -#define TARGET_SIGNAL_H - -#include "cpu.h" - -/* this struct defines a stack used during syscall handling */ - -typedef struct target_sigaltstack { - abi_ulong ss_sp; - abi_long ss_flags; - abi_ulong ss_size; -} target_stack_t; - -static inline abi_ulong get_sp_from_cpustate(CPUX86State *state) -{ - return state->regs[R_ESP]; -} - -#endif /* TARGET_SIGNAL_H */ diff --git a/chardev/baum.c b/chardev/baum.c index 5deca778bc..79d618e350 100644 --- a/chardev/baum.c +++ b/chardev/baum.c @@ -680,6 +680,7 @@ static const TypeInfo char_braille_type_info = { .instance_finalize = char_braille_finalize, .class_init = char_braille_class_init, }; +module_obj(TYPE_CHARDEV_BRAILLE); static void register_types(void) { diff --git a/chardev/char-fd.c b/chardev/char-fd.c index 1cd62f2779..93c56913b4 100644 --- a/chardev/char-fd.c +++ b/chardev/char-fd.c @@ -28,6 +28,7 @@ #include "qemu/sockets.h" #include "qapi/error.h" #include "chardev/char.h" +#include "chardev/char-fe.h" #include "io/channel-file.h" #include "chardev/char-fd.h" @@ -38,6 +39,10 @@ static int fd_chr_write(Chardev *chr, const uint8_t *buf, int len) { FDChardev *s = FD_CHARDEV(chr); + if (!s->ioc_out) { + return -1; + } + return io_channel_send(s->ioc_out, buf, len); } @@ -80,10 +85,85 @@ static int fd_chr_read_poll(void *opaque) return s->max_size; } +typedef struct FDSource { + GSource parent; + + GIOCondition cond; +} FDSource; + +static gboolean +fd_source_prepare(GSource *source, + gint *timeout_) +{ + FDSource *src = (FDSource *)source; + + return src->cond != 0; +} + +static gboolean +fd_source_check(GSource *source) +{ + FDSource *src = (FDSource *)source; + + return src->cond != 0; +} + +static gboolean +fd_source_dispatch(GSource *source, GSourceFunc callback, + gpointer user_data) +{ + FDSource *src = (FDSource *)source; + FEWatchFunc func = (FEWatchFunc)callback; + gboolean ret = G_SOURCE_CONTINUE; + + if (src->cond) { + ret = func(NULL, src->cond, user_data); + src->cond = 0; + } + + return ret; +} + +static GSourceFuncs fd_source_funcs = { + fd_source_prepare, + fd_source_check, + fd_source_dispatch, + NULL, NULL, NULL +}; + +static GSource *fd_source_new(FDChardev *chr) +{ + return g_source_new(&fd_source_funcs, sizeof(FDSource)); +} + +static gboolean child_func(GIOChannel *source, + GIOCondition condition, + gpointer data) +{ + FDSource *parent = data; + + parent->cond |= condition; + + return G_SOURCE_CONTINUE; +} + static GSource *fd_chr_add_watch(Chardev *chr, GIOCondition cond) { FDChardev *s = FD_CHARDEV(chr); - return qio_channel_create_watch(s->ioc_out, cond); + g_autoptr(GSource) source = fd_source_new(s); + + if (s->ioc_out) { + g_autoptr(GSource) child = qio_channel_create_watch(s->ioc_out, cond & ~G_IO_IN); + g_source_set_callback(child, (GSourceFunc)child_func, source, NULL); + g_source_add_child_source(source, child); + } + if (s->ioc_in) { + g_autoptr(GSource) child = qio_channel_create_watch(s->ioc_in, cond & ~G_IO_OUT); + g_source_set_callback(child, (GSourceFunc)child_func, source, NULL); + g_source_add_child_source(source, child); + } + + return g_steal_pointer(&source); } static void fd_chr_update_read_handler(Chardev *chr) @@ -131,17 +211,32 @@ void qemu_chr_open_fd(Chardev *chr, int fd_in, int fd_out) { FDChardev *s = FD_CHARDEV(chr); - char *name; + g_autofree char *name = NULL; - s->ioc_in = QIO_CHANNEL(qio_channel_file_new_fd(fd_in)); - name = g_strdup_printf("chardev-file-in-%s", chr->label); - qio_channel_set_name(QIO_CHANNEL(s->ioc_in), name); - g_free(name); - s->ioc_out = QIO_CHANNEL(qio_channel_file_new_fd(fd_out)); - name = g_strdup_printf("chardev-file-out-%s", chr->label); - qio_channel_set_name(QIO_CHANNEL(s->ioc_out), name); - g_free(name); - qemu_set_nonblock(fd_out); + if (fd_out >= 0) { + qemu_set_nonblock(fd_out); + } + + if (fd_out == fd_in && fd_in >= 0) { + s->ioc_in = QIO_CHANNEL(qio_channel_file_new_fd(fd_in)); + name = g_strdup_printf("chardev-file-%s", chr->label); + qio_channel_set_name(QIO_CHANNEL(s->ioc_in), name); + s->ioc_out = QIO_CHANNEL(object_ref(s->ioc_in)); + return; + } + + if (fd_in >= 0) { + s->ioc_in = QIO_CHANNEL(qio_channel_file_new_fd(fd_in)); + name = g_strdup_printf("chardev-file-in-%s", chr->label); + qio_channel_set_name(QIO_CHANNEL(s->ioc_in), name); + } + + if (fd_out >= 0) { + s->ioc_out = QIO_CHANNEL(qio_channel_file_new_fd(fd_out)); + g_free(name); + name = g_strdup_printf("chardev-file-out-%s", chr->label); + qio_channel_set_name(QIO_CHANNEL(s->ioc_out), name); + } } static void char_fd_class_init(ObjectClass *oc, void *data) diff --git a/chardev/char-fe.c b/chardev/char-fe.c index 474715c5a9..7789f7be9c 100644 --- a/chardev/char-fe.c +++ b/chardev/char-fe.c @@ -354,7 +354,7 @@ void qemu_chr_fe_set_open(CharBackend *be, int fe_open) } guint qemu_chr_fe_add_watch(CharBackend *be, GIOCondition cond, - GIOFunc func, void *user_data) + FEWatchFunc func, void *user_data) { Chardev *s = be->chr; GSource *src; diff --git a/chardev/char-mux.c b/chardev/char-mux.c index 72beef29d2..5baf419010 100644 --- a/chardev/char-mux.c +++ b/chardev/char-mux.c @@ -28,7 +28,6 @@ #include "qemu/option.h" #include "chardev/char.h" #include "sysemu/block-backend.h" -#include "sysemu/sysemu.h" #include "chardev-internal.h" /* MUX driver for serial I/O splitting */ diff --git a/chardev/char-socket.c b/chardev/char-socket.c index daa89fe5d1..c43668cc15 100644 --- a/chardev/char-socket.c +++ b/chardev/char-socket.c @@ -468,9 +468,9 @@ static char *qemu_chr_socket_address(SocketChardev *s, const char *prefix) #ifdef CONFIG_LINUX if (sa->has_abstract && sa->abstract) { - abstract = ",abstract"; + abstract = ",abstract=on"; if (sa->has_tight && sa->tight) { - tight = ",tight"; + tight = ",tight=on"; } } #endif @@ -1402,18 +1402,12 @@ static void qmp_chardev_open_socket(Chardev *chr, return; } object_ref(OBJECT(s->tls_creds)); - if (is_listen) { - if (s->tls_creds->endpoint != QCRYPTO_TLS_CREDS_ENDPOINT_SERVER) { - error_setg(errp, "%s", - "Expected TLS credentials for server endpoint"); - return; - } - } else { - if (s->tls_creds->endpoint != QCRYPTO_TLS_CREDS_ENDPOINT_CLIENT) { - error_setg(errp, "%s", - "Expected TLS credentials for client endpoint"); - return; - } + if (!qcrypto_tls_creds_check_endpoint(s->tls_creds, + is_listen + ? QCRYPTO_TLS_CREDS_ENDPOINT_SERVER + : QCRYPTO_TLS_CREDS_ENDPOINT_CLIENT, + errp)) { + return; } } s->tls_authz = g_strdup(sock->tls_authz); diff --git a/chardev/char.c b/chardev/char.c index f6e571fd70..225b84e094 100644 --- a/chardev/char.c +++ b/chardev/char.c @@ -25,7 +25,6 @@ #include "qemu/osdep.h" #include "qemu/cutils.h" #include "monitor/monitor.h" -#include "sysemu/sysemu.h" #include "qemu/config-file.h" #include "qemu/error-report.h" #include "qemu/qemu-print.h" @@ -952,6 +951,12 @@ QemuOptsList qemu_chardev_opts = { },{ .name = "logappend", .type = QEMU_OPT_BOOL, + },{ + .name = "mouse", + .type = QEMU_OPT_BOOL, + },{ + .name = "clipboard", + .type = QEMU_OPT_BOOL, #ifdef CONFIG_LINUX },{ .name = "tight", @@ -1055,27 +1060,31 @@ Chardev *qemu_chardev_new(const char *id, const char *typename, ChardevReturn *qmp_chardev_add(const char *id, ChardevBackend *backend, Error **errp) { + ERRP_GUARD(); const ChardevClass *cc; ChardevReturn *ret; - Chardev *chr; + g_autoptr(Chardev) chr = NULL; + + if (qemu_chr_find(id)) { + error_setg(errp, "Chardev with id '%s' already exists", id); + return NULL; + } cc = char_get_class(ChardevBackendKind_str(backend->type), errp); if (!cc) { - return NULL; + goto err; } chr = chardev_new(id, object_class_get_name(OBJECT_CLASS(cc)), backend, NULL, false, errp); if (!chr) { - return NULL; + goto err; } if (!object_property_try_add_child(get_chardevs_root(), id, OBJECT(chr), errp)) { - object_unref(OBJECT(chr)); - return NULL; + goto err; } - object_unref(OBJECT(chr)); ret = g_new0(ChardevReturn, 1); if (CHARDEV_IS_PTY(chr)) { @@ -1084,6 +1093,10 @@ ChardevReturn *qmp_chardev_add(const char *id, ChardevBackend *backend, } return ret; + +err: + error_prepend(errp, "Failed to add chardev '%s': ", id); + return NULL; } ChardevReturn *qmp_chardev_change(const char *id, ChardevBackend *backend, diff --git a/chardev/spice.c b/chardev/spice.c index 1104426e3a..bbffef4913 100644 --- a/chardev/spice.c +++ b/chardev/spice.c @@ -366,6 +366,7 @@ static const TypeInfo char_spice_type_info = { .class_init = char_spice_class_init, .abstract = true, }; +module_obj(TYPE_CHARDEV_SPICE); static void char_spicevmc_class_init(ObjectClass *oc, void *data) { @@ -381,6 +382,7 @@ static const TypeInfo char_spicevmc_type_info = { .parent = TYPE_CHARDEV_SPICE, .class_init = char_spicevmc_class_init, }; +module_obj(TYPE_CHARDEV_SPICEVMC); static void char_spiceport_class_init(ObjectClass *oc, void *data) { @@ -396,6 +398,7 @@ static const TypeInfo char_spiceport_type_info = { .parent = TYPE_CHARDEV_SPICE, .class_init = char_spiceport_class_init, }; +module_obj(TYPE_CHARDEV_SPICEPORT); static void register_types(void) { @@ -405,3 +408,5 @@ static void register_types(void) } type_init(register_types); + +module_dep("ui-spice-core"); diff --git a/chardev/trace-events b/chardev/trace-events index 5ea4408207..027107b0c1 100644 --- a/chardev/trace-events +++ b/chardev/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # wctablet.c wct_init(void) "" diff --git a/default-configs/devices/aarch64-softmmu.mak b/configs/devices/aarch64-softmmu/default.mak similarity index 82% rename from default-configs/devices/aarch64-softmmu.mak rename to configs/devices/aarch64-softmmu/default.mak index 958b1e08e4..cf43ac8da1 100644 --- a/default-configs/devices/aarch64-softmmu.mak +++ b/configs/devices/aarch64-softmmu/default.mak @@ -1,7 +1,7 @@ # Default configuration for aarch64-softmmu # We support all the 32 bit boards so need all their config -include arm-softmmu.mak +include ../arm-softmmu/default.mak CONFIG_XLNX_ZYNQMP_ARM=y CONFIG_XLNX_VERSAL=y diff --git a/configs/devices/aarch64-softmmu/minimal.mak b/configs/devices/aarch64-softmmu/minimal.mak new file mode 100644 index 0000000000..0ebc1dca56 --- /dev/null +++ b/configs/devices/aarch64-softmmu/minimal.mak @@ -0,0 +1,9 @@ +# +# A minimal version of the config that only supports only a few +# virtual machines. This avoids bringing in any of numerous legacy +# features from the 32bit platform (although virt still supports 32bit +# itself) +# + +CONFIG_ARM_VIRT=y +CONFIG_SBSA_REF=y diff --git a/default-configs/devices/alpha-softmmu.mak b/configs/devices/alpha-softmmu/default.mak similarity index 100% rename from default-configs/devices/alpha-softmmu.mak rename to configs/devices/alpha-softmmu/default.mak diff --git a/default-configs/devices/arm-softmmu.mak b/configs/devices/arm-softmmu/default.mak similarity index 89% rename from default-configs/devices/arm-softmmu.mak rename to configs/devices/arm-softmmu/default.mak index 0500156a0c..6985a25377 100644 --- a/default-configs/devices/arm-softmmu.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -1,8 +1,5 @@ # Default configuration for arm-softmmu -# TODO: ARM_V7M is currently always required - make this more flexible! -CONFIG_ARM_V7M=y - # CONFIG_PCI_DEVICES=n # CONFIG_TEST_DEVICES=n @@ -18,6 +15,7 @@ CONFIG_CHEETAH=y CONFIG_SX1=y CONFIG_NSERIES=y CONFIG_STELLARIS=y +CONFIG_STM32VLDISCOVERY=y CONFIG_REALVIEW=y CONFIG_VERSATILE=y CONFIG_VEXPRESS=y diff --git a/default-configs/devices/avr-softmmu.mak b/configs/devices/avr-softmmu/default.mak similarity index 100% rename from default-configs/devices/avr-softmmu.mak rename to configs/devices/avr-softmmu/default.mak diff --git a/default-configs/devices/cris-softmmu.mak b/configs/devices/cris-softmmu/default.mak similarity index 100% rename from default-configs/devices/cris-softmmu.mak rename to configs/devices/cris-softmmu/default.mak diff --git a/default-configs/devices/hppa-softmmu.mak b/configs/devices/hppa-softmmu/default.mak similarity index 100% rename from default-configs/devices/hppa-softmmu.mak rename to configs/devices/hppa-softmmu/default.mak diff --git a/default-configs/devices/i386-softmmu.mak b/configs/devices/i386-softmmu/default.mak similarity index 100% rename from default-configs/devices/i386-softmmu.mak rename to configs/devices/i386-softmmu/default.mak diff --git a/default-configs/devices/m68k-softmmu.mak b/configs/devices/m68k-softmmu/default.mak similarity index 100% rename from default-configs/devices/m68k-softmmu.mak rename to configs/devices/m68k-softmmu/default.mak diff --git a/default-configs/devices/microblaze-softmmu.mak b/configs/devices/microblaze-softmmu/default.mak similarity index 100% rename from default-configs/devices/microblaze-softmmu.mak rename to configs/devices/microblaze-softmmu/default.mak diff --git a/default-configs/devices/microblazeel-softmmu.mak b/configs/devices/microblazeel-softmmu/default.mak similarity index 54% rename from default-configs/devices/microblazeel-softmmu.mak rename to configs/devices/microblazeel-softmmu/default.mak index 2fcf442fc7..29f7f13816 100644 --- a/default-configs/devices/microblazeel-softmmu.mak +++ b/configs/devices/microblazeel-softmmu/default.mak @@ -1,3 +1,3 @@ # Default configuration for microblazeel-softmmu -include microblaze-softmmu.mak +include ../microblaze-softmmu/default.mak diff --git a/default-configs/devices/mips-softmmu-common.mak b/configs/devices/mips-softmmu/common.mak similarity index 100% rename from default-configs/devices/mips-softmmu-common.mak rename to configs/devices/mips-softmmu/common.mak diff --git a/default-configs/devices/mips-softmmu.mak b/configs/devices/mips-softmmu/default.mak similarity index 56% rename from default-configs/devices/mips-softmmu.mak rename to configs/devices/mips-softmmu/default.mak index 9fede6e00f..c23d95a83a 100644 --- a/default-configs/devices/mips-softmmu.mak +++ b/configs/devices/mips-softmmu/default.mak @@ -1,3 +1,3 @@ # Default configuration for mips-softmmu -include mips-softmmu-common.mak +include common.mak diff --git a/default-configs/devices/mips64-softmmu.mak b/configs/devices/mips64-softmmu/default.mak similarity index 62% rename from default-configs/devices/mips64-softmmu.mak rename to configs/devices/mips64-softmmu/default.mak index a169738635..566672f3c2 100644 --- a/default-configs/devices/mips64-softmmu.mak +++ b/configs/devices/mips64-softmmu/default.mak @@ -1,4 +1,4 @@ # Default configuration for mips64-softmmu -include mips-softmmu-common.mak +include ../mips-softmmu/common.mak CONFIG_JAZZ=y diff --git a/default-configs/devices/mips64el-softmmu.mak b/configs/devices/mips64el-softmmu/default.mak similarity index 62% rename from default-configs/devices/mips64el-softmmu.mak rename to configs/devices/mips64el-softmmu/default.mak index 26c660a05c..c610749ac1 100644 --- a/default-configs/devices/mips64el-softmmu.mak +++ b/configs/devices/mips64el-softmmu/default.mak @@ -1,6 +1,6 @@ # Default configuration for mips64el-softmmu -include mips-softmmu-common.mak +include ../mips-softmmu/common.mak CONFIG_IDE_VIA=y CONFIG_FULOONG=y CONFIG_LOONGSON3V=y @@ -8,8 +8,4 @@ CONFIG_ATI_VGA=y CONFIG_RTL8139_PCI=y CONFIG_JAZZ=y CONFIG_VT82C686=y -CONFIG_AHCI=y CONFIG_MIPS_BOSTON=y -CONFIG_FITLOADER=y -CONFIG_PCI_EXPRESS=y -CONFIG_PCI_EXPRESS_XILINX=y diff --git a/default-configs/devices/mipsel-softmmu.mak b/configs/devices/mipsel-softmmu/default.mak similarity index 55% rename from default-configs/devices/mipsel-softmmu.mak rename to configs/devices/mipsel-softmmu/default.mak index a7f6059484..009ccb0e2d 100644 --- a/default-configs/devices/mipsel-softmmu.mak +++ b/configs/devices/mipsel-softmmu/default.mak @@ -1,3 +1,3 @@ # Default configuration for mipsel-softmmu -include mips-softmmu-common.mak +include ../mips-softmmu/common.mak diff --git a/default-configs/devices/nios2-softmmu.mak b/configs/devices/nios2-softmmu/default.mak similarity index 100% rename from default-configs/devices/nios2-softmmu.mak rename to configs/devices/nios2-softmmu/default.mak diff --git a/default-configs/devices/or1k-softmmu.mak b/configs/devices/or1k-softmmu/default.mak similarity index 100% rename from default-configs/devices/or1k-softmmu.mak rename to configs/devices/or1k-softmmu/default.mak diff --git a/default-configs/devices/ppc-softmmu.mak b/configs/devices/ppc-softmmu/default.mak similarity index 92% rename from default-configs/devices/ppc-softmmu.mak rename to configs/devices/ppc-softmmu/default.mak index 61b78b844d..658a454426 100644 --- a/default-configs/devices/ppc-softmmu.mak +++ b/configs/devices/ppc-softmmu/default.mak @@ -1,7 +1,6 @@ # Default configuration for ppc-softmmu # For embedded PPCs: -CONFIG_DS1338=y CONFIG_E500=y CONFIG_PPC405=y CONFIG_PPC440=y @@ -14,5 +13,7 @@ CONFIG_SAM460EX=y CONFIG_MAC_OLDWORLD=y CONFIG_MAC_NEWWORLD=y +CONFIG_PEGASOS2=y + # For PReP CONFIG_PREP=y diff --git a/default-configs/devices/ppc64-softmmu.mak b/configs/devices/ppc64-softmmu/default.mak similarity index 77% rename from default-configs/devices/ppc64-softmmu.mak rename to configs/devices/ppc64-softmmu/default.mak index ae0841fa3a..b90e5bf455 100644 --- a/default-configs/devices/ppc64-softmmu.mak +++ b/configs/devices/ppc64-softmmu/default.mak @@ -1,11 +1,10 @@ # Default configuration for ppc64-softmmu # Include all 32-bit boards -include ppc-softmmu.mak +include ../ppc-softmmu/default.mak # For PowerNV CONFIG_POWERNV=y # For pSeries CONFIG_PSERIES=y -CONFIG_NVDIMM=y diff --git a/default-configs/devices/riscv32-softmmu.mak b/configs/devices/riscv32-softmmu/default.mak similarity index 100% rename from default-configs/devices/riscv32-softmmu.mak rename to configs/devices/riscv32-softmmu/default.mak diff --git a/default-configs/devices/riscv64-softmmu.mak b/configs/devices/riscv64-softmmu/default.mak similarity index 94% rename from default-configs/devices/riscv64-softmmu.mak rename to configs/devices/riscv64-softmmu/default.mak index d5eec75f05..bc69301fa4 100644 --- a/default-configs/devices/riscv64-softmmu.mak +++ b/configs/devices/riscv64-softmmu/default.mak @@ -13,3 +13,4 @@ CONFIG_SIFIVE_E=y CONFIG_SIFIVE_U=y CONFIG_RISCV_VIRT=y CONFIG_MICROCHIP_PFSOC=y +CONFIG_SHAKTI_C=y diff --git a/default-configs/devices/rx-softmmu.mak b/configs/devices/rx-softmmu/default.mak similarity index 100% rename from default-configs/devices/rx-softmmu.mak rename to configs/devices/rx-softmmu/default.mak diff --git a/default-configs/devices/s390x-softmmu.mak b/configs/devices/s390x-softmmu/default.mak similarity index 100% rename from default-configs/devices/s390x-softmmu.mak rename to configs/devices/s390x-softmmu/default.mak diff --git a/default-configs/devices/sh4-softmmu.mak b/configs/devices/sh4-softmmu/default.mak similarity index 100% rename from default-configs/devices/sh4-softmmu.mak rename to configs/devices/sh4-softmmu/default.mak diff --git a/default-configs/devices/sh4eb-softmmu.mak b/configs/devices/sh4eb-softmmu/default.mak similarity index 55% rename from default-configs/devices/sh4eb-softmmu.mak rename to configs/devices/sh4eb-softmmu/default.mak index 522a7a50fa..f18d1f6519 100644 --- a/default-configs/devices/sh4eb-softmmu.mak +++ b/configs/devices/sh4eb-softmmu/default.mak @@ -1,3 +1,3 @@ # Default configuration for sh4eb-softmmu -include sh4-softmmu.mak +include ../sh4-softmmu/default.mak diff --git a/default-configs/devices/sparc-softmmu.mak b/configs/devices/sparc-softmmu/default.mak similarity index 100% rename from default-configs/devices/sparc-softmmu.mak rename to configs/devices/sparc-softmmu/default.mak diff --git a/default-configs/devices/sparc64-softmmu.mak b/configs/devices/sparc64-softmmu/default.mak similarity index 100% rename from default-configs/devices/sparc64-softmmu.mak rename to configs/devices/sparc64-softmmu/default.mak diff --git a/configs/devices/tricore-softmmu/default.mak b/configs/devices/tricore-softmmu/default.mak new file mode 100644 index 0000000000..cb8fc286eb --- /dev/null +++ b/configs/devices/tricore-softmmu/default.mak @@ -0,0 +1,2 @@ +CONFIG_TRICORE_TESTBOARD=y +CONFIG_TRIBOARD=y diff --git a/default-configs/devices/x86_64-softmmu.mak b/configs/devices/x86_64-softmmu/default.mak similarity index 55% rename from default-configs/devices/x86_64-softmmu.mak rename to configs/devices/x86_64-softmmu/default.mak index 64b2ee2960..ddfc2ea626 100644 --- a/default-configs/devices/x86_64-softmmu.mak +++ b/configs/devices/x86_64-softmmu/default.mak @@ -1,3 +1,3 @@ # Default configuration for x86_64-softmmu -include i386-softmmu.mak +include ../i386-softmmu/default.mak diff --git a/default-configs/devices/xtensa-softmmu.mak b/configs/devices/xtensa-softmmu/default.mak similarity index 100% rename from default-configs/devices/xtensa-softmmu.mak rename to configs/devices/xtensa-softmmu/default.mak diff --git a/configs/devices/xtensaeb-softmmu/default.mak b/configs/devices/xtensaeb-softmmu/default.mak new file mode 100644 index 0000000000..00eafcc292 --- /dev/null +++ b/configs/devices/xtensaeb-softmmu/default.mak @@ -0,0 +1,3 @@ +# Default configuration for Xtensa + +include ../xtensa-softmmu/default.mak diff --git a/default-configs/targets/aarch64-linux-user.mak b/configs/targets/aarch64-linux-user.mak similarity index 100% rename from default-configs/targets/aarch64-linux-user.mak rename to configs/targets/aarch64-linux-user.mak diff --git a/default-configs/targets/aarch64-softmmu.mak b/configs/targets/aarch64-softmmu.mak similarity index 100% rename from default-configs/targets/aarch64-softmmu.mak rename to configs/targets/aarch64-softmmu.mak diff --git a/default-configs/targets/aarch64_be-linux-user.mak b/configs/targets/aarch64_be-linux-user.mak similarity index 100% rename from default-configs/targets/aarch64_be-linux-user.mak rename to configs/targets/aarch64_be-linux-user.mak diff --git a/default-configs/targets/alpha-linux-user.mak b/configs/targets/alpha-linux-user.mak similarity index 100% rename from default-configs/targets/alpha-linux-user.mak rename to configs/targets/alpha-linux-user.mak diff --git a/default-configs/targets/alpha-softmmu.mak b/configs/targets/alpha-softmmu.mak similarity index 100% rename from default-configs/targets/alpha-softmmu.mak rename to configs/targets/alpha-softmmu.mak diff --git a/default-configs/targets/arm-linux-user.mak b/configs/targets/arm-linux-user.mak similarity index 100% rename from default-configs/targets/arm-linux-user.mak rename to configs/targets/arm-linux-user.mak diff --git a/default-configs/targets/arm-softmmu.mak b/configs/targets/arm-softmmu.mak similarity index 100% rename from default-configs/targets/arm-softmmu.mak rename to configs/targets/arm-softmmu.mak diff --git a/default-configs/targets/armeb-linux-user.mak b/configs/targets/armeb-linux-user.mak similarity index 100% rename from default-configs/targets/armeb-linux-user.mak rename to configs/targets/armeb-linux-user.mak diff --git a/default-configs/targets/avr-softmmu.mak b/configs/targets/avr-softmmu.mak similarity index 100% rename from default-configs/targets/avr-softmmu.mak rename to configs/targets/avr-softmmu.mak diff --git a/default-configs/targets/cris-linux-user.mak b/configs/targets/cris-linux-user.mak similarity index 100% rename from default-configs/targets/cris-linux-user.mak rename to configs/targets/cris-linux-user.mak diff --git a/default-configs/targets/cris-softmmu.mak b/configs/targets/cris-softmmu.mak similarity index 100% rename from default-configs/targets/cris-softmmu.mak rename to configs/targets/cris-softmmu.mak diff --git a/default-configs/targets/hexagon-linux-user.mak b/configs/targets/hexagon-linux-user.mak similarity index 100% rename from default-configs/targets/hexagon-linux-user.mak rename to configs/targets/hexagon-linux-user.mak diff --git a/default-configs/targets/hppa-linux-user.mak b/configs/targets/hppa-linux-user.mak similarity index 100% rename from default-configs/targets/hppa-linux-user.mak rename to configs/targets/hppa-linux-user.mak diff --git a/default-configs/targets/hppa-softmmu.mak b/configs/targets/hppa-softmmu.mak similarity index 100% rename from default-configs/targets/hppa-softmmu.mak rename to configs/targets/hppa-softmmu.mak diff --git a/default-configs/targets/i386-bsd-user.mak b/configs/targets/i386-bsd-user.mak similarity index 100% rename from default-configs/targets/i386-bsd-user.mak rename to configs/targets/i386-bsd-user.mak diff --git a/default-configs/targets/i386-linux-user.mak b/configs/targets/i386-linux-user.mak similarity index 100% rename from default-configs/targets/i386-linux-user.mak rename to configs/targets/i386-linux-user.mak diff --git a/default-configs/targets/i386-softmmu.mak b/configs/targets/i386-softmmu.mak similarity index 100% rename from default-configs/targets/i386-softmmu.mak rename to configs/targets/i386-softmmu.mak diff --git a/default-configs/targets/m68k-linux-user.mak b/configs/targets/m68k-linux-user.mak similarity index 100% rename from default-configs/targets/m68k-linux-user.mak rename to configs/targets/m68k-linux-user.mak diff --git a/default-configs/targets/m68k-softmmu.mak b/configs/targets/m68k-softmmu.mak similarity index 100% rename from default-configs/targets/m68k-softmmu.mak rename to configs/targets/m68k-softmmu.mak diff --git a/default-configs/targets/microblaze-linux-user.mak b/configs/targets/microblaze-linux-user.mak similarity index 100% rename from default-configs/targets/microblaze-linux-user.mak rename to configs/targets/microblaze-linux-user.mak diff --git a/default-configs/targets/microblaze-softmmu.mak b/configs/targets/microblaze-softmmu.mak similarity index 100% rename from default-configs/targets/microblaze-softmmu.mak rename to configs/targets/microblaze-softmmu.mak diff --git a/default-configs/targets/microblazeel-linux-user.mak b/configs/targets/microblazeel-linux-user.mak similarity index 100% rename from default-configs/targets/microblazeel-linux-user.mak rename to configs/targets/microblazeel-linux-user.mak diff --git a/default-configs/targets/microblazeel-softmmu.mak b/configs/targets/microblazeel-softmmu.mak similarity index 100% rename from default-configs/targets/microblazeel-softmmu.mak rename to configs/targets/microblazeel-softmmu.mak diff --git a/default-configs/targets/mips-linux-user.mak b/configs/targets/mips-linux-user.mak similarity index 100% rename from default-configs/targets/mips-linux-user.mak rename to configs/targets/mips-linux-user.mak diff --git a/default-configs/targets/mips-softmmu.mak b/configs/targets/mips-softmmu.mak similarity index 100% rename from default-configs/targets/mips-softmmu.mak rename to configs/targets/mips-softmmu.mak diff --git a/default-configs/targets/mips64-linux-user.mak b/configs/targets/mips64-linux-user.mak similarity index 100% rename from default-configs/targets/mips64-linux-user.mak rename to configs/targets/mips64-linux-user.mak diff --git a/default-configs/targets/mips64-softmmu.mak b/configs/targets/mips64-softmmu.mak similarity index 100% rename from default-configs/targets/mips64-softmmu.mak rename to configs/targets/mips64-softmmu.mak diff --git a/default-configs/targets/mips64el-linux-user.mak b/configs/targets/mips64el-linux-user.mak similarity index 100% rename from default-configs/targets/mips64el-linux-user.mak rename to configs/targets/mips64el-linux-user.mak diff --git a/default-configs/targets/mips64el-softmmu.mak b/configs/targets/mips64el-softmmu.mak similarity index 100% rename from default-configs/targets/mips64el-softmmu.mak rename to configs/targets/mips64el-softmmu.mak diff --git a/default-configs/targets/mipsel-linux-user.mak b/configs/targets/mipsel-linux-user.mak similarity index 100% rename from default-configs/targets/mipsel-linux-user.mak rename to configs/targets/mipsel-linux-user.mak diff --git a/default-configs/targets/mipsel-softmmu.mak b/configs/targets/mipsel-softmmu.mak similarity index 100% rename from default-configs/targets/mipsel-softmmu.mak rename to configs/targets/mipsel-softmmu.mak diff --git a/default-configs/targets/mipsn32-linux-user.mak b/configs/targets/mipsn32-linux-user.mak similarity index 100% rename from default-configs/targets/mipsn32-linux-user.mak rename to configs/targets/mipsn32-linux-user.mak diff --git a/default-configs/targets/mipsn32el-linux-user.mak b/configs/targets/mipsn32el-linux-user.mak similarity index 100% rename from default-configs/targets/mipsn32el-linux-user.mak rename to configs/targets/mipsn32el-linux-user.mak diff --git a/default-configs/targets/nios2-linux-user.mak b/configs/targets/nios2-linux-user.mak similarity index 100% rename from default-configs/targets/nios2-linux-user.mak rename to configs/targets/nios2-linux-user.mak diff --git a/default-configs/targets/nios2-softmmu.mak b/configs/targets/nios2-softmmu.mak similarity index 100% rename from default-configs/targets/nios2-softmmu.mak rename to configs/targets/nios2-softmmu.mak diff --git a/default-configs/targets/or1k-linux-user.mak b/configs/targets/or1k-linux-user.mak similarity index 100% rename from default-configs/targets/or1k-linux-user.mak rename to configs/targets/or1k-linux-user.mak diff --git a/default-configs/targets/or1k-softmmu.mak b/configs/targets/or1k-softmmu.mak similarity index 100% rename from default-configs/targets/or1k-softmmu.mak rename to configs/targets/or1k-softmmu.mak diff --git a/default-configs/targets/ppc-linux-user.mak b/configs/targets/ppc-linux-user.mak similarity index 100% rename from default-configs/targets/ppc-linux-user.mak rename to configs/targets/ppc-linux-user.mak diff --git a/default-configs/targets/ppc-softmmu.mak b/configs/targets/ppc-softmmu.mak similarity index 100% rename from default-configs/targets/ppc-softmmu.mak rename to configs/targets/ppc-softmmu.mak diff --git a/default-configs/targets/ppc64-linux-user.mak b/configs/targets/ppc64-linux-user.mak similarity index 100% rename from default-configs/targets/ppc64-linux-user.mak rename to configs/targets/ppc64-linux-user.mak diff --git a/default-configs/targets/ppc64-softmmu.mak b/configs/targets/ppc64-softmmu.mak similarity index 100% rename from default-configs/targets/ppc64-softmmu.mak rename to configs/targets/ppc64-softmmu.mak diff --git a/default-configs/targets/ppc64abi32-linux-user.mak b/configs/targets/ppc64abi32-linux-user.mak similarity index 100% rename from default-configs/targets/ppc64abi32-linux-user.mak rename to configs/targets/ppc64abi32-linux-user.mak diff --git a/default-configs/targets/ppc64le-linux-user.mak b/configs/targets/ppc64le-linux-user.mak similarity index 100% rename from default-configs/targets/ppc64le-linux-user.mak rename to configs/targets/ppc64le-linux-user.mak diff --git a/default-configs/targets/riscv32-linux-user.mak b/configs/targets/riscv32-linux-user.mak similarity index 100% rename from default-configs/targets/riscv32-linux-user.mak rename to configs/targets/riscv32-linux-user.mak diff --git a/default-configs/targets/riscv32-softmmu.mak b/configs/targets/riscv32-softmmu.mak similarity index 100% rename from default-configs/targets/riscv32-softmmu.mak rename to configs/targets/riscv32-softmmu.mak diff --git a/default-configs/targets/riscv64-linux-user.mak b/configs/targets/riscv64-linux-user.mak similarity index 100% rename from default-configs/targets/riscv64-linux-user.mak rename to configs/targets/riscv64-linux-user.mak diff --git a/default-configs/targets/riscv64-softmmu.mak b/configs/targets/riscv64-softmmu.mak similarity index 100% rename from default-configs/targets/riscv64-softmmu.mak rename to configs/targets/riscv64-softmmu.mak diff --git a/default-configs/targets/rx-softmmu.mak b/configs/targets/rx-softmmu.mak similarity index 100% rename from default-configs/targets/rx-softmmu.mak rename to configs/targets/rx-softmmu.mak diff --git a/default-configs/targets/s390x-linux-user.mak b/configs/targets/s390x-linux-user.mak similarity index 100% rename from default-configs/targets/s390x-linux-user.mak rename to configs/targets/s390x-linux-user.mak diff --git a/default-configs/targets/s390x-softmmu.mak b/configs/targets/s390x-softmmu.mak similarity index 100% rename from default-configs/targets/s390x-softmmu.mak rename to configs/targets/s390x-softmmu.mak diff --git a/default-configs/targets/sh4-linux-user.mak b/configs/targets/sh4-linux-user.mak similarity index 100% rename from default-configs/targets/sh4-linux-user.mak rename to configs/targets/sh4-linux-user.mak diff --git a/default-configs/targets/sh4-softmmu.mak b/configs/targets/sh4-softmmu.mak similarity index 100% rename from default-configs/targets/sh4-softmmu.mak rename to configs/targets/sh4-softmmu.mak diff --git a/default-configs/targets/sh4eb-linux-user.mak b/configs/targets/sh4eb-linux-user.mak similarity index 100% rename from default-configs/targets/sh4eb-linux-user.mak rename to configs/targets/sh4eb-linux-user.mak diff --git a/default-configs/targets/sh4eb-softmmu.mak b/configs/targets/sh4eb-softmmu.mak similarity index 100% rename from default-configs/targets/sh4eb-softmmu.mak rename to configs/targets/sh4eb-softmmu.mak diff --git a/default-configs/targets/sparc-linux-user.mak b/configs/targets/sparc-linux-user.mak similarity index 100% rename from default-configs/targets/sparc-linux-user.mak rename to configs/targets/sparc-linux-user.mak diff --git a/default-configs/targets/sparc-softmmu.mak b/configs/targets/sparc-softmmu.mak similarity index 100% rename from default-configs/targets/sparc-softmmu.mak rename to configs/targets/sparc-softmmu.mak diff --git a/default-configs/targets/sparc32plus-linux-user.mak b/configs/targets/sparc32plus-linux-user.mak similarity index 100% rename from default-configs/targets/sparc32plus-linux-user.mak rename to configs/targets/sparc32plus-linux-user.mak diff --git a/default-configs/targets/sparc64-linux-user.mak b/configs/targets/sparc64-linux-user.mak similarity index 87% rename from default-configs/targets/sparc64-linux-user.mak rename to configs/targets/sparc64-linux-user.mak index 846924201a..9d23ab4a26 100644 --- a/default-configs/targets/sparc64-linux-user.mak +++ b/configs/targets/sparc64-linux-user.mak @@ -1,5 +1,6 @@ TARGET_ARCH=sparc64 TARGET_BASE_ARCH=sparc +TARGET_ABI_DIR=sparc TARGET_SYSTBL_ABI=common,64 TARGET_SYSTBL=syscall.tbl TARGET_ALIGNED_ONLY=y diff --git a/default-configs/targets/sparc64-softmmu.mak b/configs/targets/sparc64-softmmu.mak similarity index 100% rename from default-configs/targets/sparc64-softmmu.mak rename to configs/targets/sparc64-softmmu.mak diff --git a/default-configs/targets/tricore-softmmu.mak b/configs/targets/tricore-softmmu.mak similarity index 100% rename from default-configs/targets/tricore-softmmu.mak rename to configs/targets/tricore-softmmu.mak diff --git a/default-configs/targets/x86_64-bsd-user.mak b/configs/targets/x86_64-bsd-user.mak similarity index 100% rename from default-configs/targets/x86_64-bsd-user.mak rename to configs/targets/x86_64-bsd-user.mak diff --git a/default-configs/targets/x86_64-linux-user.mak b/configs/targets/x86_64-linux-user.mak similarity index 100% rename from default-configs/targets/x86_64-linux-user.mak rename to configs/targets/x86_64-linux-user.mak diff --git a/default-configs/targets/x86_64-softmmu.mak b/configs/targets/x86_64-softmmu.mak similarity index 100% rename from default-configs/targets/x86_64-softmmu.mak rename to configs/targets/x86_64-softmmu.mak diff --git a/default-configs/targets/xtensa-linux-user.mak b/configs/targets/xtensa-linux-user.mak similarity index 80% rename from default-configs/targets/xtensa-linux-user.mak rename to configs/targets/xtensa-linux-user.mak index fc95cc60f5..420b30a68d 100644 --- a/default-configs/targets/xtensa-linux-user.mak +++ b/configs/targets/xtensa-linux-user.mak @@ -1,5 +1,4 @@ TARGET_ARCH=xtensa TARGET_SYSTBL_ABI=common TARGET_SYSTBL=syscall.tbl -TARGET_ALIGNED_ONLY=y TARGET_HAS_BFLT=y diff --git a/default-configs/targets/xtensa-softmmu.mak b/configs/targets/xtensa-softmmu.mak similarity index 66% rename from default-configs/targets/xtensa-softmmu.mak rename to configs/targets/xtensa-softmmu.mak index 26c0285655..f075557bfa 100644 --- a/default-configs/targets/xtensa-softmmu.mak +++ b/configs/targets/xtensa-softmmu.mak @@ -1,3 +1,2 @@ TARGET_ARCH=xtensa -TARGET_ALIGNED_ONLY=y TARGET_SUPPORTS_MTTCG=y diff --git a/default-configs/targets/xtensaeb-linux-user.mak b/configs/targets/xtensaeb-linux-user.mak similarity index 83% rename from default-configs/targets/xtensaeb-linux-user.mak rename to configs/targets/xtensaeb-linux-user.mak index cfc3518118..1ea0f1ba91 100644 --- a/default-configs/targets/xtensaeb-linux-user.mak +++ b/configs/targets/xtensaeb-linux-user.mak @@ -1,6 +1,5 @@ TARGET_ARCH=xtensa TARGET_SYSTBL_ABI=common TARGET_SYSTBL=syscall.tbl -TARGET_ALIGNED_ONLY=y TARGET_WORDS_BIGENDIAN=y TARGET_HAS_BFLT=y diff --git a/default-configs/targets/xtensaeb-softmmu.mak b/configs/targets/xtensaeb-softmmu.mak similarity index 75% rename from default-configs/targets/xtensaeb-softmmu.mak rename to configs/targets/xtensaeb-softmmu.mak index 14cb9289a6..405cf5acbb 100644 --- a/default-configs/targets/xtensaeb-softmmu.mak +++ b/configs/targets/xtensaeb-softmmu.mak @@ -1,4 +1,3 @@ TARGET_ARCH=xtensa -TARGET_ALIGNED_ONLY=y TARGET_WORDS_BIGENDIAN=y TARGET_SUPPORTS_MTTCG=y diff --git a/configure b/configure index f319560edb..89dc0ab8c8 100755 --- a/configure +++ b/configure @@ -159,7 +159,7 @@ update_cxxflags() { # options which some versions of GCC's C++ compiler complain about # because they only make sense for C programs. QEMU_CXXFLAGS="$QEMU_CXXFLAGS -D__STDC_LIMIT_MACROS -D__STDC_CONSTANT_MACROS -D__STDC_FORMAT_MACROS" - CONFIGURE_CXXFLAGS=$(echo "$CONFIGURE_CFLAGS" | sed s/-std=gnu99/-std=gnu++11/) + CONFIGURE_CXXFLAGS=$(echo "$CONFIGURE_CFLAGS" | sed s/-std=gnu11/-std=gnu++11/) for arg in $QEMU_CFLAGS; do case $arg in -Wstrict-prototypes|-Wmissing-prototypes|-Wnested-externs|\ @@ -243,6 +243,7 @@ cross_prefix="" audio_drv_list="" block_drv_rw_whitelist="" block_drv_ro_whitelist="" +block_drv_whitelist_tools="no" host_cc="cc" audio_win_int="" libs_qga="" @@ -256,34 +257,11 @@ gdb_bin=$(command -v "gdb-multiarch" || command -v "gdb") if test -e "$source_path/.git" then git_submodules_action="update" - git_submodules="ui/keycodemapdb" - git_submodules="$git_submodules tests/fp/berkeley-testfloat-3" - git_submodules="$git_submodules tests/fp/berkeley-softfloat-3" - - # xemu extras - git_submodules="$git_submodules ui/imgui ui/implot hw/xbox/nv2a/xxHash" else git_submodules_action="ignore" - git_submodules="" - - if ! test -f "$source_path/ui/keycodemapdb/README" - then - echo - echo "ERROR: missing file $source_path/ui/keycodemapdb/README" - echo - echo "This is not a GIT checkout but module content appears to" - echo "be missing. Do not use 'git archive' or GitHub download links" - echo "to acquire QEMU source archives. Non-GIT builds are only" - echo "supported with source archives linked from:" - echo - echo " https://www.qemu.org/download/#source" - echo - echo "Developers working with GIT can use scripts/archive-source.sh" - echo "if they need to create valid source archives." - echo - exit 1 - fi fi + +git_submodules="ui/keycodemapdb ui/imgui ui/implot hw/xbox/nv2a/xxHash" git="git" # Don't accept a target_list environment variable. @@ -340,12 +318,13 @@ xen="$default_feature" xen_ctrl_version="$default_feature" xen_pci_passthrough="$auto" linux_aio="$default_feature" -linux_io_uring="$default_feature" +linux_io_uring="$auto" cap_ng="$auto" attr="$auto" xfs="$default_feature" tcg="enabled" membarrier="$default_feature" +vhost_kernel="$default_feature" vhost_net="$default_feature" vhost_crypto="$default_feature" vhost_scsi="$default_feature" @@ -353,10 +332,13 @@ vhost_vsock="$default_feature" vhost_user="no" vhost_user_blk_server="$auto" vhost_user_fs="$default_feature" +vhost_vdpa="$default_feature" +bpf="$auto" kvm="$auto" hax="$auto" hvf="$auto" whpx="$auto" +nvmm="$auto" rdma="$default_feature" pvrdma="$default_feature" gprof="no" @@ -393,11 +375,12 @@ qom_cast_debug="yes" trace_backends="nop" trace_file="trace" spice="$default_feature" +spice_protocol="$auto" rbd="$auto" -smartcard="$default_feature" +smartcard="$auto" u2f="$auto" -libusb="$default_feature" -usb_redir="$default_feature" +libusb="$auto" +usb_redir="$auto" opengl="yes" cpuid_h="no" avx2_opt="$default_feature" @@ -426,16 +409,12 @@ seccomp="$auto" glusterfs="$auto" gtk="$auto" tls_priority="NORMAL" -gnutls="$default_feature" -nettle="$default_feature" -nettle_xts="no" -gcrypt="$default_feature" -gcrypt_hmac="no" -gcrypt_xts="no" -qemu_private_xts="yes" -auth_pam="$default_feature" -vte="$default_feature" -virglrenderer="$default_feature" +gnutls="auto" +nettle="auto" +gcrypt="auto" +auth_pam="auto" +vte="auto" +virglrenderer="auto" tpm="$default_feature" libssh="$default_feature" live_block_migration=${default_feature:-yes} @@ -451,16 +430,15 @@ vdi=${default_feature:-yes} vvfat=${default_feature:-yes} qed=${default_feature:-yes} parallels=${default_feature:-yes} -sheepdog="no" -libxml2="$default_feature" +libxml2="$auto" debug_mutex="no" -libpmem="$default_feature" -default_devices="false" -plugins="no" +libpmem="$auto" +default_devices="true" +plugins="$default_feature" fuzzing="no" rng_none="no" secret_keyring="$default_feature" -libdaxctl="$default_feature" +libdaxctl="$auto" meson="" ninja="" skip_meson=no @@ -468,6 +446,7 @@ gettext="$auto" fuse="$auto" fuse_lseek="$auto" multiprocess="$auto" +slirp_smbd="$default_feature" malloc_trim="auto" gio="$default_feature" @@ -547,9 +526,6 @@ query_pkg_config() { pkg_config=query_pkg_config sdl2_config="${SDL2_CONFIG-${cross_prefix}sdl2-config}" -# If the user hasn't specified ARFLAGS, default to 'rv', just as make does. -ARFLAGS="${ARFLAGS-rv}" - # default flags for all hosts # We use -fwrapv to tell the compiler that we require a C dialect where # left shift of signed integers is well defined and has the expected @@ -561,7 +537,7 @@ QEMU_CFLAGS="-Wstrict-prototypes -Wredundant-decls $QEMU_CFLAGS" QEMU_CFLAGS="-D_GNU_SOURCE -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE $QEMU_CFLAGS" # Flags that are needed during configure but later taken care of by Meson -CONFIGURE_CFLAGS="-std=gnu99 -Wall" +CONFIGURE_CFLAGS="-std=gnu11 -Wall" CONFIGURE_LDFLAGS= @@ -737,6 +713,7 @@ MINGW32*) audio_drv_list="" fi supported_os="yes" + plugins="no" pie="no" ;; GNU/kFreeBSD) @@ -795,7 +772,8 @@ SunOS) ;; Haiku) haiku="yes" - QEMU_CFLAGS="-DB_USE_POSITIVE_POSIX_ERRORS -D_BSD_SOURCE $QEMU_CFLAGS" + pie="no" + QEMU_CFLAGS="-DB_USE_POSITIVE_POSIX_ERRORS -D_BSD_SOURCE -fPIC $QEMU_CFLAGS" ;; Linux) audio_drv_list="try-pa oss" @@ -840,8 +818,6 @@ do fi done -: ${smbd=${SMBD-/usr/sbin/smbd}} - # Default objcc to clang if available, otherwise use CC if has clang; then objcc=clang @@ -946,6 +922,18 @@ for opt do ;; --without-default-devices) default_devices="false" ;; + --with-devices-*[!a-zA-Z0-9_-]*=*) error_exit "Passed bad --with-devices-FOO option" + ;; + --with-devices-*) device_arch=${opt#--with-devices-}; + device_arch=${device_arch%%=*} + cf=$source_path/configs/devices/$device_arch-softmmu/$optarg.mak + if test -f "$cf"; then + device_archs="$device_archs $device_arch" + eval "devices_${device_arch}=\$optarg" + else + error_exit "File $cf does not exist" + fi + ;; --without-default-features) # processed above ;; --enable-gprof) gprof="yes" @@ -1034,6 +1022,10 @@ for opt do ;; --block-drv-ro-whitelist=*) block_drv_ro_whitelist=$(echo "$optarg" | sed -e 's/,/ /g') ;; + --enable-block-drv-whitelist-in-tools) block_drv_whitelist_tools="yes" + ;; + --disable-block-drv-whitelist-in-tools) block_drv_whitelist_tools="no" + ;; --enable-debug-tcg) debug_tcg="yes" ;; --disable-debug-tcg) debug_tcg="no" @@ -1116,6 +1108,10 @@ for opt do ;; --enable-hvf) hvf="enabled" ;; + --disable-nvmm) nvmm="disabled" + ;; + --enable-nvmm) nvmm="enabled" + ;; --disable-whpx) whpx="disabled" ;; --enable-whpx) whpx="enabled" @@ -1129,6 +1125,7 @@ for opt do --enable-cap-ng) cap_ng="enabled" ;; --disable-tcg) tcg="disabled" + plugins="no" ;; --enable-tcg) tcg="enabled" ;; @@ -1138,7 +1135,15 @@ for opt do ;; --disable-spice) spice="no" ;; - --enable-spice) spice="yes" + --enable-spice) + spice_protocol="yes" + spice="yes" + ;; + --disable-spice-protocol) + spice_protocol="no" + spice="no" + ;; + --enable-spice-protocol) spice_protocol="yes" ;; --disable-libiscsi) libiscsi="disabled" ;; @@ -1225,9 +1230,9 @@ for opt do ;; --enable-linux-aio) linux_aio="yes" ;; - --disable-linux-io-uring) linux_io_uring="no" + --disable-linux-io-uring) linux_io_uring="disabled" ;; - --enable-linux-io-uring) linux_io_uring="yes" + --enable-linux-io-uring) linux_io_uring="enabled" ;; --disable-attr) attr="disabled" ;; @@ -1237,6 +1242,10 @@ for opt do ;; --enable-membarrier) membarrier="yes" ;; + --disable-bpf) bpf="disabled" + ;; + --enable-bpf) bpf="enabled" + ;; --disable-blobs) blobs="false" ;; --with-pkgversion=*) pkgversion="$optarg" @@ -1293,21 +1302,21 @@ for opt do ;; --enable-xfsctl) xfs="yes" ;; - --disable-smartcard) smartcard="no" + --disable-smartcard) smartcard="disabled" ;; - --enable-smartcard) smartcard="yes" + --enable-smartcard) smartcard="enabled" ;; --disable-u2f) u2f="disabled" ;; --enable-u2f) u2f="enabled" ;; - --disable-libusb) libusb="no" + --disable-libusb) libusb="disabled" ;; - --enable-libusb) libusb="yes" + --enable-libusb) libusb="enabled" ;; - --disable-usb-redir) usb_redir="no" + --disable-usb-redir) usb_redir="disabled" ;; - --enable-usb-redir) usb_redir="yes" + --enable-usb-redir) usb_redir="enabled" ;; --disable-zlib-test) ;; @@ -1387,21 +1396,21 @@ for opt do ;; --tls-priority=*) tls_priority="$optarg" ;; - --disable-gnutls) gnutls="no" + --disable-gnutls) gnutls="disabled" ;; - --enable-gnutls) gnutls="yes" + --enable-gnutls) gnutls="enabled" ;; - --disable-nettle) nettle="no" + --disable-nettle) nettle="disabled" ;; - --enable-nettle) nettle="yes" + --enable-nettle) nettle="enabled" ;; - --disable-gcrypt) gcrypt="no" + --disable-gcrypt) gcrypt="disabled" ;; - --enable-gcrypt) gcrypt="yes" + --enable-gcrypt) gcrypt="enabled" ;; - --disable-auth-pam) auth_pam="no" + --disable-auth-pam) auth_pam="disabled" ;; - --enable-auth-pam) auth_pam="yes" + --enable-auth-pam) auth_pam="enabled" ;; --enable-rdma) rdma="yes" ;; @@ -1411,13 +1420,13 @@ for opt do ;; --disable-pvrdma) pvrdma="no" ;; - --disable-vte) vte="no" + --disable-vte) vte="disabled" ;; - --enable-vte) vte="yes" + --enable-vte) vte="enabled" ;; - --disable-virglrenderer) virglrenderer="no" + --disable-virglrenderer) virglrenderer="disabled" ;; - --enable-virglrenderer) virglrenderer="yes" + --enable-virglrenderer) virglrenderer="enabled" ;; --disable-tpm) tpm="no" ;; @@ -1435,9 +1444,9 @@ for opt do ;; --enable-numa) numa="yes" ;; - --disable-libxml2) libxml2="no" + --disable-libxml2) libxml2="disabled" ;; - --enable-libxml2) libxml2="yes" + --enable-libxml2) libxml2="enabled" ;; --disable-tcmalloc) tcmalloc="no" ;; @@ -1483,10 +1492,6 @@ for opt do ;; --enable-parallels) parallels="yes" ;; - --disable-sheepdog) sheepdog="no" - ;; - --enable-sheepdog) sheepdog="yes" - ;; --disable-vhost-user) vhost_user="no" ;; --enable-vhost-user) vhost_user="yes" @@ -1524,15 +1529,19 @@ for opt do ;; --disable-debug-mutex) debug_mutex=no ;; - --enable-libpmem) libpmem=yes + --enable-libpmem) libpmem="enabled" ;; - --disable-libpmem) libpmem=no + --disable-libpmem) libpmem="disabled" ;; --enable-xkbcommon) xkbcommon="enabled" ;; --disable-xkbcommon) xkbcommon="disabled" ;; - --enable-plugins) plugins="yes" + --enable-plugins) if test "$mingw32" = "yes"; then + error_exit "TCG plugins not currently supported on Windows platforms" + else + plugins="yes" + fi ;; --disable-plugins) plugins="no" ;; @@ -1554,9 +1563,9 @@ for opt do ;; --disable-keyring) secret_keyring="no" ;; - --enable-libdaxctl) libdaxctl=yes + --enable-libdaxctl) libdaxctl="enabled" ;; - --disable-libdaxctl) libdaxctl=no + --disable-libdaxctl) libdaxctl="disabled" ;; --enable-fuse) fuse="enabled" ;; @@ -1574,6 +1583,10 @@ for opt do ;; --disable-gio) gio=no ;; + --enable-slirp-smbd) slirp_smbd=yes + ;; + --disable-slirp-smbd) slirp_smbd=no + ;; *) echo "ERROR: unknown option $opt" echo "Try '$0 --help' for more information" @@ -1582,6 +1595,11 @@ for opt do esac done +# test for any invalid configuration combinations +if test "$plugins" = "yes" -a "$tcg" = "disabled"; then + error_exit "Can't enable plugins on non-TCG builds" +fi + case $git_submodules_action in update|validate) if test ! -e "$source_path/.git"; then @@ -1590,6 +1608,28 @@ case $git_submodules_action in fi ;; ignore) + if ! test -f "$source_path/ui/keycodemapdb/README" + then + echo + echo "ERROR: missing GIT submodules" + echo + if test -e "$source_path/.git"; then + echo "--with-git-submodules=ignore specified but submodules were not" + echo "checked out. Please initialize and update submodules." + else + echo "This is not a GIT checkout but module content appears to" + echo "be missing. Do not use 'git archive' or GitHub download links" + echo "to acquire QEMU source archives. Non-GIT builds are only" + echo "supported with source archives linked from:" + echo + echo " https://www.qemu.org/download/#source" + echo + echo "Developers working with GIT can use scripts/archive-source.sh" + echo "if they need to create valid source archives." + fi + echo + exit 1 + fi ;; *) echo "ERROR: invalid --with-git-submodules= value '$git_submodules_action'" @@ -1657,7 +1697,7 @@ case "$cpu" in # No special flags required for other host CPUs esac -eval "cross_cc_${cpu}=\$host_cc" +eval "cross_cc_${cpu}=\$cc" cross_cc_vars="$cross_cc_vars cross_cc_${cpu}" QEMU_CFLAGS="$CPU_CFLAGS $QEMU_CFLAGS" @@ -1669,18 +1709,18 @@ if [ "$ARCH" = "unknown" ]; then fi default_target_list="" -deprecated_targets_list=ppc64abi32-linux-user,lm32-softmmu,unicore32-softmmu +deprecated_targets_list=ppc64abi32-linux-user deprecated_features="" mak_wilds="" if [ "$softmmu" = "yes" ]; then - mak_wilds="${mak_wilds} $source_path/default-configs/targets/*-softmmu.mak" + mak_wilds="${mak_wilds} $source_path/configs/targets/*-softmmu.mak" fi if [ "$linux_user" = "yes" ]; then - mak_wilds="${mak_wilds} $source_path/default-configs/targets/*-linux-user.mak" + mak_wilds="${mak_wilds} $source_path/configs/targets/*-linux-user.mak" fi if [ "$bsd_user" = "yes" ]; then - mak_wilds="${mak_wilds} $source_path/default-configs/targets/*-bsd-user.mak" + mak_wilds="${mak_wilds} $source_path/configs/targets/*-bsd-user.mak" fi # If the user doesn't explicitly specify a deprecated target we will @@ -1761,7 +1801,8 @@ Advanced options (experts only): --without-default-features default all --enable-* options to "disabled" --without-default-devices do not include any device that is not needed to start the emulator (only use if you are including - desired devices in default-configs/devices/) + desired devices in configs/devices/) + --with-devices-ARCH=NAME override default configs/devices --enable-debug enable common debug build options --enable-sanitizers enable default sanitizers --enable-tsan enable thread sanitizer @@ -1773,10 +1814,12 @@ Advanced options (experts only): --block-drv-whitelist=L Same as --block-drv-rw-whitelist=L --block-drv-rw-whitelist=L set block driver read-write whitelist - (affects only QEMU, not qemu-img) + (by default affects only QEMU, not tools like qemu-img) --block-drv-ro-whitelist=L set block driver read-only whitelist - (affects only QEMU, not qemu-img) + (by default affects only QEMU, not tools like qemu-img) + --enable-block-drv-whitelist-in-tools + use block whitelist also in tools instead of only QEMU --enable-trace-backends=B Set trace backend Available backends: $trace_backend_list --with-trace-file=NAME Full PATH,NAME of file to store traces @@ -1857,6 +1900,7 @@ disabled with --disable-FEATURE, default is enabled if available kvm KVM acceleration support hax HAX acceleration support hvf Hypervisor.framework acceleration support + nvmm NVMM acceleration support whpx Windows Hypervisor Platform acceleration support rdma Enable RDMA-based migration pvrdma Enable PVRDMA support @@ -1874,7 +1918,9 @@ disabled with --disable-FEATURE, default is enabled if available vhost-user vhost-user backend support vhost-user-blk-server vhost-user-blk server support vhost-vdpa vhost-vdpa kernel backend support + bpf BPF kernel support spice spice + spice-protocol spice-protocol rbd rados block device (rbd) libiscsi iscsi support libnfs nfs support @@ -1916,7 +1962,6 @@ disabled with --disable-FEATURE, default is enabled if available vvfat vvfat image format support qed qed image format support parallels parallels image format support - sheepdog sheepdog block driver support (deprecated) crypto-afalg Linux AF_ALG crypto backend driver capstone capstone disassembler support debug-mutex mutex debugging support @@ -1928,6 +1973,7 @@ disabled with --disable-FEATURE, default is enabled if available fuse-lseek SEEK_HOLE/SEEK_DATA support for FUSE exports multiprocess Out of process device emulation support gio libgio support + slirp-smbd use smbd (at path --smbd=*) in slirp networking NOTE: The object files are built at the place where configure is launched EOF @@ -2050,17 +2096,17 @@ fi cat > $TMPC << EOF #if defined(__clang_major__) && defined(__clang_minor__) # ifdef __apple_build_version__ -# if __clang_major__ < 5 || (__clang_major__ == 5 && __clang_minor__ < 1) -# error You need at least XCode Clang v5.1 to compile QEMU +# if __clang_major__ < 10 || (__clang_major__ == 10 && __clang_minor__ < 0) +# error You need at least XCode Clang v10.0 to compile QEMU # endif # else -# if __clang_major__ < 3 || (__clang_major__ == 3 && __clang_minor__ < 4) -# error You need at least Clang v3.4 to compile QEMU +# if __clang_major__ < 6 || (__clang_major__ == 6 && __clang_minor__ < 0) +# error You need at least Clang v6.0 to compile QEMU # endif # endif #elif defined(__GNUC__) && defined(__GNUC_MINOR__) -# if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 8) -# error You need at least GCC v4.8 to compile QEMU +# if __GNUC__ < 7 || (__GNUC__ == 7 && __GNUC_MINOR__ < 5) +# error You need at least GCC v7.5.0 to compile QEMU # endif #else # error You either need GCC or Clang to compiler QEMU @@ -2068,7 +2114,7 @@ cat > $TMPC << EOF int main (void) { return 0; } EOF if ! compile_prog "" "" ; then - error_exit "You need at least GCC v4.8 or Clang v3.4 (or XCode Clang v5.1)" + error_exit "You need at least GCC v7.5 or Clang v6.0 (or XCode Clang v10.0)" fi # Accumulate -Wfoo and -Wno-bar separately. @@ -2172,11 +2218,16 @@ if test "$modules" = "no" && test "$module_upgrades" = "yes" ; then error_exit "Can't enable module-upgrades as Modules are not enabled" fi -# Static linking is not possible with modules or PIE +# Static linking is not possible with plugins, modules or PIE if test "$static" = "yes" ; then if test "$modules" = "yes" ; then error_exit "static and modules are mutually incompatible" fi + if test "$plugins" = "yes"; then + error_exit "static and plugins are mutually incompatible" + else + plugins="no" + fi fi # Unconditional check for compiler __thread support @@ -2276,6 +2327,11 @@ if test "$solaris" = "yes" ; then fi fi +if test "$tcg" = "enabled"; then + git_submodules="$git_submodules tests/fp/berkeley-testfloat-3" + git_submodules="$git_submodules tests/fp/berkeley-softfloat-3" +fi + if test -z "${target_list+xxx}" ; then default_targets=yes for target in $default_target_list; do @@ -2325,24 +2381,27 @@ feature_not_found() { # --- # big/little endian test cat > $TMPC << EOF +#include short big_endian[] = { 0x4269, 0x4765, 0x4e64, 0x4961, 0x4e00, 0, }; short little_endian[] = { 0x694c, 0x7454, 0x654c, 0x6e45, 0x6944, 0x6e41, 0, }; -extern int foo(short *, short *); -int main(int argc, char *argv[]) { - return foo(big_endian, little_endian); +int main(int argc, char *argv[]) +{ + return printf("%s %s\n", (char *)big_endian, (char *)little_endian); } EOF -if compile_object ; then - if strings -a $TMPO | grep -q BiGeNdIaN ; then +if compile_prog ; then + if strings -a $TMPE | grep -q BiGeNdIaN ; then bigendian="yes" - elif strings -a $TMPO | grep -q LiTtLeEnDiAn ; then + elif strings -a $TMPE | grep -q LiTtLeEnDiAn ; then bigendian="no" else echo big/little test failed + exit 1 fi else echo big/little test failed + exit 1 fi ########################################## @@ -2361,20 +2420,6 @@ if test "$softmmu" = "no"; then audio_drv_list="" fi -########################################## -# Some versions of Mac OS X incorrectly define SIZE_MAX -cat > $TMPC << EOF -#include -#include -int main(int argc, char *argv[]) { - return printf("%zu", SIZE_MAX); -} -EOF -have_broken_size_max=no -if ! compile_object -Werror ; then - have_broken_size_max=yes -fi - ########################################## # L2TPV3 probe @@ -2785,234 +2830,6 @@ EOF fi fi -########################################## -# GNUTLS probe - -if test "$gnutls" != "no"; then - pass="no" - if $pkg_config --exists "gnutls >= 3.1.18"; then - gnutls_cflags=$($pkg_config --cflags gnutls) - gnutls_libs=$($pkg_config --libs gnutls) - # Packaging for the static libraries is not always correct. - # At least ubuntu 18.04 ships only shared libraries. - write_c_skeleton - if compile_prog "" "$gnutls_libs" ; then - pass="yes" - fi - fi - if test "$pass" = "no" && test "$gnutls" = "yes"; then - feature_not_found "gnutls" "Install gnutls devel >= 3.1.18" - else - gnutls="$pass" - fi -fi - - -# If user didn't give a --disable/enable-gcrypt flag, -# then mark as disabled if user requested nettle -# explicitly -if test -z "$gcrypt" -then - if test "$nettle" = "yes" - then - gcrypt="no" - fi -fi - -# If user didn't give a --disable/enable-nettle flag, -# then mark as disabled if user requested gcrypt -# explicitly -if test -z "$nettle" -then - if test "$gcrypt" = "yes" - then - nettle="no" - fi -fi - -has_libgcrypt() { - if ! has "libgcrypt-config" - then - return 1 - fi - - if test -n "$cross_prefix" - then - host=$(libgcrypt-config --host) - if test "$host-" != $cross_prefix - then - return 1 - fi - fi - - maj=`libgcrypt-config --version | awk -F . '{print $1}'` - min=`libgcrypt-config --version | awk -F . '{print $2}'` - - if test $maj != 1 || test $min -lt 5 - then - return 1 - fi - - return 0 -} - - -if test "$nettle" != "no"; then - pass="no" - if $pkg_config --exists "nettle >= 2.7.1"; then - nettle_cflags=$($pkg_config --cflags nettle) - nettle_libs=$($pkg_config --libs nettle) - nettle_version=$($pkg_config --modversion nettle) - # Link test to make sure the given libraries work (e.g for static). - write_c_skeleton - if compile_prog "" "$nettle_libs" ; then - if test -z "$gcrypt"; then - gcrypt="no" - fi - pass="yes" - fi - fi - if test "$pass" = "yes" - then - cat > $TMPC << EOF -#include -int main(void) { - return 0; -} -EOF - if compile_prog "$nettle_cflags" "$nettle_libs" ; then - nettle_xts=yes - qemu_private_xts=no - fi - fi - if test "$pass" = "no" && test "$nettle" = "yes"; then - feature_not_found "nettle" "Install nettle devel >= 2.7.1" - else - nettle="$pass" - fi -fi - -if test "$gcrypt" != "no"; then - pass="no" - if has_libgcrypt; then - gcrypt_cflags=$(libgcrypt-config --cflags) - gcrypt_libs=$(libgcrypt-config --libs) - # Debian has removed -lgpg-error from libgcrypt-config - # as it "spreads unnecessary dependencies" which in - # turn breaks static builds... - if test "$static" = "yes" - then - gcrypt_libs="$gcrypt_libs -lgpg-error" - fi - - # Link test to make sure the given libraries work (e.g for static). - write_c_skeleton - if compile_prog "" "$gcrypt_libs" ; then - pass="yes" - fi - fi - if test "$pass" = "yes"; then - gcrypt="yes" - cat > $TMPC << EOF -#include -int main(void) { - gcry_mac_hd_t handle; - gcry_mac_open(&handle, GCRY_MAC_HMAC_MD5, - GCRY_MAC_FLAG_SECURE, NULL); - return 0; -} -EOF - if compile_prog "$gcrypt_cflags" "$gcrypt_libs" ; then - gcrypt_hmac=yes - fi - cat > $TMPC << EOF -#include -int main(void) { - gcry_cipher_hd_t handle; - gcry_cipher_open(&handle, GCRY_CIPHER_AES, GCRY_CIPHER_MODE_XTS, 0); - return 0; -} -EOF - if compile_prog "$gcrypt_cflags" "$gcrypt_libs" ; then - gcrypt_xts=yes - qemu_private_xts=no - fi - elif test "$gcrypt" = "yes"; then - feature_not_found "gcrypt" "Install gcrypt devel >= 1.5.0" - else - gcrypt="no" - fi -fi - - -if test "$gcrypt" = "yes" && test "$nettle" = "yes" -then - error_exit "Only one of gcrypt & nettle can be enabled" -fi - -########################################## -# libtasn1 - only for the TLS creds/session test suite - -tasn1=yes -tasn1_cflags="" -tasn1_libs="" -if $pkg_config --exists "libtasn1"; then - tasn1_cflags=$($pkg_config --cflags libtasn1) - tasn1_libs=$($pkg_config --libs libtasn1) -else - tasn1=no -fi - - -########################################## -# PAM probe - -if test "$auth_pam" != "no"; then - cat > $TMPC < -#include -int main(void) { - const char *service_name = "qemu"; - const char *user = "frank"; - const struct pam_conv pam_conv = { 0 }; - pam_handle_t *pamh = NULL; - pam_start(service_name, user, &pam_conv, &pamh); - return 0; -} -EOF - if compile_prog "" "-lpam" ; then - auth_pam=yes - else - if test "$auth_pam" = "yes"; then - feature_not_found "PAM" "Install PAM development package" - else - auth_pam=no - fi - fi -fi - -########################################## -# VTE probe - -if test "$vte" != "no"; then - vteminversion="0.32.0" - if $pkg_config --exists "vte-2.91"; then - vtepackage="vte-2.91" - else - vtepackage="vte-2.90" - fi - if $pkg_config --exists "$vtepackage >= $vteminversion"; then - vte_cflags=$($pkg_config --cflags $vtepackage) - vte_libs=$($pkg_config --libs $vtepackage) - vteversion=$($pkg_config --modversion $vtepackage) - vte="yes" - elif test "$vte" = "yes"; then - feature_not_found "vte" "Install libvte-2.90/2.91 devel" - else - vte="no" - fi -fi - ########################################## # RDMA needs OpenFabrics libraries if test "$rdma" != "no" ; then @@ -3306,15 +3123,78 @@ for drv in $audio_drv_list; do esac done +########################################## +# plugin linker support probe + +if test "$plugins" != "no"; then + + ######################################### + # See if --dynamic-list is supported by the linker + + ld_dynamic_list="no" + cat > $TMPTXT < $TMPC < +void foo(void); + +void foo(void) +{ + printf("foo\n"); +} + +int main(void) +{ + foo(); + return 0; +} +EOF + + if compile_prog "" "-Wl,--dynamic-list=$TMPTXT" ; then + ld_dynamic_list="yes" + fi + + ######################################### + # See if -exported_symbols_list is supported by the linker + + ld_exported_symbols_list="no" + cat > $TMPTXT < $TMPC << EOF -#include -int main(void) { return 0; } -EOF -if ! compile_prog "$glib_cflags -Werror" "$glib_libs" ; then - if cc_has_warning_flag "-Wno-unknown-attributes"; then - glib_cflags="-Wno-unknown-attributes $glib_cflags" - CONFIGURE_CFLAGS="-Wno-unknown-attributes $CONFIGURE_CFLAGS" - fi -fi - # Silence clang warnings triggered by glib < 2.57.2 cat > $TMPC << EOF #include @@ -3517,7 +3385,7 @@ fi ########################################## # libssh probe if test "$libssh" != "no" ; then - if $pkg_config --exists libssh; then + if $pkg_config --exists "libssh >= 0.8.7"; then libssh_cflags=$($pkg_config libssh --cflags) libssh_libs=$($pkg_config libssh --libs) libssh=yes @@ -3529,23 +3397,6 @@ if test "$libssh" != "no" ; then fi fi -########################################## -# Check for libssh 0.8 -# This is done like this instead of using the LIBSSH_VERSION_* and -# SSH_VERSION_* macros because some distributions in the past shipped -# snapshots of the future 0.8 from Git, and those snapshots did not -# have updated version numbers (still referring to 0.7.0). - -if test "$libssh" = "yes"; then - cat > $TMPC < -int main(void) { return ssh_get_server_publickey(NULL, NULL); } -EOF - if compile_prog "$libssh_cflags" "$libssh_libs"; then - libssh_cflags="-DHAVE_LIBSSH_0_8 $libssh_cflags" - fi -fi - ########################################## # linux-aio probe @@ -3565,21 +3416,6 @@ EOF linux_aio=no fi fi -########################################## -# linux-io-uring probe - -if test "$linux_io_uring" != "no" ; then - if $pkg_config liburing; then - linux_io_uring_cflags=$($pkg_config --cflags liburing) - linux_io_uring_libs=$($pkg_config --libs liburing) - linux_io_uring=yes - else - if test "$linux_io_uring" = "yes" ; then - feature_not_found "linux io_uring" "Install liburing devel" - fi - linux_io_uring=no - fi -fi ########################################## # TPM emulation is only on POSIX @@ -3615,14 +3451,12 @@ fi case "$fdt" in auto | enabled | internal) # Simpler to always update submodule, even if not needed. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} dtc" - fi + git_submodules="${git_submodules} dtc" ;; esac ########################################## -# opengl probe (for sdl2, gtk, milkymist-tmu2) +# opengl probe (for sdl2, gtk) gbm="no" if $pkg_config gbm; then @@ -3745,107 +3579,6 @@ else feature_not_found "samplerate" "Install libsamplerate0-dev" fi -########################################## -# libxml2 probe -if test "$libxml2" != "no" ; then - if $pkg_config --exists libxml-2.0; then - libxml2="yes" - libxml2_cflags=$($pkg_config --cflags libxml-2.0) - libxml2_libs=$($pkg_config --libs libxml-2.0) - else - if test "$libxml2" = "yes"; then - feature_not_found "libxml2" "Install libxml2 devel" - fi - libxml2="no" - fi -fi - -# Check for inotify functions when we are building linux-user -# emulator. This is done because older glibc versions don't -# have syscall stubs for these implemented. In that case we -# don't provide them even if kernel supports them. -# -inotify=no -cat > $TMPC << EOF -#include - -int -main(void) -{ - /* try to start inotify */ - return inotify_init(); -} -EOF -if compile_prog "" "" ; then - inotify=yes -fi - -inotify1=no -cat > $TMPC << EOF -#include - -int -main(void) -{ - /* try to start inotify */ - return inotify_init1(0); -} -EOF -if compile_prog "" "" ; then - inotify1=yes -fi - -# check if pipe2 is there -pipe2=no -cat > $TMPC << EOF -#include -#include - -int main(void) -{ - int pipefd[2]; - return pipe2(pipefd, O_CLOEXEC); -} -EOF -if compile_prog "" "" ; then - pipe2=yes -fi - -# check if accept4 is there -accept4=no -cat > $TMPC << EOF -#include -#include - -int main(void) -{ - accept4(0, NULL, NULL, SOCK_CLOEXEC); - return 0; -} -EOF -if compile_prog "" "" ; then - accept4=yes -fi - -# check if tee/splice is there. vmsplice was added same time. -splice=no -cat > $TMPC << EOF -#include -#include -#include - -int main(void) -{ - int len, fd = 0; - len = tee(STDIN_FILENO, STDOUT_FILENO, INT_MAX, SPLICE_F_NONBLOCK); - splice(STDIN_FILENO, NULL, fd, NULL, len, SPLICE_F_MOVE); - return 0; -} -EOF -if compile_prog "" "" ; then - splice=yes -fi - ########################################## # libnuma probe @@ -3876,59 +3609,6 @@ elif test "$jemalloc" = "yes" ; then malloc=jemalloc fi -########################################## -# signalfd probe -signalfd="no" -cat > $TMPC << EOF -#include -#include -#include -int main(void) { return syscall(SYS_signalfd, -1, NULL, _NSIG / 8); } -EOF - -if compile_prog "" "" ; then - signalfd=yes -fi - -# check if optreset global is declared by -optreset="no" -cat > $TMPC << EOF -#include -int main(void) { return optreset; } -EOF - -if compile_prog "" "" ; then - optreset=yes -fi - -# check if eventfd is supported -eventfd=no -cat > $TMPC << EOF -#include - -int main(void) -{ - return eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC); -} -EOF -if compile_prog "" "" ; then - eventfd=yes -fi - -# check if memfd is supported -memfd=no -cat > $TMPC << EOF -#include - -int main(void) -{ - return memfd_create("foo", MFD_ALLOW_SEALING); -} -EOF -if compile_prog "" "" ; then - memfd=yes -fi - # check for usbfs have_usbfs=no if test "$linux_user" = "yes"; then @@ -3953,299 +3633,21 @@ EOF fi fi -# check for fallocate -fallocate=no -cat > $TMPC << EOF -#include - -int main(void) -{ - fallocate(0, 0, 0, 0); - return 0; -} -EOF -if compile_prog "" "" ; then - fallocate=yes -fi - -# check for fallocate hole punching -fallocate_punch_hole=no -cat > $TMPC << EOF -#include -#include - -int main(void) -{ - fallocate(0, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, 0); - return 0; -} -EOF -if compile_prog "" "" ; then - fallocate_punch_hole=yes -fi - -# check that fallocate supports range zeroing inside the file -fallocate_zero_range=no -cat > $TMPC << EOF -#include -#include - -int main(void) -{ - fallocate(0, FALLOC_FL_ZERO_RANGE, 0, 0); - return 0; -} -EOF -if compile_prog "" "" ; then - fallocate_zero_range=yes -fi - -# check for posix_fallocate -posix_fallocate=no -cat > $TMPC << EOF -#include - -int main(void) -{ - posix_fallocate(0, 0, 0); - return 0; -} -EOF -if compile_prog "" "" ; then - posix_fallocate=yes -fi - -# check for sync_file_range -sync_file_range=no -cat > $TMPC << EOF -#include - -int main(void) -{ - sync_file_range(0, 0, 0, 0); - return 0; -} -EOF -if compile_prog "" "" ; then - sync_file_range=yes -fi - -# check for linux/fiemap.h and FS_IOC_FIEMAP -fiemap=no -cat > $TMPC << EOF -#include -#include -#include - -int main(void) -{ - ioctl(0, FS_IOC_FIEMAP, 0); - return 0; -} -EOF -if compile_prog "" "" ; then - fiemap=yes -fi - -# check for dup3 -dup3=no -cat > $TMPC << EOF -#include - -int main(void) -{ - dup3(0, 0, 0); - return 0; -} -EOF -if compile_prog "" "" ; then - dup3=yes -fi - -# check for ppoll support -ppoll=no -cat > $TMPC << EOF -#include - -int main(void) -{ - struct pollfd pfd = { .fd = 0, .events = 0, .revents = 0 }; - ppoll(&pfd, 1, 0, 0); - return 0; -} -EOF -if compile_prog "" "" ; then - ppoll=yes -fi - -# check for prctl(PR_SET_TIMERSLACK , ... ) support -prctl_pr_set_timerslack=no -cat > $TMPC << EOF -#include - -int main(void) -{ - prctl(PR_SET_TIMERSLACK, 1, 0, 0, 0); - return 0; -} -EOF -if compile_prog "" "" ; then - prctl_pr_set_timerslack=yes -fi - -# check for epoll support -epoll=no -cat > $TMPC << EOF -#include - -int main(void) -{ - epoll_create(0); - return 0; -} -EOF -if compile_prog "" "" ; then - epoll=yes -fi - -# epoll_create1 is a later addition -# so we must check separately for its presence -epoll_create1=no -cat > $TMPC << EOF -#include - -int main(void) -{ - /* Note that we use epoll_create1 as a value, not as - * a function being called. This is necessary so that on - * old SPARC glibc versions where the function was present in - * the library but not declared in the header file we will - * fail the configure check. (Otherwise we will get a compiler - * warning but not an error, and will proceed to fail the - * qemu compile where we compile with -Werror.) - */ - return (int)(uintptr_t)&epoll_create1; -} -EOF -if compile_prog "" "" ; then - epoll_create1=yes -fi - -# check for sendfile support -sendfile=no -cat > $TMPC << EOF -#include - -int main(void) -{ - return sendfile(0, 0, 0, 0); -} -EOF -if compile_prog "" "" ; then - sendfile=yes -fi - -# check for timerfd support (glibc 2.8 and newer) -timerfd=no -cat > $TMPC << EOF -#include - -int main(void) -{ - return(timerfd_create(CLOCK_REALTIME, 0)); -} -EOF -if compile_prog "" "" ; then - timerfd=yes -fi - -# check for setns and unshare support -setns=no -cat > $TMPC << EOF -#include - -int main(void) -{ - int ret; - ret = setns(0, 0); - ret = unshare(0); - return ret; -} -EOF -if compile_prog "" "" ; then - setns=yes -fi - -# clock_adjtime probe -clock_adjtime=no -cat > $TMPC < -#include - -int main(void) -{ - return clock_adjtime(0, 0); -} -EOF -clock_adjtime=no -if compile_prog "" "" ; then - clock_adjtime=yes -fi - -# syncfs probe -syncfs=no -cat > $TMPC < - -int main(void) -{ - return syncfs(0); -} -EOF -syncfs=no -if compile_prog "" "" ; then - syncfs=yes -fi - -# Search for bswap_32 function -byteswap_h=no -cat > $TMPC << EOF -#include -int main(void) { return bswap_32(0); } -EOF -if compile_prog "" "" ; then - byteswap_h=yes -fi - -# Search for bswap32 function -bswap_h=no -cat > $TMPC << EOF -#include -#include -#include -int main(void) { return bswap32(0); } -EOF -if compile_prog "" "" ; then - bswap_h=yes -fi - -# Check whether we have openpty() in either libc or libutil -cat > $TMPC << EOF -extern int openpty(int *am, int *as, char *name, void *termp, void *winp); -int main(void) { return openpty(0, 0, 0, 0, 0); } -EOF - -have_openpty="no" -if compile_prog "" "" ; then - have_openpty="yes" -else - if compile_prog "" "-lutil" ; then - have_openpty="yes" +########################################## +# spice probe +if test "$spice_protocol" != "no" ; then + spice_protocol_cflags=$($pkg_config --cflags spice-protocol 2>/dev/null) + if $pkg_config --atleast-version=0.12.3 spice-protocol; then + spice_protocol="yes" + else + if test "$spice_protocol" = "yes" ; then + feature_not_found "spice_protocol" \ + "Install spice-protocol(>=0.12.3) devel" + fi + spice_protocol="no" fi fi -########################################## -# spice probe if test "$spice" != "no" ; then cat > $TMPC << EOF #include @@ -4254,60 +3656,18 @@ EOF spice_cflags=$($pkg_config --cflags spice-protocol spice-server 2>/dev/null) spice_libs=$($pkg_config --libs spice-protocol spice-server 2>/dev/null) if $pkg_config --atleast-version=0.12.5 spice-server && \ - $pkg_config --atleast-version=0.12.3 spice-protocol && \ + test "$spice_protocol" = "yes" && \ compile_prog "$spice_cflags" "$spice_libs" ; then spice="yes" else if test "$spice" = "yes" ; then feature_not_found "spice" \ - "Install spice-server(>=0.12.5) and spice-protocol(>=0.12.3) devel" + "Install spice-server(>=0.12.5) devel" fi spice="no" fi fi -# check for smartcard support -if test "$smartcard" != "no"; then - if $pkg_config --atleast-version=2.5.1 libcacard; then - libcacard_cflags=$($pkg_config --cflags libcacard) - libcacard_libs=$($pkg_config --libs libcacard) - smartcard="yes" - else - if test "$smartcard" = "yes"; then - feature_not_found "smartcard" "Install libcacard devel" - fi - smartcard="no" - fi -fi - -# check for libusb -if test "$libusb" != "no" ; then - if $pkg_config --atleast-version=1.0.13 libusb-1.0; then - libusb="yes" - libusb_cflags=$($pkg_config --cflags libusb-1.0) - libusb_libs=$($pkg_config --libs libusb-1.0) - else - if test "$libusb" = "yes"; then - feature_not_found "libusb" "Install libusb devel >= 1.0.13" - fi - libusb="no" - fi -fi - -# check for usbredirparser for usb network redirection support -if test "$usb_redir" != "no" ; then - if $pkg_config --atleast-version=0.6 libusbredirparser-0.5; then - usb_redir="yes" - usb_redir_cflags=$($pkg_config --cflags libusbredirparser-0.5) - usb_redir_libs=$($pkg_config --libs libusbredirparser-0.5) - else - if test "$usb_redir" = "yes"; then - feature_not_found "usb-redir" "Install usbredir devel" - fi - usb_redir="no" - fi -fi - ########################################## # check if we have VSS SDK headers for win @@ -4386,100 +3746,16 @@ EOF fi fi -########################################## -# virgl renderer probe - -if test "$virglrenderer" != "no" ; then - cat > $TMPC << EOF -#include -int main(void) { virgl_renderer_poll(); return 0; } -EOF - virgl_cflags=$($pkg_config --cflags virglrenderer 2>/dev/null) - virgl_libs=$($pkg_config --libs virglrenderer 2>/dev/null) - virgl_version=$($pkg_config --modversion virglrenderer 2>/dev/null) - if $pkg_config virglrenderer >/dev/null 2>&1 && \ - compile_prog "$virgl_cflags" "$virgl_libs" ; then - virglrenderer="yes" - else - if test "$virglrenderer" = "yes" ; then - feature_not_found "virglrenderer" - fi - virglrenderer="no" - fi -fi - ########################################## # capstone case "$capstone" in auto | enabled | internal) # Simpler to always update submodule, even if not needed. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} capstone" - fi + git_submodules="${git_submodules} capstone" ;; esac -########################################## -# check if we have fdatasync - -fdatasync=no -cat > $TMPC << EOF -#include -int main(void) { -#if defined(_POSIX_SYNCHRONIZED_IO) && _POSIX_SYNCHRONIZED_IO > 0 -return fdatasync(0); -#else -#error Not supported -#endif -} -EOF -if compile_prog "" "" ; then - fdatasync=yes -fi - -########################################## -# check if we have madvise - -madvise=no -cat > $TMPC << EOF -#include -#include -#include -int main(void) { return madvise(NULL, 0, MADV_DONTNEED); } -EOF -if compile_prog "" "" ; then - madvise=yes -fi - -########################################## -# check if we have posix_madvise - -posix_madvise=no -cat > $TMPC << EOF -#include -#include -int main(void) { return posix_madvise(NULL, 0, POSIX_MADV_DONTNEED); } -EOF -if compile_prog "" "" ; then - posix_madvise=yes -fi - -########################################## -# check if we have posix_memalign() - -posix_memalign=no -cat > $TMPC << EOF -#include -int main(void) { - void *p; - return posix_memalign(&p, 8, 8); -} -EOF -if compile_prog "" "" ; then - posix_memalign=yes -fi - ########################################## # check if we have posix_syslog @@ -4492,46 +3768,6 @@ if compile_prog "" "" ; then posix_syslog=yes fi -########################################## -# check if we have sem_timedwait - -sem_timedwait=no -cat > $TMPC << EOF -#include -int main(void) { sem_t s; struct timespec t = {0}; return sem_timedwait(&s, &t); } -EOF -if compile_prog "" "" ; then - sem_timedwait=yes -fi - -########################################## -# check if we have strchrnul - -strchrnul=no -cat > $TMPC << EOF -#include -int main(void); -// Use a haystack that the compiler shouldn't be able to constant fold -char *haystack = (char*)&main; -int main(void) { return strchrnul(haystack, 'x') != &haystack[6]; } -EOF -if compile_prog "" "" ; then - strchrnul=yes -fi - -######################################### -# check if we have st_atim - -st_atim=no -cat > $TMPC << EOF -#include -#include -int main(void) { return offsetof(struct stat, st_atim); } -EOF -if compile_prog "" "" ; then - st_atim=yes -fi - ########################################## # check if trace backend exists @@ -4544,21 +3780,8 @@ fi ########################################## # For 'ust' backend, test if ust headers are present if have_backend "ust"; then - cat > $TMPC << EOF -#include -int main(void) { return 0; } -EOF - if compile_prog "" "-Wl,--no-as-needed -ldl" ; then - if $pkg_config lttng-ust --exists; then - lttng_ust_libs=$($pkg_config --libs lttng-ust) - else - lttng_ust_libs="-llttng-ust -ldl" - fi - if $pkg_config liburcu-bp --exists; then - urcu_bp_libs=$($pkg_config --libs liburcu-bp) - else - urcu_bp_libs="-lurcu-bp" - fi + if $pkg_config lttng-ust --exists; then + lttng_ust_libs=$($pkg_config --libs lttng-ust) else error_exit "Trace backend 'ust' missing lttng-ust header files" fi @@ -4711,65 +3934,6 @@ else # "$safe_stack" = "" fi fi -########################################## -# check if we have open_by_handle_at - -open_by_handle_at=no -cat > $TMPC << EOF -#include -#if !defined(AT_EMPTY_PATH) -# error missing definition -#else -int main(void) { struct file_handle fh; return open_by_handle_at(0, &fh, 0); } -#endif -EOF -if compile_prog "" "" ; then - open_by_handle_at=yes -fi - -######################################## -# check if we have linux/magic.h - -linux_magic_h=no -cat > $TMPC << EOF -#include -int main(void) { - return 0; -} -EOF -if compile_prog "" "" ; then - linux_magic_h=yes -fi - -######################################## -# check if we have valgrind/valgrind.h - -valgrind_h=no -cat > $TMPC << EOF -#include -int main(void) { - return 0; -} -EOF -if compile_prog "" "" ; then - valgrind_h=yes -fi - -######################################## -# check if environ is declared - -has_environ=no -cat > $TMPC << EOF -#include -int main(void) { - environ = 0; - return 0; -} -EOF -if compile_prog "" "" ; then - has_environ=yes -fi - ######################################## # check if cpuid.h is usable. @@ -4812,7 +3976,7 @@ static int bar(void *a) { } int main(int argc, char *argv[]) { return bar(argv[0]); } EOF - if compile_object "" ; then + if compile_object "-Werror" ; then avx2_opt="yes" else avx2_opt="no" @@ -4842,7 +4006,7 @@ int main(int argc, char *argv[]) return bar(argv[0]); } EOF - if ! compile_object "" ; then + if ! compile_object "-Werror" ; then avx512f_opt="no" fi else @@ -4912,18 +4076,11 @@ cat > $TMPC << EOF int main(void) { uint64_t x = 0, y = 0; -#ifdef __ATOMIC_RELAXED y = __atomic_load_n(&x, __ATOMIC_RELAXED); __atomic_store_n(&x, y, __ATOMIC_RELAXED); __atomic_compare_exchange_n(&x, &y, x, 0, __ATOMIC_RELAXED, __ATOMIC_RELAXED); __atomic_exchange_n(&x, y, __ATOMIC_RELAXED); __atomic_fetch_add(&x, y, __ATOMIC_RELAXED); -#else - typedef char is_host64[sizeof(void *) >= sizeof(uint64_t) ? 1 : -1]; - __sync_lock_test_and_set(&x, y); - __sync_val_compare_and_swap(&x, y, 0); - __sync_fetch_and_add(&x, y); -#endif return 0; } EOF @@ -4931,61 +4088,6 @@ if compile_prog "" "" ; then atomic64=yes fi -######################################### -# See if --dynamic-list is supported by the linker -ld_dynamic_list="no" -if test "$static" = "no" ; then - cat > $TMPTXT < $TMPC < -void foo(void); - -void foo(void) -{ - printf("foo\n"); -} - -int main(void) -{ - foo(); - return 0; -} -EOF - - if compile_prog "" "-Wl,--dynamic-list=$TMPTXT" ; then - ld_dynamic_list="yes" - fi -fi - -######################################### -# See if -exported_symbols_list is supported by the linker - -ld_exported_symbols_list="no" -if test "$static" = "no" ; then - cat > $TMPTXT < $TMPC << EOF -#include -int main(void) { - copy_file_range(0, NULL, 0, NULL, 0, 0); - return 0; -} -EOF -if compile_prog "" "" ; then - have_copy_file_range=yes -fi - ########################################## # check if struct fsxattr is available via linux/fs.h @@ -5102,19 +4190,6 @@ else membarrier=no fi -########################################## -# check if rtnetlink.h exists and is useful -have_rtnetlink=no -cat > $TMPC << EOF -#include -int main(void) { - return IFLA_PROTO_DOWN; -} -EOF -if compile_prog "" "" ; then - have_rtnetlink=yes -fi - ########################################## # check for usable AF_VSOCK environment have_af_vsock=no @@ -5168,63 +4243,6 @@ then fi -################################################# -# check for sysmacros.h - -have_sysmacros=no -cat > $TMPC << EOF -#include -int main(void) { - return makedev(0, 0); -} -EOF -if compile_prog "" "" ; then - have_sysmacros=yes -fi - -########################################## -# check for _Static_assert() - -have_static_assert=no -cat > $TMPC << EOF -_Static_assert(1, "success"); -int main(void) { - return 0; -} -EOF -if compile_prog "" "" ; then - have_static_assert=yes -fi - -########################################## -# check for utmpx.h, it is missing e.g. on OpenBSD - -have_utmpx=no -cat > $TMPC << EOF -#include -struct utmpx user_info; -int main(void) { - return 0; -} -EOF -if compile_prog "" "" ; then - have_utmpx=yes -fi - -########################################## -# check for getrandom() - -have_getrandom=no -cat > $TMPC << EOF -#include -int main(void) { - return getrandom(0, 0, GRND_NONBLOCK); -} -EOF -if compile_prog "" "" ; then - have_getrandom=yes -fi - ########################################## # checks for sanitizers @@ -5308,50 +4326,29 @@ EOF fi fi -########################################## -# check for libpmem - -if test "$libpmem" != "no"; then - if $pkg_config --exists "libpmem"; then - libpmem="yes" - libpmem_libs=$($pkg_config --libs libpmem) - libpmem_cflags=$($pkg_config --cflags libpmem) - else - if test "$libpmem" = "yes" ; then - feature_not_found "libpmem" "Install nvml or pmdk" - fi - libpmem="no" - fi -fi - -########################################## -# check for libdaxctl - -if test "$libdaxctl" != "no"; then - if $pkg_config --atleast-version=57 "libdaxctl"; then - libdaxctl="yes" - libdaxctl_libs=$($pkg_config --libs libdaxctl) - libdaxctl_cflags=$($pkg_config --cflags libdaxctl) - else - if test "$libdaxctl" = "yes" ; then - feature_not_found "libdaxctl" "Install libdaxctl" - fi - libdaxctl="no" - fi -fi - ########################################## # check for slirp case "$slirp" in auto | enabled | internal) # Simpler to always update submodule, even if not needed. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} slirp" - fi + git_submodules="${git_submodules} slirp" ;; esac +# Check for slirp smbd dupport +: ${smbd=${SMBD-/usr/sbin/smbd}} +if test "$slirp_smbd" != "no" ; then + if test "$mingw32" = "yes" ; then + if test "$slirp_smbd" = "yes" ; then + error_exit "Host smbd not supported on this platform." + fi + slirp_smbd=no + else + slirp_smbd=yes + fi +fi + ########################################## # check for usable __NR_keyctl syscall @@ -5463,11 +4460,6 @@ if test "$mingw32" = "yes" ; then done fi -# We can only support ivshmem if we have eventfd -if [ "$eventfd" = "yes" ]; then - ivshmem=yes -fi - # Probe for guest agent support/options if [ "$guest_agent" != "no" ]; then @@ -5514,15 +4506,20 @@ if { test "$cpu" = "i386" || test "$cpu" = "x86_64"; } && \ fi # Only build s390-ccw bios if we're on s390x and the compiler has -march=z900 +# or -march=z10 (which is the lowest architecture level that Clang supports) if test "$cpu" = "s390x" ; then write_c_skeleton - if compile_prog "-march=z900" ""; then + compile_prog "-march=z900" "" + has_z900=$? + if [ $has_z900 = 0 ] || compile_object "-march=z10 -msoft-float -Werror"; then + if [ $has_z900 != 0 ]; then + echo "WARNING: Your compiler does not support the z900!" + echo " The s390-ccw bios will only work with guest CPUs >= z10." + fi roms="$roms s390-ccw" # SLOF is required for building the s390-ccw firmware on s390x, # since it is using the libnet code from SLOF for network booting. - if test "$git_submodules_action" != "ignore"; then - git_submodules="${git_submodules} roms/SLOF" - fi + git_submodules="${git_submodules} roms/SLOF" fi fi @@ -5627,7 +4624,10 @@ fi if test "$guest_agent" = "yes" ; then echo "CONFIG_GUEST_AGENT=y" >> $config_host_mak fi -echo "CONFIG_SMBD_COMMAND=\"$smbd\"" >> $config_host_mak +if test "$slirp_smbd" = "yes" ; then + echo "CONFIG_SLIRP_SMBD=y" >> $config_host_mak + echo "CONFIG_SMBD_COMMAND=\"$smbd\"" >> $config_host_mak +fi if test "$vde" = "yes" ; then echo "CONFIG_VDE=y" >> $config_host_mak echo "VDE_LIBS=$vde_libs" >> $config_host_mak @@ -5668,6 +4668,9 @@ if test "$audio_win_int" = "yes" ; then fi echo "CONFIG_BDRV_RW_WHITELIST=$block_drv_rw_whitelist" >> $config_host_mak echo "CONFIG_BDRV_RO_WHITELIST=$block_drv_ro_whitelist" >> $config_host_mak +if test "$block_drv_whitelist_tools" = "yes" ; then + echo "CONFIG_BDRV_WHITELIST_TOOLS=y" >> $config_host_mak +fi if test "$xfs" = "yes" ; then echo "CONFIG_XFS=y" >> $config_host_mak fi @@ -5684,134 +4687,18 @@ fi if test "$module_upgrades" = "yes"; then echo "CONFIG_MODULE_UPGRADES=y" >> $config_host_mak fi -if test "$pipe2" = "yes" ; then - echo "CONFIG_PIPE2=y" >> $config_host_mak -fi -if test "$accept4" = "yes" ; then - echo "CONFIG_ACCEPT4=y" >> $config_host_mak -fi -if test "$splice" = "yes" ; then - echo "CONFIG_SPLICE=y" >> $config_host_mak -fi -if test "$eventfd" = "yes" ; then - echo "CONFIG_EVENTFD=y" >> $config_host_mak -fi -if test "$memfd" = "yes" ; then - echo "CONFIG_MEMFD=y" >> $config_host_mak -fi if test "$have_usbfs" = "yes" ; then echo "CONFIG_USBFS=y" >> $config_host_mak fi -if test "$fallocate" = "yes" ; then - echo "CONFIG_FALLOCATE=y" >> $config_host_mak -fi -if test "$fallocate_punch_hole" = "yes" ; then - echo "CONFIG_FALLOCATE_PUNCH_HOLE=y" >> $config_host_mak -fi -if test "$fallocate_zero_range" = "yes" ; then - echo "CONFIG_FALLOCATE_ZERO_RANGE=y" >> $config_host_mak -fi -if test "$posix_fallocate" = "yes" ; then - echo "CONFIG_POSIX_FALLOCATE=y" >> $config_host_mak -fi -if test "$sync_file_range" = "yes" ; then - echo "CONFIG_SYNC_FILE_RANGE=y" >> $config_host_mak -fi -if test "$fiemap" = "yes" ; then - echo "CONFIG_FIEMAP=y" >> $config_host_mak -fi -if test "$dup3" = "yes" ; then - echo "CONFIG_DUP3=y" >> $config_host_mak -fi -if test "$ppoll" = "yes" ; then - echo "CONFIG_PPOLL=y" >> $config_host_mak -fi -if test "$prctl_pr_set_timerslack" = "yes" ; then - echo "CONFIG_PRCTL_PR_SET_TIMERSLACK=y" >> $config_host_mak -fi -if test "$epoll" = "yes" ; then - echo "CONFIG_EPOLL=y" >> $config_host_mak -fi -if test "$epoll_create1" = "yes" ; then - echo "CONFIG_EPOLL_CREATE1=y" >> $config_host_mak -fi -if test "$sendfile" = "yes" ; then - echo "CONFIG_SENDFILE=y" >> $config_host_mak -fi -if test "$timerfd" = "yes" ; then - echo "CONFIG_TIMERFD=y" >> $config_host_mak -fi -if test "$setns" = "yes" ; then - echo "CONFIG_SETNS=y" >> $config_host_mak -fi -if test "$clock_adjtime" = "yes" ; then - echo "CONFIG_CLOCK_ADJTIME=y" >> $config_host_mak -fi -if test "$syncfs" = "yes" ; then - echo "CONFIG_SYNCFS=y" >> $config_host_mak -fi -if test "$inotify" = "yes" ; then - echo "CONFIG_INOTIFY=y" >> $config_host_mak -fi -if test "$inotify1" = "yes" ; then - echo "CONFIG_INOTIFY1=y" >> $config_host_mak -fi -if test "$sem_timedwait" = "yes" ; then - echo "CONFIG_SEM_TIMEDWAIT=y" >> $config_host_mak -fi -if test "$strchrnul" = "yes" ; then - echo "HAVE_STRCHRNUL=y" >> $config_host_mak -fi -if test "$st_atim" = "yes" ; then - echo "HAVE_STRUCT_STAT_ST_ATIM=y" >> $config_host_mak -fi -if test "$byteswap_h" = "yes" ; then - echo "CONFIG_BYTESWAP_H=y" >> $config_host_mak -fi -if test "$bswap_h" = "yes" ; then - echo "CONFIG_MACHINE_BSWAP_H=y" >> $config_host_mak -fi if test "$gio" = "yes" ; then echo "CONFIG_GIO=y" >> $config_host_mak echo "GIO_CFLAGS=$gio_cflags" >> $config_host_mak echo "GIO_LIBS=$gio_libs" >> $config_host_mak +fi +if test "$gdbus_codegen" != "" ; then echo "GDBUS_CODEGEN=$gdbus_codegen" >> $config_host_mak fi echo "CONFIG_TLS_PRIORITY=\"$tls_priority\"" >> $config_host_mak -if test "$gnutls" = "yes" ; then - echo "CONFIG_GNUTLS=y" >> $config_host_mak - echo "GNUTLS_CFLAGS=$gnutls_cflags" >> $config_host_mak - echo "GNUTLS_LIBS=$gnutls_libs" >> $config_host_mak -fi -if test "$gcrypt" = "yes" ; then - echo "CONFIG_GCRYPT=y" >> $config_host_mak - if test "$gcrypt_hmac" = "yes" ; then - echo "CONFIG_GCRYPT_HMAC=y" >> $config_host_mak - fi - echo "GCRYPT_CFLAGS=$gcrypt_cflags" >> $config_host_mak - echo "GCRYPT_LIBS=$gcrypt_libs" >> $config_host_mak -fi -if test "$nettle" = "yes" ; then - echo "CONFIG_NETTLE=y" >> $config_host_mak - echo "CONFIG_NETTLE_VERSION_MAJOR=${nettle_version%%.*}" >> $config_host_mak - echo "NETTLE_CFLAGS=$nettle_cflags" >> $config_host_mak - echo "NETTLE_LIBS=$nettle_libs" >> $config_host_mak -fi -if test "$qemu_private_xts" = "yes" ; then - echo "CONFIG_QEMU_PRIVATE_XTS=y" >> $config_host_mak -fi -if test "$tasn1" = "yes" ; then - echo "CONFIG_TASN1=y" >> $config_host_mak -fi -if test "$auth_pam" = "yes" ; then - echo "CONFIG_AUTH_PAM=y" >> $config_host_mak -fi -if test "$have_broken_size_max" = "yes" ; then - echo "HAVE_BROKEN_SIZE_MAX=y" >> $config_host_mak -fi -if test "$have_openpty" = "yes" ; then - echo "HAVE_OPENPTY=y" >> $config_host_mak -fi # Work around a system header bug with some kernel/XFS header # versions where they both try to define 'struct fsxattr': @@ -5820,19 +4707,6 @@ fi if test "$have_fsxattr" = "yes" ; then echo "HAVE_FSXATTR=y" >> $config_host_mak fi -if test "$have_copy_file_range" = "yes" ; then - echo "HAVE_COPY_FILE_RANGE=y" >> $config_host_mak -fi -if test "$vte" = "yes" ; then - echo "CONFIG_VTE=y" >> $config_host_mak - echo "VTE_CFLAGS=$vte_cflags" >> $config_host_mak - echo "VTE_LIBS=$vte_libs" >> $config_host_mak -fi -if test "$virglrenderer" = "yes" ; then - echo "CONFIG_VIRGL=y" >> $config_host_mak - echo "VIRGL_CFLAGS=$virgl_cflags" >> $config_host_mak - echo "VIRGL_LIBS=$virgl_libs" >> $config_host_mak -fi if test "$xen" = "enabled" ; then echo "CONFIG_XEN_BACKEND=y" >> $config_host_mak echo "CONFIG_XEN_CTRL_INTERFACE_VERSION=$xen_ctrl_version" >> $config_host_mak @@ -5842,11 +4716,6 @@ fi if test "$linux_aio" = "yes" ; then echo "CONFIG_LINUX_AIO=y" >> $config_host_mak fi -if test "$linux_io_uring" = "yes" ; then - echo "CONFIG_LINUX_IO_URING=y" >> $config_host_mak - echo "LINUX_IO_URING_CFLAGS=$linux_io_uring_cflags" >> $config_host_mak - echo "LINUX_IO_URING_LIBS=$linux_io_uring_libs" >> $config_host_mak -fi if test "$vhost_scsi" = "yes" ; then echo "CONFIG_VHOST_SCSI=y" >> $config_host_mak fi @@ -5886,48 +4755,20 @@ fi if test "$membarrier" = "yes" ; then echo "CONFIG_MEMBARRIER=y" >> $config_host_mak fi -if test "$signalfd" = "yes" ; then - echo "CONFIG_SIGNALFD=y" >> $config_host_mak +if test "$tcg" = "enabled" -a "$tcg_interpreter" = "true" ; then + echo "CONFIG_TCG_INTERPRETER=y" >> $config_host_mak fi -if test "$optreset" = "yes" ; then - echo "HAVE_OPTRESET=y" >> $config_host_mak -fi -if test "$fdatasync" = "yes" ; then - echo "CONFIG_FDATASYNC=y" >> $config_host_mak -fi -if test "$madvise" = "yes" ; then - echo "CONFIG_MADVISE=y" >> $config_host_mak -fi -if test "$posix_madvise" = "yes" ; then - echo "CONFIG_POSIX_MADVISE=y" >> $config_host_mak -fi -if test "$posix_memalign" = "yes" ; then - echo "CONFIG_POSIX_MEMALIGN=y" >> $config_host_mak + +if test "$spice_protocol" = "yes" ; then + echo "CONFIG_SPICE_PROTOCOL=y" >> $config_host_mak + echo "SPICE_PROTOCOL_CFLAGS=$spice_protocol_cflags" >> $config_host_mak fi if test "$spice" = "yes" ; then echo "CONFIG_SPICE=y" >> $config_host_mak - echo "SPICE_CFLAGS=$spice_cflags" >> $config_host_mak + echo "SPICE_CFLAGS=$spice_cflags $spice_protocol_cflags" >> $config_host_mak echo "SPICE_LIBS=$spice_libs" >> $config_host_mak fi -if test "$smartcard" = "yes" ; then - echo "CONFIG_SMARTCARD=y" >> $config_host_mak - echo "SMARTCARD_CFLAGS=$libcacard_cflags" >> $config_host_mak - echo "SMARTCARD_LIBS=$libcacard_libs" >> $config_host_mak -fi - -if test "$libusb" = "yes" ; then - echo "CONFIG_USB_LIBUSB=y" >> $config_host_mak - echo "LIBUSB_CFLAGS=$libusb_cflags" >> $config_host_mak - echo "LIBUSB_LIBS=$libusb_libs" >> $config_host_mak -fi - -if test "$usb_redir" = "yes" ; then - echo "CONFIG_USB_REDIR=y" >> $config_host_mak - echo "USB_REDIR_CFLAGS=$usb_redir_cflags" >> $config_host_mak - echo "USB_REDIR_LIBS=$usb_redir_libs" >> $config_host_mak -fi - if test "$opengl" = "yes" ; then echo "CONFIG_OPENGL=y" >> $config_host_mak echo "OPENGL_CFLAGS=$opengl_cflags" >> $config_host_mak @@ -5973,18 +4814,6 @@ if test "$crypto_afalg" = "yes" ; then echo "CONFIG_AF_ALG=y" >> $config_host_mak fi -if test "$open_by_handle_at" = "yes" ; then - echo "CONFIG_OPEN_BY_HANDLE=y" >> $config_host_mak -fi - -if test "$linux_magic_h" = "yes" ; then - echo "CONFIG_LINUX_MAGIC_H=y" >> $config_host_mak -fi - -if test "$valgrind_h" = "yes" ; then - echo "CONFIG_VALGRIND_H=y" >> $config_host_mak -fi - if test "$have_asan_iface_fiber" = "yes" ; then echo "CONFIG_ASAN_IFACE_FIBER=y" >> $config_host_mak fi @@ -5993,10 +4822,6 @@ if test "$have_tsan" = "yes" && test "$have_tsan_iface_fiber" = "yes" ; then echo "CONFIG_TSAN=y" >> $config_host_mak fi -if test "$has_environ" = "yes" ; then - echo "CONFIG_HAS_ENVIRON=y" >> $config_host_mak -fi - if test "$cpuid_h" = "yes" ; then echo "CONFIG_CPUID_H=y" >> $config_host_mak fi @@ -6050,7 +4875,6 @@ fi if have_backend "ust"; then echo "CONFIG_TRACE_UST=y" >> $config_host_mak echo "LTTNG_UST_LIBS=$lttng_ust_libs" >> $config_host_mak - echo "URCU_BP_LIBS=$urcu_bp_libs" >> $config_host_mak fi if have_backend "dtrace"; then echo "CONFIG_TRACE_DTRACE=y" >> $config_host_mak @@ -6083,10 +4907,6 @@ if test "$pvrdma" = "yes" ; then echo "CONFIG_PVRDMA=y" >> $config_host_mak fi -if test "$have_rtnetlink" = "yes" ; then - echo "CONFIG_RTNETLINK=y" >> $config_host_mak -fi - echo "XEMU_GTK_CFLAGS=$xemu_gtk_cflags" >> $config_host_mak echo "XEMU_GTK_LIBS=$xemu_gtk_libs" >> $config_host_mak @@ -6099,12 +4919,6 @@ echo "LIBPCAP_LIBS=$libpcap_libs" >> $config_host_mak echo "LIBSAMPLERATE_CFLAGS=$libsamplerate_cflags" >> $config_host_mak echo "LIBSAMPLERATE_LIBS=$libsamplerate_libs" >> $config_host_mak -if test "$libxml2" = "yes" ; then - echo "CONFIG_LIBXML2=y" >> $config_host_mak - echo "LIBXML2_CFLAGS=$libxml2_cflags" >> $config_host_mak - echo "LIBXML2_LIBS=$libxml2_libs" >> $config_host_mak -fi - if test "$replication" = "yes" ; then echo "CONFIG_REPLICATION=y" >> $config_host_mak fi @@ -6113,23 +4927,6 @@ if test "$have_af_vsock" = "yes" ; then echo "CONFIG_AF_VSOCK=y" >> $config_host_mak fi -if test "$have_sysmacros" = "yes" ; then - echo "CONFIG_SYSMACROS=y" >> $config_host_mak -fi - -if test "$have_static_assert" = "yes" ; then - echo "CONFIG_STATIC_ASSERT=y" >> $config_host_mak -fi - -if test "$have_utmpx" = "yes" ; then - echo "HAVE_UTMPX=y" >> $config_host_mak -fi -if test "$have_getrandom" = "yes" ; then - echo "CONFIG_GETRANDOM=y" >> $config_host_mak -fi -if test "$ivshmem" = "yes" ; then - echo "CONFIG_IVSHMEM=y" >> $config_host_mak -fi if test "$debug_mutex" = "yes" ; then echo "CONFIG_DEBUG_MUTEX=y" >> $config_host_mak fi @@ -6147,17 +4944,6 @@ elif test "$pthread_setname_np_wo_tid" = "yes" ; then echo "CONFIG_PTHREAD_SETNAME_NP_WO_TID=y" >> $config_host_mak fi -if test "$libpmem" = "yes" ; then - echo "CONFIG_LIBPMEM=y" >> $config_host_mak - echo "LIBPMEM_LIBS=$libpmem_libs" >> $config_host_mak - echo "LIBPMEM_CFLAGS=$libpmem_cflags" >> $config_host_mak -fi - -if test "$libdaxctl" = "yes" ; then - echo "CONFIG_LIBDAXCTL=y" >> $config_host_mak - echo "LIBDAXCTL_LIBS=$libdaxctl_libs" >> $config_host_mak -fi - if test "$bochs" = "yes" ; then echo "CONFIG_BOCHS=y" >> $config_host_mak fi @@ -6182,10 +4968,6 @@ fi if test "$parallels" = "yes" ; then echo "CONFIG_PARALLELS=y" >> $config_host_mak fi -if test "$sheepdog" = "yes" ; then - add_to deprecated_features "sheepdog" - echo "CONFIG_SHEEPDOG=y" >> $config_host_mak -fi if test "$have_mlockall" = "yes" ; then echo "HAVE_MLOCKALL=y" >> $config_host_mak fi @@ -6248,22 +5030,16 @@ echo "GENISOIMAGE=$genisoimage" >> $config_host_mak echo "MESON=$meson" >> $config_host_mak echo "NINJA=$ninja" >> $config_host_mak echo "CC=$cc" >> $config_host_mak +echo "HOST_CC=$host_cc" >> $config_host_mak if $iasl -h > /dev/null 2>&1; then echo "CONFIG_IASL=$iasl" >> $config_host_mak fi -echo "CXX=$cxx" >> $config_host_mak -echo "OBJCC=$objcc" >> $config_host_mak echo "AR=$ar" >> $config_host_mak -echo "ARFLAGS=$ARFLAGS" >> $config_host_mak echo "AS=$as" >> $config_host_mak echo "CCAS=$ccas" >> $config_host_mak echo "CPP=$cpp" >> $config_host_mak echo "OBJCOPY=$objcopy" >> $config_host_mak echo "LD=$ld" >> $config_host_mak -echo "RANLIB=$ranlib" >> $config_host_mak -echo "NM=$nm" >> $config_host_mak -echo "PKG_CONFIG=$pkg_config_exe" >> $config_host_mak -echo "WINDRES=$windres" >> $config_host_mak echo "CFLAGS_NOPIE=$CFLAGS_NOPIE" >> $config_host_mak echo "QEMU_CFLAGS=$QEMU_CFLAGS" >> $config_host_mak echo "QEMU_CXXFLAGS=$QEMU_CXXFLAGS" >> $config_host_mak @@ -6274,8 +5050,6 @@ echo "LD_I386_EMULATION=$ld_i386_emulation" >> $config_host_mak echo "EXESUF=$EXESUF" >> $config_host_mak echo "HOST_DSOSUF=$HOST_DSOSUF" >> $config_host_mak echo "LIBS_QGA=$libs_qga" >> $config_host_mak -echo "TASN1_LIBS=$tasn1_libs" >> $config_host_mak -echo "TASN1_CFLAGS=$tasn1_cflags" >> $config_host_mak if test "$gcov" = "yes" ; then echo "CONFIG_GCOV=y" >> $config_host_mak fi @@ -6360,14 +5134,13 @@ fi # UNLINK is used to remove symlinks from older development versions # that might get into the way when doing "git update" without doing # a "make distclean" in between. -DIRS="tests tests/tcg tests/tcg/lm32 tests/qapi-schema tests/qtest/libqos" +DIRS="tests tests/tcg tests/qapi-schema tests/qtest/libqos" DIRS="$DIRS tests/qtest tests/qemu-iotests tests/vm tests/fp tests/qgraph" DIRS="$DIRS docs docs/interop fsdev scsi" DIRS="$DIRS pc-bios/optionrom pc-bios/s390-ccw" DIRS="$DIRS roms/seabios" DIRS="$DIRS contrib/plugins/" LINKS="Makefile" -LINKS="$LINKS tests/tcg/lm32/Makefile" LINKS="$LINKS tests/tcg/Makefile.target" LINKS="$LINKS pc-bios/optionrom/Makefile" LINKS="$LINKS pc-bios/s390-ccw/Makefile" @@ -6428,33 +5201,40 @@ for rom in seabios; do done if test "$skip_meson" = no; then -cross="config-meson.cross.new" -meson_quote() { + cross="config-meson.cross.new" + meson_quote() { echo "'$(echo $* | sed "s/ /','/g")'" -} + } -echo "# Automatically generated by configure - do not modify" > $cross -echo "[properties]" >> $cross -test -z "$cxx" && echo "link_language = 'c'" >> $cross -echo "[built-in options]" >> $cross -echo "c_args = [${CFLAGS:+$(meson_quote $CFLAGS)}]" >> $cross -echo "cpp_args = [${CXXFLAGS:+$(meson_quote $CXXFLAGS)}]" >> $cross -echo "c_link_args = [${LDFLAGS:+$(meson_quote $LDFLAGS)}]" >> $cross -echo "cpp_link_args = [${LDFLAGS:+$(meson_quote $LDFLAGS)}]" >> $cross -echo "[binaries]" >> $cross -echo "c = [$(meson_quote $cc)]" >> $cross -test -n "$cxx" && echo "cpp = [$(meson_quote $cxx)]" >> $cross -test -n "$objcc" && echo "objc = [$(meson_quote $objcc)]" >> $cross -echo "ar = [$(meson_quote $ar)]" >> $cross -echo "nm = [$(meson_quote $nm)]" >> $cross -echo "pkgconfig = [$(meson_quote $pkg_config_exe)]" >> $cross -echo "ranlib = [$(meson_quote $ranlib)]" >> $cross -if has $sdl2_config; then - echo "sdl2-config = [$(meson_quote $sdl2_config)]" >> $cross -fi -echo "strip = [$(meson_quote $strip)]" >> $cross -echo "windres = [$(meson_quote $windres)]" >> $cross -if test "$cross_compile" = "yes"; then + echo "# Automatically generated by configure - do not modify" > $cross + echo "[properties]" >> $cross + + # unroll any custom device configs + for a in $device_archs; do + eval "c=\$devices_${a}" + echo "${a}-softmmu = '$c'" >> $cross + done + + test -z "$cxx" && echo "link_language = 'c'" >> $cross + echo "[built-in options]" >> $cross + echo "c_args = [${CFLAGS:+$(meson_quote $CFLAGS)}]" >> $cross + echo "cpp_args = [${CXXFLAGS:+$(meson_quote $CXXFLAGS)}]" >> $cross + echo "c_link_args = [${LDFLAGS:+$(meson_quote $LDFLAGS)}]" >> $cross + echo "cpp_link_args = [${LDFLAGS:+$(meson_quote $LDFLAGS)}]" >> $cross + echo "[binaries]" >> $cross + echo "c = [$(meson_quote $cc)]" >> $cross + test -n "$cxx" && echo "cpp = [$(meson_quote $cxx)]" >> $cross + test -n "$objcc" && echo "objc = [$(meson_quote $objcc)]" >> $cross + echo "ar = [$(meson_quote $ar)]" >> $cross + echo "nm = [$(meson_quote $nm)]" >> $cross + echo "pkgconfig = [$(meson_quote $pkg_config_exe)]" >> $cross + echo "ranlib = [$(meson_quote $ranlib)]" >> $cross + if has $sdl2_config; then + echo "sdl2-config = [$(meson_quote $sdl2_config)]" >> $cross + fi + echo "strip = [$(meson_quote $strip)]" >> $cross + echo "windres = [$(meson_quote $windres)]" >> $cross + if test "$cross_compile" = "yes"; then cross_arg="--cross-file config-meson.cross" echo "[host_machine]" >> $cross if test "$mingw32" = "yes" ; then @@ -6470,7 +5250,7 @@ if test "$cross_compile" = "yes"; then i386) echo "cpu_family = 'x86'" >> $cross ;; - x86_64) + x86_64|x32) echo "cpu_family = 'x86_64'" >> $cross ;; ppc64le) @@ -6486,17 +5266,17 @@ if test "$cross_compile" = "yes"; then else echo "endian = 'little'" >> $cross fi -else + else cross_arg="--native-file config-meson.cross" -fi -mv $cross config-meson.cross + fi + mv $cross config-meson.cross -rm -rf meson-private meson-info meson-logs -unset staticpic -if ! version_ge "$($meson --version)" 0.56.0; then - staticpic=$(if test "$pie" = yes; then echo true; else echo false; fi) -fi -NINJA=$ninja $meson setup \ + rm -rf meson-private meson-info meson-logs + unset staticpic + if ! version_ge "$($meson --version)" 0.56.0; then + staticpic=$(if test "$pie" = yes; then echo true; else echo false; fi) + fi + NINJA=$ninja $meson setup \ --prefix "$prefix" \ --libdir "$libdir" \ --libexecdir "$libexecdir" \ @@ -6519,36 +5299,59 @@ NINJA=$ninja $meson setup \ -Db_coverage=$(if test "$gcov" = yes; then echo true; else echo false; fi) \ -Db_lto=$lto -Dcfi=$cfi -Dcfi_debug=$cfi_debug \ -Dmalloc=$malloc -Dmalloc_trim=$malloc_trim -Dsparse=$sparse \ - -Dkvm=$kvm -Dhax=$hax -Dwhpx=$whpx -Dhvf=$hvf \ + -Dkvm=$kvm -Dhax=$hax -Dwhpx=$whpx -Dhvf=$hvf -Dnvmm=$nvmm \ -Dxen=$xen -Dxen_pci_passthrough=$xen_pci_passthrough -Dtcg=$tcg \ -Dcocoa=$cocoa -Dgtk=$gtk -Dmpath=$mpath -Dsdl=$sdl -Dsdl_image=$sdl_image \ + -Dlibusb=$libusb -Dsmartcard=$smartcard -Dusb_redir=$usb_redir -Dvte=$vte \ -Dvnc=$vnc -Dvnc_sasl=$vnc_sasl -Dvnc_jpeg=$vnc_jpeg -Dvnc_png=$vnc_png \ -Dgettext=$gettext -Dxkbcommon=$xkbcommon -Du2f=$u2f -Dvirtiofsd=$virtiofsd \ -Dcapstone=$capstone -Dslirp=$slirp -Dfdt=$fdt -Dbrlapi=$brlapi \ -Dcurl=$curl -Dglusterfs=$glusterfs -Dbzip2=$bzip2 -Dlibiscsi=$libiscsi \ -Dlibnfs=$libnfs -Diconv=$iconv -Dcurses=$curses -Dlibudev=$libudev\ - -Drbd=$rbd -Dlzo=$lzo -Dsnappy=$snappy -Dlzfse=$lzfse \ + -Drbd=$rbd -Dlzo=$lzo -Dsnappy=$snappy -Dlzfse=$lzfse -Dlibxml2=$libxml2 \ + -Dlibdaxctl=$libdaxctl -Dlibpmem=$libpmem -Dlinux_io_uring=$linux_io_uring \ + -Dgnutls=$gnutls -Dnettle=$nettle -Dgcrypt=$gcrypt -Dauth_pam=$auth_pam \ -Dzstd=$zstd -Dseccomp=$seccomp -Dvirtfs=$virtfs -Dcap_ng=$cap_ng \ - -Dattr=$attr -Ddefault_devices=$default_devices \ + -Dattr=$attr -Ddefault_devices=$default_devices -Dvirglrenderer=$virglrenderer \ -Ddocs=$docs -Dsphinx_build=$sphinx_build -Dinstall_blobs=$blobs \ -Dvhost_user_blk_server=$vhost_user_blk_server -Dmultiprocess=$multiprocess \ - -Dfuse=$fuse -Dfuse_lseek=$fuse_lseek -Dguest_agent_msi=$guest_agent_msi \ - $(if test "$default_features" = no; then echo "-Dauto_features=disabled"; fi) \ + -Dfuse=$fuse -Dfuse_lseek=$fuse_lseek -Dguest_agent_msi=$guest_agent_msi -Dbpf=$bpf\ + $(if test "$default_feature" = no; then echo "-Dauto_features=disabled"; fi) \ -Dtcg_interpreter=$tcg_interpreter \ $cross_arg \ "$PWD" "$source_path" -if test "$?" -ne 0 ; then - error_exit "meson setup failed" -fi + if test "$?" -ne 0 ; then + error_exit "meson setup failed" + fi +else + if test -f meson-private/cmd_line.txt; then + # Adjust old command line options whose type was changed + # Avoids having to use "setup --wipe" when Meson is upgraded + perl -i -ne ' + s/^gettext = true$/gettext = auto/; + s/^gettext = false$/gettext = disabled/; + print;' meson-private/cmd_line.txt + fi fi if test -n "${deprecated_features}"; then echo "Warning, deprecated features enabled." - echo "Please see docs/system/deprecated.rst" + echo "Please see docs/about/deprecated.rst" echo " features: ${deprecated_features}" fi +# Create list of config switches that should be poisoned in common code... +# but filter out CONFIG_TCG and CONFIG_USER_ONLY which are special. +target_configs_h=$(ls *-config-devices.h *-config-target.h 2>/dev/null) +if test -n "$target_configs_h" ; then + sed -n -e '/CONFIG_TCG/d' -e '/CONFIG_USER_ONLY/d' \ + -e '/^#define / { s///; s/ .*//; s/^/#pragma GCC poison /p; }' \ + $target_configs_h | sort -u > config-poison.h +else + :> config-poison.h +fi + # Save the configure command line for later reuse. cat <config.status #!/bin/sh diff --git a/contrib/gitdm/aliases b/contrib/gitdm/aliases index c1e744312f..4792413ce7 100644 --- a/contrib/gitdm/aliases +++ b/contrib/gitdm/aliases @@ -31,6 +31,12 @@ pbrook@c046a42c-6fe2-441c-8c8c-71466251a162 paul@codesourcery.com ths@c046a42c-6fe2-441c-8c8c-71466251a162 ths@networkno.de malc@c046a42c-6fe2-441c-8c8c-71466251a162 av1474@comtv.ru +# canonical emails +liq3ea@163.com liq3ea@gmail.com + +# some broken tags +yuval.shaia.ml.gmail.com yuval.shaia.ml@gmail.com + # There is also a: # (no author) <(no author)@c046a42c-6fe2-441c-8c8c-71466251a162> # for the cvs2svn initialization commit e63c3dc74bf. diff --git a/contrib/gitdm/domain-map b/contrib/gitdm/domain-map index 0074da618f..2800d9f986 100644 --- a/contrib/gitdm/domain-map +++ b/contrib/gitdm/domain-map @@ -9,6 +9,8 @@ baidu.com Baidu bytedance.com ByteDance cmss.chinamobile.com China Mobile citrix.com Citrix +crudebyte.com Crudebyte +eldorado.org.br Instituto de Pesquisas Eldorado fujitsu.com Fujitsu google.com Google greensocs.com GreenSocs @@ -17,20 +19,25 @@ ibm.com IBM igalia.com Igalia intel.com Intel linaro.org Linaro +lwn.net LWN microsoft.com Microsoft +mvista.com MontaVista nokia.com Nokia nuviainc.com NUVIA +nvidia.com NVIDIA oracle.com Oracle proxmox.com Proxmox quicinc.com Qualcomm Innovation Center redhat.com Red Hat rt-rk.com RT-RK +samsung.com Samsung siemens.com Siemens sifive.com SiFive suse.com SUSE suse.de SUSE virtuozzo.com Virtuozzo wdc.com Western Digital +windriver.com Wind River xilinx.com Xilinx yadro.com YADRO yandex-team.ru Yandex diff --git a/contrib/gitdm/group-map-academics b/contrib/gitdm/group-map-academics index bf3c894821..44745ca85b 100644 --- a/contrib/gitdm/group-map-academics +++ b/contrib/gitdm/group-map-academics @@ -16,3 +16,6 @@ cota@braap.org uni-paderborn.de edu edu.cn + +# Boston University +bu.edu diff --git a/contrib/gitdm/group-map-individuals b/contrib/gitdm/group-map-individuals index 36bbb77c39..f816aa8770 100644 --- a/contrib/gitdm/group-map-individuals +++ b/contrib/gitdm/group-map-individuals @@ -29,3 +29,8 @@ mrolnik@gmail.com huth@tuxfamily.org jhogan@kernel.org atar4qemu@gmail.com +minwoo.im.dev@gmail.com +bmeng.cn@gmail.com +liq3ea@gmail.com +chetan4windows@gmail.com +akihiko.odaki@gmail.com diff --git a/contrib/gitdm/group-map-interns b/contrib/gitdm/group-map-interns new file mode 100644 index 0000000000..fe33a3231e --- /dev/null +++ b/contrib/gitdm/group-map-interns @@ -0,0 +1,13 @@ +# +# Group together everyone working as an intern via one of the various +# outreach programs. +# + +# GSoC 2020 Virtual FIDO/U2F security key +cesar.belley@lse.epita.fr + +# GSoC 2020 TCG performance +ahmedkhaledkaraman@gmail.com + +# GSoC 2021 TCG plugins +ma.mandourr@gmail.com diff --git a/contrib/gitdm/group-map-netflix b/contrib/gitdm/group-map-netflix new file mode 100644 index 0000000000..468f95dcb2 --- /dev/null +++ b/contrib/gitdm/group-map-netflix @@ -0,0 +1,5 @@ +# +# Netflix contributors using their personal emails +# + +imp@bsdimp.com diff --git a/contrib/gitdm/group-map-robots b/contrib/gitdm/group-map-robots new file mode 100644 index 0000000000..ffd956c2eb --- /dev/null +++ b/contrib/gitdm/group-map-robots @@ -0,0 +1,7 @@ +# +# There are various automatic robots that occasionally scan and report +# bugs. Let's group them together here. +# + +# Euler Robot +euler.robot@huawei.com diff --git a/contrib/plugins/Makefile b/contrib/plugins/Makefile index b9d7935e5e..54ac5ccd9f 100644 --- a/contrib/plugins/Makefile +++ b/contrib/plugins/Makefile @@ -13,18 +13,20 @@ include $(BUILD_DIR)/config-host.mak VPATH += $(SRC_PATH)/contrib/plugins NAMES := +NAMES += execlog NAMES += hotblocks NAMES += hotpages NAMES += howvec NAMES += lockstep NAMES += hwprofile +NAMES += cache SONAMES := $(addsuffix .so,$(addprefix lib,$(NAMES))) # The main QEMU uses Glib extensively so it's perfectly fine to use it # in plugins (which many example do). CFLAGS = $(GLIB_CFLAGS) -CFLAGS += -fPIC +CFLAGS += -fPIC -Wall $(filter -W%, $(QEMU_CFLAGS)) CFLAGS += $(if $(findstring no-psabi,$(QEMU_CFLAGS)),-Wpsabi) CFLAGS += -I$(SRC_PATH)/include/qemu diff --git a/contrib/plugins/cache.c b/contrib/plugins/cache.c new file mode 100644 index 0000000000..066ea6d8ec --- /dev/null +++ b/contrib/plugins/cache.c @@ -0,0 +1,640 @@ +/* + * Copyright (C) 2021, Mahmoud Mandour + * + * License: GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include +#include +#include + +#include + +QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION; + +static enum qemu_plugin_mem_rw rw = QEMU_PLUGIN_MEM_RW; + +static GHashTable *miss_ht; + +static GMutex mtx; +static GRand *rng; + +static int limit; +static bool sys; + +static uint64_t dmem_accesses; +static uint64_t dmisses; + +static uint64_t imem_accesses; +static uint64_t imisses; + +enum EvictionPolicy { + LRU, + FIFO, + RAND, +}; + +enum EvictionPolicy policy; + +/* + * A CacheSet is a set of cache blocks. A memory block that maps to a set can be + * put in any of the blocks inside the set. The number of block per set is + * called the associativity (assoc). + * + * Each block contains the the stored tag and a valid bit. Since this is not + * a functional simulator, the data itself is not stored. We only identify + * whether a block is in the cache or not by searching for its tag. + * + * In order to search for memory data in the cache, the set identifier and tag + * are extracted from the address and the set is probed to see whether a tag + * match occur. + * + * An address is logically divided into three portions: The block offset, + * the set number, and the tag. + * + * The set number is used to identify the set in which the block may exist. + * The tag is compared against all the tags of a set to search for a match. If a + * match is found, then the access is a hit. + * + * The CacheSet also contains bookkeaping information about eviction details. + */ + +typedef struct { + uint64_t tag; + bool valid; +} CacheBlock; + +typedef struct { + CacheBlock *blocks; + uint64_t *lru_priorities; + uint64_t lru_gen_counter; + GQueue *fifo_queue; +} CacheSet; + +typedef struct { + CacheSet *sets; + int num_sets; + int cachesize; + int assoc; + int blksize_shift; + uint64_t set_mask; + uint64_t tag_mask; +} Cache; + +typedef struct { + char *disas_str; + const char *symbol; + uint64_t addr; + uint64_t dmisses; + uint64_t imisses; +} InsnData; + +void (*update_hit)(Cache *cache, int set, int blk); +void (*update_miss)(Cache *cache, int set, int blk); + +void (*metadata_init)(Cache *cache); +void (*metadata_destroy)(Cache *cache); + +Cache *dcache, *icache; + +static int pow_of_two(int num) +{ + g_assert((num & (num - 1)) == 0); + int ret = 0; + while (num /= 2) { + ret++; + } + return ret; +} + +/* + * LRU evection policy: For each set, a generation counter is maintained + * alongside a priority array. + * + * On each set access, the generation counter is incremented. + * + * On a cache hit: The hit-block is assigned the current generation counter, + * indicating that it is the most recently used block. + * + * On a cache miss: The block with the least priority is searched and replaced + * with the newly-cached block, of which the priority is set to the current + * generation number. + */ + +static void lru_priorities_init(Cache *cache) +{ + int i; + + for (i = 0; i < cache->num_sets; i++) { + cache->sets[i].lru_priorities = g_new0(uint64_t, cache->assoc); + cache->sets[i].lru_gen_counter = 0; + } +} + +static void lru_update_blk(Cache *cache, int set_idx, int blk_idx) +{ + CacheSet *set = &cache->sets[set_idx]; + set->lru_priorities[blk_idx] = cache->sets[set_idx].lru_gen_counter; + set->lru_gen_counter++; +} + +static int lru_get_lru_block(Cache *cache, int set_idx) +{ + int i, min_idx, min_priority; + + min_priority = cache->sets[set_idx].lru_priorities[0]; + min_idx = 0; + + for (i = 1; i < cache->assoc; i++) { + if (cache->sets[set_idx].lru_priorities[i] < min_priority) { + min_priority = cache->sets[set_idx].lru_priorities[i]; + min_idx = i; + } + } + return min_idx; +} + +static void lru_priorities_destroy(Cache *cache) +{ + int i; + + for (i = 0; i < cache->num_sets; i++) { + g_free(cache->sets[i].lru_priorities); + } +} + +/* + * FIFO eviction policy: a FIFO queue is maintained for each CacheSet that + * stores accesses to the cache. + * + * On a compulsory miss: The block index is enqueued to the fifo_queue to + * indicate that it's the latest cached block. + * + * On a conflict miss: The first-in block is removed from the cache and the new + * block is put in its place and enqueued to the FIFO queue. + */ + +static void fifo_init(Cache *cache) +{ + int i; + + for (i = 0; i < cache->num_sets; i++) { + cache->sets[i].fifo_queue = g_queue_new(); + } +} + +static int fifo_get_first_block(Cache *cache, int set) +{ + GQueue *q = cache->sets[set].fifo_queue; + return GPOINTER_TO_INT(g_queue_pop_tail(q)); +} + +static void fifo_update_on_miss(Cache *cache, int set, int blk_idx) +{ + GQueue *q = cache->sets[set].fifo_queue; + g_queue_push_head(q, GINT_TO_POINTER(blk_idx)); +} + +static void fifo_destroy(Cache *cache) +{ + int i; + + for (i = 0; i < cache->num_sets; i++) { + g_queue_free(cache->sets[i].fifo_queue); + } +} + +static inline uint64_t extract_tag(Cache *cache, uint64_t addr) +{ + return addr & cache->tag_mask; +} + +static inline uint64_t extract_set(Cache *cache, uint64_t addr) +{ + return (addr & cache->set_mask) >> cache->blksize_shift; +} + +static const char *cache_config_error(int blksize, int assoc, int cachesize) +{ + if (cachesize % blksize != 0) { + return "cache size must be divisible by block size"; + } else if (cachesize % (blksize * assoc) != 0) { + return "cache size must be divisible by set size (assoc * block size)"; + } else { + return NULL; + } +} + +static bool bad_cache_params(int blksize, int assoc, int cachesize) +{ + return (cachesize % blksize) != 0 || (cachesize % (blksize * assoc) != 0); +} + +static Cache *cache_init(int blksize, int assoc, int cachesize) +{ + if (bad_cache_params(blksize, assoc, cachesize)) { + return NULL; + } + + Cache *cache; + int i; + uint64_t blk_mask; + + cache = g_new(Cache, 1); + cache->assoc = assoc; + cache->cachesize = cachesize; + cache->num_sets = cachesize / (blksize * assoc); + cache->sets = g_new(CacheSet, cache->num_sets); + cache->blksize_shift = pow_of_two(blksize); + + for (i = 0; i < cache->num_sets; i++) { + cache->sets[i].blocks = g_new0(CacheBlock, assoc); + } + + blk_mask = blksize - 1; + cache->set_mask = ((cache->num_sets - 1) << cache->blksize_shift); + cache->tag_mask = ~(cache->set_mask | blk_mask); + + if (metadata_init) { + metadata_init(cache); + } + + return cache; +} + +static int get_invalid_block(Cache *cache, uint64_t set) +{ + int i; + + for (i = 0; i < cache->assoc; i++) { + if (!cache->sets[set].blocks[i].valid) { + return i; + } + } + + return -1; +} + +static int get_replaced_block(Cache *cache, int set) +{ + switch (policy) { + case RAND: + return g_rand_int_range(rng, 0, cache->assoc); + case LRU: + return lru_get_lru_block(cache, set); + case FIFO: + return fifo_get_first_block(cache, set); + default: + g_assert_not_reached(); + } +} + +static int in_cache(Cache *cache, uint64_t addr) +{ + int i; + uint64_t tag, set; + + tag = extract_tag(cache, addr); + set = extract_set(cache, addr); + + for (i = 0; i < cache->assoc; i++) { + if (cache->sets[set].blocks[i].tag == tag && + cache->sets[set].blocks[i].valid) { + return i; + } + } + + return -1; +} + +/** + * access_cache(): Simulate a cache access + * @cache: The cache under simulation + * @addr: The address of the requested memory location + * + * Returns true if the requsted data is hit in the cache and false when missed. + * The cache is updated on miss for the next access. + */ +static bool access_cache(Cache *cache, uint64_t addr) +{ + int hit_blk, replaced_blk; + uint64_t tag, set; + + tag = extract_tag(cache, addr); + set = extract_set(cache, addr); + + hit_blk = in_cache(cache, addr); + if (hit_blk != -1) { + if (update_hit) { + update_hit(cache, set, hit_blk); + } + return true; + } + + replaced_blk = get_invalid_block(cache, set); + + if (replaced_blk == -1) { + replaced_blk = get_replaced_block(cache, set); + } + + if (update_miss) { + update_miss(cache, set, replaced_blk); + } + + cache->sets[set].blocks[replaced_blk].tag = tag; + cache->sets[set].blocks[replaced_blk].valid = true; + + return false; +} + +static void vcpu_mem_access(unsigned int vcpu_index, qemu_plugin_meminfo_t info, + uint64_t vaddr, void *userdata) +{ + uint64_t effective_addr; + struct qemu_plugin_hwaddr *hwaddr; + InsnData *insn; + + hwaddr = qemu_plugin_get_hwaddr(info, vaddr); + if (hwaddr && qemu_plugin_hwaddr_is_io(hwaddr)) { + return; + } + + effective_addr = hwaddr ? qemu_plugin_hwaddr_phys_addr(hwaddr) : vaddr; + + g_mutex_lock(&mtx); + if (!access_cache(dcache, effective_addr)) { + insn = (InsnData *) userdata; + insn->dmisses++; + dmisses++; + } + dmem_accesses++; + g_mutex_unlock(&mtx); +} + +static void vcpu_insn_exec(unsigned int vcpu_index, void *userdata) +{ + uint64_t insn_addr; + InsnData *insn; + + g_mutex_lock(&mtx); + insn_addr = ((InsnData *) userdata)->addr; + + if (!access_cache(icache, insn_addr)) { + insn = (InsnData *) userdata; + insn->imisses++; + imisses++; + } + imem_accesses++; + g_mutex_unlock(&mtx); +} + +static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb) +{ + size_t n_insns; + size_t i; + InsnData *data; + + n_insns = qemu_plugin_tb_n_insns(tb); + for (i = 0; i < n_insns; i++) { + struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, i); + uint64_t effective_addr; + + if (sys) { + effective_addr = (uint64_t) qemu_plugin_insn_haddr(insn); + } else { + effective_addr = (uint64_t) qemu_plugin_insn_vaddr(insn); + } + + /* + * Instructions might get translated multiple times, we do not create + * new entries for those instructions. Instead, we fetch the same + * entry from the hash table and register it for the callback again. + */ + g_mutex_lock(&mtx); + data = g_hash_table_lookup(miss_ht, GUINT_TO_POINTER(effective_addr)); + if (data == NULL) { + data = g_new0(InsnData, 1); + data->disas_str = qemu_plugin_insn_disas(insn); + data->symbol = qemu_plugin_insn_symbol(insn); + data->addr = effective_addr; + g_hash_table_insert(miss_ht, GUINT_TO_POINTER(effective_addr), + (gpointer) data); + } + g_mutex_unlock(&mtx); + + qemu_plugin_register_vcpu_mem_cb(insn, vcpu_mem_access, + QEMU_PLUGIN_CB_NO_REGS, + rw, data); + + qemu_plugin_register_vcpu_insn_exec_cb(insn, vcpu_insn_exec, + QEMU_PLUGIN_CB_NO_REGS, data); + } +} + +static void insn_free(gpointer data) +{ + InsnData *insn = (InsnData *) data; + g_free(insn->disas_str); + g_free(insn); +} + +static void cache_free(Cache *cache) +{ + for (int i = 0; i < cache->num_sets; i++) { + g_free(cache->sets[i].blocks); + } + + if (metadata_destroy) { + metadata_destroy(cache); + } + + g_free(cache->sets); + g_free(cache); +} + +static int dcmp(gconstpointer a, gconstpointer b) +{ + InsnData *insn_a = (InsnData *) a; + InsnData *insn_b = (InsnData *) b; + + return insn_a->dmisses < insn_b->dmisses ? 1 : -1; +} + +static int icmp(gconstpointer a, gconstpointer b) +{ + InsnData *insn_a = (InsnData *) a; + InsnData *insn_b = (InsnData *) b; + + return insn_a->imisses < insn_b->imisses ? 1 : -1; +} + +static void log_stats(void) +{ + g_autoptr(GString) rep = g_string_new(""); + g_string_append_printf(rep, + "Data accesses: %lu, Misses: %lu\nMiss rate: %lf%%\n\n", + dmem_accesses, + dmisses, + ((double) dmisses / (double) dmem_accesses) * 100.0); + + g_string_append_printf(rep, + "Instruction accesses: %lu, Misses: %lu\nMiss rate: %lf%%\n\n", + imem_accesses, + imisses, + ((double) imisses / (double) imem_accesses) * 100.0); + + qemu_plugin_outs(rep->str); +} + +static void log_top_insns(void) +{ + int i; + GList *curr, *miss_insns; + InsnData *insn; + + miss_insns = g_hash_table_get_values(miss_ht); + miss_insns = g_list_sort(miss_insns, dcmp); + g_autoptr(GString) rep = g_string_new(""); + g_string_append_printf(rep, "%s", "address, data misses, instruction\n"); + + for (curr = miss_insns, i = 0; curr && i < limit; i++, curr = curr->next) { + insn = (InsnData *) curr->data; + g_string_append_printf(rep, "0x%" PRIx64, insn->addr); + if (insn->symbol) { + g_string_append_printf(rep, " (%s)", insn->symbol); + } + g_string_append_printf(rep, ", %ld, %s\n", insn->dmisses, + insn->disas_str); + } + + miss_insns = g_list_sort(miss_insns, icmp); + g_string_append_printf(rep, "%s", "\naddress, fetch misses, instruction\n"); + + for (curr = miss_insns, i = 0; curr && i < limit; i++, curr = curr->next) { + insn = (InsnData *) curr->data; + g_string_append_printf(rep, "0x%" PRIx64, insn->addr); + if (insn->symbol) { + g_string_append_printf(rep, " (%s)", insn->symbol); + } + g_string_append_printf(rep, ", %ld, %s\n", insn->imisses, + insn->disas_str); + } + + qemu_plugin_outs(rep->str); + g_list_free(miss_insns); +} + +static void plugin_exit(qemu_plugin_id_t id, void *p) +{ + log_stats(); + log_top_insns(); + + cache_free(dcache); + cache_free(icache); + + g_hash_table_destroy(miss_ht); +} + +static void policy_init(void) +{ + switch (policy) { + case LRU: + update_hit = lru_update_blk; + update_miss = lru_update_blk; + metadata_init = lru_priorities_init; + metadata_destroy = lru_priorities_destroy; + break; + case FIFO: + update_miss = fifo_update_on_miss; + metadata_init = fifo_init; + metadata_destroy = fifo_destroy; + break; + case RAND: + rng = g_rand_new(); + break; + default: + g_assert_not_reached(); + } +} + +QEMU_PLUGIN_EXPORT +int qemu_plugin_install(qemu_plugin_id_t id, const qemu_info_t *info, + int argc, char **argv) +{ + int i; + int iassoc, iblksize, icachesize; + int dassoc, dblksize, dcachesize; + + limit = 32; + sys = info->system_emulation; + + dassoc = 8; + dblksize = 64; + dcachesize = dblksize * dassoc * 32; + + iassoc = 8; + iblksize = 64; + icachesize = iblksize * iassoc * 32; + + policy = LRU; + + for (i = 0; i < argc; i++) { + char *opt = argv[i]; + if (g_str_has_prefix(opt, "iblksize=")) { + iblksize = g_ascii_strtoll(opt + 9, NULL, 10); + } else if (g_str_has_prefix(opt, "iassoc=")) { + iassoc = g_ascii_strtoll(opt + 7, NULL, 10); + } else if (g_str_has_prefix(opt, "icachesize=")) { + icachesize = g_ascii_strtoll(opt + 11, NULL, 10); + } else if (g_str_has_prefix(opt, "dblksize=")) { + dblksize = g_ascii_strtoll(opt + 9, NULL, 10); + } else if (g_str_has_prefix(opt, "dassoc=")) { + dassoc = g_ascii_strtoll(opt + 7, NULL, 10); + } else if (g_str_has_prefix(opt, "dcachesize=")) { + dcachesize = g_ascii_strtoll(opt + 11, NULL, 10); + } else if (g_str_has_prefix(opt, "limit=")) { + limit = g_ascii_strtoll(opt + 6, NULL, 10); + } else if (g_str_has_prefix(opt, "evict=")) { + gchar *p = opt + 6; + if (g_strcmp0(p, "rand") == 0) { + policy = RAND; + } else if (g_strcmp0(p, "lru") == 0) { + policy = LRU; + } else if (g_strcmp0(p, "fifo") == 0) { + policy = FIFO; + } else { + fprintf(stderr, "invalid eviction policy: %s\n", opt); + return -1; + } + } else { + fprintf(stderr, "option parsing failed: %s\n", opt); + return -1; + } + } + + policy_init(); + + dcache = cache_init(dblksize, dassoc, dcachesize); + if (!dcache) { + const char *err = cache_config_error(dblksize, dassoc, dcachesize); + fprintf(stderr, "dcache cannot be constructed from given parameters\n"); + fprintf(stderr, "%s\n", err); + return -1; + } + + icache = cache_init(iblksize, iassoc, icachesize); + if (!icache) { + const char *err = cache_config_error(iblksize, iassoc, icachesize); + fprintf(stderr, "icache cannot be constructed from given parameters\n"); + fprintf(stderr, "%s\n", err); + return -1; + } + + qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans); + qemu_plugin_register_atexit_cb(id, plugin_exit, NULL); + + miss_ht = g_hash_table_new_full(NULL, g_direct_equal, NULL, insn_free); + + return 0; +} diff --git a/contrib/plugins/execlog.c b/contrib/plugins/execlog.c new file mode 100644 index 0000000000..2de9f0d7d4 --- /dev/null +++ b/contrib/plugins/execlog.c @@ -0,0 +1,153 @@ +/* + * Copyright (C) 2021, Alexandre Iooss + * + * Log instruction execution with memory access. + * + * License: GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#include +#include +#include +#include +#include +#include + +#include + +QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION; + +/* Store last executed instruction on each vCPU as a GString */ +GArray *last_exec; + +/** + * Add memory read or write information to current instruction log + */ +static void vcpu_mem(unsigned int cpu_index, qemu_plugin_meminfo_t info, + uint64_t vaddr, void *udata) +{ + GString *s; + + /* Find vCPU in array */ + g_assert(cpu_index < last_exec->len); + s = g_array_index(last_exec, GString *, cpu_index); + + /* Indicate type of memory access */ + if (qemu_plugin_mem_is_store(info)) { + g_string_append(s, ", store"); + } else { + g_string_append(s, ", load"); + } + + /* If full system emulation log physical address and device name */ + struct qemu_plugin_hwaddr *hwaddr = qemu_plugin_get_hwaddr(info, vaddr); + if (hwaddr) { + uint64_t addr = qemu_plugin_hwaddr_phys_addr(hwaddr); + const char *name = qemu_plugin_hwaddr_device_name(hwaddr); + g_string_append_printf(s, ", 0x%08"PRIx64", %s", addr, name); + } else { + g_string_append_printf(s, ", 0x%08"PRIx64, vaddr); + } +} + +/** + * Log instruction execution + */ +static void vcpu_insn_exec(unsigned int cpu_index, void *udata) +{ + GString *s; + + /* Find or create vCPU in array */ + while (cpu_index >= last_exec->len) { + s = g_string_new(NULL); + g_array_append_val(last_exec, s); + } + s = g_array_index(last_exec, GString *, cpu_index); + + /* Print previous instruction in cache */ + if (s->len) { + qemu_plugin_outs(s->str); + qemu_plugin_outs("s\n"); + } + + /* Store new instruction in cache */ + /* vcpu_mem will add memory access information to last_exec */ + g_string_printf(s, "%u, ", cpu_index); + g_string_append(s, (char *)udata); +} + +/** + * On translation block new translation + * + * QEMU convert code by translation block (TB). By hooking here we can then hook + * a callback on each instruction and memory access. + */ +static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb) +{ + struct qemu_plugin_insn *insn; + uint64_t insn_vaddr; + uint32_t insn_opcode; + char *insn_disas; + + size_t n = qemu_plugin_tb_n_insns(tb); + for (size_t i = 0; i < n; i++) { + /* + * `insn` is shared between translations in QEMU, copy needed data here. + * `output` is never freed as it might be used multiple times during + * the emulation lifetime. + * We only consider the first 32 bits of the instruction, this may be + * a limitation for CISC architectures. + */ + insn = qemu_plugin_tb_get_insn(tb, i); + insn_vaddr = qemu_plugin_insn_vaddr(insn); + insn_opcode = *((uint32_t *)qemu_plugin_insn_data(insn)); + insn_disas = qemu_plugin_insn_disas(insn); + char *output = g_strdup_printf("0x%"PRIx64", 0x%"PRIx32", \"%s\"", + insn_vaddr, insn_opcode, insn_disas); + + /* Register callback on memory read or write */ + qemu_plugin_register_vcpu_mem_cb(insn, vcpu_mem, + QEMU_PLUGIN_CB_NO_REGS, + QEMU_PLUGIN_MEM_RW, NULL); + + /* Register callback on instruction */ + qemu_plugin_register_vcpu_insn_exec_cb(insn, vcpu_insn_exec, + QEMU_PLUGIN_CB_NO_REGS, output); + } +} + +/** + * On plugin exit, print last instruction in cache + */ +static void plugin_exit(qemu_plugin_id_t id, void *p) +{ + guint i; + GString *s; + for (i = 0; i < last_exec->len; i++) { + s = g_array_index(last_exec, GString *, i); + if (s->str) { + qemu_plugin_outs(s->str); + qemu_plugin_outs("\n"); + } + } +} + +/** + * Install the plugin + */ +QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id, + const qemu_info_t *info, int argc, + char **argv) +{ + /* + * Initialize dynamic array to cache vCPU instruction. In user mode + * we don't know the size before emulation. + */ + last_exec = g_array_new(FALSE, FALSE, sizeof(GString *)); + + /* Register translation block and exit callbacks */ + qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans); + qemu_plugin_register_atexit_cb(id, plugin_exit, NULL); + + return 0; +} diff --git a/contrib/vhost-user-gpu/meson.build b/contrib/vhost-user-gpu/meson.build index 0ce1515a10..4cb52a91d7 100644 --- a/contrib/vhost-user-gpu/meson.build +++ b/contrib/vhost-user-gpu/meson.build @@ -1,4 +1,4 @@ -if 'CONFIG_TOOLS' in config_host and 'CONFIG_VIRGL' in config_host \ +if 'CONFIG_TOOLS' in config_host and virgl.found() \ and 'CONFIG_GBM' in config_host and 'CONFIG_LINUX' in config_host \ and pixman.found() executable('vhost-user-gpu', files('vhost-user-gpu.c', 'virgl.c', 'vugbm.c'), diff --git a/contrib/vhost-user-gpu/vhost-user-gpu.c b/contrib/vhost-user-gpu/vhost-user-gpu.c index f73f292c9f..611360e6b4 100644 --- a/contrib/vhost-user-gpu/vhost-user-gpu.c +++ b/contrib/vhost-user-gpu/vhost-user-gpu.c @@ -49,6 +49,8 @@ static char *opt_render_node; static gboolean opt_virgl; static void vg_handle_ctrl(VuDev *dev, int qidx); +static void vg_cleanup_mapping(VuGpu *g, + struct virtio_gpu_simple_resource *res); static const char * vg_cmd_to_string(int cmd) @@ -348,6 +350,7 @@ vg_resource_create_2d(VuGpu *g, if (!res->image) { g_critical("%s: resource creation failed %d %d %d", __func__, c2d.resource_id, c2d.width, c2d.height); + vugbm_buffer_destroy(&res->buffer); g_free(res); cmd->error = VIRTIO_GPU_RESP_ERR_OUT_OF_MEMORY; return; @@ -399,6 +402,7 @@ vg_resource_destroy(VuGpu *g, } vugbm_buffer_destroy(&res->buffer); + vg_cleanup_mapping(g, res); pixman_image_unref(res->image); QTAILQ_REMOVE(&g->reslist, res, next); g_free(res); @@ -488,6 +492,11 @@ vg_resource_attach_backing(VuGpu *g, return; } + if (res->iov) { + cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; + return; + } + ret = vg_create_mapping_iov(g, &ab, cmd, &res->iov); if (ret != 0) { cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; @@ -497,6 +506,22 @@ vg_resource_attach_backing(VuGpu *g, res->iov_cnt = ab.nr_entries; } +/* Though currently only free iov, maybe later will do more work. */ +void vg_cleanup_mapping_iov(VuGpu *g, + struct iovec *iov, uint32_t count) +{ + g_free(iov); +} + +static void +vg_cleanup_mapping(VuGpu *g, + struct virtio_gpu_simple_resource *res) +{ + vg_cleanup_mapping_iov(g, res->iov, res->iov_cnt); + res->iov = NULL; + res->iov_cnt = 0; +} + static void vg_resource_detach_backing(VuGpu *g, struct virtio_gpu_ctrl_command *cmd) @@ -515,9 +540,7 @@ vg_resource_detach_backing(VuGpu *g, return; } - g_free(res->iov); - res->iov = NULL; - res->iov_cnt = 0; + vg_cleanup_mapping(g, res); } static void diff --git a/contrib/vhost-user-gpu/virgl.c b/contrib/vhost-user-gpu/virgl.c index 9e6660c7ab..3e45e1bd33 100644 --- a/contrib/vhost-user-gpu/virgl.c +++ b/contrib/vhost-user-gpu/virgl.c @@ -108,9 +108,17 @@ virgl_cmd_resource_unref(VuGpu *g, struct virtio_gpu_ctrl_command *cmd) { struct virtio_gpu_resource_unref unref; + struct iovec *res_iovs = NULL; + int num_iovs = 0; VUGPU_FILL_CMD(unref); + virgl_renderer_resource_detach_iov(unref.resource_id, + &res_iovs, + &num_iovs); + if (res_iovs != NULL && num_iovs != 0) { + vg_cleanup_mapping_iov(g, res_iovs, num_iovs); + } virgl_renderer_resource_unref(unref.resource_id); } @@ -128,6 +136,7 @@ virgl_cmd_get_capset_info(VuGpu *g, VUGPU_FILL_CMD(info); + memset(&resp, 0, sizeof(resp)); if (info.capset_index == 0) { resp.capset_id = VIRTIO_GPU_CAPSET_VIRGL; virgl_renderer_get_cap_set(resp.capset_id, @@ -169,6 +178,10 @@ virgl_cmd_get_capset(VuGpu *g, virgl_renderer_get_cap_set(gc.capset_id, &max_ver, &max_size); + if (!max_size) { + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + return; + } resp = g_malloc0(sizeof(*resp) + max_size); resp->hdr.type = VIRTIO_GPU_RESP_OK_CAPSET; @@ -279,8 +292,11 @@ virgl_resource_attach_backing(VuGpu *g, return; } - virgl_renderer_resource_attach_iov(att_rb.resource_id, + ret = virgl_renderer_resource_attach_iov(att_rb.resource_id, res_iovs, att_rb.nr_entries); + if (ret != 0) { + vg_cleanup_mapping_iov(g, res_iovs, att_rb.nr_entries); + } } static void @@ -299,7 +315,7 @@ virgl_resource_detach_backing(VuGpu *g, if (res_iovs == NULL || num_iovs == 0) { return; } - g_free(res_iovs); + vg_cleanup_mapping_iov(g, res_iovs, num_iovs); } static void diff --git a/contrib/vhost-user-gpu/vugpu.h b/contrib/vhost-user-gpu/vugpu.h index 04d5615812..e2864bba68 100644 --- a/contrib/vhost-user-gpu/vugpu.h +++ b/contrib/vhost-user-gpu/vugpu.h @@ -169,7 +169,7 @@ int vg_create_mapping_iov(VuGpu *g, struct virtio_gpu_resource_attach_backing *ab, struct virtio_gpu_ctrl_command *cmd, struct iovec **iov); - +void vg_cleanup_mapping_iov(VuGpu *g, struct iovec *iov, uint32_t count); void vg_get_display_info(VuGpu *vg, struct virtio_gpu_ctrl_command *cmd); void vg_wait_ok(VuGpu *g); diff --git a/contrib/vhost-user-input/main.c b/contrib/vhost-user-input/main.c index c15d18c33f..081230da54 100644 --- a/contrib/vhost-user-input/main.c +++ b/contrib/vhost-user-input/main.c @@ -6,12 +6,13 @@ #include "qemu/osdep.h" -#include +#include #include "qemu/iov.h" #include "qemu/bswap.h" #include "qemu/sockets.h" #include "libvhost-user-glib.h" +#include "standard-headers/linux/input.h" #include "standard-headers/linux/virtio_input.h" #include "qapi/error.h" @@ -113,13 +114,16 @@ vi_evdev_watch(VuDev *dev, int condition, void *data) static void vi_handle_status(VuInput *vi, virtio_input_event *event) { struct input_event evdev; + struct timeval tval; int rc; - if (gettimeofday(&evdev.time, NULL)) { + if (gettimeofday(&tval, NULL)) { perror("vi_handle_status: gettimeofday"); return; } + evdev.input_event_sec = tval.tv_sec; + evdev.input_event_usec = tval.tv_usec; evdev.type = le16toh(event->type); evdev.code = le16toh(event->code); evdev.value = le32toh(event->value); diff --git a/cpu.c b/cpu.c index bfbe5a66f9..e1799a15bc 100644 --- a/cpu.c +++ b/cpu.c @@ -29,6 +29,7 @@ #ifdef CONFIG_USER_ONLY #include "qemu.h" #else +#include "hw/core/sysemu-cpu-ops.h" #include "exec/address-spaces.h" #endif #include "sysemu/tcg.h" @@ -36,6 +37,8 @@ #include "sysemu/replay.h" #include "exec/translate-all.h" #include "exec/log.h" +#include "hw/core/accel-cpu.h" +#include "trace/trace-root.h" uintptr_t qemu_host_page_size; intptr_t qemu_host_page_mask; @@ -126,10 +129,14 @@ const VMStateDescription vmstate_cpu_common = { void cpu_exec_realizefn(CPUState *cpu, Error **errp) { +#ifndef CONFIG_USER_ONLY CPUClass *cc = CPU_GET_CLASS(cpu); +#endif cpu_list_add(cpu); - + if (!accel_cpu_realizefn(cpu, errp)) { + return; + } #ifdef CONFIG_TCG /* NB: errp parameter is unused currently */ if (tcg_enabled()) { @@ -138,26 +145,25 @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp) #endif /* CONFIG_TCG */ #ifdef CONFIG_USER_ONLY - assert(cc->vmsd == NULL); + assert(qdev_get_vmsd(DEVICE(cpu)) == NULL || + qdev_get_vmsd(DEVICE(cpu))->unmigratable); #else if (qdev_get_vmsd(DEVICE(cpu)) == NULL) { vmstate_register(NULL, cpu->cpu_index, &vmstate_cpu_common, cpu); } - if (cc->vmsd != NULL) { - vmstate_register(NULL, cpu->cpu_index, cc->vmsd, cpu); + if (cc->sysemu_ops->legacy_vmsd != NULL) { + vmstate_register(NULL, cpu->cpu_index, cc->sysemu_ops->legacy_vmsd, cpu); } #endif /* CONFIG_USER_ONLY */ } void cpu_exec_unrealizefn(CPUState *cpu) { +#ifndef CONFIG_USER_ONLY CPUClass *cc = CPU_GET_CLASS(cpu); -#ifdef CONFIG_USER_ONLY - assert(cc->vmsd == NULL); -#else - if (cc->vmsd != NULL) { - vmstate_unregister(NULL, cc->vmsd, cpu); + if (cc->sysemu_ops->legacy_vmsd != NULL) { + vmstate_unregister(NULL, cc->sysemu_ops->legacy_vmsd, cpu); } if (qdev_get_vmsd(DEVICE(cpu)) == NULL) { vmstate_unregister(NULL, &vmstate_cpu_common, cpu); @@ -219,11 +225,6 @@ void tb_invalidate_phys_addr(target_ulong addr) tb_invalidate_phys_page_range(addr, addr + 1); mmap_unlock(); } - -static void breakpoint_invalidate(CPUState *cpu, target_ulong pc) -{ - tb_invalidate_phys_addr(pc); -} #else void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, MemTxAttrs attrs) { @@ -244,25 +245,19 @@ void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, MemTxAttrs attrs) ram_addr = memory_region_get_ram_addr(mr) + addr; tb_invalidate_phys_page_range(ram_addr, ram_addr + 1); } - -static void breakpoint_invalidate(CPUState *cpu, target_ulong pc) -{ - /* - * There may not be a virtual to physical translation for the pc - * right now, but there may exist cached TB for this pc. - * Flush the whole TB cache to force re-translation of such TBs. - * This is heavyweight, but we're debugging anyway. - */ - tb_flush(cpu); -} #endif /* Add a breakpoint. */ int cpu_breakpoint_insert(CPUState *cpu, vaddr pc, int flags, CPUBreakpoint **breakpoint) { + CPUClass *cc = CPU_GET_CLASS(cpu); CPUBreakpoint *bp; + if (cc->gdb_adjust_breakpoint) { + pc = cc->gdb_adjust_breakpoint(cpu, pc); + } + bp = g_malloc(sizeof(*bp)); bp->pc = pc; @@ -275,19 +270,24 @@ int cpu_breakpoint_insert(CPUState *cpu, vaddr pc, int flags, QTAILQ_INSERT_TAIL(&cpu->breakpoints, bp, entry); } - breakpoint_invalidate(cpu, pc); - if (breakpoint) { *breakpoint = bp; } + + trace_breakpoint_insert(cpu->cpu_index, pc, flags); return 0; } /* Remove a specific breakpoint. */ int cpu_breakpoint_remove(CPUState *cpu, vaddr pc, int flags) { + CPUClass *cc = CPU_GET_CLASS(cpu); CPUBreakpoint *bp; + if (cc->gdb_adjust_breakpoint) { + pc = cc->gdb_adjust_breakpoint(cpu, pc); + } + QTAILQ_FOREACH(bp, &cpu->breakpoints, entry) { if (bp->pc == pc && bp->flags == flags) { cpu_breakpoint_remove_by_ref(cpu, bp); @@ -298,13 +298,12 @@ int cpu_breakpoint_remove(CPUState *cpu, vaddr pc, int flags) } /* Remove a specific breakpoint by reference. */ -void cpu_breakpoint_remove_by_ref(CPUState *cpu, CPUBreakpoint *breakpoint) +void cpu_breakpoint_remove_by_ref(CPUState *cpu, CPUBreakpoint *bp) { - QTAILQ_REMOVE(&cpu->breakpoints, breakpoint, entry); + QTAILQ_REMOVE(&cpu->breakpoints, bp, entry); - breakpoint_invalidate(cpu, breakpoint->pc); - - g_free(breakpoint); + trace_breakpoint_remove(cpu->cpu_index, bp->pc, bp->flags); + g_free(bp); } /* Remove all matching breakpoints. */ @@ -327,11 +326,8 @@ void cpu_single_step(CPUState *cpu, int enabled) cpu->singlestep_enabled = enabled; if (kvm_enabled()) { kvm_update_guest_debug(cpu, 0); - } else { - /* must flush all the translated code to avoid inconsistencies */ - /* XXX: only flush what is necessary */ - tb_flush(cpu); } + trace_breakpoint_singlestep(cpu->cpu_index, enabled); } } diff --git a/crypto/cipher-builtin.c.inc b/crypto/cipher-builtin.c.inc index 7597cf4a10..b409089095 100644 --- a/crypto/cipher-builtin.c.inc +++ b/crypto/cipher-builtin.c.inc @@ -19,8 +19,6 @@ */ #include "crypto/aes.h" -#include "crypto/desrfb.h" -#include "crypto/xts.h" typedef struct QCryptoCipherBuiltinAESContext QCryptoCipherBuiltinAESContext; struct QCryptoCipherBuiltinAESContext { @@ -32,7 +30,6 @@ typedef struct QCryptoCipherBuiltinAES QCryptoCipherBuiltinAES; struct QCryptoCipherBuiltinAES { QCryptoCipher base; QCryptoCipherBuiltinAESContext key; - QCryptoCipherBuiltinAESContext key_tweak; uint8_t iv[AES_BLOCK_SIZE]; }; @@ -194,39 +191,6 @@ static int qcrypto_cipher_aes_decrypt_cbc(QCryptoCipher *cipher, return 0; } -static int qcrypto_cipher_aes_encrypt_xts(QCryptoCipher *cipher, - const void *in, void *out, - size_t len, Error **errp) -{ - QCryptoCipherBuiltinAES *ctx - = container_of(cipher, QCryptoCipherBuiltinAES, base); - - if (!qcrypto_length_check(len, AES_BLOCK_SIZE, errp)) { - return -1; - } - xts_encrypt(&ctx->key, &ctx->key_tweak, - do_aes_encrypt_ecb, do_aes_decrypt_ecb, - ctx->iv, len, out, in); - return 0; -} - -static int qcrypto_cipher_aes_decrypt_xts(QCryptoCipher *cipher, - const void *in, void *out, - size_t len, Error **errp) -{ - QCryptoCipherBuiltinAES *ctx - = container_of(cipher, QCryptoCipherBuiltinAES, base); - - if (!qcrypto_length_check(len, AES_BLOCK_SIZE, errp)) { - return -1; - } - xts_decrypt(&ctx->key, &ctx->key_tweak, - do_aes_encrypt_ecb, do_aes_decrypt_ecb, - ctx->iv, len, out, in); - return 0; -} - - static int qcrypto_cipher_aes_setiv(QCryptoCipher *cipher, const uint8_t *iv, size_t niv, Error **errp) { @@ -257,84 +221,16 @@ static const struct QCryptoCipherDriver qcrypto_cipher_aes_driver_cbc = { .cipher_free = qcrypto_cipher_ctx_free, }; -static const struct QCryptoCipherDriver qcrypto_cipher_aes_driver_xts = { - .cipher_encrypt = qcrypto_cipher_aes_encrypt_xts, - .cipher_decrypt = qcrypto_cipher_aes_decrypt_xts, - .cipher_setiv = qcrypto_cipher_aes_setiv, - .cipher_free = qcrypto_cipher_ctx_free, -}; - - -typedef struct QCryptoCipherBuiltinDESRFB QCryptoCipherBuiltinDESRFB; -struct QCryptoCipherBuiltinDESRFB { - QCryptoCipher base; - - /* C.f. alg_key_len[QCRYPTO_CIPHER_ALG_DES_RFB] */ - uint8_t key[8]; -}; - -static int qcrypto_cipher_encrypt_des_rfb(QCryptoCipher *cipher, - const void *in, void *out, - size_t len, Error **errp) -{ - QCryptoCipherBuiltinDESRFB *ctx - = container_of(cipher, QCryptoCipherBuiltinDESRFB, base); - size_t i; - - if (!qcrypto_length_check(len, 8, errp)) { - return -1; - } - - deskey(ctx->key, EN0); - - for (i = 0; i < len; i += 8) { - des((void *)in + i, out + i); - } - - return 0; -} - -static int qcrypto_cipher_decrypt_des_rfb(QCryptoCipher *cipher, - const void *in, void *out, - size_t len, Error **errp) -{ - QCryptoCipherBuiltinDESRFB *ctx - = container_of(cipher, QCryptoCipherBuiltinDESRFB, base); - size_t i; - - if (!qcrypto_length_check(len, 8, errp)) { - return -1; - } - - deskey(ctx->key, DE1); - - for (i = 0; i < len; i += 8) { - des((void *)in + i, out + i); - } - - return 0; -} - -static const struct QCryptoCipherDriver qcrypto_cipher_des_rfb_driver = { - .cipher_encrypt = qcrypto_cipher_encrypt_des_rfb, - .cipher_decrypt = qcrypto_cipher_decrypt_des_rfb, - .cipher_setiv = qcrypto_cipher_no_setiv, - .cipher_free = qcrypto_cipher_ctx_free, -}; - bool qcrypto_cipher_supports(QCryptoCipherAlgorithm alg, QCryptoCipherMode mode) { switch (alg) { - case QCRYPTO_CIPHER_ALG_DES_RFB: - return mode == QCRYPTO_CIPHER_MODE_ECB; case QCRYPTO_CIPHER_ALG_AES_128: case QCRYPTO_CIPHER_ALG_AES_192: case QCRYPTO_CIPHER_ALG_AES_256: switch (mode) { case QCRYPTO_CIPHER_MODE_ECB: case QCRYPTO_CIPHER_MODE_CBC: - case QCRYPTO_CIPHER_MODE_XTS: return true; default: return false; @@ -356,18 +252,6 @@ static QCryptoCipher *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg, } switch (alg) { - case QCRYPTO_CIPHER_ALG_DES_RFB: - if (mode == QCRYPTO_CIPHER_MODE_ECB) { - QCryptoCipherBuiltinDESRFB *ctx; - - ctx = g_new0(QCryptoCipherBuiltinDESRFB, 1); - ctx->base.driver = &qcrypto_cipher_des_rfb_driver; - memcpy(ctx->key, key, sizeof(ctx->key)); - - return &ctx->base; - } - goto bad_mode; - case QCRYPTO_CIPHER_ALG_AES_128: case QCRYPTO_CIPHER_ALG_AES_192: case QCRYPTO_CIPHER_ALG_AES_256: @@ -382,9 +266,6 @@ static QCryptoCipher *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg, case QCRYPTO_CIPHER_MODE_CBC: drv = &qcrypto_cipher_aes_driver_cbc; break; - case QCRYPTO_CIPHER_MODE_XTS: - drv = &qcrypto_cipher_aes_driver_xts; - break; default: goto bad_mode; } @@ -392,19 +273,6 @@ static QCryptoCipher *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg, ctx = g_new0(QCryptoCipherBuiltinAES, 1); ctx->base.driver = drv; - if (mode == QCRYPTO_CIPHER_MODE_XTS) { - nkey /= 2; - if (AES_set_encrypt_key(key + nkey, nkey * 8, - &ctx->key_tweak.enc)) { - error_setg(errp, "Failed to set encryption key"); - goto error; - } - if (AES_set_decrypt_key(key + nkey, nkey * 8, - &ctx->key_tweak.dec)) { - error_setg(errp, "Failed to set decryption key"); - goto error; - } - } if (AES_set_encrypt_key(key, nkey * 8, &ctx->key.enc)) { error_setg(errp, "Failed to set encryption key"); goto error; diff --git a/crypto/cipher-gcrypt.c.inc b/crypto/cipher-gcrypt.c.inc index 42d4137534..a6a0117717 100644 --- a/crypto/cipher-gcrypt.c.inc +++ b/crypto/cipher-gcrypt.c.inc @@ -18,17 +18,13 @@ * */ -#ifdef CONFIG_QEMU_PRIVATE_XTS -#include "crypto/xts.h" -#endif - #include bool qcrypto_cipher_supports(QCryptoCipherAlgorithm alg, QCryptoCipherMode mode) { switch (alg) { - case QCRYPTO_CIPHER_ALG_DES_RFB: + case QCRYPTO_CIPHER_ALG_DES: case QCRYPTO_CIPHER_ALG_3DES: case QCRYPTO_CIPHER_ALG_AES_128: case QCRYPTO_CIPHER_ALG_AES_192: @@ -59,10 +55,6 @@ typedef struct QCryptoCipherGcrypt { QCryptoCipher base; gcry_cipher_hd_t handle; size_t blocksize; -#ifdef CONFIG_QEMU_PRIVATE_XTS - gcry_cipher_hd_t tweakhandle; - uint8_t iv[XTS_BLOCK_SIZE]; -#endif } QCryptoCipherGcrypt; @@ -178,90 +170,6 @@ static const struct QCryptoCipherDriver qcrypto_gcrypt_ctr_driver = { .cipher_free = qcrypto_gcrypt_ctx_free, }; -#ifdef CONFIG_QEMU_PRIVATE_XTS -static void qcrypto_gcrypt_xts_ctx_free(QCryptoCipher *cipher) -{ - QCryptoCipherGcrypt *ctx = container_of(cipher, QCryptoCipherGcrypt, base); - - gcry_cipher_close(ctx->tweakhandle); - qcrypto_gcrypt_ctx_free(cipher); -} - -static void qcrypto_gcrypt_xts_wrape(const void *ctx, size_t length, - uint8_t *dst, const uint8_t *src) -{ - gcry_error_t err; - err = gcry_cipher_encrypt((gcry_cipher_hd_t)ctx, dst, length, src, length); - g_assert(err == 0); -} - -static void qcrypto_gcrypt_xts_wrapd(const void *ctx, size_t length, - uint8_t *dst, const uint8_t *src) -{ - gcry_error_t err; - err = gcry_cipher_decrypt((gcry_cipher_hd_t)ctx, dst, length, src, length); - g_assert(err == 0); -} - -static int qcrypto_gcrypt_xts_encrypt(QCryptoCipher *cipher, const void *in, - void *out, size_t len, Error **errp) -{ - QCryptoCipherGcrypt *ctx = container_of(cipher, QCryptoCipherGcrypt, base); - - if (len & (ctx->blocksize - 1)) { - error_setg(errp, "Length %zu must be a multiple of block size %zu", - len, ctx->blocksize); - return -1; - } - - xts_encrypt(ctx->handle, ctx->tweakhandle, - qcrypto_gcrypt_xts_wrape, qcrypto_gcrypt_xts_wrapd, - ctx->iv, len, out, in); - return 0; -} - -static int qcrypto_gcrypt_xts_decrypt(QCryptoCipher *cipher, const void *in, - void *out, size_t len, Error **errp) -{ - QCryptoCipherGcrypt *ctx = container_of(cipher, QCryptoCipherGcrypt, base); - - if (len & (ctx->blocksize - 1)) { - error_setg(errp, "Length %zu must be a multiple of block size %zu", - len, ctx->blocksize); - return -1; - } - - xts_decrypt(ctx->handle, ctx->tweakhandle, - qcrypto_gcrypt_xts_wrape, qcrypto_gcrypt_xts_wrapd, - ctx->iv, len, out, in); - return 0; -} - -static int qcrypto_gcrypt_xts_setiv(QCryptoCipher *cipher, - const uint8_t *iv, size_t niv, - Error **errp) -{ - QCryptoCipherGcrypt *ctx = container_of(cipher, QCryptoCipherGcrypt, base); - - if (niv != ctx->blocksize) { - error_setg(errp, "Expected IV size %zu not %zu", - ctx->blocksize, niv); - return -1; - } - - memcpy(ctx->iv, iv, niv); - return 0; -} - -static const struct QCryptoCipherDriver qcrypto_gcrypt_xts_driver = { - .cipher_encrypt = qcrypto_gcrypt_xts_encrypt, - .cipher_decrypt = qcrypto_gcrypt_xts_decrypt, - .cipher_setiv = qcrypto_gcrypt_xts_setiv, - .cipher_free = qcrypto_gcrypt_xts_ctx_free, -}; -#endif /* CONFIG_QEMU_PRIVATE_XTS */ - - static QCryptoCipher *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg, QCryptoCipherMode mode, const uint8_t *key, @@ -278,7 +186,7 @@ static QCryptoCipher *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg, } switch (alg) { - case QCRYPTO_CIPHER_ALG_DES_RFB: + case QCRYPTO_CIPHER_ALG_DES: gcryalg = GCRY_CIPHER_DES; break; case QCRYPTO_CIPHER_ALG_3DES: @@ -323,12 +231,7 @@ static QCryptoCipher *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg, gcrymode = GCRY_CIPHER_MODE_ECB; break; case QCRYPTO_CIPHER_MODE_XTS: -#ifdef CONFIG_QEMU_PRIVATE_XTS - drv = &qcrypto_gcrypt_xts_driver; - gcrymode = GCRY_CIPHER_MODE_ECB; -#else gcrymode = GCRY_CIPHER_MODE_XTS; -#endif break; case QCRYPTO_CIPHER_MODE_CBC: gcrymode = GCRY_CIPHER_MODE_CBC; @@ -354,44 +257,7 @@ static QCryptoCipher *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg, } ctx->blocksize = gcry_cipher_get_algo_blklen(gcryalg); -#ifdef CONFIG_QEMU_PRIVATE_XTS - if (mode == QCRYPTO_CIPHER_MODE_XTS) { - if (ctx->blocksize != XTS_BLOCK_SIZE) { - error_setg(errp, - "Cipher block size %zu must equal XTS block size %d", - ctx->blocksize, XTS_BLOCK_SIZE); - goto error; - } - err = gcry_cipher_open(&ctx->tweakhandle, gcryalg, gcrymode, 0); - if (err != 0) { - error_setg(errp, "Cannot initialize cipher: %s", - gcry_strerror(err)); - goto error; - } - } -#endif - - if (alg == QCRYPTO_CIPHER_ALG_DES_RFB) { - /* We're using standard DES cipher from gcrypt, so we need - * to munge the key so that the results are the same as the - * bizarre RFB variant of DES :-) - */ - uint8_t *rfbkey = qcrypto_cipher_munge_des_rfb_key(key, nkey); - err = gcry_cipher_setkey(ctx->handle, rfbkey, nkey); - g_free(rfbkey); - } else { -#ifdef CONFIG_QEMU_PRIVATE_XTS - if (mode == QCRYPTO_CIPHER_MODE_XTS) { - nkey /= 2; - err = gcry_cipher_setkey(ctx->tweakhandle, key + nkey, nkey); - if (err != 0) { - error_setg(errp, "Cannot set key: %s", gcry_strerror(err)); - goto error; - } - } -#endif - err = gcry_cipher_setkey(ctx->handle, key, nkey); - } + err = gcry_cipher_setkey(ctx->handle, key, nkey); if (err != 0) { error_setg(errp, "Cannot set key: %s", gcry_strerror(err)); goto error; @@ -400,9 +266,6 @@ static QCryptoCipher *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg, return &ctx->base; error: -#ifdef CONFIG_QEMU_PRIVATE_XTS - gcry_cipher_close(ctx->tweakhandle); -#endif gcry_cipher_close(ctx->handle); g_free(ctx); return NULL; diff --git a/crypto/cipher-gnutls.c.inc b/crypto/cipher-gnutls.c.inc new file mode 100644 index 0000000000..501e4e07a5 --- /dev/null +++ b/crypto/cipher-gnutls.c.inc @@ -0,0 +1,335 @@ +/* + * QEMU Crypto cipher gnutls algorithms + * + * Copyright (c) 2021 Red Hat, Inc. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see . + * + */ + +#include "qemu/osdep.h" +#include "cipherpriv.h" + +#include + +#if GNUTLS_VERSION_NUMBER >= 0x030608 +#define QEMU_GNUTLS_XTS +#endif + +bool qcrypto_cipher_supports(QCryptoCipherAlgorithm alg, + QCryptoCipherMode mode) +{ + + switch (mode) { + case QCRYPTO_CIPHER_MODE_ECB: + case QCRYPTO_CIPHER_MODE_CBC: + switch (alg) { + case QCRYPTO_CIPHER_ALG_AES_128: + case QCRYPTO_CIPHER_ALG_AES_192: + case QCRYPTO_CIPHER_ALG_AES_256: + case QCRYPTO_CIPHER_ALG_DES: + case QCRYPTO_CIPHER_ALG_3DES: + return true; + default: + return false; + } +#ifdef QEMU_GNUTLS_XTS + case QCRYPTO_CIPHER_MODE_XTS: + switch (alg) { + case QCRYPTO_CIPHER_ALG_AES_128: + case QCRYPTO_CIPHER_ALG_AES_256: + return true; + default: + return false; + } +#endif + default: + return false; + } +} + +typedef struct QCryptoCipherGnutls QCryptoCipherGnutls; +struct QCryptoCipherGnutls { + QCryptoCipher base; + gnutls_cipher_hd_t handle; /* XTS & CBC mode */ + gnutls_cipher_algorithm_t galg; /* ECB mode */ + guint8 *key; /* ECB mode */ + size_t nkey; /* ECB mode */ + size_t blocksize; +}; + + +static void +qcrypto_gnutls_cipher_free(QCryptoCipher *cipher) +{ + QCryptoCipherGnutls *ctx = container_of(cipher, QCryptoCipherGnutls, base); + + g_free(ctx->key); + if (ctx->handle) { + gnutls_cipher_deinit(ctx->handle); + } + g_free(ctx); +} + + +static int +qcrypto_gnutls_cipher_encrypt(QCryptoCipher *cipher, + const void *in, + void *out, + size_t len, + Error **errp) +{ + QCryptoCipherGnutls *ctx = container_of(cipher, QCryptoCipherGnutls, base); + int err; + + if (len % ctx->blocksize) { + error_setg(errp, "Length %zu must be a multiple of block size %zu", + len, ctx->blocksize); + return -1; + } + + if (ctx->handle) { /* CBC / XTS mode */ + err = gnutls_cipher_encrypt2(ctx->handle, + in, len, + out, len); + if (err != 0) { + error_setg(errp, "Cannot encrypt data: %s", + gnutls_strerror(err)); + return -1; + } + } else { /* ECB mode very inefficiently faked with CBC */ + g_autofree unsigned char *iv = g_new0(unsigned char, ctx->blocksize); + while (len) { + gnutls_cipher_hd_t handle; + gnutls_datum_t gkey = { (unsigned char *)ctx->key, ctx->nkey }; + int err = gnutls_cipher_init(&handle, ctx->galg, &gkey, NULL); + if (err != 0) { + error_setg(errp, "Cannot initialize cipher: %s", + gnutls_strerror(err)); + return -1; + } + + gnutls_cipher_set_iv(handle, iv, ctx->blocksize); + + err = gnutls_cipher_encrypt2(handle, + in, ctx->blocksize, + out, ctx->blocksize); + if (err != 0) { + gnutls_cipher_deinit(handle); + error_setg(errp, "Cannot encrypt data: %s", + gnutls_strerror(err)); + return -1; + } + gnutls_cipher_deinit(handle); + + len -= ctx->blocksize; + in += ctx->blocksize; + out += ctx->blocksize; + } + } + + return 0; +} + + +static int +qcrypto_gnutls_cipher_decrypt(QCryptoCipher *cipher, + const void *in, + void *out, + size_t len, + Error **errp) +{ + QCryptoCipherGnutls *ctx = container_of(cipher, QCryptoCipherGnutls, base); + int err; + + if (len % ctx->blocksize) { + error_setg(errp, "Length %zu must be a multiple of block size %zu", + len, ctx->blocksize); + return -1; + } + + if (ctx->handle) { /* CBC / XTS mode */ + err = gnutls_cipher_decrypt2(ctx->handle, + in, len, + out, len); + + if (err != 0) { + error_setg(errp, "Cannot decrypt data: %s", + gnutls_strerror(err)); + return -1; + } + } else { /* ECB mode very inefficiently faked with CBC */ + g_autofree unsigned char *iv = g_new0(unsigned char, ctx->blocksize); + while (len) { + gnutls_cipher_hd_t handle; + gnutls_datum_t gkey = { (unsigned char *)ctx->key, ctx->nkey }; + int err = gnutls_cipher_init(&handle, ctx->galg, &gkey, NULL); + if (err != 0) { + error_setg(errp, "Cannot initialize cipher: %s", + gnutls_strerror(err)); + return -1; + } + + gnutls_cipher_set_iv(handle, iv, ctx->blocksize); + + err = gnutls_cipher_decrypt2(handle, + in, ctx->blocksize, + out, ctx->blocksize); + if (err != 0) { + gnutls_cipher_deinit(handle); + error_setg(errp, "Cannot encrypt data: %s", + gnutls_strerror(err)); + return -1; + } + gnutls_cipher_deinit(handle); + + len -= ctx->blocksize; + in += ctx->blocksize; + out += ctx->blocksize; + } + } + + return 0; +} + +static int +qcrypto_gnutls_cipher_setiv(QCryptoCipher *cipher, + const uint8_t *iv, size_t niv, + Error **errp) +{ + QCryptoCipherGnutls *ctx = container_of(cipher, QCryptoCipherGnutls, base); + + if (niv != ctx->blocksize) { + error_setg(errp, "Expected IV size %zu not %zu", + ctx->blocksize, niv); + return -1; + } + + gnutls_cipher_set_iv(ctx->handle, (unsigned char *)iv, niv); + + return 0; +} + + +static struct QCryptoCipherDriver gnutls_driver = { + .cipher_encrypt = qcrypto_gnutls_cipher_encrypt, + .cipher_decrypt = qcrypto_gnutls_cipher_decrypt, + .cipher_setiv = qcrypto_gnutls_cipher_setiv, + .cipher_free = qcrypto_gnutls_cipher_free, +}; + +static QCryptoCipher *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg, + QCryptoCipherMode mode, + const uint8_t *key, + size_t nkey, + Error **errp) +{ + QCryptoCipherGnutls *ctx; + gnutls_datum_t gkey = { (unsigned char *)key, nkey }; + gnutls_cipher_algorithm_t galg = GNUTLS_CIPHER_UNKNOWN; + int err; + + switch (mode) { +#ifdef QEMU_GNUTLS_XTS + case QCRYPTO_CIPHER_MODE_XTS: + switch (alg) { + case QCRYPTO_CIPHER_ALG_AES_128: + galg = GNUTLS_CIPHER_AES_128_XTS; + break; + case QCRYPTO_CIPHER_ALG_AES_256: + galg = GNUTLS_CIPHER_AES_256_XTS; + break; + default: + break; + } + break; +#endif + + case QCRYPTO_CIPHER_MODE_ECB: + case QCRYPTO_CIPHER_MODE_CBC: + switch (alg) { + case QCRYPTO_CIPHER_ALG_AES_128: + galg = GNUTLS_CIPHER_AES_128_CBC; + break; + case QCRYPTO_CIPHER_ALG_AES_192: + galg = GNUTLS_CIPHER_AES_192_CBC; + break; + case QCRYPTO_CIPHER_ALG_AES_256: + galg = GNUTLS_CIPHER_AES_256_CBC; + break; + case QCRYPTO_CIPHER_ALG_DES: + galg = GNUTLS_CIPHER_DES_CBC; + break; + case QCRYPTO_CIPHER_ALG_3DES: + galg = GNUTLS_CIPHER_3DES_CBC; + break; + default: + break; + } + break; + default: + break; + } + + if (galg == GNUTLS_CIPHER_UNKNOWN) { + error_setg(errp, "Unsupported cipher algorithm %s with %s mode", + QCryptoCipherAlgorithm_str(alg), + QCryptoCipherMode_str(mode)); + return NULL; + } + + if (!qcrypto_cipher_validate_key_length(alg, mode, nkey, errp)) { + return NULL; + } + + ctx = g_new0(QCryptoCipherGnutls, 1); + ctx->base.driver = &gnutls_driver; + + if (mode == QCRYPTO_CIPHER_MODE_ECB) { + ctx->key = g_new0(guint8, nkey); + memcpy(ctx->key, key, nkey); + ctx->nkey = nkey; + ctx->galg = galg; + } else { + err = gnutls_cipher_init(&ctx->handle, galg, &gkey, NULL); + if (err != 0) { + error_setg(errp, "Cannot initialize cipher: %s", + gnutls_strerror(err)); + goto error; + } + } + + if (alg == QCRYPTO_CIPHER_ALG_DES || + alg == QCRYPTO_CIPHER_ALG_3DES) + ctx->blocksize = 8; + else + ctx->blocksize = 16; + + /* + * Our API contract for requires iv to be optional + * but nettle gets unhappy when called by gnutls + * in this case, so we just force set a default + * all-zeros IV, to match behaviour of other backends. + */ + if (mode != QCRYPTO_CIPHER_MODE_ECB) { + g_autofree unsigned char *iv = g_new0(unsigned char, ctx->blocksize); + gnutls_cipher_set_iv(ctx->handle, iv, ctx->blocksize); + } + + return &ctx->base; + + error: + qcrypto_gnutls_cipher_free(&ctx->base); + return NULL; +} diff --git a/crypto/cipher-nettle.c.inc b/crypto/cipher-nettle.c.inc index cac771e4ff..24cc61f87b 100644 --- a/crypto/cipher-nettle.c.inc +++ b/crypto/cipher-nettle.c.inc @@ -34,47 +34,6 @@ #include #endif -typedef void (*QCryptoCipherNettleFuncWrapper)(const void *ctx, - size_t length, - uint8_t *dst, - const uint8_t *src); - -#if CONFIG_NETTLE_VERSION_MAJOR < 3 -typedef nettle_crypt_func * QCryptoCipherNettleFuncNative; -typedef void * cipher_ctx_t; -typedef unsigned cipher_length_t; -#define CONST_CTX - -#define cast5_set_key cast128_set_key - -#define aes128_ctx aes_ctx -#define aes192_ctx aes_ctx -#define aes256_ctx aes_ctx -#define aes128_set_encrypt_key(c, k) \ - aes_set_encrypt_key(c, 16, k) -#define aes192_set_encrypt_key(c, k) \ - aes_set_encrypt_key(c, 24, k) -#define aes256_set_encrypt_key(c, k) \ - aes_set_encrypt_key(c, 32, k) -#define aes128_set_decrypt_key(c, k) \ - aes_set_decrypt_key(c, 16, k) -#define aes192_set_decrypt_key(c, k) \ - aes_set_decrypt_key(c, 24, k) -#define aes256_set_decrypt_key(c, k) \ - aes_set_decrypt_key(c, 32, k) -#define aes128_encrypt aes_encrypt -#define aes192_encrypt aes_encrypt -#define aes256_encrypt aes_encrypt -#define aes128_decrypt aes_decrypt -#define aes192_decrypt aes_decrypt -#define aes256_decrypt aes_decrypt -#else -typedef nettle_cipher_func * QCryptoCipherNettleFuncNative; -typedef const void * cipher_ctx_t; -typedef size_t cipher_length_t; -#define CONST_CTX const -#endif - static inline bool qcrypto_length_check(size_t len, size_t blocksize, Error **errp) { @@ -197,12 +156,12 @@ static const struct QCryptoCipherDriver NAME##_driver_ctr = { \ static void NAME##_xts_wrape(const void *ctx, size_t length, \ uint8_t *dst, const uint8_t *src) \ { \ - ENCRYPT((cipher_ctx_t)ctx, length, dst, src); \ + ENCRYPT((const void *)ctx, length, dst, src); \ } \ static void NAME##_xts_wrapd(const void *ctx, size_t length, \ uint8_t *dst, const uint8_t *src) \ { \ - DECRYPT((cipher_ctx_t)ctx, length, dst, src); \ + DECRYPT((const void *)ctx, length, dst, src); \ } \ static int NAME##_encrypt_xts(QCryptoCipher *cipher, const void *in, \ void *out, size_t len, Error **errp) \ @@ -276,25 +235,25 @@ static const struct QCryptoCipherDriver NAME##_driver_xts = { \ DEFINE_XTS(NAME, TYPE, BLEN, ENCRYPT, DECRYPT) -typedef struct QCryptoNettleDESRFB { +typedef struct QCryptoNettleDES { QCryptoCipher base; struct des_ctx key; uint8_t iv[DES_BLOCK_SIZE]; -} QCryptoNettleDESRFB; +} QCryptoNettleDES; -static void des_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void des_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { des_encrypt(ctx, length, dst, src); } -static void des_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void des_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { des_decrypt(ctx, length, dst, src); } -DEFINE_ECB_CBC_CTR(qcrypto_nettle_des_rfb, QCryptoNettleDESRFB, +DEFINE_ECB_CBC_CTR(qcrypto_nettle_des, QCryptoNettleDES, DES_BLOCK_SIZE, des_encrypt_native, des_decrypt_native) @@ -304,13 +263,13 @@ typedef struct QCryptoNettleDES3 { uint8_t iv[DES3_BLOCK_SIZE]; } QCryptoNettleDES3; -static void des3_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void des3_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { des3_encrypt(ctx, length, dst, src); } -static void des3_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void des3_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { des3_decrypt(ctx, length, dst, src); @@ -327,17 +286,17 @@ typedef struct QCryptoNettleAES128 { struct aes128_ctx key[2], key_xts[2]; } QCryptoNettleAES128; -static void aes128_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void aes128_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes128_ctx *keys = ctx; + const struct aes128_ctx *keys = ctx; aes128_encrypt(&keys[0], length, dst, src); } -static void aes128_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void aes128_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes128_ctx *keys = ctx; + const struct aes128_ctx *keys = ctx; aes128_decrypt(&keys[1], length, dst, src); } @@ -353,17 +312,17 @@ typedef struct QCryptoNettleAES192 { struct aes192_ctx key[2], key_xts[2]; } QCryptoNettleAES192; -static void aes192_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void aes192_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes192_ctx *keys = ctx; + const struct aes192_ctx *keys = ctx; aes192_encrypt(&keys[0], length, dst, src); } -static void aes192_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void aes192_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes192_ctx *keys = ctx; + const struct aes192_ctx *keys = ctx; aes192_decrypt(&keys[1], length, dst, src); } @@ -379,17 +338,17 @@ typedef struct QCryptoNettleAES256 { struct aes256_ctx key[2], key_xts[2]; } QCryptoNettleAES256; -static void aes256_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void aes256_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes256_ctx *keys = ctx; + const struct aes256_ctx *keys = ctx; aes256_encrypt(&keys[0], length, dst, src); } -static void aes256_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, - uint8_t *dst, const uint8_t *src) +static void aes256_decrypt_native(const void *ctx, size_t length, + uint8_t *dst, const uint8_t *src) { - CONST_CTX struct aes256_ctx *keys = ctx; + const struct aes256_ctx *keys = ctx; aes256_decrypt(&keys[1], length, dst, src); } @@ -404,13 +363,13 @@ typedef struct QCryptoNettleCAST128 { struct cast128_ctx key, key_xts; } QCryptoNettleCAST128; -static void cast128_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void cast128_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { cast128_encrypt(ctx, length, dst, src); } -static void cast128_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void cast128_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { cast128_decrypt(ctx, length, dst, src); @@ -428,13 +387,13 @@ typedef struct QCryptoNettleSerpent { } QCryptoNettleSerpent; -static void serpent_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void serpent_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { serpent_encrypt(ctx, length, dst, src); } -static void serpent_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void serpent_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { serpent_decrypt(ctx, length, dst, src); @@ -451,13 +410,13 @@ typedef struct QCryptoNettleTwofish { struct twofish_ctx key, key_xts; } QCryptoNettleTwofish; -static void twofish_encrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void twofish_encrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { twofish_encrypt(ctx, length, dst, src); } -static void twofish_decrypt_native(cipher_ctx_t ctx, cipher_length_t length, +static void twofish_decrypt_native(const void *ctx, size_t length, uint8_t *dst, const uint8_t *src) { twofish_decrypt(ctx, length, dst, src); @@ -472,7 +431,7 @@ bool qcrypto_cipher_supports(QCryptoCipherAlgorithm alg, QCryptoCipherMode mode) { switch (alg) { - case QCRYPTO_CIPHER_ALG_DES_RFB: + case QCRYPTO_CIPHER_ALG_DES: case QCRYPTO_CIPHER_ALG_3DES: case QCRYPTO_CIPHER_ALG_AES_128: case QCRYPTO_CIPHER_ALG_AES_192: @@ -521,32 +480,28 @@ static QCryptoCipher *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg, } switch (alg) { - case QCRYPTO_CIPHER_ALG_DES_RFB: + case QCRYPTO_CIPHER_ALG_DES: { - QCryptoNettleDESRFB *ctx; + QCryptoNettleDES *ctx; const QCryptoCipherDriver *drv; - uint8_t *rfbkey; switch (mode) { case QCRYPTO_CIPHER_MODE_ECB: - drv = &qcrypto_nettle_des_rfb_driver_ecb; + drv = &qcrypto_nettle_des_driver_ecb; break; case QCRYPTO_CIPHER_MODE_CBC: - drv = &qcrypto_nettle_des_rfb_driver_cbc; + drv = &qcrypto_nettle_des_driver_cbc; break; case QCRYPTO_CIPHER_MODE_CTR: - drv = &qcrypto_nettle_des_rfb_driver_ctr; + drv = &qcrypto_nettle_des_driver_ctr; break; default: goto bad_cipher_mode; } - ctx = g_new0(QCryptoNettleDESRFB, 1); + ctx = g_new0(QCryptoNettleDES, 1); ctx->base.driver = drv; - - rfbkey = qcrypto_cipher_munge_des_rfb_key(key, nkey); - des_set_key(&ctx->key, rfbkey); - g_free(rfbkey); + des_set_key(&ctx->key, key); return &ctx->base; } diff --git a/crypto/cipher.c b/crypto/cipher.c index 068b2fb867..74b09a5b26 100644 --- a/crypto/cipher.c +++ b/crypto/cipher.c @@ -29,7 +29,7 @@ static const size_t alg_key_len[QCRYPTO_CIPHER_ALG__MAX] = { [QCRYPTO_CIPHER_ALG_AES_128] = 16, [QCRYPTO_CIPHER_ALG_AES_192] = 24, [QCRYPTO_CIPHER_ALG_AES_256] = 32, - [QCRYPTO_CIPHER_ALG_DES_RFB] = 8, + [QCRYPTO_CIPHER_ALG_DES] = 8, [QCRYPTO_CIPHER_ALG_3DES] = 24, [QCRYPTO_CIPHER_ALG_CAST5_128] = 16, [QCRYPTO_CIPHER_ALG_SERPENT_128] = 16, @@ -44,7 +44,7 @@ static const size_t alg_block_len[QCRYPTO_CIPHER_ALG__MAX] = { [QCRYPTO_CIPHER_ALG_AES_128] = 16, [QCRYPTO_CIPHER_ALG_AES_192] = 16, [QCRYPTO_CIPHER_ALG_AES_256] = 16, - [QCRYPTO_CIPHER_ALG_DES_RFB] = 8, + [QCRYPTO_CIPHER_ALG_DES] = 8, [QCRYPTO_CIPHER_ALG_3DES] = 8, [QCRYPTO_CIPHER_ALG_CAST5_128] = 8, [QCRYPTO_CIPHER_ALG_SERPENT_128] = 16, @@ -107,9 +107,9 @@ qcrypto_cipher_validate_key_length(QCryptoCipherAlgorithm alg, } if (mode == QCRYPTO_CIPHER_MODE_XTS) { - if (alg == QCRYPTO_CIPHER_ALG_DES_RFB - || alg == QCRYPTO_CIPHER_ALG_3DES) { - error_setg(errp, "XTS mode not compatible with DES-RFB/3DES"); + if (alg == QCRYPTO_CIPHER_ALG_DES || + alg == QCRYPTO_CIPHER_ALG_3DES) { + error_setg(errp, "XTS mode not compatible with DES/3DES"); return false; } if (nkey % 2) { @@ -132,28 +132,12 @@ qcrypto_cipher_validate_key_length(QCryptoCipherAlgorithm alg, return true; } -#if defined(CONFIG_GCRYPT) || defined(CONFIG_NETTLE) -static uint8_t * -qcrypto_cipher_munge_des_rfb_key(const uint8_t *key, - size_t nkey) -{ - uint8_t *ret = g_new0(uint8_t, nkey); - size_t i; - for (i = 0; i < nkey; i++) { - uint8_t r = key[i]; - r = (r & 0xf0) >> 4 | (r & 0x0f) << 4; - r = (r & 0xcc) >> 2 | (r & 0x33) << 2; - r = (r & 0xaa) >> 1 | (r & 0x55) << 1; - ret[i] = r; - } - return ret; -} -#endif /* CONFIG_GCRYPT || CONFIG_NETTLE */ - #ifdef CONFIG_GCRYPT #include "cipher-gcrypt.c.inc" #elif defined CONFIG_NETTLE #include "cipher-nettle.c.inc" +#elif defined CONFIG_GNUTLS_CRYPTO +#include "cipher-gnutls.c.inc" #else #include "cipher-builtin.c.inc" #endif diff --git a/crypto/desrfb.c b/crypto/desrfb.c deleted file mode 100644 index b2a105ebbc..0000000000 --- a/crypto/desrfb.c +++ /dev/null @@ -1,416 +0,0 @@ -/* - * This is D3DES (V5.09) by Richard Outerbridge with the double and - * triple-length support removed for use in VNC. Also the bytebit[] array - * has been reversed so that the most significant bit in each byte of the - * key is ignored, not the least significant. - * - * These changes are: - * Copyright (C) 1999 AT&T Laboratories Cambridge. All Rights Reserved. - * - * This software is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - */ - -/* D3DES (V5.09) - - * - * A portable, public domain, version of the Data Encryption Standard. - * - * Written with Symantec's THINK (Lightspeed) C by Richard Outerbridge. - * Thanks to: Dan Hoey for his excellent Initial and Inverse permutation - * code; Jim Gillogly & Phil Karn for the DES key schedule code; Dennis - * Ferguson, Eric Young and Dana How for comparing notes; and Ray Lau, - * for humouring me on. - * - * Copyright (c) 1988,1989,1990,1991,1992 by Richard Outerbridge. - * (GEnie : OUTER; CIS : [71755,204]) Graven Imagery, 1992. - */ - -#include "qemu/osdep.h" -#include "crypto/desrfb.h" - -static void scrunch(unsigned char *, unsigned long *); -static void unscrun(unsigned long *, unsigned char *); -static void desfunc(unsigned long *, unsigned long *); -static void cookey(unsigned long *); - -static unsigned long KnL[32] = { 0L }; - -static const unsigned short bytebit[8] = { - 01, 02, 04, 010, 020, 040, 0100, 0200 }; - -static const unsigned long bigbyte[24] = { - 0x800000L, 0x400000L, 0x200000L, 0x100000L, - 0x80000L, 0x40000L, 0x20000L, 0x10000L, - 0x8000L, 0x4000L, 0x2000L, 0x1000L, - 0x800L, 0x400L, 0x200L, 0x100L, - 0x80L, 0x40L, 0x20L, 0x10L, - 0x8L, 0x4L, 0x2L, 0x1L }; - -/* Use the key schedule specified in the Standard (ANSI X3.92-1981). */ - -static const unsigned char pc1[56] = { - 56, 48, 40, 32, 24, 16, 8, 0, 57, 49, 41, 33, 25, 17, - 9, 1, 58, 50, 42, 34, 26, 18, 10, 2, 59, 51, 43, 35, - 62, 54, 46, 38, 30, 22, 14, 6, 61, 53, 45, 37, 29, 21, - 13, 5, 60, 52, 44, 36, 28, 20, 12, 4, 27, 19, 11, 3 }; - -static const unsigned char totrot[16] = { - 1, 2, 4, 6, 8, 10, 12, 14, 15, 17, 19, 21, 23, 25, 27, 28 }; - -static const unsigned char pc2[48] = { - 13, 16, 10, 23, 0, 4, 2, 27, 14, 5, 20, 9, - 22, 18, 11, 3, 25, 7, 15, 6, 26, 19, 12, 1, - 40, 51, 30, 36, 46, 54, 29, 39, 50, 44, 32, 47, - 43, 48, 38, 55, 33, 52, 45, 41, 49, 35, 28, 31 }; - -/* Thanks to James Gillogly & Phil Karn! */ -void deskey(unsigned char *key, int edf) -{ - register int i, j, l, m, n; - unsigned char pc1m[56], pcr[56]; - unsigned long kn[32]; - - for ( j = 0; j < 56; j++ ) { - l = pc1[j]; - m = l & 07; - pc1m[j] = (key[l >> 3] & bytebit[m]) ? 1 : 0; - } - for( i = 0; i < 16; i++ ) { - if( edf == DE1 ) m = (15 - i) << 1; - else m = i << 1; - n = m + 1; - kn[m] = kn[n] = 0L; - for( j = 0; j < 28; j++ ) { - l = j + totrot[i]; - if( l < 28 ) pcr[j] = pc1m[l]; - else pcr[j] = pc1m[l - 28]; - } - for( j = 28; j < 56; j++ ) { - l = j + totrot[i]; - if( l < 56 ) pcr[j] = pc1m[l]; - else pcr[j] = pc1m[l - 28]; - } - for( j = 0; j < 24; j++ ) { - if( pcr[pc2[j]] ) kn[m] |= bigbyte[j]; - if( pcr[pc2[j + 24]] ) kn[n] |= bigbyte[j]; - } - } - cookey(kn); - return; - } - -static void cookey(register unsigned long *raw1) -{ - register unsigned long *cook, *raw0; - unsigned long dough[32]; - register int i; - - cook = dough; - for( i = 0; i < 16; i++, raw1++ ) { - raw0 = raw1++; - *cook = (*raw0 & 0x00fc0000L) << 6; - *cook |= (*raw0 & 0x00000fc0L) << 10; - *cook |= (*raw1 & 0x00fc0000L) >> 10; - *cook++ |= (*raw1 & 0x00000fc0L) >> 6; - *cook = (*raw0 & 0x0003f000L) << 12; - *cook |= (*raw0 & 0x0000003fL) << 16; - *cook |= (*raw1 & 0x0003f000L) >> 4; - *cook++ |= (*raw1 & 0x0000003fL); - } - usekey(dough); - return; - } - -void usekey(register unsigned long *from) -{ - register unsigned long *to, *endp; - - to = KnL, endp = &KnL[32]; - while( to < endp ) *to++ = *from++; - return; - } - -void des(unsigned char *inblock, unsigned char *outblock) -{ - unsigned long work[2]; - - scrunch(inblock, work); - desfunc(work, KnL); - unscrun(work, outblock); - return; - } - -static void scrunch(register unsigned char *outof, register unsigned long *into) -{ - *into = (*outof++ & 0xffL) << 24; - *into |= (*outof++ & 0xffL) << 16; - *into |= (*outof++ & 0xffL) << 8; - *into++ |= (*outof++ & 0xffL); - *into = (*outof++ & 0xffL) << 24; - *into |= (*outof++ & 0xffL) << 16; - *into |= (*outof++ & 0xffL) << 8; - *into |= (*outof & 0xffL); - return; - } - -static void unscrun(register unsigned long *outof, register unsigned char *into) -{ - *into++ = (unsigned char)((*outof >> 24) & 0xffL); - *into++ = (unsigned char)((*outof >> 16) & 0xffL); - *into++ = (unsigned char)((*outof >> 8) & 0xffL); - *into++ = (unsigned char)(*outof++ & 0xffL); - *into++ = (unsigned char)((*outof >> 24) & 0xffL); - *into++ = (unsigned char)((*outof >> 16) & 0xffL); - *into++ = (unsigned char)((*outof >> 8) & 0xffL); - *into = (unsigned char)(*outof & 0xffL); - return; - } - -static const unsigned long SP1[64] = { - 0x01010400L, 0x00000000L, 0x00010000L, 0x01010404L, - 0x01010004L, 0x00010404L, 0x00000004L, 0x00010000L, - 0x00000400L, 0x01010400L, 0x01010404L, 0x00000400L, - 0x01000404L, 0x01010004L, 0x01000000L, 0x00000004L, - 0x00000404L, 0x01000400L, 0x01000400L, 0x00010400L, - 0x00010400L, 0x01010000L, 0x01010000L, 0x01000404L, - 0x00010004L, 0x01000004L, 0x01000004L, 0x00010004L, - 0x00000000L, 0x00000404L, 0x00010404L, 0x01000000L, - 0x00010000L, 0x01010404L, 0x00000004L, 0x01010000L, - 0x01010400L, 0x01000000L, 0x01000000L, 0x00000400L, - 0x01010004L, 0x00010000L, 0x00010400L, 0x01000004L, - 0x00000400L, 0x00000004L, 0x01000404L, 0x00010404L, - 0x01010404L, 0x00010004L, 0x01010000L, 0x01000404L, - 0x01000004L, 0x00000404L, 0x00010404L, 0x01010400L, - 0x00000404L, 0x01000400L, 0x01000400L, 0x00000000L, - 0x00010004L, 0x00010400L, 0x00000000L, 0x01010004L }; - -static const unsigned long SP2[64] = { - 0x80108020L, 0x80008000L, 0x00008000L, 0x00108020L, - 0x00100000L, 0x00000020L, 0x80100020L, 0x80008020L, - 0x80000020L, 0x80108020L, 0x80108000L, 0x80000000L, - 0x80008000L, 0x00100000L, 0x00000020L, 0x80100020L, - 0x00108000L, 0x00100020L, 0x80008020L, 0x00000000L, - 0x80000000L, 0x00008000L, 0x00108020L, 0x80100000L, - 0x00100020L, 0x80000020L, 0x00000000L, 0x00108000L, - 0x00008020L, 0x80108000L, 0x80100000L, 0x00008020L, - 0x00000000L, 0x00108020L, 0x80100020L, 0x00100000L, - 0x80008020L, 0x80100000L, 0x80108000L, 0x00008000L, - 0x80100000L, 0x80008000L, 0x00000020L, 0x80108020L, - 0x00108020L, 0x00000020L, 0x00008000L, 0x80000000L, - 0x00008020L, 0x80108000L, 0x00100000L, 0x80000020L, - 0x00100020L, 0x80008020L, 0x80000020L, 0x00100020L, - 0x00108000L, 0x00000000L, 0x80008000L, 0x00008020L, - 0x80000000L, 0x80100020L, 0x80108020L, 0x00108000L }; - -static const unsigned long SP3[64] = { - 0x00000208L, 0x08020200L, 0x00000000L, 0x08020008L, - 0x08000200L, 0x00000000L, 0x00020208L, 0x08000200L, - 0x00020008L, 0x08000008L, 0x08000008L, 0x00020000L, - 0x08020208L, 0x00020008L, 0x08020000L, 0x00000208L, - 0x08000000L, 0x00000008L, 0x08020200L, 0x00000200L, - 0x00020200L, 0x08020000L, 0x08020008L, 0x00020208L, - 0x08000208L, 0x00020200L, 0x00020000L, 0x08000208L, - 0x00000008L, 0x08020208L, 0x00000200L, 0x08000000L, - 0x08020200L, 0x08000000L, 0x00020008L, 0x00000208L, - 0x00020000L, 0x08020200L, 0x08000200L, 0x00000000L, - 0x00000200L, 0x00020008L, 0x08020208L, 0x08000200L, - 0x08000008L, 0x00000200L, 0x00000000L, 0x08020008L, - 0x08000208L, 0x00020000L, 0x08000000L, 0x08020208L, - 0x00000008L, 0x00020208L, 0x00020200L, 0x08000008L, - 0x08020000L, 0x08000208L, 0x00000208L, 0x08020000L, - 0x00020208L, 0x00000008L, 0x08020008L, 0x00020200L }; - -static const unsigned long SP4[64] = { - 0x00802001L, 0x00002081L, 0x00002081L, 0x00000080L, - 0x00802080L, 0x00800081L, 0x00800001L, 0x00002001L, - 0x00000000L, 0x00802000L, 0x00802000L, 0x00802081L, - 0x00000081L, 0x00000000L, 0x00800080L, 0x00800001L, - 0x00000001L, 0x00002000L, 0x00800000L, 0x00802001L, - 0x00000080L, 0x00800000L, 0x00002001L, 0x00002080L, - 0x00800081L, 0x00000001L, 0x00002080L, 0x00800080L, - 0x00002000L, 0x00802080L, 0x00802081L, 0x00000081L, - 0x00800080L, 0x00800001L, 0x00802000L, 0x00802081L, - 0x00000081L, 0x00000000L, 0x00000000L, 0x00802000L, - 0x00002080L, 0x00800080L, 0x00800081L, 0x00000001L, - 0x00802001L, 0x00002081L, 0x00002081L, 0x00000080L, - 0x00802081L, 0x00000081L, 0x00000001L, 0x00002000L, - 0x00800001L, 0x00002001L, 0x00802080L, 0x00800081L, - 0x00002001L, 0x00002080L, 0x00800000L, 0x00802001L, - 0x00000080L, 0x00800000L, 0x00002000L, 0x00802080L }; - -static const unsigned long SP5[64] = { - 0x00000100L, 0x02080100L, 0x02080000L, 0x42000100L, - 0x00080000L, 0x00000100L, 0x40000000L, 0x02080000L, - 0x40080100L, 0x00080000L, 0x02000100L, 0x40080100L, - 0x42000100L, 0x42080000L, 0x00080100L, 0x40000000L, - 0x02000000L, 0x40080000L, 0x40080000L, 0x00000000L, - 0x40000100L, 0x42080100L, 0x42080100L, 0x02000100L, - 0x42080000L, 0x40000100L, 0x00000000L, 0x42000000L, - 0x02080100L, 0x02000000L, 0x42000000L, 0x00080100L, - 0x00080000L, 0x42000100L, 0x00000100L, 0x02000000L, - 0x40000000L, 0x02080000L, 0x42000100L, 0x40080100L, - 0x02000100L, 0x40000000L, 0x42080000L, 0x02080100L, - 0x40080100L, 0x00000100L, 0x02000000L, 0x42080000L, - 0x42080100L, 0x00080100L, 0x42000000L, 0x42080100L, - 0x02080000L, 0x00000000L, 0x40080000L, 0x42000000L, - 0x00080100L, 0x02000100L, 0x40000100L, 0x00080000L, - 0x00000000L, 0x40080000L, 0x02080100L, 0x40000100L }; - -static const unsigned long SP6[64] = { - 0x20000010L, 0x20400000L, 0x00004000L, 0x20404010L, - 0x20400000L, 0x00000010L, 0x20404010L, 0x00400000L, - 0x20004000L, 0x00404010L, 0x00400000L, 0x20000010L, - 0x00400010L, 0x20004000L, 0x20000000L, 0x00004010L, - 0x00000000L, 0x00400010L, 0x20004010L, 0x00004000L, - 0x00404000L, 0x20004010L, 0x00000010L, 0x20400010L, - 0x20400010L, 0x00000000L, 0x00404010L, 0x20404000L, - 0x00004010L, 0x00404000L, 0x20404000L, 0x20000000L, - 0x20004000L, 0x00000010L, 0x20400010L, 0x00404000L, - 0x20404010L, 0x00400000L, 0x00004010L, 0x20000010L, - 0x00400000L, 0x20004000L, 0x20000000L, 0x00004010L, - 0x20000010L, 0x20404010L, 0x00404000L, 0x20400000L, - 0x00404010L, 0x20404000L, 0x00000000L, 0x20400010L, - 0x00000010L, 0x00004000L, 0x20400000L, 0x00404010L, - 0x00004000L, 0x00400010L, 0x20004010L, 0x00000000L, - 0x20404000L, 0x20000000L, 0x00400010L, 0x20004010L }; - -static const unsigned long SP7[64] = { - 0x00200000L, 0x04200002L, 0x04000802L, 0x00000000L, - 0x00000800L, 0x04000802L, 0x00200802L, 0x04200800L, - 0x04200802L, 0x00200000L, 0x00000000L, 0x04000002L, - 0x00000002L, 0x04000000L, 0x04200002L, 0x00000802L, - 0x04000800L, 0x00200802L, 0x00200002L, 0x04000800L, - 0x04000002L, 0x04200000L, 0x04200800L, 0x00200002L, - 0x04200000L, 0x00000800L, 0x00000802L, 0x04200802L, - 0x00200800L, 0x00000002L, 0x04000000L, 0x00200800L, - 0x04000000L, 0x00200800L, 0x00200000L, 0x04000802L, - 0x04000802L, 0x04200002L, 0x04200002L, 0x00000002L, - 0x00200002L, 0x04000000L, 0x04000800L, 0x00200000L, - 0x04200800L, 0x00000802L, 0x00200802L, 0x04200800L, - 0x00000802L, 0x04000002L, 0x04200802L, 0x04200000L, - 0x00200800L, 0x00000000L, 0x00000002L, 0x04200802L, - 0x00000000L, 0x00200802L, 0x04200000L, 0x00000800L, - 0x04000002L, 0x04000800L, 0x00000800L, 0x00200002L }; - -static const unsigned long SP8[64] = { - 0x10001040L, 0x00001000L, 0x00040000L, 0x10041040L, - 0x10000000L, 0x10001040L, 0x00000040L, 0x10000000L, - 0x00040040L, 0x10040000L, 0x10041040L, 0x00041000L, - 0x10041000L, 0x00041040L, 0x00001000L, 0x00000040L, - 0x10040000L, 0x10000040L, 0x10001000L, 0x00001040L, - 0x00041000L, 0x00040040L, 0x10040040L, 0x10041000L, - 0x00001040L, 0x00000000L, 0x00000000L, 0x10040040L, - 0x10000040L, 0x10001000L, 0x00041040L, 0x00040000L, - 0x00041040L, 0x00040000L, 0x10041000L, 0x00001000L, - 0x00000040L, 0x10040040L, 0x00001000L, 0x00041040L, - 0x10001000L, 0x00000040L, 0x10000040L, 0x10040000L, - 0x10040040L, 0x10000000L, 0x00040000L, 0x10001040L, - 0x00000000L, 0x10041040L, 0x00040040L, 0x10000040L, - 0x10040000L, 0x10001000L, 0x10001040L, 0x00000000L, - 0x10041040L, 0x00041000L, 0x00041000L, 0x00001040L, - 0x00001040L, 0x00040040L, 0x10000000L, 0x10041000L }; - -static void desfunc(register unsigned long *block, register unsigned long *keys) -{ - register unsigned long fval, work, right, leftt; - register int round; - - leftt = block[0]; - right = block[1]; - work = ((leftt >> 4) ^ right) & 0x0f0f0f0fL; - right ^= work; - leftt ^= (work << 4); - work = ((leftt >> 16) ^ right) & 0x0000ffffL; - right ^= work; - leftt ^= (work << 16); - work = ((right >> 2) ^ leftt) & 0x33333333L; - leftt ^= work; - right ^= (work << 2); - work = ((right >> 8) ^ leftt) & 0x00ff00ffL; - leftt ^= work; - right ^= (work << 8); - right = ((right << 1) | ((right >> 31) & 1L)) & 0xffffffffL; - work = (leftt ^ right) & 0xaaaaaaaaL; - leftt ^= work; - right ^= work; - leftt = ((leftt << 1) | ((leftt >> 31) & 1L)) & 0xffffffffL; - - for( round = 0; round < 8; round++ ) { - work = (right << 28) | (right >> 4); - work ^= *keys++; - fval = SP7[ work & 0x3fL]; - fval |= SP5[(work >> 8) & 0x3fL]; - fval |= SP3[(work >> 16) & 0x3fL]; - fval |= SP1[(work >> 24) & 0x3fL]; - work = right ^ *keys++; - fval |= SP8[ work & 0x3fL]; - fval |= SP6[(work >> 8) & 0x3fL]; - fval |= SP4[(work >> 16) & 0x3fL]; - fval |= SP2[(work >> 24) & 0x3fL]; - leftt ^= fval; - work = (leftt << 28) | (leftt >> 4); - work ^= *keys++; - fval = SP7[ work & 0x3fL]; - fval |= SP5[(work >> 8) & 0x3fL]; - fval |= SP3[(work >> 16) & 0x3fL]; - fval |= SP1[(work >> 24) & 0x3fL]; - work = leftt ^ *keys++; - fval |= SP8[ work & 0x3fL]; - fval |= SP6[(work >> 8) & 0x3fL]; - fval |= SP4[(work >> 16) & 0x3fL]; - fval |= SP2[(work >> 24) & 0x3fL]; - right ^= fval; - } - - right = (right << 31) | (right >> 1); - work = (leftt ^ right) & 0xaaaaaaaaL; - leftt ^= work; - right ^= work; - leftt = (leftt << 31) | (leftt >> 1); - work = ((leftt >> 8) ^ right) & 0x00ff00ffL; - right ^= work; - leftt ^= (work << 8); - work = ((leftt >> 2) ^ right) & 0x33333333L; - right ^= work; - leftt ^= (work << 2); - work = ((right >> 16) ^ leftt) & 0x0000ffffL; - leftt ^= work; - right ^= (work << 16); - work = ((right >> 4) ^ leftt) & 0x0f0f0f0fL; - leftt ^= work; - right ^= (work << 4); - *block++ = right; - *block = leftt; - return; - } - -/* Validation sets: - * - * Single-length key, single-length plaintext - - * Key : 0123 4567 89ab cdef - * Plain : 0123 4567 89ab cde7 - * Cipher : c957 4425 6a5e d31d - * - * Double-length key, single-length plaintext - - * Key : 0123 4567 89ab cdef fedc ba98 7654 3210 - * Plain : 0123 4567 89ab cde7 - * Cipher : 7f1d 0a77 826b 8aff - * - * Double-length key, double-length plaintext - - * Key : 0123 4567 89ab cdef fedc ba98 7654 3210 - * Plain : 0123 4567 89ab cdef 0123 4567 89ab cdff - * Cipher : 27a0 8440 406a df60 278f 47cf 42d6 15d7 - * - * Triple-length key, single-length plaintext - - * Key : 0123 4567 89ab cdef fedc ba98 7654 3210 89ab cdef 0123 4567 - * Plain : 0123 4567 89ab cde7 - * Cipher : de0b 7c06 ae5e 0ed5 - * - * Triple-length key, double-length plaintext - - * Key : 0123 4567 89ab cdef fedc ba98 7654 3210 89ab cdef 0123 4567 - * Plain : 0123 4567 89ab cdef 0123 4567 89ab cdff - * Cipher : ad0d 1b30 ac17 cf07 0ed1 1c63 81e4 4de5 - * - * d3des V5.0a rwo 9208.07 18:44 Graven Imagery - **********************************************************************/ diff --git a/crypto/hash-gnutls.c b/crypto/hash-gnutls.c new file mode 100644 index 0000000000..17911ac5d1 --- /dev/null +++ b/crypto/hash-gnutls.c @@ -0,0 +1,104 @@ +/* + * QEMU Crypto hash algorithms + * + * Copyright (c) 2021 Red Hat, Inc. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see . + * + */ + +#include "qemu/osdep.h" +#include +#include "qapi/error.h" +#include "crypto/hash.h" +#include "hashpriv.h" + + +static int qcrypto_hash_alg_map[QCRYPTO_HASH_ALG__MAX] = { + [QCRYPTO_HASH_ALG_MD5] = GNUTLS_DIG_MD5, + [QCRYPTO_HASH_ALG_SHA1] = GNUTLS_DIG_SHA1, + [QCRYPTO_HASH_ALG_SHA224] = GNUTLS_DIG_SHA224, + [QCRYPTO_HASH_ALG_SHA256] = GNUTLS_DIG_SHA256, + [QCRYPTO_HASH_ALG_SHA384] = GNUTLS_DIG_SHA384, + [QCRYPTO_HASH_ALG_SHA512] = GNUTLS_DIG_SHA512, + [QCRYPTO_HASH_ALG_RIPEMD160] = GNUTLS_DIG_RMD160, +}; + +gboolean qcrypto_hash_supports(QCryptoHashAlgorithm alg) +{ + size_t i; + const gnutls_digest_algorithm_t *algs; + if (alg >= G_N_ELEMENTS(qcrypto_hash_alg_map) || + qcrypto_hash_alg_map[alg] == GNUTLS_DIG_UNKNOWN) { + return false; + } + algs = gnutls_digest_list(); + for (i = 0; algs[i] != GNUTLS_DIG_UNKNOWN; i++) { + if (algs[i] == qcrypto_hash_alg_map[alg]) { + return true; + } + } + return false; +} + + +static int +qcrypto_gnutls_hash_bytesv(QCryptoHashAlgorithm alg, + const struct iovec *iov, + size_t niov, + uint8_t **result, + size_t *resultlen, + Error **errp) +{ + int i, ret; + gnutls_hash_hd_t hash; + + if (!qcrypto_hash_supports(alg)) { + error_setg(errp, + "Unknown hash algorithm %d", + alg); + return -1; + } + + ret = gnutls_hash_get_len(qcrypto_hash_alg_map[alg]); + if (*resultlen == 0) { + *resultlen = ret; + *result = g_new0(uint8_t, *resultlen); + } else if (*resultlen != ret) { + error_setg(errp, + "Result buffer size %zu is smaller than hash %d", + *resultlen, ret); + return -1; + } + + ret = gnutls_hash_init(&hash, qcrypto_hash_alg_map[alg]); + if (ret < 0) { + error_setg(errp, + "Unable to initialize hash algorithm: %s", + gnutls_strerror(ret)); + return -1; + } + + for (i = 0; i < niov; i++) { + gnutls_hash(hash, iov[i].iov_base, iov[i].iov_len); + } + + gnutls_hash_deinit(hash, *result); + return 0; +} + + +QCryptoHashDriver qcrypto_hash_lib_driver = { + .hash_bytesv = qcrypto_gnutls_hash_bytesv, +}; diff --git a/crypto/hash-nettle.c b/crypto/hash-nettle.c index 2a6ee7c7d5..1ca1a41062 100644 --- a/crypto/hash-nettle.c +++ b/crypto/hash-nettle.c @@ -26,18 +26,12 @@ #include #include -#if CONFIG_NETTLE_VERSION_MAJOR < 3 -typedef unsigned int hash_length_t; -#else -typedef size_t hash_length_t; -#endif - typedef void (*qcrypto_nettle_init)(void *ctx); typedef void (*qcrypto_nettle_write)(void *ctx, - hash_length_t len, + size_t len, const uint8_t *buf); typedef void (*qcrypto_nettle_result)(void *ctx, - hash_length_t len, + size_t len, uint8_t *buf); union qcrypto_hash_ctx { diff --git a/crypto/hmac-gnutls.c b/crypto/hmac-gnutls.c new file mode 100644 index 0000000000..24db383322 --- /dev/null +++ b/crypto/hmac-gnutls.c @@ -0,0 +1,139 @@ +/* + * QEMU Crypto hmac algorithms + * + * Copyright (c) 2021 Red Hat, Inc. + * + * Derived from hmac-gcrypt.c: + * + * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD. + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + * + */ + +#include "qemu/osdep.h" +#include + +#include "qapi/error.h" +#include "crypto/hmac.h" +#include "hmacpriv.h" + +static int qcrypto_hmac_alg_map[QCRYPTO_HASH_ALG__MAX] = { + [QCRYPTO_HASH_ALG_MD5] = GNUTLS_MAC_MD5, + [QCRYPTO_HASH_ALG_SHA1] = GNUTLS_MAC_SHA1, + [QCRYPTO_HASH_ALG_SHA224] = GNUTLS_MAC_SHA224, + [QCRYPTO_HASH_ALG_SHA256] = GNUTLS_MAC_SHA256, + [QCRYPTO_HASH_ALG_SHA384] = GNUTLS_MAC_SHA384, + [QCRYPTO_HASH_ALG_SHA512] = GNUTLS_MAC_SHA512, + [QCRYPTO_HASH_ALG_RIPEMD160] = GNUTLS_MAC_RMD160, +}; + +typedef struct QCryptoHmacGnutls QCryptoHmacGnutls; +struct QCryptoHmacGnutls { + gnutls_hmac_hd_t handle; +}; + +bool qcrypto_hmac_supports(QCryptoHashAlgorithm alg) +{ + size_t i; + const gnutls_digest_algorithm_t *algs; + if (alg >= G_N_ELEMENTS(qcrypto_hmac_alg_map) || + qcrypto_hmac_alg_map[alg] == GNUTLS_DIG_UNKNOWN) { + return false; + } + algs = gnutls_digest_list(); + for (i = 0; algs[i] != GNUTLS_DIG_UNKNOWN; i++) { + if (algs[i] == qcrypto_hmac_alg_map[alg]) { + return true; + } + } + return false; +} + +void *qcrypto_hmac_ctx_new(QCryptoHashAlgorithm alg, + const uint8_t *key, size_t nkey, + Error **errp) +{ + QCryptoHmacGnutls *ctx; + int err; + + if (!qcrypto_hmac_supports(alg)) { + error_setg(errp, "Unsupported hmac algorithm %s", + QCryptoHashAlgorithm_str(alg)); + return NULL; + } + + ctx = g_new0(QCryptoHmacGnutls, 1); + + err = gnutls_hmac_init(&ctx->handle, + qcrypto_hmac_alg_map[alg], + (const void *)key, nkey); + if (err != 0) { + error_setg(errp, "Cannot initialize hmac: %s", + gnutls_strerror(err)); + goto error; + } + + return ctx; + +error: + g_free(ctx); + return NULL; +} + +static void +qcrypto_gnutls_hmac_ctx_free(QCryptoHmac *hmac) +{ + QCryptoHmacGnutls *ctx; + + ctx = hmac->opaque; + gnutls_hmac_deinit(ctx->handle, NULL); + + g_free(ctx); +} + +static int +qcrypto_gnutls_hmac_bytesv(QCryptoHmac *hmac, + const struct iovec *iov, + size_t niov, + uint8_t **result, + size_t *resultlen, + Error **errp) +{ + QCryptoHmacGnutls *ctx; + uint32_t ret; + int i; + + ctx = hmac->opaque; + + for (i = 0; i < niov; i++) { + gnutls_hmac(ctx->handle, iov[i].iov_base, iov[i].iov_len); + } + + ret = gnutls_hmac_get_len(qcrypto_hmac_alg_map[hmac->alg]); + if (ret <= 0) { + error_setg(errp, "Unable to get hmac length: %s", + gnutls_strerror(ret)); + return -1; + } + + if (*resultlen == 0) { + *resultlen = ret; + *result = g_new0(uint8_t, *resultlen); + } else if (*resultlen != ret) { + error_setg(errp, "Result buffer size %zu is smaller than hmac %d", + *resultlen, ret); + return -1; + } + + gnutls_hmac_output(ctx->handle, *result); + + return 0; +} + +QCryptoHmacDriver qcrypto_hmac_lib_driver = { + .hmac_bytesv = qcrypto_gnutls_hmac_bytesv, + .hmac_free = qcrypto_gnutls_hmac_ctx_free, +}; diff --git a/crypto/hmac-nettle.c b/crypto/hmac-nettle.c index 1152b741fd..1ad6c4f253 100644 --- a/crypto/hmac-nettle.c +++ b/crypto/hmac-nettle.c @@ -18,22 +18,16 @@ #include "hmacpriv.h" #include -#if CONFIG_NETTLE_VERSION_MAJOR < 3 -typedef unsigned int hmac_length_t; -#else -typedef size_t hmac_length_t; -#endif - typedef void (*qcrypto_nettle_hmac_setkey)(void *ctx, - hmac_length_t key_length, + size_t key_length, const uint8_t *key); typedef void (*qcrypto_nettle_hmac_update)(void *ctx, - hmac_length_t length, + size_t length, const uint8_t *data); typedef void (*qcrypto_nettle_hmac_digest)(void *ctx, - hmac_length_t length, + size_t length, uint8_t *digest); typedef struct QCryptoHmacNettle QCryptoHmacNettle; diff --git a/crypto/init.c b/crypto/init.c index ea233b9192..fb7f1bff10 100644 --- a/crypto/init.c +++ b/crypto/init.c @@ -35,21 +35,6 @@ #include "crypto/random.h" /* #define DEBUG_GNUTLS */ - -/* - * We need to init gcrypt threading if - * - * - gcrypt < 1.6.0 - * - */ - -#if (defined(CONFIG_GCRYPT) && \ - (GCRYPT_VERSION_NUMBER < 0x010600)) -#define QCRYPTO_INIT_GCRYPT_THREADS -#else -#undef QCRYPTO_INIT_GCRYPT_THREADS -#endif - #ifdef DEBUG_GNUTLS static void qcrypto_gnutls_log(int level, const char *str) { @@ -57,55 +42,8 @@ static void qcrypto_gnutls_log(int level, const char *str) } #endif -#ifdef QCRYPTO_INIT_GCRYPT_THREADS -static int qcrypto_gcrypt_mutex_init(void **priv) -{ \ - QemuMutex *lock = NULL; - lock = g_new0(QemuMutex, 1); - qemu_mutex_init(lock); - *priv = lock; - return 0; -} - -static int qcrypto_gcrypt_mutex_destroy(void **priv) -{ - QemuMutex *lock = *priv; - qemu_mutex_destroy(lock); - g_free(lock); - return 0; -} - -static int qcrypto_gcrypt_mutex_lock(void **priv) -{ - QemuMutex *lock = *priv; - qemu_mutex_lock(lock); - return 0; -} - -static int qcrypto_gcrypt_mutex_unlock(void **priv) -{ - QemuMutex *lock = *priv; - qemu_mutex_unlock(lock); - return 0; -} - -static struct gcry_thread_cbs qcrypto_gcrypt_thread_impl = { - (GCRY_THREAD_OPTION_PTHREAD | (GCRY_THREAD_OPTION_VERSION << 8)), - NULL, - qcrypto_gcrypt_mutex_init, - qcrypto_gcrypt_mutex_destroy, - qcrypto_gcrypt_mutex_lock, - qcrypto_gcrypt_mutex_unlock, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL -}; -#endif /* QCRYPTO_INIT_GCRYPT */ - int qcrypto_init(Error **errp) { -#ifdef QCRYPTO_INIT_GCRYPT_THREADS - gcry_control(GCRYCTL_SET_THREAD_CBS, &qcrypto_gcrypt_thread_impl); -#endif /* QCRYPTO_INIT_GCRYPT_THREADS */ - #ifdef CONFIG_GNUTLS int ret; ret = gnutls_global_init(); diff --git a/crypto/meson.build b/crypto/meson.build index 7f37b5d335..95a6a83504 100644 --- a/crypto/meson.build +++ b/crypto/meson.build @@ -5,7 +5,6 @@ crypto_ss.add(files( 'block-qcow.c', 'block.c', 'cipher.c', - 'desrfb.c', 'hash.c', 'hmac.c', 'ivgen-essiv.c', @@ -22,52 +21,36 @@ crypto_ss.add(files( 'tlssession.c', )) -if 'CONFIG_NETTLE' in config_host - crypto_ss.add(files('hash-nettle.c', 'hmac-nettle.c', 'pbkdf-nettle.c')) -elif 'CONFIG_GCRYPT' in config_host - crypto_ss.add(files('hash-gcrypt.c', 'pbkdf-gcrypt.c')) - if 'CONFIG_GCRYPT_HMAC' in config_host - crypto_ss.add(files('hmac-gcrypt.c')) - else - crypto_ss.add(files('hmac-glib.c')) +if nettle.found() + crypto_ss.add(nettle, files('hash-nettle.c', 'hmac-nettle.c', 'pbkdf-nettle.c')) + if xts == 'private' + crypto_ss.add(files('xts.c')) endif +elif gcrypt.found() + crypto_ss.add(gcrypt, files('hash-gcrypt.c', 'hmac-gcrypt.c', 'pbkdf-gcrypt.c')) +elif gnutls_crypto.found() + crypto_ss.add(gnutls, files('hash-gnutls.c', 'hmac-gnutls.c', 'pbkdf-gnutls.c')) else crypto_ss.add(files('hash-glib.c', 'hmac-glib.c', 'pbkdf-stub.c')) endif crypto_ss.add(when: 'CONFIG_SECRET_KEYRING', if_true: files('secret_keyring.c')) -crypto_ss.add(when: 'CONFIG_QEMU_PRIVATE_XTS', if_true: files('xts.c')) crypto_ss.add(when: 'CONFIG_AF_ALG', if_true: files('afalg.c', 'cipher-afalg.c', 'hash-afalg.c')) -crypto_ss.add(when: 'CONFIG_GNUTLS', if_true: files('tls-cipher-suites.c')) - -if 'CONFIG_NETTLE' in config_host - crypto_ss.add(nettle) -elif 'CONFIG_GCRYPT' in config_host - crypto_ss.add(gcrypt) -endif - -if 'CONFIG_GNUTLS' in config_host - crypto_ss.add(gnutls) -endif - +crypto_ss.add(when: gnutls, if_true: files('tls-cipher-suites.c')) util_ss.add(files('aes.c')) util_ss.add(files('init.c')) +if gnutls.found() + util_ss.add(gnutls) +endif -if 'CONFIG_GCRYPT' in config_host - util_ss.add(files('random-gcrypt.c')) -elif 'CONFIG_GNUTLS' in config_host - util_ss.add(files('random-gnutls.c')) +if gcrypt.found() + util_ss.add(gcrypt, files('random-gcrypt.c')) +elif gnutls.found() + util_ss.add(gnutls, files('random-gnutls.c')) elif 'CONFIG_RNG_NONE' in config_host util_ss.add(files('random-none.c')) else util_ss.add(files('random-platform.c')) endif -if 'CONFIG_GCRYPT' in config_host - util_ss.add(gcrypt) -endif - -if 'CONFIG_GNUTLS' in config_host - util_ss.add(gnutls) -endif diff --git a/crypto/pbkdf-gnutls.c b/crypto/pbkdf-gnutls.c new file mode 100644 index 0000000000..2dfbbd382c --- /dev/null +++ b/crypto/pbkdf-gnutls.c @@ -0,0 +1,90 @@ +/* + * QEMU Crypto PBKDF support (Password-Based Key Derivation Function) + * + * Copyright (c) 2021 Red Hat, Inc. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see . + * + */ + +#include "qemu/osdep.h" +#include +#include "qapi/error.h" +#include "crypto/pbkdf.h" + +bool qcrypto_pbkdf2_supports(QCryptoHashAlgorithm hash) +{ + switch (hash) { + case QCRYPTO_HASH_ALG_MD5: + case QCRYPTO_HASH_ALG_SHA1: + case QCRYPTO_HASH_ALG_SHA224: + case QCRYPTO_HASH_ALG_SHA256: + case QCRYPTO_HASH_ALG_SHA384: + case QCRYPTO_HASH_ALG_SHA512: + case QCRYPTO_HASH_ALG_RIPEMD160: + return true; + default: + return false; + } +} + +int qcrypto_pbkdf2(QCryptoHashAlgorithm hash, + const uint8_t *key, size_t nkey, + const uint8_t *salt, size_t nsalt, + uint64_t iterations, + uint8_t *out, size_t nout, + Error **errp) +{ + static const int hash_map[QCRYPTO_HASH_ALG__MAX] = { + [QCRYPTO_HASH_ALG_MD5] = GNUTLS_DIG_MD5, + [QCRYPTO_HASH_ALG_SHA1] = GNUTLS_DIG_SHA1, + [QCRYPTO_HASH_ALG_SHA224] = GNUTLS_DIG_SHA224, + [QCRYPTO_HASH_ALG_SHA256] = GNUTLS_DIG_SHA256, + [QCRYPTO_HASH_ALG_SHA384] = GNUTLS_DIG_SHA384, + [QCRYPTO_HASH_ALG_SHA512] = GNUTLS_DIG_SHA512, + [QCRYPTO_HASH_ALG_RIPEMD160] = GNUTLS_DIG_RMD160, + }; + int ret; + const gnutls_datum_t gkey = { (unsigned char *)key, nkey }; + const gnutls_datum_t gsalt = { (unsigned char *)salt, nsalt }; + + if (iterations > ULONG_MAX) { + error_setg_errno(errp, ERANGE, + "PBKDF iterations %llu must be less than %lu", + (long long unsigned)iterations, ULONG_MAX); + return -1; + } + + if (hash >= G_N_ELEMENTS(hash_map) || + hash_map[hash] == GNUTLS_DIG_UNKNOWN) { + error_setg_errno(errp, ENOSYS, + "PBKDF does not support hash algorithm %s", + QCryptoHashAlgorithm_str(hash)); + return -1; + } + + ret = gnutls_pbkdf2(hash_map[hash], + &gkey, + &gsalt, + iterations, + out, + nout); + if (ret != 0) { + error_setg(errp, "Cannot derive password: %s", + gnutls_strerror(ret)); + return -1; + } + + return 0; +} diff --git a/crypto/tls-cipher-suites.c b/crypto/tls-cipher-suites.c index 55fb5f7c19..5e4f597464 100644 --- a/crypto/tls-cipher-suites.c +++ b/crypto/tls-cipher-suites.c @@ -14,8 +14,15 @@ #include "crypto/tlscreds.h" #include "crypto/tls-cipher-suites.h" #include "hw/nvram/fw_cfg.h" +#include "tlscredspriv.h" #include "trace.h" +struct QCryptoTLSCipherSuites { + /* */ + QCryptoTLSCreds parent_obj; + /* */ +}; + /* * IANA registered TLS ciphers: * https://www.iana.org/assignments/tls-parameters/tls-parameters.xhtml#tls-parameters-4 diff --git a/crypto/tlscreds.c b/crypto/tlscreds.c index b68735f06f..084ce0d51a 100644 --- a/crypto/tlscreds.c +++ b/crypto/tlscreds.c @@ -20,6 +20,7 @@ #include "qemu/osdep.h" #include "qapi/error.h" +#include "qapi-types-crypto.h" #include "qemu/module.h" #include "tlscredspriv.h" #include "trace.h" @@ -259,6 +260,17 @@ qcrypto_tls_creds_finalize(Object *obj) g_free(creds->priority); } +bool qcrypto_tls_creds_check_endpoint(QCryptoTLSCreds *creds, + QCryptoTLSCredsEndpoint endpoint, + Error **errp) +{ + if (creds->endpoint != endpoint) { + error_setg(errp, "Expected TLS credentials for a %s endpoint", + QCryptoTLSCredsEndpoint_str(endpoint)); + return false; + } + return true; +} static const TypeInfo qcrypto_tls_creds_info = { .parent = TYPE_OBJECT, diff --git a/crypto/tlscredsanon.c b/crypto/tlscredsanon.c index bea5f76c55..6fb83639ec 100644 --- a/crypto/tlscredsanon.c +++ b/crypto/tlscredsanon.c @@ -29,6 +29,8 @@ #ifdef CONFIG_GNUTLS +#include + static int qcrypto_tls_creds_anon_load(QCryptoTLSCredsAnon *creds, diff --git a/crypto/tlscredspriv.h b/crypto/tlscredspriv.h index 39f1a91c41..df9815a286 100644 --- a/crypto/tlscredspriv.h +++ b/crypto/tlscredspriv.h @@ -23,6 +23,51 @@ #include "crypto/tlscreds.h" +#ifdef CONFIG_GNUTLS +#include +#endif + +struct QCryptoTLSCreds { + Object parent_obj; + char *dir; + QCryptoTLSCredsEndpoint endpoint; +#ifdef CONFIG_GNUTLS + gnutls_dh_params_t dh_params; +#endif + bool verifyPeer; + char *priority; +}; + +struct QCryptoTLSCredsAnon { + QCryptoTLSCreds parent_obj; +#ifdef CONFIG_GNUTLS + union { + gnutls_anon_server_credentials_t server; + gnutls_anon_client_credentials_t client; + } data; +#endif +}; + +struct QCryptoTLSCredsPSK { + QCryptoTLSCreds parent_obj; + char *username; +#ifdef CONFIG_GNUTLS + union { + gnutls_psk_server_credentials_t server; + gnutls_psk_client_credentials_t client; + } data; +#endif +}; + +struct QCryptoTLSCredsX509 { + QCryptoTLSCreds parent_obj; +#ifdef CONFIG_GNUTLS + gnutls_certificate_credentials_t data; +#endif + bool sanityCheck; + char *passwordid; +}; + #ifdef CONFIG_GNUTLS int qcrypto_tls_creds_get_path(QCryptoTLSCreds *creds, diff --git a/crypto/tlscredspsk.c b/crypto/tlscredspsk.c index f5a31108d1..752f2d92be 100644 --- a/crypto/tlscredspsk.c +++ b/crypto/tlscredspsk.c @@ -29,6 +29,8 @@ #ifdef CONFIG_GNUTLS +#include + static int lookup_key(const char *pskfile, const char *username, gnutls_datum_t *key, Error **errp) diff --git a/crypto/tlscredsx509.c b/crypto/tlscredsx509.c index bc503bab55..32948a6bdc 100644 --- a/crypto/tlscredsx509.c +++ b/crypto/tlscredsx509.c @@ -30,6 +30,7 @@ #ifdef CONFIG_GNUTLS +#include #include @@ -354,11 +355,9 @@ qcrypto_tls_creds_check_cert_pair(gnutls_x509_crt_t cert, reason = "The certificate has been revoked"; } -#ifndef GNUTLS_1_0_COMPAT if (status & GNUTLS_CERT_INSECURE_ALGORITHM) { reason = "The certificate uses an insecure algorithm"; } -#endif error_setg(errp, "Our own certificate %s failed validation against %s: %s", diff --git a/crypto/tlssession.c b/crypto/tlssession.c index 33203e8ca7..a8db8c76d1 100644 --- a/crypto/tlssession.c +++ b/crypto/tlssession.c @@ -25,6 +25,7 @@ #include "crypto/tlscredsx509.h" #include "qapi/error.h" #include "authz/base.h" +#include "tlscredspriv.h" #include "trace.h" #ifdef CONFIG_GNUTLS diff --git a/crypto/trace-events b/crypto/trace-events index 798b6067ab..bccd0bbf29 100644 --- a/crypto/trace-events +++ b/crypto/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # tlscreds.c qcrypto_tls_creds_load_dh(void *creds, const char *filename) "TLS creds load DH creds=%p filename=%s" diff --git a/default-configs/devices/lm32-softmmu.mak b/default-configs/devices/lm32-softmmu.mak deleted file mode 100644 index 1bce3f6e8b..0000000000 --- a/default-configs/devices/lm32-softmmu.mak +++ /dev/null @@ -1,12 +0,0 @@ -# Default configuration for lm32-softmmu - -# Uncomment the following lines to disable these optional devices: -# -#CONFIG_MILKYMIST_TMU2=n # disabling it actually causes compile-time failures - -CONFIG_SEMIHOSTING=y - -# Boards: -# -CONFIG_LM32_EVR=y -CONFIG_MILKYMIST=y diff --git a/default-configs/devices/moxie-softmmu.mak b/default-configs/devices/moxie-softmmu.mak deleted file mode 100644 index bd50da3c58..0000000000 --- a/default-configs/devices/moxie-softmmu.mak +++ /dev/null @@ -1,5 +0,0 @@ -# Default configuration for moxie-softmmu - -# Boards: -# -CONFIG_MOXIESIM=y diff --git a/default-configs/devices/tricore-softmmu.mak b/default-configs/devices/tricore-softmmu.mak deleted file mode 100644 index 5cc91cebce..0000000000 --- a/default-configs/devices/tricore-softmmu.mak +++ /dev/null @@ -1 +0,0 @@ -CONFIG_TRIBOARD=y diff --git a/default-configs/devices/unicore32-softmmu.mak b/default-configs/devices/unicore32-softmmu.mak deleted file mode 100644 index 899288e3d7..0000000000 --- a/default-configs/devices/unicore32-softmmu.mak +++ /dev/null @@ -1,6 +0,0 @@ -# Default configuration for unicore32-softmmu - -# Boards: -# -CONFIG_PUV3=y -CONFIG_SEMIHOSTING=y diff --git a/default-configs/devices/xtensaeb-softmmu.mak b/default-configs/devices/xtensaeb-softmmu.mak deleted file mode 100644 index f7e48c750c..0000000000 --- a/default-configs/devices/xtensaeb-softmmu.mak +++ /dev/null @@ -1,3 +0,0 @@ -# Default configuration for Xtensa - -include xtensa-softmmu.mak diff --git a/default-configs/targets/lm32-softmmu.mak b/default-configs/targets/lm32-softmmu.mak deleted file mode 100644 index 55e7184a3d..0000000000 --- a/default-configs/targets/lm32-softmmu.mak +++ /dev/null @@ -1,2 +0,0 @@ -TARGET_ARCH=lm32 -TARGET_WORDS_BIGENDIAN=y diff --git a/default-configs/targets/moxie-softmmu.mak b/default-configs/targets/moxie-softmmu.mak deleted file mode 100644 index 183e6b0ebd..0000000000 --- a/default-configs/targets/moxie-softmmu.mak +++ /dev/null @@ -1,2 +0,0 @@ -TARGET_ARCH=moxie -TARGET_WORDS_BIGENDIAN=y diff --git a/default-configs/targets/sparc-bsd-user.mak b/default-configs/targets/sparc-bsd-user.mak deleted file mode 100644 index 9ba3d7b07f..0000000000 --- a/default-configs/targets/sparc-bsd-user.mak +++ /dev/null @@ -1,3 +0,0 @@ -TARGET_ARCH=sparc -TARGET_ALIGNED_ONLY=y -TARGET_WORDS_BIGENDIAN=y diff --git a/default-configs/targets/sparc64-bsd-user.mak b/default-configs/targets/sparc64-bsd-user.mak deleted file mode 100644 index 8dd3217800..0000000000 --- a/default-configs/targets/sparc64-bsd-user.mak +++ /dev/null @@ -1,4 +0,0 @@ -TARGET_ARCH=sparc64 -TARGET_BASE_ARCH=sparc -TARGET_ALIGNED_ONLY=y -TARGET_WORDS_BIGENDIAN=y diff --git a/default-configs/targets/unicore32-softmmu.mak b/default-configs/targets/unicore32-softmmu.mak deleted file mode 100644 index 57331e94fe..0000000000 --- a/default-configs/targets/unicore32-softmmu.mak +++ /dev/null @@ -1 +0,0 @@ -TARGET_ARCH=unicore32 diff --git a/disas.c b/disas.c index a61f95b580..3dab4482d1 100644 --- a/disas.c +++ b/disas.c @@ -4,7 +4,6 @@ #include "elf.h" #include "qemu/qemu-print.h" -#include "cpu.h" #include "disas/disas.h" #include "disas/capstone.h" diff --git a/disas/arm-a64.cc b/disas/arm-a64.cc index 27613d4b25..a1402a2e07 100644 --- a/disas/arm-a64.cc +++ b/disas/arm-a64.cc @@ -18,9 +18,7 @@ */ #include "qemu/osdep.h" -extern "C" { #include "disas/dis-asm.h" -} #include "vixl/a64/disasm-a64.h" diff --git a/disas/hexagon.c b/disas/hexagon.c index 3c24e2a94a..c1a4ffc5f6 100644 --- a/disas/hexagon.c +++ b/disas/hexagon.c @@ -33,7 +33,7 @@ int print_insn_hexagon(bfd_vma memaddr, struct disassemble_info *info) { uint32_t words[PACKET_WORDS_MAX]; bool found_end = false; - GString *buf = g_string_sized_new(PACKET_BUFFER_LEN); + GString *buf; int i, len; for (i = 0; i < PACKET_WORDS_MAX && !found_end; i++) { @@ -57,6 +57,7 @@ int print_insn_hexagon(bfd_vma memaddr, struct disassemble_info *info) return PACKET_WORDS_MAX * sizeof(uint32_t); } + buf = g_string_sized_new(PACKET_BUFFER_LEN); len = disassemble_hexagon(words, i, memaddr, buf); (*info->fprintf_func)(info->stream, "%s", buf->str); g_string_free(buf, true); diff --git a/disas/libvixl/vixl/code-buffer.h b/disas/libvixl/vixl/code-buffer.h index f93ebb6b82..b95babbdee 100644 --- a/disas/libvixl/vixl/code-buffer.h +++ b/disas/libvixl/vixl/code-buffer.h @@ -27,7 +27,7 @@ #ifndef VIXL_CODE_BUFFER_H #define VIXL_CODE_BUFFER_H -#include +#include #include "vixl/globals.h" namespace vixl { diff --git a/disas/libvixl/vixl/globals.h b/disas/libvixl/vixl/globals.h index 7099aa599f..3a71942f1e 100644 --- a/disas/libvixl/vixl/globals.h +++ b/disas/libvixl/vixl/globals.h @@ -40,15 +40,17 @@ #define __STDC_FORMAT_MACROS #endif -#include +extern "C" { #include - -#include -#include -#include #include -#include -#include +} + +#include +#include +#include +#include +#include + #include "vixl/platform.h" diff --git a/disas/libvixl/vixl/invalset.h b/disas/libvixl/vixl/invalset.h index ffdc0237b4..2e0871f8c3 100644 --- a/disas/libvixl/vixl/invalset.h +++ b/disas/libvixl/vixl/invalset.h @@ -27,7 +27,7 @@ #ifndef VIXL_INVALSET_H_ #define VIXL_INVALSET_H_ -#include +#include #include #include diff --git a/disas/libvixl/vixl/platform.h b/disas/libvixl/vixl/platform.h index ab588f07f5..26a74de81b 100644 --- a/disas/libvixl/vixl/platform.h +++ b/disas/libvixl/vixl/platform.h @@ -28,7 +28,9 @@ #define PLATFORM_H // Define platform specific functionalities. +extern "C" { #include +} namespace vixl { inline void HostBreakpoint() { raise(SIGINT); } diff --git a/disas/libvixl/vixl/utils.cc b/disas/libvixl/vixl/utils.cc index 3b8bd75fba..69304d266d 100644 --- a/disas/libvixl/vixl/utils.cc +++ b/disas/libvixl/vixl/utils.cc @@ -25,7 +25,7 @@ // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #include "vixl/utils.h" -#include +#include namespace vixl { diff --git a/disas/libvixl/vixl/utils.h b/disas/libvixl/vixl/utils.h index 5ab134e240..ecb0f1014a 100644 --- a/disas/libvixl/vixl/utils.h +++ b/disas/libvixl/vixl/utils.h @@ -27,8 +27,8 @@ #ifndef VIXL_UTILS_H #define VIXL_UTILS_H -#include #include +#include #include "vixl/globals.h" #include "vixl/compiler-intrinsics.h" diff --git a/disas/lm32.c b/disas/lm32.c deleted file mode 100644 index 4fbb124534..0000000000 --- a/disas/lm32.c +++ /dev/null @@ -1,361 +0,0 @@ -/* - * Simple LatticeMico32 disassembler. - * - * Copyright (c) 2012 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - */ - -#include "qemu/osdep.h" -#include "disas/dis-asm.h" - -typedef enum { - LM32_OP_SRUI = 0, LM32_OP_NORI, LM32_OP_MULI, LM32_OP_SH, LM32_OP_LB, - LM32_OP_SRI, LM32_OP_XORI, LM32_OP_LH, LM32_OP_ANDI, LM32_OP_XNORI, - LM32_OP_LW, LM32_OP_LHU, LM32_OP_SB, LM32_OP_ADDI, LM32_OP_ORI, - LM32_OP_SLI, LM32_OP_LBU, LM32_OP_BE, LM32_OP_BG, LM32_OP_BGE, - LM32_OP_BGEU, LM32_OP_BGU, LM32_OP_SW, LM32_OP_BNE, LM32_OP_ANDHI, - LM32_OP_CMPEI, LM32_OP_CMPGI, LM32_OP_CMPGEI, LM32_OP_CMPGEUI, - LM32_OP_CMPGUI, LM32_OP_ORHI, LM32_OP_CMPNEI, LM32_OP_SRU, LM32_OP_NOR, - LM32_OP_MUL, LM32_OP_DIVU, LM32_OP_RCSR, LM32_OP_SR, LM32_OP_XOR, - LM32_OP_ILL0, LM32_OP_AND, LM32_OP_XNOR, LM32_OP_ILL1, LM32_OP_SCALL, - LM32_OP_SEXTB, LM32_OP_ADD, LM32_OP_OR, LM32_OP_SL, LM32_OP_B, - LM32_OP_MODU, LM32_OP_SUB, LM32_OP_ILL2, LM32_OP_WCSR, LM32_OP_ILL3, - LM32_OP_CALL, LM32_OP_SEXTH, LM32_OP_BI, LM32_OP_CMPE, LM32_OP_CMPG, - LM32_OP_CMPGE, LM32_OP_CMPGEU, LM32_OP_CMPGU, LM32_OP_CALLI, LM32_OP_CMPNE, -} Lm32Opcode; - -typedef enum { - FMT_INVALID = 0, FMT_RRI5, FMT_RRI16, FMT_IMM26, FMT_LOAD, FMT_STORE, - FMT_RRR, FMT_R, FMT_RNR, FMT_CRN, FMT_CNR, FMT_BREAK, -} Lm32OpcodeFmt; - -typedef enum { - LM32_CSR_IE = 0, LM32_CSR_IM, LM32_CSR_IP, LM32_CSR_ICC, LM32_CSR_DCC, - LM32_CSR_CC, LM32_CSR_CFG, LM32_CSR_EBA, LM32_CSR_DC, LM32_CSR_DEBA, - LM32_CSR_CFG2, LM32_CSR_JTX = 0xe, LM32_CSR_JRX, LM32_CSR_BP0, - LM32_CSR_BP1, LM32_CSR_BP2, LM32_CSR_BP3, LM32_CSR_WP0 = 0x18, - LM32_CSR_WP1, LM32_CSR_WP2, LM32_CSR_WP3, -} Lm32CsrNum; - -typedef struct { - int csr; - const char *name; -} Lm32CsrInfo; - -static const Lm32CsrInfo lm32_csr_info[] = { - {LM32_CSR_IE, "ie", }, - {LM32_CSR_IM, "im", }, - {LM32_CSR_IP, "ip", }, - {LM32_CSR_ICC, "icc", }, - {LM32_CSR_DCC, "dcc", }, - {LM32_CSR_CC, "cc", }, - {LM32_CSR_CFG, "cfg", }, - {LM32_CSR_EBA, "eba", }, - {LM32_CSR_DC, "dc", }, - {LM32_CSR_DEBA, "deba", }, - {LM32_CSR_CFG2, "cfg2", }, - {LM32_CSR_JTX, "jtx", }, - {LM32_CSR_JRX, "jrx", }, - {LM32_CSR_BP0, "bp0", }, - {LM32_CSR_BP1, "bp1", }, - {LM32_CSR_BP2, "bp2", }, - {LM32_CSR_BP3, "bp3", }, - {LM32_CSR_WP0, "wp0", }, - {LM32_CSR_WP1, "wp1", }, - {LM32_CSR_WP2, "wp2", }, - {LM32_CSR_WP3, "wp3", }, -}; - -static const Lm32CsrInfo *find_csr_info(int csr) -{ - const Lm32CsrInfo *info; - int i; - - for (i = 0; i < ARRAY_SIZE(lm32_csr_info); i++) { - info = &lm32_csr_info[i]; - if (csr == info->csr) { - return info; - } - } - - return NULL; -} - -typedef struct { - int reg; - const char *name; -} Lm32RegInfo; - -typedef enum { - LM32_REG_R0 = 0, LM32_REG_R1, LM32_REG_R2, LM32_REG_R3, LM32_REG_R4, - LM32_REG_R5, LM32_REG_R6, LM32_REG_R7, LM32_REG_R8, LM32_REG_R9, - LM32_REG_R10, LM32_REG_R11, LM32_REG_R12, LM32_REG_R13, LM32_REG_R14, - LM32_REG_R15, LM32_REG_R16, LM32_REG_R17, LM32_REG_R18, LM32_REG_R19, - LM32_REG_R20, LM32_REG_R21, LM32_REG_R22, LM32_REG_R23, LM32_REG_R24, - LM32_REG_R25, LM32_REG_GP, LM32_REG_FP, LM32_REG_SP, LM32_REG_RA, - LM32_REG_EA, LM32_REG_BA, -} Lm32RegNum; - -static const Lm32RegInfo lm32_reg_info[] = { - {LM32_REG_R0, "r0", }, - {LM32_REG_R1, "r1", }, - {LM32_REG_R2, "r2", }, - {LM32_REG_R3, "r3", }, - {LM32_REG_R4, "r4", }, - {LM32_REG_R5, "r5", }, - {LM32_REG_R6, "r6", }, - {LM32_REG_R7, "r7", }, - {LM32_REG_R8, "r8", }, - {LM32_REG_R9, "r9", }, - {LM32_REG_R10, "r10", }, - {LM32_REG_R11, "r11", }, - {LM32_REG_R12, "r12", }, - {LM32_REG_R13, "r13", }, - {LM32_REG_R14, "r14", }, - {LM32_REG_R15, "r15", }, - {LM32_REG_R16, "r16", }, - {LM32_REG_R17, "r17", }, - {LM32_REG_R18, "r18", }, - {LM32_REG_R19, "r19", }, - {LM32_REG_R20, "r20", }, - {LM32_REG_R21, "r21", }, - {LM32_REG_R22, "r22", }, - {LM32_REG_R23, "r23", }, - {LM32_REG_R24, "r24", }, - {LM32_REG_R25, "r25", }, - {LM32_REG_GP, "gp", }, - {LM32_REG_FP, "fp", }, - {LM32_REG_SP, "sp", }, - {LM32_REG_RA, "ra", }, - {LM32_REG_EA, "ea", }, - {LM32_REG_BA, "ba", }, -}; - -static const Lm32RegInfo *find_reg_info(int reg) -{ - assert(ARRAY_SIZE(lm32_reg_info) == 32); - return &lm32_reg_info[reg & 0x1f]; -} - -typedef struct { - struct { - uint32_t code; - uint32_t mask; - } op; - const char *name; - const char *args_fmt; -} Lm32OpcodeInfo; - -static const Lm32OpcodeInfo lm32_opcode_info[] = { - /* pseudo instructions */ - {{0x34000000, 0xffffffff}, "nop", NULL}, - {{0xac000002, 0xffffffff}, "break", NULL}, - {{0xac000003, 0xffffffff}, "scall", NULL}, - {{0xc3e00000, 0xffffffff}, "bret", NULL}, - {{0xc3c00000, 0xffffffff}, "eret", NULL}, - {{0xc3a00000, 0xffffffff}, "ret", NULL}, - {{0xa4000000, 0xfc1f07ff}, "not", "%2, %0"}, - {{0xb8000000, 0xfc1f07ff}, "mv", "%2, %0"}, - {{0x71e00000, 0xffe00000}, "mvhi", "%1, %u"}, - {{0x34000000, 0xffe00000}, "mvi", "%1, %s"}, - -#define _O(op) {op << 26, 0x3f << 26} - /* regular opcodes */ - {_O(LM32_OP_ADD), "add", "%2, %0, %1" }, - {_O(LM32_OP_ADDI), "addi", "%1, %0, %s" }, - {_O(LM32_OP_AND), "and", "%2, %0, %1" }, - {_O(LM32_OP_ANDHI), "andhi", "%1, %0, %u" }, - {_O(LM32_OP_ANDI), "andi", "%1, %0, %u" }, - {_O(LM32_OP_B), "b", "%0", }, - {_O(LM32_OP_BE), "be", "%1, %0, %r" }, - {_O(LM32_OP_BG), "bg", "%1, %0, %r" }, - {_O(LM32_OP_BGE), "bge", "%1, %0, %r" }, - {_O(LM32_OP_BGEU), "bgeu", "%1, %0, %r" }, - {_O(LM32_OP_BGU), "bgu", "%1, %0, %r" }, - {_O(LM32_OP_BI), "bi", "%R", }, - {_O(LM32_OP_BNE), "bne", "%1, %0, %r" }, - {_O(LM32_OP_CALL), "call", "%0", }, - {_O(LM32_OP_CALLI), "calli", "%R", }, - {_O(LM32_OP_CMPE), "cmpe", "%2, %0, %1" }, - {_O(LM32_OP_CMPEI), "cmpei", "%1, %0, %s" }, - {_O(LM32_OP_CMPG), "cmpg", "%2, %0, %1" }, - {_O(LM32_OP_CMPGE), "cmpge", "%2, %0, %1" }, - {_O(LM32_OP_CMPGEI), "cmpgei", "%1, %0, %s" }, - {_O(LM32_OP_CMPGEU), "cmpgeu", "%2, %0, %1" }, - {_O(LM32_OP_CMPGEUI), "cmpgeui", "%1, %0, %s" }, - {_O(LM32_OP_CMPGI), "cmpgi", "%1, %0, %s" }, - {_O(LM32_OP_CMPGU), "cmpgu", "%2, %0, %1" }, - {_O(LM32_OP_CMPGUI), "cmpgui", "%1, %0, %s" }, - {_O(LM32_OP_CMPNE), "cmpne", "%2, %0, %1" }, - {_O(LM32_OP_CMPNEI), "cmpnei", "%1, %0, %s" }, - {_O(LM32_OP_DIVU), "divu", "%2, %0, %1" }, - {_O(LM32_OP_LB), "lb", "%1, (%0+%s)" }, - {_O(LM32_OP_LBU), "lbu", "%1, (%0+%s)" }, - {_O(LM32_OP_LH), "lh", "%1, (%0+%s)" }, - {_O(LM32_OP_LHU), "lhu", "%1, (%0+%s)" }, - {_O(LM32_OP_LW), "lw", "%1, (%0+%s)" }, - {_O(LM32_OP_MODU), "modu", "%2, %0, %1" }, - {_O(LM32_OP_MULI), "muli", "%1, %0, %s" }, - {_O(LM32_OP_MUL), "mul", "%2, %0, %1" }, - {_O(LM32_OP_NORI), "nori", "%1, %0, %u" }, - {_O(LM32_OP_NOR), "nor", "%2, %0, %1" }, - {_O(LM32_OP_ORHI), "orhi", "%1, %0, %u" }, - {_O(LM32_OP_ORI), "ori", "%1, %0, %u" }, - {_O(LM32_OP_OR), "or", "%2, %0, %1" }, - {_O(LM32_OP_RCSR), "rcsr", "%2, %c", }, - {_O(LM32_OP_SB), "sb", "(%0+%s), %1" }, - {_O(LM32_OP_SEXTB), "sextb", "%2, %0", }, - {_O(LM32_OP_SEXTH), "sexth", "%2, %0", }, - {_O(LM32_OP_SH), "sh", "(%0+%s), %1" }, - {_O(LM32_OP_SLI), "sli", "%1, %0, %h" }, - {_O(LM32_OP_SL), "sl", "%2, %0, %1" }, - {_O(LM32_OP_SRI), "sri", "%1, %0, %h" }, - {_O(LM32_OP_SR), "sr", "%2, %0, %1" }, - {_O(LM32_OP_SRUI), "srui", "%1, %0, %d" }, - {_O(LM32_OP_SRU), "sru", "%2, %0, %s" }, - {_O(LM32_OP_SUB), "sub", "%2, %0, %s" }, - {_O(LM32_OP_SW), "sw", "(%0+%s), %1" }, - {_O(LM32_OP_WCSR), "wcsr", "%c, %1", }, - {_O(LM32_OP_XNORI), "xnori", "%1, %0, %u" }, - {_O(LM32_OP_XNOR), "xnor", "%2, %0, %1" }, - {_O(LM32_OP_XORI), "xori", "%1, %0, %u" }, - {_O(LM32_OP_XOR), "xor", "%2, %0, %1" }, -#undef _O -}; - -static const Lm32OpcodeInfo *find_opcode_info(uint32_t opcode) -{ - const Lm32OpcodeInfo *info; - int i; - for (i = 0; i < ARRAY_SIZE(lm32_opcode_info); i++) { - info = &lm32_opcode_info[i]; - if ((opcode & info->op.mask) == info->op.code) { - return info; - } - } - - return NULL; -} - -int print_insn_lm32(bfd_vma memaddr, struct disassemble_info *info) -{ - fprintf_function fprintf_fn = info->fprintf_func; - void *stream = info->stream; - int rc; - uint8_t insn[4]; - const Lm32OpcodeInfo *opc_info; - uint32_t op; - const char *args_fmt; - - rc = info->read_memory_func(memaddr, insn, 4, info); - if (rc != 0) { - info->memory_error_func(rc, memaddr, info); - return -1; - } - - fprintf_fn(stream, "%02x %02x %02x %02x ", - insn[0], insn[1], insn[2], insn[3]); - - op = bfd_getb32(insn); - opc_info = find_opcode_info(op); - if (opc_info) { - fprintf_fn(stream, "%-8s ", opc_info->name); - args_fmt = opc_info->args_fmt; - while (args_fmt && *args_fmt) { - if (*args_fmt == '%') { - switch (*(++args_fmt)) { - case '0': { - uint8_t r0; - const char *r0_name; - r0 = (op >> 21) & 0x1f; - r0_name = find_reg_info(r0)->name; - fprintf_fn(stream, "%s", r0_name); - break; - } - case '1': { - uint8_t r1; - const char *r1_name; - r1 = (op >> 16) & 0x1f; - r1_name = find_reg_info(r1)->name; - fprintf_fn(stream, "%s", r1_name); - break; - } - case '2': { - uint8_t r2; - const char *r2_name; - r2 = (op >> 11) & 0x1f; - r2_name = find_reg_info(r2)->name; - fprintf_fn(stream, "%s", r2_name); - break; - } - case 'c': { - uint8_t csr; - const Lm32CsrInfo *info; - csr = (op >> 21) & 0x1f; - info = find_csr_info(csr); - if (info) { - fprintf_fn(stream, "%s", info->name); - } else { - fprintf_fn(stream, "0x%x", csr); - } - break; - } - case 'u': { - uint16_t u16; - u16 = op & 0xffff; - fprintf_fn(stream, "0x%x", u16); - break; - } - case 's': { - int16_t s16; - s16 = (int16_t)(op & 0xffff); - fprintf_fn(stream, "%d", s16); - break; - } - case 'r': { - uint32_t rela; - rela = memaddr + (((int16_t)(op & 0xffff)) << 2); - fprintf_fn(stream, "%x", rela); - break; - } - case 'R': { - uint32_t rela; - int32_t imm26; - imm26 = (int32_t)((op & 0x3ffffff) << 6) >> 4; - rela = memaddr + imm26; - fprintf_fn(stream, "%x", rela); - break; - } - case 'h': { - uint8_t u5; - u5 = (op & 0x1f); - fprintf_fn(stream, "%d", u5); - break; - } - default: - break; - } - } else { - fprintf_fn(stream, "%c", *args_fmt); - } - args_fmt++; - } - } else { - fprintf_fn(stream, ".word 0x%x", op); - } - - return 4; -} diff --git a/disas/meson.build b/disas/meson.build index 4c8da01877..449f99e1de 100644 --- a/disas/meson.build +++ b/disas/meson.build @@ -9,11 +9,9 @@ common_ss.add(when: 'CONFIG_CRIS_DIS', if_true: files('cris.c')) common_ss.add(when: 'CONFIG_HEXAGON_DIS', if_true: files('hexagon.c')) common_ss.add(when: 'CONFIG_HPPA_DIS', if_true: files('hppa.c')) common_ss.add(when: 'CONFIG_I386_DIS', if_true: files('i386.c')) -common_ss.add(when: 'CONFIG_LM32_DIS', if_true: files('lm32.c')) common_ss.add(when: 'CONFIG_M68K_DIS', if_true: files('m68k.c')) common_ss.add(when: 'CONFIG_MICROBLAZE_DIS', if_true: files('microblaze.c')) common_ss.add(when: 'CONFIG_MIPS_DIS', if_true: files('mips.c')) -common_ss.add(when: 'CONFIG_MOXIE_DIS', if_true: files('moxie.c')) common_ss.add(when: 'CONFIG_NANOMIPS_DIS', if_true: files('nanomips.cpp')) common_ss.add(when: 'CONFIG_NIOS2_DIS', if_true: files('nios2.c')) common_ss.add(when: 'CONFIG_PPC_DIS', if_true: files('ppc.c')) diff --git a/disas/moxie.c b/disas/moxie.c deleted file mode 100644 index e94ab4c33d..0000000000 --- a/disas/moxie.c +++ /dev/null @@ -1,360 +0,0 @@ -/* Disassemble moxie instructions. - Copyright (c) 2009 Free Software Foundation, Inc. - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, see . */ - -#include "qemu/osdep.h" -#define STATIC_TABLE -#define DEFINE_TABLE - -#include "disas/dis-asm.h" - -static void *stream; - -/* Form 1 instructions come in different flavors: - - Some have no arguments (MOXIE_F1_NARG) - Some only use the A operand (MOXIE_F1_A) - Some use A and B registers (MOXIE_F1_AB) - Some use A and consume a 4 byte immediate value (MOXIE_F1_A4) - Some use just a 4 byte immediate value (MOXIE_F1_4) - Some use just a 4 byte memory address (MOXIE_F1_M) - Some use B and an indirect A (MOXIE_F1_AiB) - Some use A and an indirect B (MOXIE_F1_ABi) - Some consume a 4 byte immediate value and use X (MOXIE_F1_4A) - Some use B and an indirect A plus 4 bytes (MOXIE_F1_AiB4) - Some use A and an indirect B plus 4 bytes (MOXIE_F1_ABi4) - - Form 2 instructions also come in different flavors: - - Some have no arguments (MOXIE_F2_NARG) - Some use the A register and an 8-bit value (MOXIE_F2_A8V) - - Form 3 instructions also come in different flavors: - - Some have no arguments (MOXIE_F3_NARG) - Some have a 10-bit PC relative operand (MOXIE_F3_PCREL). */ - -#define MOXIE_F1_NARG 0x100 -#define MOXIE_F1_A 0x101 -#define MOXIE_F1_AB 0x102 -/* #define MOXIE_F1_ABC 0x103 */ -#define MOXIE_F1_A4 0x104 -#define MOXIE_F1_4 0x105 -#define MOXIE_F1_AiB 0x106 -#define MOXIE_F1_ABi 0x107 -#define MOXIE_F1_4A 0x108 -#define MOXIE_F1_AiB4 0x109 -#define MOXIE_F1_ABi4 0x10a -#define MOXIE_F1_M 0x10b - -#define MOXIE_F2_NARG 0x200 -#define MOXIE_F2_A8V 0x201 - -#define MOXIE_F3_NARG 0x300 -#define MOXIE_F3_PCREL 0x301 - -typedef struct moxie_opc_info_t { - short opcode; - unsigned itype; - const char * name; -} moxie_opc_info_t; - -extern const moxie_opc_info_t moxie_form1_opc_info[64]; -extern const moxie_opc_info_t moxie_form2_opc_info[4]; -extern const moxie_opc_info_t moxie_form3_opc_info[16]; - -/* The moxie processor's 16-bit instructions come in two forms: - - FORM 1 instructions start with a 0 bit... - - 0oooooooaaaabbbb - 0 F - - ooooooo - form 1 opcode number - aaaa - operand A - bbbb - operand B - - FORM 2 instructions start with bits "10"... - - 10ooaaaavvvvvvvv - 0 F - - oo - form 2 opcode number - aaaa - operand A - vvvvvvvv - 8-bit immediate value - - FORM 3 instructions start with a bits "11"... - - 11oooovvvvvvvvvv - 0 F - - oooo - form 3 opcode number - vvvvvvvvvv - 10-bit immediate value. */ - -const moxie_opc_info_t moxie_form1_opc_info[64] = - { - { 0x00, MOXIE_F1_NARG, "nop" }, - { 0x01, MOXIE_F1_A4, "ldi.l" }, - { 0x02, MOXIE_F1_AB, "mov" }, - { 0x03, MOXIE_F1_M, "jsra" }, - { 0x04, MOXIE_F1_NARG, "ret" }, - { 0x05, MOXIE_F1_AB, "add.l" }, - { 0x06, MOXIE_F1_AB, "push" }, - { 0x07, MOXIE_F1_AB, "pop" }, - { 0x08, MOXIE_F1_A4, "lda.l" }, - { 0x09, MOXIE_F1_4A, "sta.l" }, - { 0x0a, MOXIE_F1_ABi, "ld.l" }, - { 0x0b, MOXIE_F1_AiB, "st.l" }, - { 0x0c, MOXIE_F1_ABi4, "ldo.l" }, - { 0x0d, MOXIE_F1_AiB4, "sto.l" }, - { 0x0e, MOXIE_F1_AB, "cmp" }, - { 0x0f, MOXIE_F1_NARG, "bad" }, - { 0x10, MOXIE_F1_NARG, "bad" }, - { 0x11, MOXIE_F1_NARG, "bad" }, - { 0x12, MOXIE_F1_NARG, "bad" }, - { 0x13, MOXIE_F1_NARG, "bad" }, - { 0x14, MOXIE_F1_NARG, "bad" }, - { 0x15, MOXIE_F1_NARG, "bad" }, - { 0x16, MOXIE_F1_NARG, "bad" }, - { 0x17, MOXIE_F1_NARG, "bad" }, - { 0x18, MOXIE_F1_NARG, "bad" }, - { 0x19, MOXIE_F1_A, "jsr" }, - { 0x1a, MOXIE_F1_M, "jmpa" }, - { 0x1b, MOXIE_F1_A4, "ldi.b" }, - { 0x1c, MOXIE_F1_ABi, "ld.b" }, - { 0x1d, MOXIE_F1_A4, "lda.b" }, - { 0x1e, MOXIE_F1_AiB, "st.b" }, - { 0x1f, MOXIE_F1_4A, "sta.b" }, - { 0x20, MOXIE_F1_A4, "ldi.s" }, - { 0x21, MOXIE_F1_ABi, "ld.s" }, - { 0x22, MOXIE_F1_A4, "lda.s" }, - { 0x23, MOXIE_F1_AiB, "st.s" }, - { 0x24, MOXIE_F1_4A, "sta.s" }, - { 0x25, MOXIE_F1_A, "jmp" }, - { 0x26, MOXIE_F1_AB, "and" }, - { 0x27, MOXIE_F1_AB, "lshr" }, - { 0x28, MOXIE_F1_AB, "ashl" }, - { 0x29, MOXIE_F1_AB, "sub.l" }, - { 0x2a, MOXIE_F1_AB, "neg" }, - { 0x2b, MOXIE_F1_AB, "or" }, - { 0x2c, MOXIE_F1_AB, "not" }, - { 0x2d, MOXIE_F1_AB, "ashr" }, - { 0x2e, MOXIE_F1_AB, "xor" }, - { 0x2f, MOXIE_F1_AB, "mul.l" }, - { 0x30, MOXIE_F1_4, "swi" }, - { 0x31, MOXIE_F1_AB, "div.l" }, - { 0x32, MOXIE_F1_AB, "udiv.l" }, - { 0x33, MOXIE_F1_AB, "mod.l" }, - { 0x34, MOXIE_F1_AB, "umod.l" }, - { 0x35, MOXIE_F1_NARG, "brk" }, - { 0x36, MOXIE_F1_ABi4, "ldo.b" }, - { 0x37, MOXIE_F1_AiB4, "sto.b" }, - { 0x38, MOXIE_F1_ABi4, "ldo.s" }, - { 0x39, MOXIE_F1_AiB4, "sto.s" }, - { 0x3a, MOXIE_F1_NARG, "bad" }, - { 0x3b, MOXIE_F1_NARG, "bad" }, - { 0x3c, MOXIE_F1_NARG, "bad" }, - { 0x3d, MOXIE_F1_NARG, "bad" }, - { 0x3e, MOXIE_F1_NARG, "bad" }, - { 0x3f, MOXIE_F1_NARG, "bad" } - }; - -const moxie_opc_info_t moxie_form2_opc_info[4] = - { - { 0x00, MOXIE_F2_A8V, "inc" }, - { 0x01, MOXIE_F2_A8V, "dec" }, - { 0x02, MOXIE_F2_A8V, "gsr" }, - { 0x03, MOXIE_F2_A8V, "ssr" } - }; - -const moxie_opc_info_t moxie_form3_opc_info[16] = - { - { 0x00, MOXIE_F3_PCREL,"beq" }, - { 0x01, MOXIE_F3_PCREL,"bne" }, - { 0x02, MOXIE_F3_PCREL,"blt" }, - { 0x03, MOXIE_F3_PCREL,"bgt" }, - { 0x04, MOXIE_F3_PCREL,"bltu" }, - { 0x05, MOXIE_F3_PCREL,"bgtu" }, - { 0x06, MOXIE_F3_PCREL,"bge" }, - { 0x07, MOXIE_F3_PCREL,"ble" }, - { 0x08, MOXIE_F3_PCREL,"bgeu" }, - { 0x09, MOXIE_F3_PCREL,"bleu" }, - { 0x0a, MOXIE_F3_NARG, "bad" }, - { 0x0b, MOXIE_F3_NARG, "bad" }, - { 0x0c, MOXIE_F3_NARG, "bad" }, - { 0x0d, MOXIE_F3_NARG, "bad" }, - { 0x0e, MOXIE_F3_NARG, "bad" }, - { 0x0f, MOXIE_F3_NARG, "bad" } - }; - -/* Macros to extract operands from the instruction word. */ -#define OP_A(i) ((i >> 4) & 0xf) -#define OP_B(i) (i & 0xf) -#define INST2OFFSET(o) ((((signed short)((o & ((1<<10)-1))<<6))>>6)<<1) - -static const char * reg_names[16] = - { "$fp", "$sp", "$r0", "$r1", "$r2", "$r3", "$r4", "$r5", - "$r6", "$r7", "$r8", "$r9", "$r10", "$r11", "$r12", "$r13" }; - -int -print_insn_moxie(bfd_vma addr, struct disassemble_info * info) -{ - int length = 2; - int status; - stream = info->stream; - const moxie_opc_info_t * opcode; - bfd_byte buffer[4]; - unsigned short iword; - fprintf_function fpr = info->fprintf_func; - - if ((status = info->read_memory_func(addr, buffer, 2, info))) - goto fail; - iword = (bfd_getb16(buffer) >> 16); - - /* Form 1 instructions have the high bit set to 0. */ - if ((iword & (1<<15)) == 0) { - /* Extract the Form 1 opcode. */ - opcode = &moxie_form1_opc_info[iword >> 8]; - switch (opcode->itype) { - case MOXIE_F1_NARG: - fpr(stream, "%s", opcode->name); - break; - case MOXIE_F1_A: - fpr(stream, "%s\t%s", opcode->name, - reg_names[OP_A(iword)]); - break; - case MOXIE_F1_AB: - fpr(stream, "%s\t%s, %s", opcode->name, - reg_names[OP_A(iword)], - reg_names[OP_B(iword)]); - break; - case MOXIE_F1_A4: - { - unsigned imm; - if ((status = info->read_memory_func(addr + 2, buffer, 4, info))) - goto fail; - imm = bfd_getb32(buffer); - fpr(stream, "%s\t%s, 0x%x", opcode->name, - reg_names[OP_A(iword)], imm); - length = 6; - } - break; - case MOXIE_F1_4: - { - unsigned imm; - if ((status = info->read_memory_func(addr + 2, buffer, 4, info))) - goto fail; - imm = bfd_getb32(buffer); - fpr(stream, "%s\t0x%x", opcode->name, imm); - length = 6; - } - break; - case MOXIE_F1_M: - { - unsigned imm; - if ((status = info->read_memory_func(addr + 2, buffer, 4, info))) - goto fail; - imm = bfd_getb32(buffer); - fpr(stream, "%s\t", opcode->name); - info->print_address_func((bfd_vma) imm, info); - length = 6; - } - break; - case MOXIE_F1_AiB: - fpr (stream, "%s\t(%s), %s", opcode->name, - reg_names[OP_A(iword)], reg_names[OP_B(iword)]); - break; - case MOXIE_F1_ABi: - fpr(stream, "%s\t%s, (%s)", opcode->name, - reg_names[OP_A(iword)], reg_names[OP_B(iword)]); - break; - case MOXIE_F1_4A: - { - unsigned imm; - if ((status = info->read_memory_func(addr + 2, buffer, 4, info))) - goto fail; - imm = bfd_getb32(buffer); - fpr(stream, "%s\t0x%x, %s", - opcode->name, imm, reg_names[OP_A(iword)]); - length = 6; - } - break; - case MOXIE_F1_AiB4: - { - unsigned imm; - if ((status = info->read_memory_func(addr+2, buffer, 4, info))) - goto fail; - imm = bfd_getb32(buffer); - fpr(stream, "%s\t0x%x(%s), %s", opcode->name, - imm, - reg_names[OP_A(iword)], - reg_names[OP_B(iword)]); - length = 6; - } - break; - case MOXIE_F1_ABi4: - { - unsigned imm; - if ((status = info->read_memory_func(addr+2, buffer, 4, info))) - goto fail; - imm = bfd_getb32(buffer); - fpr(stream, "%s\t%s, 0x%x(%s)", - opcode->name, - reg_names[OP_A(iword)], - imm, - reg_names[OP_B(iword)]); - length = 6; - } - break; - default: - abort(); - } - } - else if ((iword & (1<<14)) == 0) { - /* Extract the Form 2 opcode. */ - opcode = &moxie_form2_opc_info[(iword >> 12) & 3]; - switch (opcode->itype) { - case MOXIE_F2_A8V: - fpr(stream, "%s\t%s, 0x%x", - opcode->name, - reg_names[(iword >> 8) & 0xf], - iword & ((1 << 8) - 1)); - break; - case MOXIE_F2_NARG: - fpr(stream, "%s", opcode->name); - break; - default: - abort(); - } - } else { - /* Extract the Form 3 opcode. */ - opcode = &moxie_form3_opc_info[(iword >> 10) & 15]; - switch (opcode->itype) { - case MOXIE_F3_PCREL: - fpr(stream, "%s\t", opcode->name); - info->print_address_func((bfd_vma) (addr + INST2OFFSET(iword) + 2), - info); - break; - default: - abort(); - } - } - - return length; - - fail: - info->memory_error_func(status, addr, info); - return -1; -} diff --git a/disas/nanomips.cpp b/disas/nanomips.cpp index 8ddef897f0..9be8df75dd 100644 --- a/disas/nanomips.cpp +++ b/disas/nanomips.cpp @@ -28,9 +28,7 @@ */ #include "qemu/osdep.h" -extern "C" { #include "disas/dis-asm.h" -} #include #include diff --git a/docs/_templates/editpage.html b/docs/_templates/editpage.html deleted file mode 100644 index 4319b0f5ac..0000000000 --- a/docs/_templates/editpage.html +++ /dev/null @@ -1,5 +0,0 @@ -
- -
diff --git a/docs/_templates/footer.html b/docs/_templates/footer.html new file mode 100644 index 0000000000..977053b541 --- /dev/null +++ b/docs/_templates/footer.html @@ -0,0 +1,14 @@ +{% extends "!footer.html" %} +{% block extrafooter %} + + +

+ +

This documentation is for QEMU version {{ version }}.

+ +{% trans path=pathto('about/license') %} +

QEMU and this manual are released under the +GNU General Public License, version 2.

+{% endtrans %} +{{ super() }} +{% endblock %} diff --git a/docs/system/build-platforms.rst b/docs/about/build-platforms.rst similarity index 100% rename from docs/system/build-platforms.rst rename to docs/about/build-platforms.rst diff --git a/docs/system/deprecated.rst b/docs/about/deprecated.rst similarity index 74% rename from docs/system/deprecated.rst rename to docs/about/deprecated.rst index 80cae86252..6d438f1c8d 100644 --- a/docs/system/deprecated.rst +++ b/docs/about/deprecated.rst @@ -52,25 +52,6 @@ pcspk-audiodev=``. ``tty`` and ``parport`` are aliases that will be removed. Instead, the actual backend names ``serial`` and ``parallel`` should be used. -RISC-V ``-bios`` (since 5.1) -'''''''''''''''''''''''''''' - -QEMU 4.1 introduced support for the -bios option in QEMU for RISC-V for the -RISC-V virt machine and sifive_u machine. QEMU 4.1 had no changes to the -default behaviour to avoid breakages. - -QEMU 5.1 changes the default behaviour from ``-bios none`` to ``-bios default``. - -QEMU 5.1 has three options: - 1. ``-bios default`` - This is the current default behavior if no -bios option - is included. This option will load the default OpenSBI firmware automatically. - The firmware is included with the QEMU release and no user interaction is - required. All a user needs to do is specify the kernel they want to boot - with the -kernel option - 2. ``-bios none`` - QEMU will not automatically load any firmware. It is up - to the user to load all the images they need. - 3. ``-bios `` - Tells QEMU to load the specified file as the firmwrae. - Short-form boolean options (since 6.0) '''''''''''''''''''''''''''''''''''''' @@ -145,6 +126,18 @@ other options have been processed. This will either have no effect (if if they were not given. The property is therefore useless and should not be specified. +``-display sdl,window_close=...`` (since 6.1) +''''''''''''''''''''''''''''''''''''''''''''' + +Use ``-display sdl,window-close=...`` instead (i.e. with a minus instead of +an underscore between "window" and "close"). + +``-no-quit`` (since 6.1) +'''''''''''''''''''''''' + +The ``-no-quit`` is a synonym for ``-display ...,window-close=off`` which +should be used instead. + QEMU Machine Protocol (QMP) commands ------------------------------------ @@ -198,30 +191,6 @@ from Linux upstream kernel, declare it deprecated. System emulator CPUS -------------------- -``moxie`` CPU (since 5.2.0) -''''''''''''''''''''''''''' - -The ``moxie`` guest CPU support is deprecated and will be removed in -a future version of QEMU. It's unclear whether anybody is still using -CPU emulation in QEMU, and there are no test images available to make -sure that the code is still working. - -``lm32`` CPUs (since 5.2.0) -''''''''''''''''''''''''''' - -The ``lm32`` guest CPU support is deprecated and will be removed in -a future version of QEMU. The only public user of this architecture -was the milkymist project, which has been dead for years; there was -never an upstream Linux port. - -``unicore32`` CPUs (since 5.2.0) -'''''''''''''''''''''''''''''''' - -The ``unicore32`` guest CPU support is deprecated and will be removed in -a future version of QEMU. Support for this CPU was removed from the -upstream Linux kernel, and there is no available upstream toolchain -to build binaries for it. - ``Icelake-Client`` CPU Model (since 5.2.0) '''''''''''''''''''''''''''''''''''''''''' @@ -245,6 +214,31 @@ The Raspberry Pi machines come in various models (A, A+, B, B+). To be able to distinguish which model QEMU is implementing, the ``raspi2`` and ``raspi3`` machines have been renamed ``raspi2b`` and ``raspi3b``. +Aspeed ``swift-bmc`` machine (since 6.1) +'''''''''''''''''''''''''''''''''''''''' + +This machine is deprecated because we have enough AST2500 based OpenPOWER +machines. It can be easily replaced by the ``witherspoon-bmc`` or the +``romulus-bmc`` machines. + +Backend options +--------------- + +Using non-persistent backing file with pmem=on (since 6.1) +'''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +This option is used when ``memory-backend-file`` is consumed by emulated NVDIMM +device. However enabling ``memory-backend-file.pmem`` option, when backing file +is (a) not DAX capable or (b) not on a filesystem that support direct mapping +of persistent memory, is not safe and may lead to data loss or corruption in case +of host crash. +Options are: + + - modify VM configuration to set ``pmem=off`` to continue using fake NVDIMM + (without persistence guaranties) with backing file on non DAX storage + - move backing file to NVDIMM storage and keep ``pmem=on`` + (to have NVDIMM with persistence guaranties). + Device options -------------- @@ -286,15 +280,6 @@ The above, converted to the current supported format:: json:{"file.driver":"rbd", "file.pool":"rbd", "file.image":"name"} -``sheepdog`` driver (since 5.2.0) -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - -The ``sheepdog`` block device driver is deprecated. The corresponding upstream -server project is no longer actively maintained. Users are recommended to switch -to an alternative distributed block device driver such as RBD. The -``qemu-img convert`` command can be used to liberate existing data by moving -it out of sheepdog volumes into an alternative storage backend. - linux-user mode CPUs -------------------- @@ -315,38 +300,6 @@ this CPU is also deprecated. Related binaries ---------------- -qemu-img amend to adjust backing file (since 5.1) -''''''''''''''''''''''''''''''''''''''''''''''''' - -The use of ``qemu-img amend`` to modify the name or format of a qcow2 -backing image is deprecated; this functionality was never fully -documented or tested, and interferes with other amend operations that -need access to the original backing image (such as deciding whether a -v3 zero cluster may be left unallocated when converting to a v2 -image). Rather, any changes to the backing chain should be performed -with ``qemu-img rebase -u`` either before or after the remaining -changes being performed by amend, as appropriate. - -qemu-img backing file without format (since 5.1) -'''''''''''''''''''''''''''''''''''''''''''''''' - -The use of ``qemu-img create``, ``qemu-img rebase``, or ``qemu-img -convert`` to create or modify an image that depends on a backing file -now recommends that an explicit backing format be provided. This is -for safety: if QEMU probes a different format than what you thought, -the data presented to the guest will be corrupt; similarly, presenting -a raw image to a guest allows a potential security exploit if a future -probe sees a non-raw image based on guest writes. - -To avoid the warning message, or even future refusal to create an -unsafe image, you must pass ``-o backing_fmt=`` (or the shorthand -``-F`` during create) to specify the intended backing format. You may -use ``qemu-img rebase -u`` to retroactively add a backing format to an -existing image. However, be aware that there are already potential -security risks to blindly using ``qemu-img info`` to probe the format -of an untrusted backing image, when deciding what format to add into -an existing image. - Backwards compatibility ----------------------- diff --git a/docs/about/index.rst b/docs/about/index.rst new file mode 100644 index 0000000000..beb762aa0a --- /dev/null +++ b/docs/about/index.rst @@ -0,0 +1,27 @@ +About QEMU +========== + +QEMU is a generic and open source machine emulator and virtualizer. + +QEMU can be used in several different ways. The most common is for +"system emulation", where it provides a virtual model of an +entire machine (CPU, memory and emulated devices) to run a guest OS. +In this mode the CPU may be fully emulated, or it may work with +a hypervisor such as KVM, Xen, Hax or Hypervisor.Framework to +allow the guest to run directly on the host CPU. + +The second supported way to use QEMU is "user mode emulation", +where QEMU can launch processes compiled for one CPU on another CPU. +In this mode the CPU is always emulated. + +QEMU also provides a number of standalone commandline utilities, +such as the ``qemu-img`` disk image utility that allows you to create, +convert and modify disk images. + +.. toctree:: + :maxdepth: 2 + + build-platforms + deprecated + removed-features + license diff --git a/docs/system/license.rst b/docs/about/license.rst similarity index 100% rename from docs/system/license.rst rename to docs/about/license.rst diff --git a/docs/system/removed-features.rst b/docs/about/removed-features.rst similarity index 63% rename from docs/system/removed-features.rst rename to docs/about/removed-features.rst index 29e90601a5..cbfa1a8e31 100644 --- a/docs/system/removed-features.rst +++ b/docs/about/removed-features.rst @@ -9,8 +9,145 @@ trouble after a recent upgrade. System emulator command line arguments -------------------------------------- -``-net ...,name=``\ *name* (removed in 5.1) -''''''''''''''''''''''''''''''''''''''''''' +``-hdachs`` (removed in 2.12) +''''''''''''''''''''''''''''' + +The geometry defined by ``-hdachs c,h,s,t`` should now be specified via +``-device ide-hd,drive=dr,cyls=c,heads=h,secs=s,bios-chs-trans=t`` +(together with ``-drive if=none,id=dr,...``). + +``-net channel`` (removed in 2.12) +'''''''''''''''''''''''''''''''''' + +This option has been replaced by ``-net user,guestfwd=...``. + +``-net dump`` (removed in 2.12) +''''''''''''''''''''''''''''''' + +``-net dump[,vlan=n][,file=filename][,len=maxlen]`` has been replaced by +``-object filter-dump,id=id,netdev=dev[,file=filename][,maxlen=maxlen]``. +Note that the new syntax works with netdev IDs instead of the old "vlan" hubs. + +``-no-kvm-pit`` (removed in 2.12) +''''''''''''''''''''''''''''''''' + +This was just a dummy option that has been ignored, since the in-kernel PIT +cannot be disabled separately from the irqchip anymore. A similar effect +(which also disables the KVM IOAPIC) can be obtained with +``-M kernel_irqchip=split``. + +``-tdf`` (removed in 2.12) +'''''''''''''''''''''''''' + +There is no replacement, the ``-tdf`` option has just been ignored since the +behaviour that could be changed by this option in qemu-kvm is now the default +when using the KVM PIT. It still can be requested explicitly using +``-global kvm-pit.lost_tick_policy=delay``. + +``-drive secs=s``, ``-drive heads=h`` & ``-drive cyls=c`` (removed in 3.0) +'''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The drive geometry should now be specified via +``-device ...,drive=dr,cyls=c,heads=h,secs=s`` (together with +``-drive if=none,id=dr,...``). + +``-drive serial=``, ``-drive trans=`` & ``-drive addr=`` (removed in 3.0) +''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +Use ``-device ...,drive=dr,serial=r,bios-chs-trans=t,addr=a`` instead +(together with ``-drive if=none,id=dr,...``). + +``-net ...,vlan=x`` (removed in 3.0) +'''''''''''''''''''''''''''''''''''' + +The term "vlan" was very confusing for most users in this context (it's about +specifying a hub ID, not about IEEE 802.1Q or something similar), so this +has been removed. To connect one NIC frontend with a network backend, either +use ``-nic ...`` (e.g. for on-board NICs) or use ``-netdev ...,id=n`` together +with ``-device ...,netdev=n`` (for full control over pluggable NICs). To +connect multiple NICs or network backends via a hub device (which is what +vlan did), use ``-nic hubport,hubid=x,...`` or +``-netdev hubport,id=n,hubid=x,...`` (with ``-device ...,netdev=n``) instead. + +``-no-kvm-irqchip`` (removed in 3.0) +'''''''''''''''''''''''''''''''''''' + +Use ``-machine kernel_irqchip=off`` instead. + +``-no-kvm-pit-reinjection`` (removed in 3.0) +'''''''''''''''''''''''''''''''''''''''''''' + +Use ``-global kvm-pit.lost_tick_policy=discard`` instead. + +``-balloon`` (removed in 3.1) +''''''''''''''''''''''''''''' + +The ``-balloon virtio`` option has been replaced by ``-device virtio-balloon``. +The ``-balloon none`` option was a no-op and has no replacement. + +``-bootp`` (removed in 3.1) +''''''''''''''''''''''''''' + +The ``-bootp /some/file`` argument is replaced by either +``-netdev user,id=x,bootp=/some/file`` (for pluggable NICs, accompanied with +``-device ...,netdev=x``), or ``-nic user,bootp=/some/file`` (for on-board NICs). +The new syntax allows different settings to be provided per NIC. + +``-redir`` (removed in 3.1) +''''''''''''''''''''''''''' + +The ``-redir [tcp|udp]:hostport:[guestaddr]:guestport`` option is replaced +by either ``-netdev +user,id=x,hostfwd=[tcp|udp]:[hostaddr]:hostport-[guestaddr]:guestport`` +(for pluggable NICs, accompanied with ``-device ...,netdev=x``) or by the option +``-nic user,hostfwd=[tcp|udp]:[hostaddr]:hostport-[guestaddr]:guestport`` +(for on-board NICs). The new syntax allows different settings to be provided +per NIC. + +``-smb`` (removed in 3.1) +''''''''''''''''''''''''' + +The ``-smb /some/dir`` argument is replaced by either +``-netdev user,id=x,smb=/some/dir`` (for pluggable NICs, accompanied with +``-device ...,netdev=x``), or ``-nic user,smb=/some/dir`` (for on-board NICs). +The new syntax allows different settings to be provided per NIC. + +``-tftp`` (removed in 3.1) +'''''''''''''''''''''''''' + +The ``-tftp /some/dir`` argument is replaced by either +``-netdev user,id=x,tftp=/some/dir`` (for pluggable NICs, accompanied with +``-device ...,netdev=x``), or ``-nic user,tftp=/some/dir`` (for embedded NICs). +The new syntax allows different settings to be provided per NIC. + +``-localtime`` (removed in 3.1) +''''''''''''''''''''''''''''''' + +Replaced by ``-rtc base=localtime``. + +``-nodefconfig`` (removed in 3.1) +''''''''''''''''''''''''''''''''' + +Use ``-no-user-config`` instead. + +``-rtc-td-hack`` (removed in 3.1) +''''''''''''''''''''''''''''''''' + +Use ``-rtc driftfix=slew`` instead. + +``-startdate`` (removed in 3.1) +''''''''''''''''''''''''''''''' + +Replaced by ``-rtc base=date``. + +``-vnc ...,tls=...``, ``-vnc ...,x509=...`` & ``-vnc ...,x509verify=...`` +''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The "tls-creds" option should be used instead to point to a "tls-creds-x509" +object created using "-object". + +``-net ...,name=...`` (removed in 5.1) +'''''''''''''''''''''''''''''''''''''' The ``name`` parameter of the ``-net`` option was a synonym for the ``id`` parameter, which should now be used instead. @@ -124,8 +261,13 @@ devices. Drives the board doesn't pick up can no longer be used with ''''''''''''''''''''''''''''''''''''' This option was undocumented and not used in the field. -Use `-device usb-ccid`` instead. +Use ``-device usb-ccid`` instead. +RISC-V firmware not booted by default (removed in 5.1) +'''''''''''''''''''''''''''''''''''''''''''''''''''''' + +QEMU 5.1 changes the default behaviour from ``-bios none`` to ``-bios default`` +for the RISC-V ``virt`` machine and ``sifive_u`` machine. QEMU Machine Protocol (QMP) commands ------------------------------------ @@ -214,6 +356,17 @@ Specify the properties for the object as top-level arguments instead. Human Monitor Protocol (HMP) commands ------------------------------------- +``usb_add`` and ``usb_remove`` (removed in 2.12) +'''''''''''''''''''''''''''''''''''''''''''''''' + +Replaced by ``device_add`` and ``device_del`` (use ``device_add help`` for a +list of available devices). + +``host_net_add`` and ``host_net_remove`` (removed in 2.12) +'''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +Replaced by ``netdev_add`` and ``netdev_del``. + The ``hub_id`` parameter of ``hostfwd_add`` / ``hostfwd_remove`` (removed in 5.0) ''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' @@ -249,6 +402,11 @@ Use ``migrate-set-parameters`` and ``info migrate-parameters`` instead. Use ``migrate-set-parameters`` instead. +``info cpustats`` (removed in 6.1) +'''''''''''''''''''''''''''''''''' + +This command didn't produce any output already. Removed with no replacement. + Guest Emulator ISAs ------------------- @@ -285,9 +443,52 @@ The RISC-V no MMU cpus have been removed. The two CPUs: ``rv32imacu-nommu`` and ``rv64imacu-nommu`` can no longer be used. Instead the MMU status can be specified via the CPU ``mmu`` option when using the ``rv32`` or ``rv64`` CPUs. +``compat`` property of server class POWER CPUs (removed in 6.0) +''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The ``max-cpu-compat`` property of the ``pseries`` machine type should be used +instead. + +``moxie`` CPU (removed in 6.1) +'''''''''''''''''''''''''''''' + +Nobody was using this CPU emulation in QEMU, and there were no test images +available to make sure that the code is still working, so it has been removed +without replacement. + +``lm32`` CPUs (removed in 6.1.0) +'''''''''''''''''''''''''''''''' + +The only public user of this architecture was the milkymist project, +which has been dead for years; there was never an upstream Linux +port. Removed without replacement. + +``unicore32`` CPUs (since 6.1.0) +'''''''''''''''''''''''''''''''' + +Support for this CPU was removed from the upstream Linux kernel, and +there is no available upstream toolchain to build binaries for it. +Removed without replacement. + System emulator machines ------------------------ +``s390-virtio`` (removed in 2.6) +'''''''''''''''''''''''''''''''' + +Use the ``s390-ccw-virtio`` machine instead. + +The m68k ``dummy`` machine (removed in 2.9) +''''''''''''''''''''''''''''''''''''''''''' + +Use the ``none`` machine with the ``loader`` device instead. + +``xlnx-ep108`` (removed in 3.0) +''''''''''''''''''''''''''''''' + +The EP108 was an early access development board that is no longer used. +Use the ``xlnx-zcu102`` machine instead. + ``spike_v1.9.1`` and ``spike_v1.10`` (removed in 5.1) ''''''''''''''''''''''''''''''''''''''''''''''''''''' @@ -306,8 +507,8 @@ mips ``fulong2e`` machine alias (removed in 6.0) This machine has been renamed ``fuloong2e``. -``pc-1.0``, ``pc-1.1``, ``pc-1.2`` and ``pc-1.3`` (removed in 6.0) -'''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' +``pc-0.10`` up to ``pc-1.3`` (removed in 4.0 up to 6.0) +''''''''''''''''''''''''''''''''''''''''''''''''''''''' These machine types were very old and likely could not be used for live migration from old QEMU versions anymore. Use a newer machine type instead. @@ -328,6 +529,17 @@ running the old binaries, you can use older versions of QEMU. System emulator devices ----------------------- +``spapr-pci-vfio-host-bridge`` (removed in 2.12) +''''''''''''''''''''''''''''''''''''''''''''''''' + +The ``spapr-pci-vfio-host-bridge`` device type has been replaced by the +``spapr-pci-host-bridge`` device type. + +``ivshmem`` (removed in 4.0) +'''''''''''''''''''''''''''' + +Replaced by either the ``ivshmem-plain`` or ``ivshmem-doorbell``. + ``ide-drive`` (removed in 6.0) '''''''''''''''''''''''''''''' @@ -454,6 +666,37 @@ topologies described with -smp include all possible cpus, i.e. The ``enforce-config-section`` property was replaced by the ``-global migration.send-configuration={on|off}`` option. +qemu-img amend to adjust backing file (removed in 6.1) +'''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The use of ``qemu-img amend`` to modify the name or format of a qcow2 +backing image was never fully documented or tested, and interferes +with other amend operations that need access to the original backing +image (such as deciding whether a v3 zero cluster may be left +unallocated when converting to a v2 image). Any changes to the +backing chain should be performed with ``qemu-img rebase -u`` either +before or after the remaining changes being performed by amend, as +appropriate. + +qemu-img backing file without format (removed in 6.1) +''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The use of ``qemu-img create``, ``qemu-img rebase``, or ``qemu-img +convert`` to create or modify an image that depends on a backing file +now requires that an explicit backing format be provided. This is +for safety: if QEMU probes a different format than what you thought, +the data presented to the guest will be corrupt; similarly, presenting +a raw image to a guest allows a potential security exploit if a future +probe sees a non-raw image based on guest writes. + +To avoid creating unsafe backing chains, you must pass ``-o +backing_fmt=`` (or the shorthand ``-F`` during create) to specify the +intended backing format. You may use ``qemu-img rebase -u`` to +retroactively add a backing format to an existing image. However, be +aware that there are already potential security risks to blindly using +``qemu-img info`` to probe the format of an untrusted backing image, +when deciding what format to add into an existing image. + Block devices ------------- @@ -461,3 +704,10 @@ VXHS backend (removed in 5.1) ''''''''''''''''''''''''''''' The VXHS code did not compile since v2.12.0. It was removed in 5.1. + +``sheepdog`` driver (removed in 6.0) +'''''''''''''''''''''''''''''''''''' + +The corresponding upstream server project is no longer maintained. +Users are recommended to switch to an alternative distributed block +device driver such as RBD. diff --git a/docs/amd-memory-encryption.txt b/docs/amd-memory-encryption.txt index 145896aec7..ffca382b5f 100644 --- a/docs/amd-memory-encryption.txt +++ b/docs/amd-memory-encryption.txt @@ -1,38 +1,48 @@ Secure Encrypted Virtualization (SEV) is a feature found on AMD processors. SEV is an extension to the AMD-V architecture which supports running encrypted -virtual machine (VMs) under the control of KVM. Encrypted VMs have their pages +virtual machines (VMs) under the control of KVM. Encrypted VMs have their pages (code and data) secured such that only the guest itself has access to the unencrypted version. Each encrypted VM is associated with a unique encryption -key; if its data is accessed to a different entity using a different key the +key; if its data is accessed by a different entity using a different key the encrypted guests data will be incorrectly decrypted, leading to unintelligible data. -The key management of this feature is handled by separate processor known as -AMD secure processor (AMD-SP) which is present in AMD SOCs. Firmware running -inside the AMD-SP provide commands to support common VM lifecycle. This +Key management for this feature is handled by a separate processor known as the +AMD secure processor (AMD-SP), which is present in AMD SOCs. Firmware running +inside the AMD-SP provides commands to support a common VM lifecycle. This includes commands for launching, snapshotting, migrating and debugging the -encrypted guest. Those SEV command can be issued via KVM_MEMORY_ENCRYPT_OP +encrypted guest. These SEV commands can be issued via KVM_MEMORY_ENCRYPT_OP ioctls. +Secure Encrypted Virtualization - Encrypted State (SEV-ES) builds on the SEV +support to additionally protect the guest register state. In order to allow a +hypervisor to perform functions on behalf of a guest, there is architectural +support for notifying a guest's operating system when certain types of VMEXITs +are about to occur. This allows the guest to selectively share information with +the hypervisor to satisfy the requested function. + Launching --------- -Boot images (such as bios) must be encrypted before guest can be booted. -MEMORY_ENCRYPT_OP ioctl provides commands to encrypt the images :LAUNCH_START, +Boot images (such as bios) must be encrypted before a guest can be booted. The +MEMORY_ENCRYPT_OP ioctl provides commands to encrypt the images: LAUNCH_START, LAUNCH_UPDATE_DATA, LAUNCH_MEASURE and LAUNCH_FINISH. These four commands together generate a fresh memory encryption key for the VM, encrypt the boot -images and provide a measurement than can be used as an attestation of the +images and provide a measurement than can be used as an attestation of a successful launch. -LAUNCH_START is called first to create a cryptographic launch context within -the firmware. To create this context, guest owner must provides guest policy, -its public Diffie-Hellman key (PDH) and session parameters. These inputs -should be treated as binary blob and must be passed as-is to the SEV firmware. +For a SEV-ES guest, the LAUNCH_UPDATE_VMSA command is also used to encrypt the +guest register state, or VM save area (VMSA), for all of the guest vCPUs. -The guest policy is passed as plaintext and hypervisor may able to read it +LAUNCH_START is called first to create a cryptographic launch context within +the firmware. To create this context, guest owner must provide a guest policy, +its public Diffie-Hellman key (PDH) and session parameters. These inputs +should be treated as a binary blob and must be passed as-is to the SEV firmware. + +The guest policy is passed as plaintext. A hypervisor may choose to read it, but should not modify it (any modification of the policy bits will result in bad measurement). The guest policy is a 4-byte data structure containing -several flags that restricts what can be done on running SEV guest. +several flags that restricts what can be done on a running SEV guest. See KM Spec section 3 and 6.2 for more details. The guest policy can be provided via the 'policy' property (see below) @@ -40,31 +50,42 @@ The guest policy can be provided via the 'policy' property (see below) # ${QEMU} \ sev-guest,id=sev0,policy=0x1...\ -Guest owners provided DH certificate and session parameters will be used to +Setting the "SEV-ES required" policy bit (bit 2) will launch the guest as a +SEV-ES guest (see below) + +# ${QEMU} \ + sev-guest,id=sev0,policy=0x5...\ + +The guest owner provided DH certificate and session parameters will be used to establish a cryptographic session with the guest owner to negotiate keys used for the attestation. -The DH certificate and session blob can be provided via 'dh-cert-file' and -'session-file' property (see below +The DH certificate and session blob can be provided via the 'dh-cert-file' and +'session-file' properties (see below) # ${QEMU} \ sev-guest,id=sev0,dh-cert-file=,session-file= LAUNCH_UPDATE_DATA encrypts the memory region using the cryptographic context -created via LAUNCH_START command. If required, this command can be called +created via the LAUNCH_START command. If required, this command can be called multiple times to encrypt different memory regions. The command also calculates the measurement of the memory contents as it encrypts. -LAUNCH_MEASURE command can be used to retrieve the measurement of encrypted -memory. This measurement is a signature of the memory contents that can be -sent to the guest owner as an attestation that the memory was encrypted +LAUNCH_UPDATE_VMSA encrypts all the vCPU VMSAs for a SEV-ES guest using the +cryptographic context created via the LAUNCH_START command. The command also +calculates the measurement of the VMSAs as it encrypts them. + +LAUNCH_MEASURE can be used to retrieve the measurement of encrypted memory and, +for a SEV-ES guest, encrypted VMSAs. This measurement is a signature of the +memory contents and, for a SEV-ES guest, the VMSA contents, that can be sent +to the guest owner as an attestation that the memory and VMSAs were encrypted correctly by the firmware. The guest owner may wait to provide the guest confidential information until it can verify the attestation measurement. Since the guest owner knows the initial contents of the guest at boot, the attestation measurement can be verified by comparing it to what the guest owner expects. -LAUNCH_FINISH command finalizes the guest launch and destroy's the cryptographic +LAUNCH_FINISH finalizes the guest launch and destroys the cryptographic context. See SEV KM API Spec [1] 'Launching a guest' usage flow (Appendix A) for the @@ -76,12 +97,28 @@ To launch a SEV guest -machine ...,confidential-guest-support=sev0 \ -object sev-guest,id=sev0,cbitpos=47,reduced-phys-bits=1 +To launch a SEV-ES guest + +# ${QEMU} \ + -machine ...,confidential-guest-support=sev0 \ + -object sev-guest,id=sev0,cbitpos=47,reduced-phys-bits=1,policy=0x5 + +An SEV-ES guest has some restrictions as compared to a SEV guest. Because the +guest register state is encrypted and cannot be updated by the VMM/hypervisor, +a SEV-ES guest: + - Does not support SMM - SMM support requires updating the guest register + state. + - Does not support reboot - a system reset requires updating the guest register + state. + - Requires in-kernel irqchip - the burden is placed on the hypervisor to + manage booting APs. + Debugging ----------- -Since memory contents of SEV guest is encrypted hence hypervisor access to the -guest memory will get a cipher text. If guest policy allows debugging, then -hypervisor can use DEBUG_DECRYPT and DEBUG_ENCRYPT commands access the guest -memory region for debug purposes. This is not supported in QEMU yet. +Since the memory contents of a SEV guest are encrypted, hypervisor access to +the guest memory will return cipher text. If the guest policy allows debugging, +then a hypervisor can use the DEBUG_DECRYPT and DEBUG_ENCRYPT commands to access +the guest memory region for debug purposes. This is not supported in QEMU yet. Snapshot/Restore ----------------- @@ -102,8 +139,10 @@ Secure Encrypted Virtualization Key Management: KVM Forum slides: http://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf +https://www.linux-kvm.org/images/9/94/Extending-Secure-Encrypted-Virtualization-with-SEV-ES-Thomas-Lendacky-AMD.pdf AMD64 Architecture Programmer's Manual: http://support.amd.com/TechDocs/24593.pdf SME is section 7.10 SEV is section 15.34 + SEV-ES is section 15.35 diff --git a/docs/barrier.txt b/docs/barrier.txt deleted file mode 100644 index b21d15015d..0000000000 --- a/docs/barrier.txt +++ /dev/null @@ -1,370 +0,0 @@ - QEMU Barrier Client - - -* About - - Barrier is a KVM (Keyboard-Video-Mouse) software forked from Symless's - synergy 1.9 codebase. - - See https://github.com/debauchee/barrier - -* QEMU usage - - Generally, mouse and keyboard are grabbed through the QEMU video - interface emulation. - - But when we want to use a video graphic adapter via a PCI passthrough - there is no way to provide the keyboard and mouse inputs to the VM - except by plugging a second set of mouse and keyboard to the host - or by installing a KVM software in the guest OS. - - The QEMU Barrier client avoids this by implementing directly the Barrier - protocol into QEMU. - - This protocol is enabled by adding an input-barrier object to QEMU. - - Syntax: input-barrier,id=,name= - [,server=][,port=] - [,x-origin=][,y-origin=] - [,width=][,height=] - - The object can be added on the QEMU command line, for instance with: - - ... -object input-barrier,id=barrier0,name=VM-1 ... - - where VM-1 is the name the display configured int the Barrier server - on the host providing the mouse and the keyboard events. - - by default is "localhost", port is 24800, - and are set to 0, and to - 1920 and 1080. - - If Barrier server is stopped QEMU needs to be reconnected manually, - by removing and re-adding the input-barrier object, for instance - with the help of the HMP monitor: - - (qemu) object_del barrier0 - (qemu) object_add input-barrier,id=barrier0,name=VM-1 - -* Message format - - Message format between the server and client is in two parts: - - 1- the payload length is a 32bit integer in network endianness, - 2- the payload - - The payload starts with a 4byte string (without NUL) which is the - command. The first command between the server and the client - is the only command not encoded on 4 bytes ("Barrier"). - The remaining part of the payload is decoded according to the command. - -* Protocol Description (from barrier/src/lib/barrier/protocol_types.h) - - - barrierCmdHello "Barrier" - - Direction: server -> client - Parameters: { int16_t minor, int16_t major } - Description: - - Say hello to client - minor = protocol major version number supported by server - major = protocol minor version number supported by server - - - barrierCmdHelloBack "Barrier" - - Direction: client ->server - Parameters: { int16_t minor, int16_t major, char *name} - Description: - - Respond to hello from server - minor = protocol major version number supported by client - major = protocol minor version number supported by client - name = client name - - - barrierCmdDInfo "DINF" - - Direction: client ->server - Parameters: { int16_t x_origin, int16_t y_origin, int16_t width, int16_t height, int16_t x, int16_t y} - Description: - - The client screen must send this message in response to the - barrierCmdQInfo message. It must also send this message when the - screen's resolution changes. In this case, the client screen should - ignore any barrierCmdDMouseMove messages until it receives a - barrierCmdCInfoAck in order to prevent attempts to move the mouse off - the new screen area. - - - barrierCmdCNoop "CNOP" - - Direction: client -> server - Parameters: None - Description: - - No operation - - - barrierCmdCClose "CBYE" - - Direction: server -> client - Parameters: None - Description: - - Close connection - - - barrierCmdCEnter "CINN" - - Direction: server -> client - Parameters: { int16_t x, int16_t y, int32_t seq, int16_t modifier } - Description: - - Enter screen. - x,y = entering screen absolute coordinates - seq = sequence number, which is used to order messages between - screens. the secondary screen must return this number - with some messages - modifier = modifier key mask. this will have bits set for each - toggle modifier key that is activated on entry to the - screen. the secondary screen should adjust its toggle - modifiers to reflect that state. - - - barrierCmdCLeave "COUT" - - Direction: server -> client - Parameters: None - Description: - - Leaving screen. the secondary screen should send clipboard data in - response to this message for those clipboards that it has grabbed - (i.e. has sent a barrierCmdCClipboard for and has not received a - barrierCmdCClipboard for with a greater sequence number) and that - were grabbed or have changed since the last leave. - - - barrierCmdCClipboard "CCLP" - - Direction: server -> client - Parameters: { int8_t id, int32_t seq } - Description: - - Grab clipboard. Sent by screen when some other app on that screen - grabs a clipboard. - id = the clipboard identifier - seq = sequence number. Client must use the sequence number passed in - the most recent barrierCmdCEnter. the server always sends 0. - - - barrierCmdCScreenSaver "CSEC" - - Direction: server -> client - Parameters: { int8_t started } - Description: - - Screensaver change. - started = Screensaver on primary has started (1) or closed (0) - - - barrierCmdCResetOptions "CROP" - - Direction: server -> client - Parameters: None - Description: - - Reset options. Client should reset all of its options to their - defaults. - - - barrierCmdCInfoAck "CIAK" - - Direction: server -> client - Parameters: None - Description: - - Resolution change acknowledgment. Sent by server in response to a - client screen's barrierCmdDInfo. This is sent for every - barrierCmdDInfo, whether or not the server had sent a barrierCmdQInfo. - - - barrierCmdCKeepAlive "CALV" - - Direction: server -> client - Parameters: None - Description: - - Keep connection alive. Sent by the server periodically to verify - that connections are still up and running. clients must reply in - kind on receipt. if the server gets an error sending the message or - does not receive a reply within a reasonable time then the server - disconnects the client. if the client doesn't receive these (or any - message) periodically then it should disconnect from the server. the - appropriate interval is defined by an option. - - - barrierCmdDKeyDown "DKDN" - - Direction: server -> client - Parameters: { int16_t keyid, int16_t modifier [,int16_t button] } - Description: - - Key pressed. - keyid = X11 key id - modified = modified mask - button = X11 Xkb keycode (optional) - - - barrierCmdDKeyRepeat "DKRP" - - Direction: server -> client - Parameters: { int16_t keyid, int16_t modifier, int16_t repeat [,int16_t button] } - Description: - - Key auto-repeat. - keyid = X11 key id - modified = modified mask - repeat = number of repeats - button = X11 Xkb keycode (optional) - - - barrierCmdDKeyUp "DKUP" - - Direction: server -> client - Parameters: { int16_t keyid, int16_t modifier [,int16_t button] } - Description: - - Key released. - keyid = X11 key id - modified = modified mask - button = X11 Xkb keycode (optional) - - - barrierCmdDMouseDown "DMDN" - - Direction: server -> client - Parameters: { int8_t button } - Description: - - Mouse button pressed. - button = button id - - - barrierCmdDMouseUp "DMUP" - - Direction: server -> client - Parameters: { int8_t button } - Description: - - Mouse button release. - button = button id - - - barrierCmdDMouseMove "DMMV" - - Direction: server -> client - Parameters: { int16_t x, int16_t y } - Description: - - Absolute mouse moved. - x,y = absolute screen coordinates - - - barrierCmdDMouseRelMove "DMRM" - - Direction: server -> client - Parameters: { int16_t x, int16_t y } - Description: - - Relative mouse moved. - x,y = r relative screen coordinates - - - barrierCmdDMouseWheel "DMWM" - - Direction: server -> client - Parameters: { int16_t x , int16_t y } or { int16_t y } - Description: - - Mouse scroll. The delta should be +120 for one tick forward (away - from the user) or right and -120 for one tick backward (toward the - user) or left. - x = x delta - y = y delta - - - barrierCmdDClipboard "DCLP" - - Direction: server -> client - Parameters: { int8_t id, int32_t seq, int8_t mark, char *data } - Description: - - Clipboard data. - id = clipboard id - seq = sequence number. The sequence number is 0 when sent by the - server. Client screens should use the/ sequence number from - the most recent barrierCmdCEnter. - - - barrierCmdDSetOptions "DSOP" - - Direction: server -> client - Parameters: { int32 t nb, { int32_t id, int32_t val }[] } - Description: - - Set options. Client should set the given option/value pairs. - nb = numbers of { id, val } entries - id = option id - val = option new value - - - barrierCmdDFileTransfer "DFTR" - - Direction: server -> client - Parameters: { int8_t mark, char *content } - Description: - - Transfer file data. - mark = 0 means the content followed is the file size - 1 means the content followed is the chunk data - 2 means the file transfer is finished - - - barrierCmdDDragInfo "DDRG" int16_t char * - - Direction: server -> client - Parameters: { int16_t nb, char *content } - Description: - - Drag information. - nb = number of dragging objects - content = object's directory - - - barrierCmdQInfo "QINF" - - Direction: server -> client - Parameters: None - Description: - - Query screen info - Client should reply with a barrierCmdDInfo - - - barrierCmdEIncompatible "EICV" - - Direction: server -> client - Parameters: { int16_t nb, major *minor } - Description: - - Incompatible version. - major = major version - minor = minor version - - - barrierCmdEBusy "EBSY" - - Direction: server -> client - Parameters: None - Description: - - Name provided when connecting is already in use. - - - barrierCmdEUnknown "EUNK" - - Direction: server -> client - Parameters: None - Description: - - Unknown client. Name provided when connecting is not in primary's - screen configuration map. - - - barrierCmdEBad "EBAD" - - Direction: server -> client - Parameters: None - Description: - - Protocol violation. Server should disconnect after sending this - message. - -* TO DO - - - Enable SSL - - Manage SetOptions/ResetOptions commands - diff --git a/docs/bootindex.txt b/docs/bootindex.txt deleted file mode 100644 index 6937862ba0..0000000000 --- a/docs/bootindex.txt +++ /dev/null @@ -1,52 +0,0 @@ -= Bootindex property = - -Block and net devices have bootindex property. This property is used to -determine the order in which firmware will consider devices for booting -the guest OS. If the bootindex property is not set for a device, it gets -lowest boot priority. There is no particular order in which devices with -unset bootindex property will be considered for booting, but they will -still be bootable. - -== Example == - -Let's assume we have a QEMU machine with two NICs (virtio, e1000) and two -disks (IDE, virtio): - -qemu -drive file=disk1.img,if=none,id=disk1 - -device ide-hd,drive=disk1,bootindex=4 - -drive file=disk2.img,if=none,id=disk2 - -device virtio-blk-pci,drive=disk2,bootindex=3 - -netdev type=user,id=net0 -device virtio-net-pci,netdev=net0,bootindex=2 - -netdev type=user,id=net1 -device e1000,netdev=net1,bootindex=1 - -Given the command above, firmware should try to boot from the e1000 NIC -first. If this fails, it should try the virtio NIC next; if this fails -too, it should try the virtio disk, and then the IDE disk. - -== Limitations == - -1. Some firmware has limitations on which devices can be considered for -booting. For instance, the PC BIOS boot specification allows only one -disk to be bootable. If boot from disk fails for some reason, the BIOS -won't retry booting from other disk. It can still try to boot from -floppy or net, though. - -2. Sometimes, firmware cannot map the device path QEMU wants firmware to -boot from to a boot method. It doesn't happen for devices the firmware -can natively boot from, but if firmware relies on an option ROM for -booting, and the same option ROM is used for booting from more then one -device, the firmware may not be able to ask the option ROM to boot from -a particular device reliably. For instance with the PC BIOS, if a SCSI HBA -has three bootable devices target1, target3, target5 connected to it, -the option ROM will have a boot method for each of them, but it is not -possible to map from boot method back to a specific target. This is a -shortcoming of the PC BIOS boot specification. - -== Mixing bootindex and boot order parameters == - -Note that it does not make sense to use the bootindex property together -with the "-boot order=..." (or "-boot once=...") parameter. The guest -firmware implementations normally either support the one or the other, -but not both parameters at the same time. Mixing them will result in -undefined behavior, and thus the guest firmware will likely not boot -from the expected devices. diff --git a/docs/bypass-iommu.txt b/docs/bypass-iommu.txt new file mode 100644 index 0000000000..e6677bddd3 --- /dev/null +++ b/docs/bypass-iommu.txt @@ -0,0 +1,89 @@ +BYPASS IOMMU PROPERTY +===================== + +Description +=========== +Traditionally, there is a global switch to enable/disable vIOMMU. All +devices in the system can only support go through vIOMMU or not, which +is not flexible. We introduce this bypass iommu property to support +coexist of devices go through vIOMMU and devices not. This is useful to +passthrough devices with no-iommu mode and devices go through vIOMMU in +the same virtual machine. + +PCI host bridges have a bypass_iommu property. This property is used to +determine whether the devices attached on the PCI host bridge will bypass +virtual iommu. The bypass_iommu property is valid only when there is a +virtual iommu in the system, it is implemented to allow some devices to +bypass vIOMMU. When bypass_iommu property is not set for a host bridge, +the attached devices will go through vIOMMU by default. + +Usage +===== +The bypass iommu feature support PXB host bridge and default main host +bridge, we add a bypass_iommu property for PXB and default_bus_bypass_iommu +for machine. Note that default_bus_bypass_iommu is available only when +the 'q35' machine type on x86 architecture and the 'virt' machine type +on AArch64. Other machine types do not support bypass iommu for default +root bus. + +1. The following is the bypass iommu options: + (1) PCI expander bridge + qemu -device pxb-pcie,bus_nr=0x10,addr=0x1,bypass_iommu=true + (2) Arm default host bridge + qemu -machine virt,iommu=smmuv3,default_bus_bypass_iommu=true + (3) X86 default root bus bypass iommu: + qemu -machine q35,default_bus_bypass_iommu=true + +2. Here is the detailed qemu command line for 'virt' machine with PXB on +AArch64: + +qemu-system-aarch64 \ + -machine virt,kernel_irqchip=on,iommu=smmuv3,default_bus_bypass_iommu=true \ + -device pxb-pcie,bus_nr=0x10,id=pci.10,bus=pcie.0,addr=0x3.0x1 \ + -device pxb-pcie,bus_nr=0x20,id=pci.20,bus=pcie.0,addr=0x3.0x2,bypass_iommu=true \ + +And we got: + - a default host bridge which bypass SMMUv3 + - a pxb host bridge which go through SMMUv3 + - a pxb host bridge which bypass SMMUv3 + +3. Here is the detailed qemu command line for 'q35' machine with PXB on +x86 architecture: + +qemu-system-x86_64 \ + -machine q35,accel=kvm,default_bus_bypass_iommu=true \ + -device pxb-pcie,bus_nr=0x10,id=pci.10,bus=pcie.0,addr=0x3 \ + -device pxb-pcie,bus_nr=0x20,id=pci.20,bus=pcie.0,addr=0x4,bypass_iommu=true \ + -device intel-iommu \ + +And we got: + - a default host bridge which bypass iommu + - a pxb host bridge which go through iommu + - a pxb host bridge which bypass iommu + +Limitations +=========== +There might be potential security risk when devices bypass iommu, because +devices might send malicious dma request to virtual machine if there is no +iommu isolation. So it would be necessary to only bypass iommu for trusted +device. + +Implementation +============== +The bypass iommu feature includes: + - Address space + Add bypass iommu property check of PCI Host and do not get iommu address + space for devices bypass iommu. + - Arm SMMUv3 support + We traverse all PCI root bus and get bus number ranges, then build explicit + RID mapping for devices which do not bypass iommu. + - X86 IOMMU support + To support Intel iommu, we traverse all PCI host bridge and get information + of devices which do not bypass iommu, then fill the DMAR drhd struct with + explicit device scope info. To support AMD iommu, add check of bypass iommu + when traverse the PCI hsot bridge. + - Machine and PXB options + We add bypass iommu options in machine option for default root bus, and add + option for PXB also. Note that the default value of bypass iommu is false, + so that the devices will by default go through iommu if there exist one. + diff --git a/docs/ccid.txt b/docs/ccid.txt index c97fbd2de0..2b85b1bd42 100644 --- a/docs/ccid.txt +++ b/docs/ccid.txt @@ -34,15 +34,14 @@ reader and smart card (i.e. not backed by a physical device) using this device. 2. Building -The cryptographic functions and access to the physical card is done via NSS. - -Installing NSS: +The cryptographic functions and access to the physical card is done via the +libcacard library, whose development package must be installed prior to +building QEMU: In redhat/fedora: - yum install nss-devel -In ubuntu/debian: - apt-get install libnss3-dev - (not tested on ubuntu) + yum install libcacard-devel +In ubuntu: + apt-get install libcacard-dev Configuring and building: ./configure --enable-smartcard && make @@ -51,7 +50,7 @@ Configuring and building: 3. Using ccid-card-emulated with hardware Assuming you have a working smartcard on the host with the current -user, using NSS, qemu acts as another NSS client using ccid-card-emulated: +user, using libcacard, QEMU acts as another client using ccid-card-emulated: qemu -usb -device usb-ccid -device ccid-card-emulated diff --git a/docs/conf.py b/docs/conf.py index 2ee6111872..ff6e92c6e2 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -29,6 +29,7 @@ import os import sys import sphinx +from distutils.version import LooseVersion from sphinx.errors import ConfigError # Make Sphinx fail cleanly if using an old Python, rather than obscurely @@ -86,7 +87,7 @@ master_doc = 'index' # General information about the project. project = u'QEMU' -copyright = u'2020, The QEMU Project Developers' +copyright = u'2021, The QEMU Project Developers' author = u'The QEMU Project Developers' # The version info for the project you're documenting, acts as replacement for @@ -150,38 +151,47 @@ with open(os.path.join(qemu_docdir, 'defs.rst.inc')) as f: # The theme to use for HTML and HTML Help pages. See the documentation for # a list of builtin themes. # -html_theme = 'alabaster' +try: + import sphinx_rtd_theme +except ImportError: + raise ConfigError( + 'The Sphinx \'sphinx_rtd_theme\' HTML theme was not found.\n' + ) + +html_theme = 'sphinx_rtd_theme' # Theme options are theme-specific and customize the look and feel of a theme # further. For a list of options available for each theme, see the # documentation. -# We initialize this to empty here, so the per-manual conf.py can just -# add individual key/value entries. -html_theme_options = { -} +if LooseVersion(sphinx_rtd_theme.__version__) >= LooseVersion("0.4.3"): + html_theme_options = { + "style_nav_header_background": "#802400", + } + +html_logo = os.path.join(qemu_docdir, "../ui/icons/qemu_128x128.png") + +html_favicon = os.path.join(qemu_docdir, "../ui/icons/qemu_32x32.png") # Add any paths that contain custom static files (such as style sheets) here, # relative to this directory. They are copied after the builtin static files, # so a file named "default.css" will overwrite the builtin "default.css". -# QEMU doesn't yet have any static files, so comment this out so we don't -# get a warning about a missing directory. -# If we do ever add this then it would probably be better to call the -# subdirectory sphinx_static, as the Linux kernel does. -# html_static_path = ['_static'] +html_static_path = [os.path.join(qemu_docdir, "sphinx-static")] + +html_css_files = [ + 'theme_overrides.css', +] + +html_context = { + "display_gitlab": True, + "gitlab_user": "qemu-project", + "gitlab_repo": "qemu", + "gitlab_version": "master", + "conf_py_path": "/docs/", # Path in the checkout to the docs root +} # Custom sidebar templates, must be a dictionary that maps document names # to template names. -# -# This is required for the alabaster theme -# refs: http://alabaster.readthedocs.io/en/latest/installation.html#sidebars -html_sidebars = { - '**': [ - 'about.html', - 'editpage.html', - 'navigation.html', - 'searchbox.html', - ] -} +#html_sidebars = {} # Don't copy the rST source files to the HTML output directory, # and don't put links to the sources into the output HTML. @@ -269,6 +279,7 @@ man_pages = [ ['Stefan Hajnoczi ', 'Masayoshi Mizuma '], 1), ] +man_make_section_directory = False # -- Options for Texinfo output ------------------------------------------- diff --git a/docs/devel/_templates/editpage.html b/docs/devel/_templates/editpage.html deleted file mode 100644 index a86d22bca8..0000000000 --- a/docs/devel/_templates/editpage.html +++ /dev/null @@ -1,5 +0,0 @@ -
- -
diff --git a/docs/devel/build-system.rst b/docs/devel/build-system.rst index 7ef36f42d0..3baec158f2 100644 --- a/docs/devel/build-system.rst +++ b/docs/devel/build-system.rst @@ -53,14 +53,14 @@ following tasks: - Add a Meson build option to meson_options.txt. - Add support to the command line arg parser to handle any new - `--enable-XXX`/`--disable-XXX` flags required by the feature. + ``--enable-XXX``/``--disable-XXX`` flags required by the feature. - Add information to the help output message to report on the new feature flag. - Add code to perform the actual feature check. - - Add code to include the feature status in `config-host.h` + - Add code to include the feature status in ``config-host.h`` - Add code to print out the feature status in the configure summary upon completion. @@ -116,51 +116,51 @@ Helper functions The configure script provides a variety of helper functions to assist developers in checking for system features: -`do_cc $ARGS...` +``do_cc $ARGS...`` Attempt to run the system C compiler passing it $ARGS... -`do_cxx $ARGS...` +``do_cxx $ARGS...`` Attempt to run the system C++ compiler passing it $ARGS... -`compile_object $CFLAGS` +``compile_object $CFLAGS`` Attempt to compile a test program with the system C compiler using $CFLAGS. The test program must have been previously written to a file - called $TMPC. The replacement in Meson is the compiler object `cc`, - which has methods such as `cc.compiles()`, - `cc.check_header()`, `cc.has_function()`. + called $TMPC. The replacement in Meson is the compiler object ``cc``, + which has methods such as ``cc.compiles()``, + ``cc.check_header()``, ``cc.has_function()``. -`compile_prog $CFLAGS $LDFLAGS` +``compile_prog $CFLAGS $LDFLAGS`` Attempt to compile a test program with the system C compiler using $CFLAGS and link it with the system linker using $LDFLAGS. The test program must have been previously written to a file called $TMPC. - The replacement in Meson is `cc.find_library()` and `cc.links()`. + The replacement in Meson is ``cc.find_library()`` and ``cc.links()``. -`has $COMMAND` +``has $COMMAND`` Determine if $COMMAND exists in the current environment, either as a shell builtin, or executable binary, returning 0 on success. The - replacement in Meson is `find_program()`. + replacement in Meson is ``find_program()``. -`check_define $NAME` +``check_define $NAME`` Determine if the macro $NAME is defined by the system C compiler -`check_include $NAME` +``check_include $NAME`` Determine if the include $NAME file is available to the system C - compiler. The replacement in Meson is `cc.has_header()`. + compiler. The replacement in Meson is ``cc.has_header()``. -`write_c_skeleton` +``write_c_skeleton`` Write a minimal C program main() function to the temporary file indicated by $TMPC -`feature_not_found $NAME $REMEDY` +``feature_not_found $NAME $REMEDY`` Print a message to stderr that the feature $NAME was not available on the system, suggesting the user try $REMEDY to address the problem. -`error_exit $MESSAGE $MORE...` +``error_exit $MESSAGE $MORE...`` Print $MESSAGE to stderr, followed by $MORE... and then exit from the configure script with non-zero status -`query_pkg_config $ARGS...` +``query_pkg_config $ARGS...`` Run pkg-config passing it $ARGS. If QEMU is doing a static build, then --static will be automatically added to $ARGS @@ -187,7 +187,7 @@ process for: 4) other data files, such as icons or desktop files -All executables are built by default, except for some `contrib/` +All executables are built by default, except for some ``contrib/`` binaries that are known to fail to build on some platforms (for example 32-bit or big-endian platforms). Tests are also built by default, though that might change in the future. @@ -195,14 +195,14 @@ though that might change in the future. The source code is highly modularized, split across many files to facilitate building of all of these components with as little duplicated compilation as possible. Using the Meson "sourceset" functionality, -`meson.build` files group the source files in rules that are +``meson.build`` files group the source files in rules that are enabled according to the available system libraries and to various configuration symbols. Sourcesets belong to one of four groups: Subsystem sourcesets: Various subsystems that are common to both tools and emulators have - their own sourceset, for example `block_ss` for the block device subsystem, - `chardev_ss` for the character device subsystem, etc. These sourcesets + their own sourceset, for example ``block_ss`` for the block device subsystem, + ``chardev_ss`` for the character device subsystem, etc. These sourcesets are then turned into static libraries as follows:: libchardev = static_library('chardev', chardev_ss.sources(), @@ -211,8 +211,8 @@ Subsystem sourcesets: chardev = declare_dependency(link_whole: libchardev) - As of Meson 0.55.1, the special `.fa` suffix should be used for everything - that is used with `link_whole`, to ensure that the link flags are placed + As of Meson 0.55.1, the special ``.fa`` suffix should be used for everything + that is used with ``link_whole``, to ensure that the link flags are placed correctly in the command line. Target-independent emulator sourcesets: @@ -221,38 +221,38 @@ Target-independent emulator sourcesets: This includes error handling infrastructure, standard data structures, platform portability wrapper functions, etc. - Target-independent code lives in the `common_ss`, `softmmu_ss` and - `user_ss` sourcesets. `common_ss` is linked into all emulators, - `softmmu_ss` only in system emulators, `user_ss` only in user-mode + Target-independent code lives in the ``common_ss``, ``softmmu_ss`` and + ``user_ss`` sourcesets. ``common_ss`` is linked into all emulators, + ``softmmu_ss`` only in system emulators, ``user_ss`` only in user-mode emulators. Target-independent sourcesets must exercise particular care when using - `if_false` rules. The `if_false` rule will be used correctly when linking + ``if_false`` rules. The ``if_false`` rule will be used correctly when linking emulator binaries; however, when *compiling* target-independent files - into .o files, Meson may need to pick *both* the `if_true` and - `if_false` sides to cater for targets that want either side. To + into .o files, Meson may need to pick *both* the ``if_true`` and + ``if_false`` sides to cater for targets that want either side. To achieve that, you can add a special rule using the ``CONFIG_ALL`` symbol:: # Some targets have CONFIG_ACPI, some don't, so this is not enough - softmmu_ss.add(when: 'CONFIG_ACPI`, if_true: files('acpi.c'), + softmmu_ss.add(when: 'CONFIG_ACPI', if_true: files('acpi.c'), if_false: files('acpi-stub.c')) # This is required as well: - softmmu_ss.add(when: 'CONFIG_ALL`, if_true: files('acpi-stub.c')) + softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('acpi-stub.c')) Target-dependent emulator sourcesets: In the target-dependent set lives CPU emulation, some device emulation and much glue code. This sometimes also has to be compiled multiple times, once for each target being built. Target-dependent files are included - in the `specific_ss` sourceset. + in the ``specific_ss`` sourceset. - Each emulator also includes sources for files in the `hw/` and `target/` + Each emulator also includes sources for files in the ``hw/`` and ``target/`` subdirectories. The subdirectory used for each emulator comes from the target's definition of ``TARGET_BASE_ARCH`` or (if missing) - ``TARGET_ARCH``, as found in `default-configs/targets/*.mak`. + ``TARGET_ARCH``, as found in ``default-configs/targets/*.mak``. - Each subdirectory in `hw/` adds one sourceset to the `hw_arch` dictionary, + Each subdirectory in ``hw/`` adds one sourceset to the ``hw_arch`` dictionary, for example:: arm_ss = ss.source_set() @@ -262,8 +262,8 @@ Target-dependent emulator sourcesets: The sourceset is only used for system emulators. - Each subdirectory in `target/` instead should add one sourceset to each - of the `target_arch` and `target_softmmu_arch`, which are used respectively + Each subdirectory in ``target/`` instead should add one sourceset to each + of the ``target_arch`` and ``target_softmmu_arch``, which are used respectively for all emulators and for system emulators only. For example:: arm_ss = ss.source_set() @@ -272,16 +272,33 @@ Target-dependent emulator sourcesets: target_arch += {'arm': arm_ss} target_softmmu_arch += {'arm': arm_softmmu_ss} +Module sourcesets: + There are two dictionaries for modules: ``modules`` is used for + target-independent modules and ``target_modules`` is used for + target-dependent modules. When modules are disabled the ``module`` + source sets are added to ``softmmu_ss`` and the ``target_modules`` + source sets are added to ``specific_ss``. + + Both dictionaries are nested. One dictionary is created per + subdirectory, and these per-subdirectory dictionaries are added to + the toplevel dictionaries. For example:: + + hw_display_modules = {} + qxl_ss = ss.source_set() + ... + hw_display_modules += { 'qxl': qxl_ss } + modules += { 'hw-display': hw_display_modules } + Utility sourcesets: - All binaries link with a static library `libqemuutil.a`. This library + All binaries link with a static library ``libqemuutil.a``. This library is built from several sourcesets; most of them however host generated - code, and the only two of general interest are `util_ss` and `stub_ss`. + code, and the only two of general interest are ``util_ss`` and ``stub_ss``. The separation between these two is purely for documentation purposes. - `util_ss` contains generic utility files. Even though this code is only + ``util_ss`` contains generic utility files. Even though this code is only linked in some binaries, sometimes it requires hooks only in some of these and depend on other functions that are not fully implemented by - all QEMU binaries. `stub_ss` links dummy stubs that will only be linked + all QEMU binaries. ``stub_ss`` links dummy stubs that will only be linked into the binary if the real implementation is not present. In a way, the stubs can be thought of as a portable implementation of the weak symbols concept. @@ -290,8 +307,8 @@ Utility sourcesets: The following files concur in the definition of which files are linked into each emulator: -`default-configs/devices/*.mak` - The files under `default-configs/devices/` control the boards and devices +``default-configs/devices/*.mak`` + The files under ``default-configs/devices/`` control the boards and devices that are built into each QEMU system emulation targets. They merely contain a list of config variable definitions such as:: @@ -299,18 +316,18 @@ into each emulator: CONFIG_XLNX_ZYNQMP_ARM=y CONFIG_XLNX_VERSAL=y -`*/Kconfig` - These files are processed together with `default-configs/devices/*.mak` and +``*/Kconfig`` + These files are processed together with ``default-configs/devices/*.mak`` and describe the dependencies between various features, subsystems and device models. They are described in :ref:`kconfig` -`default-configs/targets/*.mak` - These files mostly define symbols that appear in the `*-config-target.h` +``default-configs/targets/*.mak`` + These files mostly define symbols that appear in the ``*-config-target.h`` file for each emulator [#cfgtarget]_. However, the ``TARGET_ARCH`` - and ``TARGET_BASE_ARCH`` will also be used to select the `hw/` and - `target/` subdirectories that are compiled into each target. + and ``TARGET_BASE_ARCH`` will also be used to select the ``hw/`` and + ``target/`` subdirectories that are compiled into each target. -.. [#cfgtarget] This header is included by `qemu/osdep.h` when +.. [#cfgtarget] This header is included by ``qemu/osdep.h`` when compiling files from the target-specific sourcesets. These files rarely need changing unless you are adding a completely @@ -322,19 +339,19 @@ Support scripts --------------- Meson has a special convention for invoking Python scripts: if their -first line is `#! /usr/bin/env python3` and the file is *not* executable, +first line is ``#! /usr/bin/env python3`` and the file is *not* executable, find_program() arranges to invoke the script under the same Python interpreter that was used to invoke Meson. This is the most common and preferred way to invoke support scripts from Meson build files, because it automatically uses the value of configure's --python= option. -In case the script is not written in Python, use a `#! /usr/bin/env ...` +In case the script is not written in Python, use a ``#! /usr/bin/env ...`` line and make the script executable. Scripts written in Python, where it is desirable to make the script executable (for example for test scripts that developers may want to invoke from the command line, such as tests/qapi-schema/test-qapi.py), -should be invoked through the `python` variable in meson.build. For +should be invoked through the ``python`` variable in meson.build. For example:: test('QAPI schema regression tests', python, @@ -358,10 +375,10 @@ rules and wraps them so that e.g. submodules are built before QEMU. The resulting build system is largely non-recursive in nature, in contrast to common practices seen with automake. -Tests are also ran by the Makefile with the traditional `make check` -phony target, while benchmarks are run with `make bench`. Meson test -suites such as `unit` can be ran with `make check-unit` too. It is also -possible to run tests defined in meson.build with `meson test`. +Tests are also ran by the Makefile with the traditional ``make check`` +phony target, while benchmarks are run with ``make bench``. Meson test +suites such as ``unit`` can be ran with ``make check-unit`` too. It is also +possible to run tests defined in meson.build with ``meson test``. Important files for the build system ==================================== @@ -373,28 +390,28 @@ The following key files are statically defined in the source tree, with the rules needed to build QEMU. Their behaviour is influenced by a number of dynamically created files listed later. -`Makefile` +``Makefile`` The main entry point used when invoking make to build all the components of QEMU. The default 'all' target will naturally result in the build of every component. Makefile takes care of recursively building submodules directly via a non-recursive set of rules. -`*/meson.build` +``*/meson.build`` The meson.build file in the root directory is the main entry point for the Meson build system, and it coordinates the configuration and build of all executables. Build rules for various subdirectories are included in other meson.build files spread throughout the QEMU source tree. -`tests/Makefile.include` +``tests/Makefile.include`` Rules for external test harnesses. These include the TCG tests, - `qemu-iotests` and the Avocado-based acceptance tests. + ``qemu-iotests`` and the Avocado-based acceptance tests. -`tests/docker/Makefile.include` +``tests/docker/Makefile.include`` Rules for Docker tests. Like tests/Makefile, this file is included directly by the top level Makefile, anything defined in this file will influence the entire build system. -`tests/vm/Makefile.include` +``tests/vm/Makefile.include`` Rules for VM-based tests. Like tests/Makefile, this file is included directly by the top level Makefile, anything defined in this file will influence the entire build system. @@ -410,11 +427,11 @@ Makefile. Built by configure: -`config-host.mak` +``config-host.mak`` When configure has determined the characteristics of the build host it will write a long list of variables to config-host.mak file. This provides the various install directories, compiler / linker flags and a - variety of `CONFIG_*` variables related to optionally enabled features. + variety of ``CONFIG_*`` variables related to optionally enabled features. This is imported by the top level Makefile and meson.build in order to tailor the build output. @@ -429,29 +446,29 @@ Built by configure: Built by Meson: -`${TARGET-NAME}-config-devices.mak` +``${TARGET-NAME}-config-devices.mak`` TARGET-NAME is again the name of a system or userspace emulator. The config-devices.mak file is automatically generated by make using the scripts/make_device_config.sh program, feeding it the default-configs/$TARGET-NAME file as input. -`config-host.h`, `$TARGET-NAME/config-target.h`, `$TARGET-NAME/config-devices.h` +``config-host.h``, ``$TARGET-NAME/config-target.h``, ``$TARGET-NAME/config-devices.h`` These files are used by source code to determine what features are enabled. They are generated from the contents of the corresponding - `*.h` files using the scripts/create_config program. This extracts + ``*.h`` files using the scripts/create_config program. This extracts relevant variables and formats them as C preprocessor macros. -`build.ninja` +``build.ninja`` The build rules. Built by Makefile: -`Makefile.ninja` +``Makefile.ninja`` A Makefile include that bridges to ninja for the actual build. The Makefile is mostly a list of targets that Meson included in build.ninja. -`Makefile.mtest` +``Makefile.mtest`` The Makefile definitions that let "make check" run tests defined in meson.build. The rules are produced from Meson's JSON description of tests (obtained with "meson introspect --tests") through the script @@ -461,9 +478,9 @@ Built by Makefile: Useful make targets ------------------- -`help` +``help`` Print a help message for the most common build targets. -`print-VAR` +``print-VAR`` Print the value of the variable VAR. Useful for debugging the build system. diff --git a/docs/devel/ci.rst b/docs/devel/ci.rst new file mode 100644 index 0000000000..205572510c --- /dev/null +++ b/docs/devel/ci.rst @@ -0,0 +1,167 @@ +== +CI +== + +QEMU has configurations enabled for a number of different CI services. +The most up to date information about them and their status can be +found at:: + + https://wiki.qemu.org/Testing/CI + +Custom CI/CD variables +====================== + +QEMU CI pipelines can be tuned by setting some CI environment variables. + +Set variable globally in the user's CI namespace +------------------------------------------------ + +Variables can be set globally in the user's CI namespace setting. + +For further information about how to set these variables, please refer to:: + + https://docs.gitlab.com/ee/ci/variables/#add-a-cicd-variable-to-a-project + +Set variable manually when pushing a branch or tag to the user's repository +--------------------------------------------------------------------------- + +Variables can be set manually when pushing a branch or tag, using +git-push command line arguments. + +Example setting the QEMU_CI_EXAMPLE_VAR variable: + +.. code:: + + git push -o ci.variable="QEMU_CI_EXAMPLE_VAR=value" myrepo mybranch + +For further information about how to set these variables, please refer to:: + + https://docs.gitlab.com/ee/user/project/push_options.html#push-options-for-gitlab-cicd + +Here is a list of the most used variables: + +QEMU_CI_AVOCADO_TESTING +~~~~~~~~~~~~~~~~~~~~~~~ +By default, tests using the Avocado framework are not run automatically in +the pipelines (because multiple artifacts have to be downloaded, and if +these artifacts are not already cached, downloading them make the jobs +reach the timeout limit). Set this variable to have the tests using the +Avocado framework run automatically. + +Jobs on Custom Runners +====================== + +Besides the jobs run under the various CI systems listed before, there +are a number additional jobs that will run before an actual merge. +These use the same GitLab CI's service/framework already used for all +other GitLab based CI jobs, but rely on additional systems, not the +ones provided by GitLab as "shared runners". + +The architecture of GitLab's CI service allows different machines to +be set up with GitLab's "agent", called gitlab-runner, which will take +care of running jobs created by events such as a push to a branch. +Here, the combination of a machine, properly configured with GitLab's +gitlab-runner, is called a "custom runner". + +The GitLab CI jobs definition for the custom runners are located under:: + + .gitlab-ci.d/custom-runners.yml + +Custom runners entail custom machines. To see a list of the machines +currently deployed in the QEMU GitLab CI and their maintainers, please +refer to the QEMU `wiki `__. + +Machine Setup Howto +------------------- + +For all Linux based systems, the setup can be mostly automated by the +execution of two Ansible playbooks. Create an ``inventory`` file +under ``scripts/ci/setup``, such as this:: + + fully.qualified.domain + other.machine.hostname + +You may need to set some variables in the inventory file itself. One +very common need is to tell Ansible to use a Python 3 interpreter on +those hosts. This would look like:: + + fully.qualified.domain ansible_python_interpreter=/usr/bin/python3 + other.machine.hostname ansible_python_interpreter=/usr/bin/python3 + +Build environment +~~~~~~~~~~~~~~~~~ + +The ``scripts/ci/setup/build-environment.yml`` Ansible playbook will +set up machines with the environment needed to perform builds and run +QEMU tests. This playbook consists on the installation of various +required packages (and a general package update while at it). It +currently covers a number of different Linux distributions, but it can +be expanded to cover other systems. + +The minimum required version of Ansible successfully tested in this +playbook is 2.8.0 (a version check is embedded within the playbook +itself). To run the playbook, execute:: + + cd scripts/ci/setup + ansible-playbook -i inventory build-environment.yml + +Please note that most of the tasks in the playbook require superuser +privileges, such as those from the ``root`` account or those obtained +by ``sudo``. If necessary, please refer to ``ansible-playbook`` +options such as ``--become``, ``--become-method``, ``--become-user`` +and ``--ask-become-pass``. + +gitlab-runner setup and registration +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The gitlab-runner agent needs to be installed on each machine that +will run jobs. The association between a machine and a GitLab project +happens with a registration token. To find the registration token for +your repository/project, navigate on GitLab's web UI to: + + * Settings (the gears-like icon at the bottom of the left hand side + vertical toolbar), then + * CI/CD, then + * Runners, and click on the "Expand" button, then + * Under "Set up a specific Runner manually", look for the value under + "And this registration token:" + +Copy the ``scripts/ci/setup/vars.yml.template`` file to +``scripts/ci/setup/vars.yml``. Then, set the +``gitlab_runner_registration_token`` variable to the value obtained +earlier. + +To run the playbook, execute:: + + cd scripts/ci/setup + ansible-playbook -i inventory gitlab-runner.yml + +Following the registration, it's necessary to configure the runner tags, +and optionally other configurations on the GitLab UI. Navigate to: + + * Settings (the gears like icon), then + * CI/CD, then + * Runners, and click on the "Expand" button, then + * "Runners activated for this project", then + * Click on the "Edit" icon (next to the "Lock" Icon) + +Tags are very important as they are used to route specific jobs to +specific types of runners, so it's a good idea to double check that +the automatically created tags are consistent with the OS and +architecture. For instance, an Ubuntu 20.04 aarch64 system should +have tags set as:: + + ubuntu_20.04,aarch64 + +Because the job definition at ``.gitlab-ci.d/custom-runners.yml`` +would contain:: + + ubuntu-20.04-aarch64-all: + tags: + - ubuntu_20.04 + - aarch64 + +It's also recommended to: + + * increase the "Maximum job timeout" to something like ``2h`` + * give it a better Description diff --git a/docs/devel/control-flow-integrity.rst b/docs/devel/control-flow-integrity.rst index d89d70733d..e6b73a4fe1 100644 --- a/docs/devel/control-flow-integrity.rst +++ b/docs/devel/control-flow-integrity.rst @@ -39,7 +39,7 @@ later). Given the use of LTO, a version of AR that supports LLVM IR is required. The easies way of doing this is by selecting the AR provided by LLVM:: - AR=llvm-ar-9 CC=clang-9 CXX=lang++-9 /path/to/configure --enable-cfi + AR=llvm-ar-9 CC=clang-9 CXX=clang++-9 /path/to/configure --enable-cfi CFI is enabled on every binary produced. @@ -131,7 +131,7 @@ lld with version 11+. In other words, to compile with fuzzing and CFI, clang 11+ is required, and lld needs to be used as a linker:: - AR=llvm-ar-11 CC=clang-11 CXX=lang++-11 /path/to/configure --enable-cfi \ + AR=llvm-ar-11 CC=clang-11 CXX=clang++-11 /path/to/configure --enable-cfi \ -enable-fuzzing --extra-ldflags="-fuse-ld=lld" and then, compile the fuzzers as usual. diff --git a/docs/devel/decodetree.rst b/docs/devel/decodetree.rst index 74f66bf46e..49ea50c2a7 100644 --- a/docs/devel/decodetree.rst +++ b/docs/devel/decodetree.rst @@ -40,9 +40,6 @@ and returns an integral value extracted from there. A field with no ``unnamed_fields`` and no ``!function`` is in error. -FIXME: the fields of the structure into which this result will be stored -is restricted to ``int``. Which means that we cannot expand 64-bit items. - Field examples: +---------------------------+---------------------------------------------+ @@ -66,9 +63,14 @@ Argument Sets Syntax:: args_def := '&' identifier ( args_elt )+ ( !extern )? - args_elt := identifier + args_elt := identifier (':' identifier)? Each *args_elt* defines an argument within the argument set. +If the form of the *args_elt* contains a colon, the first +identifier is the argument name and the second identifier is +the argument type. If the colon is missing, the argument +type will be ``int``. + Each argument set will be rendered as a C structure "arg_$name" with each of the fields being one of the member arguments. @@ -86,6 +88,7 @@ Argument set examples:: ®3 ra rb rc &loadstore reg base offset + &longldst reg base offset:int64_t Formats diff --git a/docs/devel/ebpf_rss.rst b/docs/devel/ebpf_rss.rst new file mode 100644 index 0000000000..4a68682b31 --- /dev/null +++ b/docs/devel/ebpf_rss.rst @@ -0,0 +1,125 @@ +=========================== +eBPF RSS virtio-net support +=========================== + +RSS(Receive Side Scaling) is used to distribute network packets to guest virtqueues +by calculating packet hash. Usually every queue is processed then by a specific guest CPU core. + +For now there are 2 RSS implementations in qemu: +- 'in-qemu' RSS (functions if qemu receives network packets, i.e. vhost=off) +- eBPF RSS (can function with also with vhost=on) + +eBPF support (CONFIG_EBPF) is enabled by 'configure' script. +To enable eBPF RSS support use './configure --enable-bpf'. + +If steering BPF is not set for kernel's TUN module, the TUN uses automatic selection +of rx virtqueue based on lookup table built according to calculated symmetric hash +of transmitted packets. +If steering BPF is set for TUN the BPF code calculates the hash of packet header and +returns the virtqueue number to place the packet to. + +Simplified decision formula: + +.. code:: C + + queue_index = indirection_table[hash()%] + + +Not for all packets, the hash can/should be calculated. + +Note: currently, eBPF RSS does not support hash reporting. + +eBPF RSS turned on by different combinations of vhost-net, vitrio-net and tap configurations: + +- eBPF is used: + + tap,vhost=off & virtio-net-pci,rss=on,hash=off + +- eBPF is used: + + tap,vhost=on & virtio-net-pci,rss=on,hash=off + +- 'in-qemu' RSS is used: + + tap,vhost=off & virtio-net-pci,rss=on,hash=on + +- eBPF is used, hash population feature is not reported to the guest: + + tap,vhost=on & virtio-net-pci,rss=on,hash=on + +If CONFIG_EBPF is not set then only 'in-qemu' RSS is supported. +Also 'in-qemu' RSS, as a fallback, is used if the eBPF program failed to load or set to TUN. + +RSS eBPF program +---------------- + +RSS program located in ebpf/rss.bpf.skeleton.h generated by bpftool. +So the program is part of the qemu binary. +Initially, the eBPF program was compiled by clang and source code located at tools/ebpf/rss.bpf.c. +Prerequisites to recompile the eBPF program (regenerate ebpf/rss.bpf.skeleton.h): + + llvm, clang, kernel source tree, bpftool + Adjust Makefile.ebpf to reflect the location of the kernel source tree + + $ cd tools/ebpf + $ make -f Makefile.ebpf + +Current eBPF RSS implementation uses 'bounded loops' with 'backward jump instructions' which present in the last kernels. +Overall eBPF RSS works on kernels 5.8+. + +eBPF RSS implementation +----------------------- + +eBPF RSS loading functionality located in ebpf/ebpf_rss.c and ebpf/ebpf_rss.h. + +The ``struct EBPFRSSContext`` structure that holds 4 file descriptors: + +- ctx - pointer of the libbpf context. +- program_fd - file descriptor of the eBPF RSS program. +- map_configuration - file descriptor of the 'configuration' map. This map contains one element of 'struct EBPFRSSConfig'. This configuration determines eBPF program behavior. +- map_toeplitz_key - file descriptor of the 'Toeplitz key' map. One element of the 40byte key prepared for the hashing algorithm. +- map_indirections_table - 128 elements of queue indexes. + +``struct EBPFRSSConfig`` fields: + +- redirect - "boolean" value, should the hash be calculated, on false - ``default_queue`` would be used as the final decision. +- populate_hash - for now, not used. eBPF RSS doesn't support hash reporting. +- hash_types - binary mask of different hash types. See ``VIRTIO_NET_RSS_HASH_TYPE_*`` defines. If for packet hash should not be calculated - ``default_queue`` would be used. +- indirections_len - length of the indirections table, maximum 128. +- default_queue - the queue index that used for packet that shouldn't be hashed. For some packets, the hash can't be calculated(g.e ARP). + +Functions: + +- ``ebpf_rss_init()`` - sets ctx to NULL, which indicates that EBPFRSSContext is not loaded. +- ``ebpf_rss_load()`` - creates 3 maps and loads eBPF program from the rss.bpf.skeleton.h. Returns 'true' on success. After that, program_fd can be used to set steering for TAP. +- ``ebpf_rss_set_all()`` - sets values for eBPF maps. ``indirections_table`` length is in EBPFRSSConfig. ``toeplitz_key`` is VIRTIO_NET_RSS_MAX_KEY_SIZE aka 40 bytes array. +- ``ebpf_rss_unload()`` - close all file descriptors and set ctx to NULL. + +Simplified eBPF RSS workflow: + +.. code:: C + + struct EBPFRSSConfig config; + config.redirect = 1; + config.hash_types = VIRTIO_NET_RSS_HASH_TYPE_UDPv4 | VIRTIO_NET_RSS_HASH_TYPE_TCPv4; + config.indirections_len = VIRTIO_NET_RSS_MAX_TABLE_LEN; + config.default_queue = 0; + + uint16_t table[VIRTIO_NET_RSS_MAX_TABLE_LEN] = {...}; + uint8_t key[VIRTIO_NET_RSS_MAX_KEY_SIZE] = {...}; + + struct EBPFRSSContext ctx; + ebpf_rss_init(&ctx); + ebpf_rss_load(&ctx); + ebpf_rss_set_all(&ctx, &config, table, key); + if (net_client->info->set_steering_ebpf != NULL) { + net_client->info->set_steering_ebpf(net_client, ctx->program_fd); + } + ... + ebpf_unload(&ctx); + + +NetClientState SetSteeringEBPF() +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +For now, ``set_steering_ebpf()`` method supported by Linux TAP NetClientState. The method requires an eBPF program file descriptor as an argument. diff --git a/docs/devel/index.rst b/docs/devel/index.rst index 6cf7e2d233..5522db7241 100644 --- a/docs/devel/index.rst +++ b/docs/devel/index.rst @@ -1,15 +1,10 @@ -.. This is the top level page for the 'devel' manual. - - Developer Information ===================== -This manual documents various parts of the internals of QEMU. +This section of the manual documents various parts of the internals of QEMU. You only need to read it if you are interested in reading or modifying QEMU's source code. -Contents: - .. toctree:: :maxdepth: 2 :includehidden: @@ -27,6 +22,7 @@ Contents: migration atomics stable-process + ci qtest decodetree secure-coding-practices @@ -36,9 +32,15 @@ Contents: multi-thread-tcg tcg-plugins bitops + ui reset s390-dasd-ipl clocks qom + modules block-coroutine-wrapper multi-process + ebpf_rss + vfio-migration + qapi-code-gen + writing-qmp-commands diff --git a/docs/devel/kconfig.rst b/docs/devel/kconfig.rst index cb2d7ffac0..a1cdbec751 100644 --- a/docs/devel/kconfig.rst +++ b/docs/devel/kconfig.rst @@ -303,5 +303,5 @@ variable:: host_kconfig = \ ('CONFIG_TPM' in config_host ? ['CONFIG_TPM=y'] : []) + \ ('CONFIG_SPICE' in config_host ? ['CONFIG_SPICE=y'] : []) + \ - ('CONFIG_IVSHMEM' in config_host ? ['CONFIG_IVSHMEM=y'] : []) + \ + (have_ivshmem ? ['CONFIG_IVSHMEM=y'] : []) + \ ... diff --git a/docs/devel/lockcnt.txt b/docs/devel/lockcnt.txt index 2d85462fe3..a3fb3bc5d8 100644 --- a/docs/devel/lockcnt.txt +++ b/docs/devel/lockcnt.txt @@ -145,7 +145,7 @@ can also be more efficient in two ways: - on some platforms, one can implement QemuLockCnt to hold the lock and the mutex in a single word, making the fast path no more expensive than simply managing a counter using atomic operations (see - docs/devel/atomics.txt). This can be very helpful if concurrent access to + docs/devel/atomics.rst). This can be very helpful if concurrent access to the data structure is expected to be rare. diff --git a/docs/devel/migration.rst b/docs/devel/migration.rst index 19c3d4f3ea..2401253482 100644 --- a/docs/devel/migration.rst +++ b/docs/devel/migration.rst @@ -53,7 +53,7 @@ savevm/loadvm functionality. Debugging ========= -The migration stream can be analyzed thanks to `scripts/analyze-migration.py`. +The migration stream can be analyzed thanks to ``scripts/analyze-migration.py``. Example usage: @@ -75,8 +75,8 @@ Common infrastructure ===================== The files, sockets or fd's that carry the migration stream are abstracted by -the ``QEMUFile`` type (see `migration/qemu-file.h`). In most cases this -is connected to a subtype of ``QIOChannel`` (see `io/`). +the ``QEMUFile`` type (see ``migration/qemu-file.h``). In most cases this +is connected to a subtype of ``QIOChannel`` (see ``io/``). Saving the state of one device @@ -166,14 +166,14 @@ An example (from hw/input/pckbd.c) }; We are declaring the state with name "pckbd". -The `version_id` is 3, and the fields are 4 uint8_t in a KBDState structure. +The ``version_id`` is 3, and the fields are 4 uint8_t in a KBDState structure. We registered this with: .. code:: c vmstate_register(NULL, 0, &vmstate_kbd, s); -For devices that are `qdev` based, we can register the device in the class +For devices that are ``qdev`` based, we can register the device in the class init function: .. code:: c @@ -210,9 +210,9 @@ another to load the state back. SaveVMHandlers *ops, void *opaque); -Two functions in the ``ops`` structure are the `save_state` -and `load_state` functions. Notice that `load_state` receives a version_id -parameter to know what state format is receiving. `save_state` doesn't +Two functions in the ``ops`` structure are the ``save_state`` +and ``load_state`` functions. Notice that ``load_state`` receives a version_id +parameter to know what state format is receiving. ``save_state`` doesn't have a version_id parameter because it always uses the latest version. Note that because the VMState macros still save the data in a raw @@ -385,18 +385,18 @@ migration of a device, and using them breaks backward-migration compatibility; in general most changes can be made by adding Subsections (see above) or _TEST macros (see above) which won't break compatibility. -Each version is associated with a series of fields saved. The `save_state` always saves -the state as the newer version. But `load_state` sometimes is able to +Each version is associated with a series of fields saved. The ``save_state`` always saves +the state as the newer version. But ``load_state`` sometimes is able to load state from an older version. You can see that there are several version fields: -- `version_id`: the maximum version_id supported by VMState for that device. -- `minimum_version_id`: the minimum version_id that VMState is able to understand +- ``version_id``: the maximum version_id supported by VMState for that device. +- ``minimum_version_id``: the minimum version_id that VMState is able to understand for that device. -- `minimum_version_id_old`: For devices that were not able to port to vmstate, we can +- ``minimum_version_id_old``: For devices that were not able to port to vmstate, we can assign a function that knows how to read this old state. This field is - ignored if there is no `load_state_old` handler. + ignored if there is no ``load_state_old`` handler. VMState is able to read versions from minimum_version_id to version_id. And the function ``load_state_old()`` (if present) is able to @@ -454,7 +454,7 @@ data and then transferred to the main structure. If you use memory API functions that update memory layout outside initialization (i.e., in response to a guest action), this is a strong -indication that you need to call these functions in a `post_load` callback. +indication that you need to call these functions in a ``post_load`` callback. Examples of such memory API functions are: - memory_region_add_subregion() @@ -823,12 +823,12 @@ Postcopy migration with shared memory needs explicit support from the other processes that share memory and from QEMU. There are restrictions on the type of memory that userfault can support shared. -The Linux kernel userfault support works on `/dev/shm` memory and on `hugetlbfs` -(although the kernel doesn't provide an equivalent to `madvise(MADV_DONTNEED)` +The Linux kernel userfault support works on ``/dev/shm`` memory and on ``hugetlbfs`` +(although the kernel doesn't provide an equivalent to ``madvise(MADV_DONTNEED)`` for hugetlbfs which may be a problem in some configurations). The vhost-user code in QEMU supports clients that have Postcopy support, -and the `vhost-user-bridge` (in `tests/`) and the DPDK package have changes +and the ``vhost-user-bridge`` (in ``tests/``) and the DPDK package have changes to support postcopy. The client needs to open a userfaultfd and register the areas diff --git a/docs/devel/modules.rst b/docs/devel/modules.rst new file mode 100644 index 0000000000..066f347b89 --- /dev/null +++ b/docs/devel/modules.rst @@ -0,0 +1,5 @@ +============ +Qemu modules +============ + +.. kernel-doc:: include/qemu/module.h diff --git a/docs/devel/multi-thread-tcg.rst b/docs/devel/multi-thread-tcg.rst index 92a9eba13c..5b446ee08b 100644 --- a/docs/devel/multi-thread-tcg.rst +++ b/docs/devel/multi-thread-tcg.rst @@ -4,8 +4,9 @@ This work is licensed under the terms of the GNU GPL, version 2 or later. See the COPYING file in the top-level directory. -Introduction -============ +================== +Multi-threaded TCG +================== This document outlines the design for multi-threaded TCG (a.k.a MTTCG) system-mode emulation. user-mode emulation has always mirrored the diff --git a/docs/devel/qapi-code-gen.txt b/docs/devel/qapi-code-gen.rst similarity index 75% rename from docs/devel/qapi-code-gen.txt rename to docs/devel/qapi-code-gen.rst index c1cb6f987d..26c62b0e7b 100644 --- a/docs/devel/qapi-code-gen.txt +++ b/docs/devel/qapi-code-gen.rst @@ -1,12 +1,17 @@ -= How to use the QAPI code generator = +================================== +How to use the QAPI code generator +================================== -Copyright IBM Corp. 2011 -Copyright (C) 2012-2016 Red Hat, Inc. +.. + Copyright IBM Corp. 2011 + Copyright (C) 2012-2016 Red Hat, Inc. -This work is licensed under the terms of the GNU GPL, version 2 or -later. See the COPYING file in the top-level directory. + This work is licensed under the terms of the GNU GPL, version 2 or + later. See the COPYING file in the top-level directory. -== Introduction == + +Introduction +============ QAPI is a native C API within QEMU which provides management-level functionality to internal and external users. For external @@ -23,7 +28,8 @@ Protocol and to C. It additionally provides guidance on maintaining Client JSON Protocol compatibility. -== The QAPI schema language == +The QAPI schema language +======================== The QAPI schema defines the Client JSON Protocol's commands and events, as well as types used by them. Forward references are @@ -34,52 +40,53 @@ by any commands or events, for the side effect of generated C code used internally. There are several kinds of types: simple types (a number of built-in -types, such as 'int' and 'str'; as well as enumerations), arrays, +types, such as ``int`` and ``str``; as well as enumerations), arrays, complex types (structs and two flavors of unions), and alternate types (a choice between other types). -=== Schema syntax === +Schema syntax +------------- -Syntax is loosely based on JSON (http://www.ietf.org/rfc/rfc8259.txt). +Syntax is loosely based on `JSON `_. Differences: -* Comments: start with a hash character (#) that is not part of a +* Comments: start with a hash character (``#``) that is not part of a string, and extend to the end of the line. -* Strings are enclosed in 'single quotes', not "double quotes". +* Strings are enclosed in ``'single quotes'``, not ``"double quotes"``. * Strings are restricted to printable ASCII, and escape sequences to - just '\\'. + just ``\\``. -* Numbers and null are not supported. +* Numbers and ``null`` are not supported. A second layer of syntax defines the sequences of JSON texts that are a correctly structured QAPI schema. We provide a grammar for this syntax in an EBNF-like notation: -* Production rules look like non-terminal = expression -* Concatenation: expression A B matches expression A, then B -* Alternation: expression A | B matches expression A or B -* Repetition: expression A... matches zero or more occurrences of - expression A -* Repetition: expression A, ... matches zero or more occurrences of - expression A separated by , -* Grouping: expression ( A ) matches expression A -* JSON's structural characters are terminals: { } [ ] : , -* JSON's literal names are terminals: false true -* String literals enclosed in 'single quotes' are terminal, and match - this JSON string, with a leading '*' stripped off -* When JSON object member's name starts with '*', the member is +* Production rules look like ``non-terminal = expression`` +* Concatenation: expression ``A B`` matches expression ``A``, then ``B`` +* Alternation: expression ``A | B`` matches expression ``A`` or ``B`` +* Repetition: expression ``A...`` matches zero or more occurrences of + expression ``A`` +* Repetition: expression ``A, ...`` matches zero or more occurrences of + expression ``A`` separated by ``,`` +* Grouping: expression ``( A )`` matches expression ``A`` +* JSON's structural characters are terminals: ``{ } [ ] : ,`` +* JSON's literal names are terminals: ``false true`` +* String literals enclosed in ``'single quotes'`` are terminal, and match + this JSON string, with a leading ``*`` stripped off +* When JSON object member's name starts with ``*``, the member is optional. -* The symbol STRING is a terminal, and matches any JSON string -* The symbol BOOL is a terminal, and matches JSON false or true -* ALL-CAPS words other than STRING are non-terminals +* The symbol ``STRING`` is a terminal, and matches any JSON string +* The symbol ``BOOL`` is a terminal, and matches JSON ``false`` or ``true`` +* ALL-CAPS words other than ``STRING`` are non-terminals The order of members within JSON objects does not matter unless explicitly noted. -A QAPI schema consists of a series of top-level expressions: +A QAPI schema consists of a series of top-level expressions:: SCHEMA = TOP-LEVEL-EXPR... @@ -87,11 +94,11 @@ The top-level expressions are all JSON objects. Code and documentation is generated in schema definition order. Code order should not matter. -A top-level expressions is either a directive or a definition: +A top-level expressions is either a directive or a definition:: TOP-LEVEL-EXPR = DIRECTIVE | DEFINITION -There are two kinds of directives and six kinds of definitions: +There are two kinds of directives and six kinds of definitions:: DIRECTIVE = INCLUDE | PRAGMA DEFINITION = ENUM | STRUCT | UNION | ALTERNATE | COMMAND | EVENT @@ -99,37 +106,43 @@ There are two kinds of directives and six kinds of definitions: These are discussed in detail below. -=== Built-in Types === +Built-in Types +-------------- The following types are predefined, and map to C as follows: - Schema C JSON - str char * any JSON string, UTF-8 - number double any JSON number - int int64_t a JSON number without fractional part - that fits into the C integer type - int8 int8_t likewise - int16 int16_t likewise - int32 int32_t likewise - int64 int64_t likewise - uint8 uint8_t likewise - uint16 uint16_t likewise - uint32 uint32_t likewise - uint64 uint64_t likewise - size uint64_t like uint64_t, except StringInputVisitor - accepts size suffixes - bool bool JSON true or false - null QNull * JSON null - any QObject * any JSON value - QType QType JSON string matching enum QType values + ============= ============== ============================================ + Schema C JSON + ============= ============== ============================================ + ``str`` ``char *`` any JSON string, UTF-8 + ``number`` ``double`` any JSON number + ``int`` ``int64_t`` a JSON number without fractional part + that fits into the C integer type + ``int8`` ``int8_t`` likewise + ``int16`` ``int16_t`` likewise + ``int32`` ``int32_t`` likewise + ``int64`` ``int64_t`` likewise + ``uint8`` ``uint8_t`` likewise + ``uint16`` ``uint16_t`` likewise + ``uint32`` ``uint32_t`` likewise + ``uint64`` ``uint64_t`` likewise + ``size`` ``uint64_t`` like ``uint64_t``, except + ``StringInputVisitor`` accepts size suffixes + ``bool`` ``bool`` JSON ``true`` or ``false`` + ``null`` ``QNull *`` JSON ``null`` + ``any`` ``QObject *`` any JSON value + ``QType`` ``QType`` JSON string matching enum ``QType`` values + ============= ============== ============================================ -=== Include directives === +Include directives +------------------ + +Syntax:: -Syntax: INCLUDE = { 'include': STRING } -The QAPI schema definitions can be modularized using the 'include' directive: +The QAPI schema definitions can be modularized using the 'include' directive:: { 'include': 'path/to/file.json' } @@ -143,10 +156,13 @@ from making a forward reference to a type that is only introduced by an outer file. The parser may be made stricter in the future to prevent incomplete include files. +.. _pragma: -=== Pragma directives === +Pragma directives +----------------- + +Syntax:: -Syntax: PRAGMA = { 'pragma': { '*doc-required': BOOL, '*command-name-exceptions': [ STRING, ... ], @@ -162,19 +178,22 @@ Pragma 'doc-required' takes a boolean value. If true, documentation is required. Default is false. Pragma 'command-name-exceptions' takes a list of commands whose names -may contain '_' instead of '-'. Default is none. +may contain ``"_"`` instead of ``"-"``. Default is none. Pragma 'command-returns-exceptions' takes a list of commands that may violate the rules on permitted return types. Default is none. Pragma 'member-name-exceptions' takes a list of types whose member -names may contain uppercase letters, and '_' instead of '-'. Default -is none. +names may contain uppercase letters, and ``"_"`` instead of ``"-"``. +Default is none. +.. _ENUM-VALUE: -=== Enumeration types === +Enumeration types +----------------- + +Syntax:: -Syntax: ENUM = { 'enum': STRING, 'data': [ ENUM-VALUE, ... ], '*prefix': STRING, @@ -186,10 +205,10 @@ Syntax: Member 'enum' names the enum type. Each member of the 'data' array defines a value of the enumeration -type. The form STRING is shorthand for { 'name': STRING }. The +type. The form STRING is shorthand for :code:`{ 'name': STRING }`. The 'name' values must be be distinct. -Example: +Example:: { 'enum': 'MyEnum', 'data': [ 'value1', 'value2', 'value3' ] } @@ -211,28 +230,34 @@ additional enumeration constant PREFIX__MAX with value N. Do not use string or an integer type when an enumeration type can do the job satisfactorily. -The optional 'if' member specifies a conditional. See "Configuring -the schema" below for more on this. +The optional 'if' member specifies a conditional. See `Configuring the +schema`_ below for more on this. -The optional 'features' member specifies features. See "Features" +The optional 'features' member specifies features. See Features_ below for more on this. -=== Type references and array types === +.. _TYPE-REF: + +Type references and array types +------------------------------- + +Syntax:: -Syntax: TYPE-REF = STRING | ARRAY-TYPE ARRAY-TYPE = [ STRING ] A string denotes the type named by the string. A one-element array containing a string denotes an array of the type -named by the string. Example: ['int'] denotes an array of 'int'. +named by the string. Example: ``['int']`` denotes an array of ``int``. -=== Struct types === +Struct types +------------ + +Syntax:: -Syntax: STRUCT = { 'struct': STRING, 'data': MEMBERS, '*base': STRING, @@ -248,13 +273,15 @@ Member 'struct' names the struct type. Each MEMBER of the 'data' object defines a member of the struct type. -The MEMBER's STRING name consists of an optional '*' prefix and the -struct member name. If '*' is present, the member is optional. +.. _MEMBERS: + +The MEMBER's STRING name consists of an optional ``*`` prefix and the +struct member name. If ``*`` is present, the member is optional. The MEMBER's value defines its properties, in particular its type. -The form TYPE-REF is shorthand for { 'type': TYPE-REF }. +The form TYPE-REF_ is shorthand for :code:`{ 'type': TYPE-REF }`. -Example: +Example:: { 'struct': 'MyType', 'data': { 'member1': 'str', 'member2': ['int'], '*member3': 'str' } } @@ -265,7 +292,7 @@ The C struct's members are generated in QAPI schema order. The optional 'base' member names a struct type whose members are to be included in this type. They go first in the C struct. -Example: +Example:: { 'struct': 'BlockdevOptionsGenericFormat', 'data': { 'file': 'str' } } @@ -274,21 +301,23 @@ Example: 'data': { '*backing': 'str' } } An example BlockdevOptionsGenericCOWFormat object on the wire could use -both members like this: +both members like this:: { "file": "/some/place/my-image", "backing": "/some/place/my-backing-file" } -The optional 'if' member specifies a conditional. See "Configuring -the schema" below for more on this. +The optional 'if' member specifies a conditional. See `Configuring +the schema`_ below for more on this. -The optional 'features' member specifies features. See "Features" +The optional 'features' member specifies features. See Features_ below for more on this. -=== Union types === +Union types +----------- + +Syntax:: -Syntax: UNION = { 'union': STRING, 'data': BRANCHES, '*if': COND, @@ -314,10 +343,10 @@ union must have at least one branch. The BRANCH's STRING name is the branch name. The BRANCH's value defines the branch's properties, in particular its -type. The form TYPE-REF is shorthand for { 'type': TYPE-REF }. +type. The form TYPE-REF_ is shorthand for :code:`{ 'type': TYPE-REF }`. A simple union type defines a mapping from automatic discriminator -values to data types like in this example: +values to data types like in this example:: { 'struct': 'BlockdevOptionsFile', 'data': { 'filename': 'str' } } { 'struct': 'BlockdevOptionsQcow2', @@ -330,7 +359,7 @@ values to data types like in this example: In the Client JSON Protocol, a simple union is represented by an object that contains the 'type' member as a discriminator, and a 'data' member that is of the specified data type corresponding to the -discriminator value, as in these examples: +discriminator value, as in these examples:: { "type": "file", "data": { "filename": "/some/place/my-image" } } { "type": "qcow2", "data": { "backing": "/some/place/my-image", @@ -345,12 +374,12 @@ Flat unions permit arbitrary common members that occur in all variants of the union, not just a discriminator. Their discriminators need not be named 'type'. They also avoid nesting on the wire. -The 'base' member defines the common members. If it is a MEMBERS +The 'base' member defines the common members. If it is a MEMBERS_ object, it defines common members just like a struct type's 'data' member defines struct type members. If it is a STRING, it names a struct type whose members are the common members. -All flat union branches must be of struct type. +All flat union branches must be `Struct types`_. In the Client JSON Protocol, a flat union is represented by an object with the common members (from the base type) and the selected branch's @@ -361,7 +390,7 @@ struct. The following example enhances the above simple union example by adding an optional common member 'read-only', renaming the discriminator to something more applicable than the simple union's -default of 'type', and reducing the number of {} required on the wire: +default of 'type', and reducing the number of ``{}`` required on the wire:: { 'enum': 'BlockdevDriver', 'data': [ 'file', 'qcow2' ] } { 'union': 'BlockdevOptions', @@ -370,7 +399,7 @@ default of 'type', and reducing the number of {} required on the wire: 'data': { 'file': 'BlockdevOptionsFile', 'qcow2': 'BlockdevOptionsQcow2' } } -Resulting in these JSON objects: +Resulting in these JSON objects:: { "driver": "file", "read-only": true, "filename": "/some/place/my-image" } @@ -390,11 +419,11 @@ struct. A simple union can always be re-written as a flat union where the base class has a single member named 'type', and where each branch of the -union has a struct with a single member named 'data'. That is, +union has a struct with a single member named 'data'. That is, :: { 'union': 'Simple', 'data': { 'one': 'str', 'two': 'int' } } -is identical on the wire to: +is identical on the wire to:: { 'enum': 'Enum', 'data': ['one', 'two'] } { 'struct': 'Branch1', 'data': { 'data': 'str' } } @@ -402,16 +431,18 @@ is identical on the wire to: { 'union': 'Flat', 'base': { 'type': 'Enum' }, 'discriminator': 'type', 'data': { 'one': 'Branch1', 'two': 'Branch2' } } -The optional 'if' member specifies a conditional. See "Configuring -the schema" below for more on this. +The optional 'if' member specifies a conditional. See `Configuring +the schema`_ below for more on this. -The optional 'features' member specifies features. See "Features" +The optional 'features' member specifies features. See Features_ below for more on this. -=== Alternate types === +Alternate types +--------------- + +Syntax:: -Syntax: ALTERNATE = { 'alternate': STRING, 'data': ALTERNATIVES, '*if': COND, @@ -428,9 +459,9 @@ alternate. An alternate must have at least one branch. The ALTERNATIVE's STRING name is the branch name. The ALTERNATIVE's value defines the branch's properties, in particular -its type. The form STRING is shorthand for { 'type': STRING }. +its type. The form STRING is shorthand for :code:`{ 'type': STRING }`. -Example: +Example:: { 'alternate': 'BlockdevRef', 'data': { 'definition': 'BlockdevOptions', @@ -449,23 +480,25 @@ as the 'null' built-in, it accepts JSON null; and if it is typed as a complex type (struct or union), it accepts a JSON object. The example alternate declaration above allows using both of the -following example objects: +following example objects:: { "file": "my_existing_block_device_id" } { "file": { "driver": "file", "read-only": false, "filename": "/tmp/mydisk.qcow2" } } -The optional 'if' member specifies a conditional. See "Configuring -the schema" below for more on this. +The optional 'if' member specifies a conditional. See `Configuring +the schema`_ below for more on this. -The optional 'features' member specifies features. See "Features" +The optional 'features' member specifies features. See Features_ below for more on this. -=== Commands === +Commands +-------- + +Syntax:: -Syntax: COMMAND = { 'command': STRING, ( '*data': ( MEMBERS | STRING ), @@ -484,14 +517,14 @@ Syntax: Member 'command' names the command. -Member 'data' defines the arguments. It defaults to an empty MEMBERS +Member 'data' defines the arguments. It defaults to an empty MEMBERS_ object. -If 'data' is a MEMBERS object, then MEMBERS defines arguments just +If 'data' is a MEMBERS_ object, then MEMBERS defines arguments just like a struct type's 'data' defines struct type members. If 'data' is a STRING, then STRING names a complex type whose members -are the arguments. A union type requires 'boxed': true. +are the arguments. A union type requires ``'boxed': true``. Member 'returns' defines the command's return type. It defaults to an empty struct type. It must normally be a complex type or an array of @@ -508,7 +541,7 @@ member is the command name. The value of the "arguments" member then has to conform to the arguments, and the value of the success response's "return" member will conform to the return type. -Some example commands: +Some example commands:: { 'command': 'my-first-command', 'data': { 'arg1': 'str', '*arg2': 'str' } } @@ -516,7 +549,7 @@ Some example commands: { 'command': 'my-second-command', 'returns': [ 'MyType' ] } -which would validate this Client JSON Protocol transaction: +which would validate this Client JSON Protocol transaction:: => { "execute": "my-first-command", "arguments": { "arg1": "hello" } } @@ -526,12 +559,12 @@ which would validate this Client JSON Protocol transaction: The generator emits a prototype for the C function implementing the command. The function itself needs to be written by hand. See -section "Code generated for commands" for examples. +section `Code generated for commands`_ for examples. The function returns the return type. When member 'boxed' is absent, it takes the command arguments as arguments one by one, in QAPI schema order. Else it takes them wrapped in the C struct generated for the -complex argument type. It takes an additional Error ** argument in +complex argument type. It takes an additional ``Error **`` argument in either case. The generator also emits a marshalling function that extracts @@ -543,7 +576,7 @@ In rare cases, QAPI cannot express a type-safe representation of a corresponding Client JSON Protocol command. You then have to suppress generation of a marshalling function by including a member 'gen' with boolean value false, and instead write your own function. For -example: +example:: { 'command': 'netdev_add', 'data': {'type': 'str', 'id': 'str'}, @@ -561,7 +594,7 @@ the command definition includes the optional member 'success-response' with boolean value false. So far, only QGA makes use of this member. Member 'allow-oob' declares whether the command supports out-of-band -(OOB) execution. It defaults to false. For example: +(OOB) execution. It defaults to false. For example:: { 'command': 'migrate_recover', 'data': { 'uri': 'str' }, 'allow-oob': true } @@ -594,7 +627,7 @@ other "slow" lock. When in doubt, do not implement OOB execution support. Member 'allow-preconfig' declares whether the command is available -before the machine is built. It defaults to false. For example: +before the machine is built. It defaults to false. For example:: { 'enum': 'QMPCapability', 'data': [ 'oob' ] } @@ -614,11 +647,11 @@ blocking the guest and other background operations. Coroutine safety can be hard to prove, similar to thread safety. Common pitfalls are: -- The global mutex isn't held across qemu_coroutine_yield(), so +- The global mutex isn't held across ``qemu_coroutine_yield()``, so operations that used to assume that they execute atomically may have to be more careful to protect against changes in the global state. -- Nested event loops (AIO_WAIT_WHILE() etc.) are problematic in +- Nested event loops (``AIO_WAIT_WHILE()`` etc.) are problematic in coroutine context and can easily lead to deadlocks. They should be replaced by yielding and reentering the coroutine when the condition becomes false. @@ -626,23 +659,25 @@ pitfalls are: Since the command handler may assume coroutine context, any callers other than the QMP dispatcher must also call it in coroutine context. In particular, HMP commands calling such a QMP command handler must be -marked .coroutine = true in hmp-commands.hx. +marked ``.coroutine = true`` in hmp-commands.hx. -It is an error to specify both 'coroutine': true and 'allow-oob': true +It is an error to specify both ``'coroutine': true`` and ``'allow-oob': true`` for a command. We don't currently have a use case for both together and without a use case, it's not entirely clear what the semantics should be. -The optional 'if' member specifies a conditional. See "Configuring -the schema" below for more on this. +The optional 'if' member specifies a conditional. See `Configuring +the schema`_ below for more on this. -The optional 'features' member specifies features. See "Features" +The optional 'features' member specifies features. See Features_ below for more on this. -=== Events === +Events +------ + +Syntax:: -Syntax: EVENT = { 'event': STRING, ( '*data': ( MEMBERS | STRING ), @@ -663,34 +698,38 @@ If 'data' is a MEMBERS object, then MEMBERS defines event-specific data just like a struct type's 'data' defines struct type members. If 'data' is a STRING, then STRING names a complex type whose members -are the event-specific data. A union type requires 'boxed': true. +are the event-specific data. A union type requires ``'boxed': true``. -An example event is: +An example event is:: -{ 'event': 'EVENT_C', - 'data': { '*a': 'int', 'b': 'str' } } + { 'event': 'EVENT_C', + 'data': { '*a': 'int', 'b': 'str' } } -Resulting in this JSON object: +Resulting in this JSON object:: -{ "event": "EVENT_C", - "data": { "b": "test string" }, - "timestamp": { "seconds": 1267020223, "microseconds": 435656 } } + { "event": "EVENT_C", + "data": { "b": "test string" }, + "timestamp": { "seconds": 1267020223, "microseconds": 435656 } } The generator emits a function to send the event. When member 'boxed' is absent, it takes event-specific data one by one, in QAPI schema order. Else it takes them wrapped in the C struct generated for the -complex type. See section "Code generated for events" for examples. +complex type. See section `Code generated for events`_ for examples. -The optional 'if' member specifies a conditional. See "Configuring -the schema" below for more on this. +The optional 'if' member specifies a conditional. See `Configuring +the schema`_ below for more on this. -The optional 'features' member specifies features. See "Features" +The optional 'features' member specifies features. See Features_ below for more on this. -=== Features === +.. _FEATURE: + +Features +-------- + +Syntax:: -Syntax: FEATURES = [ FEATURE, ... ] FEATURE = STRING | { 'name': STRING, '*if': COND } @@ -701,48 +740,50 @@ that previously resulted in an error). QMP clients may still need to know whether the extension is available. For this purpose, a list of features can be specified for a command or -struct type. Each list member can either be { 'name': STRING, '*if': -COND }, or STRING, which is shorthand for { 'name': STRING }. +struct type. Each list member can either be ``{ 'name': STRING, '*if': +COND }``, or STRING, which is shorthand for ``{ 'name': STRING }``. -The optional 'if' member specifies a conditional. See "Configuring -the schema" below for more on this. +The optional 'if' member specifies a conditional. See `Configuring +the schema`_ below for more on this. -Example: +Example:: -{ 'struct': 'TestType', - 'data': { 'number': 'int' }, - 'features': [ 'allow-negative-numbers' ] } + { 'struct': 'TestType', + 'data': { 'number': 'int' }, + 'features': [ 'allow-negative-numbers' ] } The feature strings are exposed to clients in introspection, as -explained in section "Client JSON Protocol introspection". +explained in section `Client JSON Protocol introspection`_. Intended use is to have each feature string signal that this build of QEMU shows a certain behaviour. -==== Special features ==== +Special features +~~~~~~~~~~~~~~~~ Feature "deprecated" marks a command, event, or struct member as deprecated. It is not supported elsewhere so far. -=== Naming rules and reserved names === +Naming rules and reserved names +------------------------------- All names must begin with a letter, and contain only ASCII letters, digits, hyphen, and underscore. There are two exceptions: enum values may start with a digit, and names that are downstream extensions (see -section Downstream extensions) start with underscore. +section `Downstream extensions`_) start with underscore. -Names beginning with 'q_' are reserved for the generator, which uses +Names beginning with ``q_`` are reserved for the generator, which uses them for munging QMP names that resemble C keywords or other -problematic strings. For example, a member named "default" in qapi -becomes "q_default" in the generated C code. +problematic strings. For example, a member named ``default`` in qapi +becomes ``q_default`` in the generated C code. Types, commands, and events share a common namespace. Therefore, generally speaking, type definitions should always use CamelCase for user-defined type names, while built-in types are lowercase. -Type names ending with 'Kind' or 'List' are reserved for the +Type names ending with ``Kind`` or ``List`` are reserved for the generator, which uses them for implicit union enums and array types, respectively. @@ -753,19 +794,21 @@ consistency is preferred over blindly avoiding underscore. Event names should be ALL_CAPS with words separated by underscore. -Member name 'u' and names starting with 'has-' or 'has_' are reserved +Member name ``u`` and names starting with ``has-`` or ``has_`` are reserved for the generator, which uses them for unions and for tracking optional members. Any name (command, event, type, member, or enum value) beginning with -"x-" is marked experimental, and may be withdrawn or changed +``x-`` is marked experimental, and may be withdrawn or changed incompatibly in a future release. -Pragmas 'command-name-exceptions' and 'member-name-exceptions' let you -violate naming rules. Use for new code is strongly discouraged. +Pragmas ``command-name-exceptions`` and ``member-name-exceptions`` let +you violate naming rules. Use for new code is strongly discouraged. See +`Pragma directives`_ for details. -=== Downstream extensions === +Downstream extensions +--------------------- QAPI schema names that are externally visible, say in the Client JSON Protocol, need to be managed with care. Names starting with a @@ -774,12 +817,14 @@ who controls the valid, reverse fully qualified domain name RFQDN. RFQDN may only contain ASCII letters, digits, hyphen and period. Example: Red Hat, Inc. controls redhat.com, and may therefore add a -downstream command __com.redhat_drive-mirror. +downstream command ``__com.redhat_drive-mirror``. -=== Configuring the schema === +Configuring the schema +---------------------- + +Syntax:: -Syntax: COND = STRING | [ STRING, ... ] @@ -788,12 +833,12 @@ string or a list of strings. A string is shorthand for a list containing just that string. The code generated for the definition will then be guarded by #if STRING for each STRING in the COND list. -Example: a conditional struct +Example: a conditional struct :: { 'struct': 'IfStruct', 'data': { 'foo': 'int' }, 'if': ['defined(CONFIG_FOO)', 'defined(HAVE_BAR)'] } -gets its generated code guarded like this: +gets its generated code guarded like this:: #if defined(CONFIG_FOO) #if defined(HAVE_BAR) @@ -806,33 +851,33 @@ event-specific data can also be made conditional. This requires the longhand form of MEMBER. Example: a struct type with unconditional member 'foo' and conditional -member 'bar' +member 'bar' :: -{ 'struct': 'IfStruct', 'data': - { 'foo': 'int', - 'bar': { 'type': 'int', 'if': 'defined(IFCOND)'} } } + { 'struct': 'IfStruct', 'data': + { 'foo': 'int', + 'bar': { 'type': 'int', 'if': 'defined(IFCOND)'} } } A union's discriminator may not be conditional. Likewise, individual enumeration values be conditional. This requires -the longhand form of ENUM-VALUE. +the longhand form of ENUM-VALUE_. Example: an enum type with unconditional value 'foo' and conditional -value 'bar' +value 'bar' :: -{ 'enum': 'IfEnum', 'data': - [ 'foo', - { 'name' : 'bar', 'if': 'defined(IFCOND)' } ] } + { 'enum': 'IfEnum', 'data': + [ 'foo', + { 'name' : 'bar', 'if': 'defined(IFCOND)' } ] } Likewise, features can be conditional. This requires the longhand -form of FEATURE. +form of FEATURE_. -Example: a struct with conditional feature 'allow-negative-numbers' +Example: a struct with conditional feature 'allow-negative-numbers' :: -{ 'struct': 'TestType', - 'data': { 'number': 'int' }, - 'features': [ { 'name': 'allow-negative-numbers', - 'if': 'defined(IFCOND)' } ] } + { 'struct': 'TestType', + 'data': { 'number': 'int' }, + 'features': [ { 'name': 'allow-negative-numbers', + 'if': 'defined(IFCOND)' } ] } Please note that you are responsible to ensure that the C code will compile with an arbitrary combination of conditions, since the @@ -843,28 +888,31 @@ shows a conditional entity only when the condition is satisfied in this particular build. -=== Documentation comments === +Documentation comments +---------------------- -A multi-line comment that starts and ends with a '##' line is a +A multi-line comment that starts and ends with a ``##`` line is a documentation comment. -If the documentation comment starts like +If the documentation comment starts like :: ## # @SYMBOL: -it documents the definition if SYMBOL, else it's free-form +it documents the definition of SYMBOL, else it's free-form documentation. -See below for more on definition documentation. +See below for more on `Definition documentation`_. Free-form documentation may be used to provide additional text and structuring content. -==== Headings and subheadings ==== + +Headings and subheadings +~~~~~~~~~~~~~~~~~~~~~~~~ A free-form documentation comment containing a line which starts with -some '=' symbols and then a space defines a section heading: +some ``=`` symbols and then a space defines a section heading:: ## # = This is a top level heading @@ -883,25 +931,27 @@ comment block. Section headings must always be correctly nested, so you can only define a third-level heading inside a second-level heading, and so on. -==== Documentation markup ==== + +Documentation markup +~~~~~~~~~~~~~~~~~~~~ Documentation comments can use most rST markup. In particular, -a '::' literal block can be used for examples: +a ``::`` literal block can be used for examples:: # :: # # Text of the example, may span # multiple lines -'*' starts an itemized list: +``*`` starts an itemized list:: # * First item, may span # multiple lines # * Second item -You can also use '-' instead of '*'. +You can also use ``-`` instead of ``*``. -A decimal number followed by '.' starts a numbered list: +A decimal number followed by ``.`` starts a numbered list:: # 1. First item, may span # multiple lines @@ -914,35 +964,36 @@ If a list item's text spans multiple lines, then the second and subsequent lines must be correctly indented to line up with the first character of the first line. -The usual '**strong**', '*emphasised*' and '``literal``' markup should -be used. If you need a single literal '*' you will need to +The usual ****strong****, *\*emphasized\** and ````literal```` markup +should be used. If you need a single literal ``*``, you will need to backslash-escape it. As an extension beyond the usual rST syntax, you -can also use '@foo' to reference a name in the schema; this is -rendered the same way as '``foo``'. +can also use ``@foo`` to reference a name in the schema; this is rendered +the same way as ````foo````. -Example: +Example:: -## -# Some text foo with **bold** and *emphasis* -# 1. with a list -# 2. like that -# -# And some code: -# -# :: -# -# $ echo foo -# -> do this -# <- get that -## + ## + # Some text foo with **bold** and *emphasis* + # 1. with a list + # 2. like that + # + # And some code: + # + # :: + # + # $ echo foo + # -> do this + # <- get that + ## -==== Definition documentation ==== +Definition documentation +~~~~~~~~~~~~~~~~~~~~~~~~ Definition documentation, if present, must immediately precede the definition it documents. -When documentation is required (see pragma 'doc-required'), every +When documentation is required (see pragma_ 'doc-required'), every definition must have documentation. Definition documentation starts with a line naming the definition, @@ -952,23 +1003,28 @@ alternates), or value (for enums), and finally optional tagged sections. Descriptions of arguments can span multiple lines. The description -text can start on the line following the '@argname:', in which case it +text can start on the line following the '\@argname:', in which case it must not be indented at all. It can also start on the same line as -the '@argname:'. In this case if it spans multiple lines then second +the '\@argname:'. In this case if it spans multiple lines then second and subsequent lines must be indented to line up with the first -character of the first line of the description: +character of the first line of the description:: -# @argone: -# This is a two line description -# in the first style. -# -# @argtwo: This is a two line description -# in the second style. + # @argone: + # This is a two line description + # in the first style. + # + # @argtwo: This is a two line description + # in the second style. The number of spaces between the ':' and the text is not significant. -FIXME: the parser accepts these things in almost any order. -FIXME: union branches should be described, too. +.. admonition:: FIXME + + The parser accepts these things in almost any order. + +.. admonition:: FIXME + + union branches should be described, too. Extensions added after the definition was first released carry a '(since x.y.z)' comment. @@ -997,52 +1053,53 @@ An 'Example' or 'Examples' section is automatically rendered entirely as literal fixed-width text. In other sections, the text is formatted, and rST markup can be used. -For example: +For example:: -## -# @BlockStats: -# -# Statistics of a virtual block device or a block backing device. -# -# @device: If the stats are for a virtual block device, the name -# corresponding to the virtual block device. -# -# @node-name: The node name of the device. (since 2.3) -# -# ... more members ... -# -# Since: 0.14.0 -## -{ 'struct': 'BlockStats', - 'data': {'*device': 'str', '*node-name': 'str', - ... more members ... } } + ## + # @BlockStats: + # + # Statistics of a virtual block device or a block backing device. + # + # @device: If the stats are for a virtual block device, the name + # corresponding to the virtual block device. + # + # @node-name: The node name of the device. (since 2.3) + # + # ... more members ... + # + # Since: 0.14.0 + ## + { 'struct': 'BlockStats', + 'data': {'*device': 'str', '*node-name': 'str', + ... more members ... } } -## -# @query-blockstats: -# -# Query the @BlockStats for all virtual block devices. -# -# @query-nodes: If true, the command will query all the -# block nodes ... explain, explain ... (since 2.3) -# -# Returns: A list of @BlockStats for each virtual block devices. -# -# Since: 0.14.0 -# -# Example: -# -# -> { "execute": "query-blockstats" } -# <- { -# ... lots of output ... -# } -# -## -{ 'command': 'query-blockstats', - 'data': { '*query-nodes': 'bool' }, - 'returns': ['BlockStats'] } + ## + # @query-blockstats: + # + # Query the @BlockStats for all virtual block devices. + # + # @query-nodes: If true, the command will query all the + # block nodes ... explain, explain ... (since 2.3) + # + # Returns: A list of @BlockStats for each virtual block devices. + # + # Since: 0.14.0 + # + # Example: + # + # -> { "execute": "query-blockstats" } + # <- { + # ... lots of output ... + # } + # + ## + { 'command': 'query-blockstats', + 'data': { '*query-nodes': 'bool' }, + 'returns': ['BlockStats'] } -== Client JSON Protocol introspection == +Client JSON Protocol introspection +================================== Clients of a Client JSON Protocol commonly need to figure out what exactly the server (QEMU) supports. @@ -1114,13 +1171,13 @@ If the command takes no arguments, "arg-type" names an object type without members. Likewise, if the command returns nothing, "ret-type" names an object type without members. -Example: the SchemaInfo for command query-qmp-schema +Example: the SchemaInfo for command query-qmp-schema :: - { "name": "query-qmp-schema", "meta-type": "command", - "arg-type": "q_empty", "ret-type": "SchemaInfoList" } + { "name": "query-qmp-schema", "meta-type": "command", + "arg-type": "q_empty", "ret-type": "SchemaInfoList" } - Type "q_empty" is an automatic object type without members, and type - "SchemaInfoList" is the array of SchemaInfo type. + Type "q_empty" is an automatic object type without members, and type + "SchemaInfoList" is the array of SchemaInfo type. The SchemaInfo for an event has meta-type "event", and variant member "arg-type". On the wire, a "data" member that the server passes in an @@ -1133,7 +1190,7 @@ the wire then. Each command or event defined with 'data' as MEMBERS object in the QAPI schema implicitly defines an object type. -Example: the SchemaInfo for EVENT_C from section Events +Example: the SchemaInfo for EVENT_C from section Events_ :: { "name": "EVENT_C", "meta-type": "event", "arg-type": "q_obj-EVENT_C-arg" } @@ -1157,7 +1214,7 @@ extensions. The "members" array is in no particular order; clients must search the entire object when learning whether a particular member is supported. -Example: the SchemaInfo for MyType from section Struct types +Example: the SchemaInfo for MyType from section `Struct types`_ :: { "name": "MyType", "meta-type": "object", "members": [ @@ -1168,7 +1225,7 @@ Example: the SchemaInfo for MyType from section Struct types "features" exposes the command's feature strings as a JSON array of strings. -Example: the SchemaInfo for TestType from section Features: +Example: the SchemaInfo for TestType from section Features_:: { "name": "TestType", "meta-type": "object", "members": [ @@ -1184,7 +1241,7 @@ that provides the variant members for this type tag value). The list cases in the same order as the corresponding "tag" enum type. Example: the SchemaInfo for flat union BlockdevOptions from section -Union types +`Union types`_ :: { "name": "BlockdevOptions", "meta-type": "object", "members": [ @@ -1199,13 +1256,13 @@ Note that base types are "flattened": its members are included in the "members" array. A simple union implicitly defines an enumeration type for its implicit -discriminator (called "type" on the wire, see section Union types). +discriminator (called "type" on the wire, see section `Union types`_). A simple union implicitly defines an object type for each of its variants. Example: the SchemaInfo for simple union BlockdevOptionsSimple from section -Union types +`Union types`_ :: { "name": "BlockdevOptionsSimple", "meta-type": "object", "members": [ @@ -1225,7 +1282,7 @@ a JSON object with member "type", which names a type. Values of the alternate type conform to exactly one of its member types. There is no guarantee on the order in which "members" will be listed. -Example: the SchemaInfo for BlockdevRef from section Alternate types +Example: the SchemaInfo for BlockdevRef from section `Alternate types`_ :: { "name": "BlockdevRef", "meta-type": "alternate", "members": [ @@ -1239,7 +1296,7 @@ resemble the element type; however, clients should examine member "element-type" instead of making assumptions based on parsing member "name". -Example: the SchemaInfo for ['str'] +Example: the SchemaInfo for ['str'] :: { "name": "[str]", "meta-type": "array", "element-type": "str" } @@ -1249,17 +1306,17 @@ variant member "values". The values are listed in no particular order; clients must search the entire enum when learning whether a particular value is supported. -Example: the SchemaInfo for MyEnum from section Enumeration types +Example: the SchemaInfo for MyEnum from section `Enumeration types`_ :: { "name": "MyEnum", "meta-type": "enum", "values": [ "value1", "value2", "value3" ] } The SchemaInfo for a built-in type has the same name as the type in -the QAPI schema (see section Built-in Types), with one exception +the QAPI schema (see section `Built-in Types`_), with one exception detailed below. It has variant member "json-type" that shows how values of this type are encoded on the wire. -Example: the SchemaInfo for str +Example: the SchemaInfo for str :: { "name": "str", "meta-type": "builtin", "json-type": "string" } @@ -1273,7 +1330,8 @@ the names of built-in types. Clients should examine member "json-type" instead of hard-coding names of built-in types. -== Compatibility considerations == +Compatibility considerations +============================ Maintaining backward compatibility at the Client JSON Protocol level while evolving the schema requires some care. This section is about @@ -1333,7 +1391,8 @@ may be freely renamed. Even certain refactorings are invisible, such as splitting members from one type into a common base type. -== Code generation == +Code generation +=============== The QAPI code generator qapi-gen.py generates code and documentation from the schema. Together with the core QAPI libraries, this code @@ -1347,7 +1406,7 @@ As an example, we'll use the following schema, which describes a single complex user-defined type, along with command which takes a list of that type as a parameter, and returns a single element of that type. The user is responsible for writing the implementation of -qmp_my_command(); everything else is produced by the generator. +qmp_my_command(); everything else is produced by the generator. :: $ cat example-schema.json { 'struct': 'UserDefOne', @@ -1359,7 +1418,7 @@ qmp_my_command(); everything else is produced by the generator. { 'event': 'MY_EVENT' } -We run qapi-gen.py like this: +We run qapi-gen.py like this:: $ python scripts/qapi-gen.py --output-dir="qapi-generated" \ --prefix="example-" example-schema.json @@ -1369,24 +1428,27 @@ tests/qapi-schema/qapi-schema-tests.json that covers more examples of what the generator will accept, and compiles the resulting C code as part of 'make check-unit'. -=== Code generated for QAPI types === + +Code generated for QAPI types +----------------------------- The following files are created: -$(prefix)qapi-types.h - C types corresponding to types defined in - the schema + ``$(prefix)qapi-types.h`` + C types corresponding to types defined in the schema -$(prefix)qapi-types.c - Cleanup functions for the above C types + ``$(prefix)qapi-types.c`` + Cleanup functions for the above C types The $(prefix) is an optional parameter used as a namespace to keep the generated code from one schema/code-generation separated from others so code can be generated/used from multiple schemas without clobbering previously created code. -Example: +Example:: $ cat qapi-generated/example-qapi-types.h -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] #ifndef EXAMPLE_QAPI_TYPES_H #define EXAMPLE_QAPI_TYPES_H @@ -1422,7 +1484,7 @@ Example: #endif /* EXAMPLE_QAPI_TYPES_H */ $ cat qapi-generated/example-qapi-types.c -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] void qapi_free_UserDefOne(UserDefOne *obj) { @@ -1450,22 +1512,26 @@ Example: visit_free(v); } -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] -For a modular QAPI schema (see section Include directives), code for -each sub-module SUBDIR/SUBMODULE.json is actually generated into +For a modular QAPI schema (see section `Include directives`_), code for +each sub-module SUBDIR/SUBMODULE.json is actually generated into :: -SUBDIR/$(prefix)qapi-types-SUBMODULE.h -SUBDIR/$(prefix)qapi-types-SUBMODULE.c + SUBDIR/$(prefix)qapi-types-SUBMODULE.h + SUBDIR/$(prefix)qapi-types-SUBMODULE.c If qapi-gen.py is run with option --builtins, additional files are created: -qapi-builtin-types.h - C types corresponding to built-in types + ``qapi-builtin-types.h`` + C types corresponding to built-in types -qapi-builtin-types.c - Cleanup functions for the above C types + ``qapi-builtin-types.c`` + Cleanup functions for the above C types -=== Code generated for visiting QAPI types === + +Code generated for visiting QAPI types +-------------------------------------- These are the visitor functions used to walk through and convert between a native QAPI C data structure and some other format (such as @@ -1474,19 +1540,18 @@ visit_type_FOO_members(). The following files are generated: -$(prefix)qapi-visit.c: Visitor function for a particular C type, used - to automagically convert QObjects into the - corresponding C type and vice-versa, as well - as for deallocating memory for an existing C - type + ``$(prefix)qapi-visit.c`` + Visitor function for a particular C type, used to automagically + convert QObjects into the corresponding C type and vice-versa, as + well as for deallocating memory for an existing C type -$(prefix)qapi-visit.h: Declarations for previously mentioned visitor - functions + ``$(prefix)qapi-visit.h`` + Declarations for previously mentioned visitor functions -Example: +Example:: $ cat qapi-generated/example-qapi-visit.h -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] #ifndef EXAMPLE_QAPI_VISIT_H #define EXAMPLE_QAPI_VISIT_H @@ -1496,14 +1561,18 @@ Example: bool visit_type_UserDefOne_members(Visitor *v, UserDefOne *obj, Error **errp); - bool visit_type_UserDefOne(Visitor *v, const char *name, UserDefOne **obj, Error **errp); - bool visit_type_UserDefOneList(Visitor *v, const char *name, UserDefOneList **obj, Error **errp); + + bool visit_type_UserDefOne(Visitor *v, const char *name, + UserDefOne **obj, Error **errp); + + bool visit_type_UserDefOneList(Visitor *v, const char *name, + UserDefOneList **obj, Error **errp); bool visit_type_q_obj_my_command_arg_members(Visitor *v, q_obj_my_command_arg *obj, Error **errp); #endif /* EXAMPLE_QAPI_VISIT_H */ $ cat qapi-generated/example-qapi-visit.c -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] bool visit_type_UserDefOne_members(Visitor *v, UserDefOne *obj, Error **errp) { @@ -1518,7 +1587,8 @@ Example: return true; } - bool visit_type_UserDefOne(Visitor *v, const char *name, UserDefOne **obj, Error **errp) + bool visit_type_UserDefOne(Visitor *v, const char *name, + UserDefOne **obj, Error **errp) { bool ok = false; @@ -1528,6 +1598,7 @@ Example: if (!*obj) { /* incomplete */ assert(visit_is_dealloc(v)); + ok = true; goto out_obj; } if (!visit_type_UserDefOne_members(v, *obj, errp)) { @@ -1543,7 +1614,8 @@ Example: return ok; } - bool visit_type_UserDefOneList(Visitor *v, const char *name, UserDefOneList **obj, Error **errp) + bool visit_type_UserDefOneList(Visitor *v, const char *name, + UserDefOneList **obj, Error **errp) { bool ok = false; UserDefOneList *tail; @@ -1578,22 +1650,26 @@ Example: return true; } -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] -For a modular QAPI schema (see section Include directives), code for -each sub-module SUBDIR/SUBMODULE.json is actually generated into +For a modular QAPI schema (see section `Include directives`_), code for +each sub-module SUBDIR/SUBMODULE.json is actually generated into :: -SUBDIR/$(prefix)qapi-visit-SUBMODULE.h -SUBDIR/$(prefix)qapi-visit-SUBMODULE.c + SUBDIR/$(prefix)qapi-visit-SUBMODULE.h + SUBDIR/$(prefix)qapi-visit-SUBMODULE.c If qapi-gen.py is run with option --builtins, additional files are created: -qapi-builtin-visit.h - Visitor functions for built-in types + ``qapi-builtin-visit.h`` + Visitor functions for built-in types -qapi-builtin-visit.c - Declarations for these visitor functions + ``qapi-builtin-visit.c`` + Declarations for these visitor functions -=== Code generated for commands === + +Code generated for commands +--------------------------- These are the marshaling/dispatch functions for the commands defined in the schema. The generated code provides qmp_marshal_COMMAND(), and @@ -1601,20 +1677,23 @@ declares qmp_COMMAND() that the user must implement. The following files are generated: -$(prefix)qapi-commands.c: Command marshal/dispatch functions for each - QMP command defined in the schema + ``$(prefix)qapi-commands.c`` + Command marshal/dispatch functions for each QMP command defined in + the schema -$(prefix)qapi-commands.h: Function prototypes for the QMP commands - specified in the schema + ``$(prefix)qapi-commands.h`` + Function prototypes for the QMP commands specified in the schema -$(prefix)qapi-init-commands.h - Command initialization prototype + ``$(prefix)qapi-init-commands.h`` + Command initialization prototype -$(prefix)qapi-init-commands.c - Command initialization code + ``$(prefix)qapi-init-commands.c`` + Command initialization code -Example: +Example:: $ cat qapi-generated/example-qapi-commands.h -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] #ifndef EXAMPLE_QAPI_COMMANDS_H #define EXAMPLE_QAPI_COMMANDS_H @@ -1626,13 +1705,15 @@ Example: #endif /* EXAMPLE_QAPI_COMMANDS_H */ $ cat qapi-generated/example-qapi-commands.c -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] - static void qmp_marshal_output_UserDefOne(UserDefOne *ret_in, QObject **ret_out, Error **errp) + + static void qmp_marshal_output_UserDefOne(UserDefOne *ret_in, + QObject **ret_out, Error **errp) { Visitor *v; - v = qobject_output_visitor_new(ret_out); + v = qobject_output_visitor_new_qmp(ret_out); if (visit_type_UserDefOne(v, "unused", &ret_in, errp)) { visit_complete(v, ret_out); } @@ -1650,7 +1731,7 @@ Example: UserDefOne *retval; q_obj_my_command_arg arg = {0}; - v = qobject_input_visitor_new(QOBJECT(args)); + v = qobject_input_visitor_new_qmp(QOBJECT(args)); if (!visit_start_struct(v, NULL, NULL, 0, errp)) { goto out; } @@ -1679,9 +1760,9 @@ Example: visit_free(v); } -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] $ cat qapi-generated/example-qapi-init-commands.h -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] #ifndef EXAMPLE_QAPI_INIT_COMMANDS_H #define EXAMPLE_QAPI_INIT_COMMANDS_H @@ -1691,7 +1772,7 @@ Example: #endif /* EXAMPLE_QAPI_INIT_COMMANDS_H */ $ cat qapi-generated/example-qapi-init-commands.c -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] void example_qmp_init_marshal(QmpCommandList *cmds) { QTAILQ_INIT(cmds); @@ -1699,34 +1780,39 @@ Example: qmp_register_command(cmds, "my-command", qmp_marshal_my_command, QCO_NO_OPTIONS); } -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] -For a modular QAPI schema (see section Include directives), code for -each sub-module SUBDIR/SUBMODULE.json is actually generated into +For a modular QAPI schema (see section `Include directives`_), code for +each sub-module SUBDIR/SUBMODULE.json is actually generated into:: -SUBDIR/$(prefix)qapi-commands-SUBMODULE.h -SUBDIR/$(prefix)qapi-commands-SUBMODULE.c + SUBDIR/$(prefix)qapi-commands-SUBMODULE.h + SUBDIR/$(prefix)qapi-commands-SUBMODULE.c -=== Code generated for events === + +Code generated for events +------------------------- This is the code related to events defined in the schema, providing qapi_event_send_EVENT(). The following files are created: -$(prefix)qapi-events.h - Function prototypes for each event type + ``$(prefix)qapi-events.h`` + Function prototypes for each event type -$(prefix)qapi-events.c - Implementation of functions to send an event + ``$(prefix)qapi-events.c`` + Implementation of functions to send an event -$(prefix)qapi-emit-events.h - Enumeration of all event names, and - common event code declarations + ``$(prefix)qapi-emit-events.h`` + Enumeration of all event names, and common event code declarations -$(prefix)qapi-emit-events.c - Common event code definitions + ``$(prefix)qapi-emit-events.c`` + Common event code definitions -Example: +Example:: $ cat qapi-generated/example-qapi-events.h -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] #ifndef EXAMPLE_QAPI_EVENTS_H #define EXAMPLE_QAPI_EVENTS_H @@ -1738,7 +1824,7 @@ Example: #endif /* EXAMPLE_QAPI_EVENTS_H */ $ cat qapi-generated/example-qapi-events.c -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] void qapi_event_send_my_event(void) { @@ -1751,9 +1837,9 @@ Example: qobject_unref(qmp); } -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] $ cat qapi-generated/example-qapi-emit-events.h -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] #ifndef EXAMPLE_QAPI_EMIT_EVENTS_H #define EXAMPLE_QAPI_EMIT_EVENTS_H @@ -1774,7 +1860,7 @@ Example: #endif /* EXAMPLE_QAPI_EMIT_EVENTS_H */ $ cat qapi-generated/example-qapi-emit-events.c -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] const QEnumLookup example_QAPIEvent_lookup = { .array = (const char *const[]) { @@ -1783,27 +1869,30 @@ Example: .size = EXAMPLE_QAPI_EVENT__MAX }; -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] -For a modular QAPI schema (see section Include directives), code for -each sub-module SUBDIR/SUBMODULE.json is actually generated into +For a modular QAPI schema (see section `Include directives`_), code for +each sub-module SUBDIR/SUBMODULE.json is actually generated into :: -SUBDIR/$(prefix)qapi-events-SUBMODULE.h -SUBDIR/$(prefix)qapi-events-SUBMODULE.c + SUBDIR/$(prefix)qapi-events-SUBMODULE.h + SUBDIR/$(prefix)qapi-events-SUBMODULE.c -=== Code generated for introspection === + +Code generated for introspection +-------------------------------- The following files are created: -$(prefix)qapi-introspect.c - Defines a string holding a JSON - description of the schema + ``$(prefix)qapi-introspect.c`` + Defines a string holding a JSON description of the schema -$(prefix)qapi-introspect.h - Declares the above string + ``$(prefix)qapi-introspect.h`` + Declares the above string -Example: +Example:: $ cat qapi-generated/example-qapi-introspect.h -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] #ifndef EXAMPLE_QAPI_INTROSPECT_H #define EXAMPLE_QAPI_INTROSPECT_H @@ -1814,7 +1903,7 @@ Example: #endif /* EXAMPLE_QAPI_INTROSPECT_H */ $ cat qapi-generated/example-qapi-introspect.c -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] const QLitObject example_qmp_schema_qlit = QLIT_QLIST(((QLitObject[]) { QLIT_QDICT(((QLitDictEntry[]) { @@ -1894,4 +1983,4 @@ Example: {} })); -[Uninteresting stuff omitted...] + [Uninteresting stuff omitted...] diff --git a/docs/devel/qgraph.rst b/docs/devel/qgraph.rst index a9aff167ad..39e293687e 100644 --- a/docs/devel/qgraph.rst +++ b/docs/devel/qgraph.rst @@ -66,11 +66,11 @@ Notes for the nodes: Edges ^^^^^^ -An edge relation between two nodes (drivers or machines) `X` and `Y` can be: +An edge relation between two nodes (drivers or machines) ``X`` and ``Y`` can be: -- ``X CONSUMES Y``: `Y` can be plugged into `X` -- ``X PRODUCES Y``: `X` provides the interface `Y` -- ``X CONTAINS Y``: `Y` is part of `X` component +- ``X CONSUMES Y``: ``Y`` can be plugged into ``X`` +- ``X PRODUCES Y``: ``X`` provides the interface ``Y`` +- ``X CONTAINS Y``: ``Y`` is part of ``X`` component Execution steps ^^^^^^^^^^^^^^^ @@ -92,6 +92,64 @@ The basic framework steps are the following: Depending on the QEMU binary used, only some drivers/machines will be available and only test that are reached by them will be executed. +Troubleshooting unavailable tests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +If there is no path from an available machine to a test then that test will be +unavailable and won't execute. This can happen if a test or driver did not set +up its qgraph node correctly. It can also happen if the necessary machine type +or device is missing from the QEMU binary because it was compiled out or +otherwise. + +It is possible to troubleshoot unavailable tests by running:: + + $ QTEST_QEMU_BINARY=build/qemu-system-x86_64 build/tests/qtest/qos-test --verbose + # ALL QGRAPH EDGES: { + # src='virtio-net' + # |-> dest='virtio-net-tests/vhost-user/multiqueue' type=2 (node=0x559142109e30) + # |-> dest='virtio-net-tests/vhost-user/migrate' type=2 (node=0x559142109d00) + # src='virtio-net-pci' + # |-> dest='virtio-net' type=1 (node=0x55914210d740) + # src='pci-bus' + # |-> dest='virtio-net-pci' type=2 (node=0x55914210d880) + # src='pci-bus-pc' + # |-> dest='pci-bus' type=1 (node=0x559142103f40) + # src='i440FX-pcihost' + # |-> dest='pci-bus-pc' type=0 (node=0x55914210ac70) + # src='x86_64/pc' + # |-> dest='i440FX-pcihost' type=0 (node=0x5591421117f0) + # src='' + # |-> dest='x86_64/pc' type=0 (node=0x559142111600) + # |-> dest='arm/raspi2' type=0 (node=0x559142110740) + ... + # } + # ALL QGRAPH NODES: { + # name='virtio-net-tests/announce-self' type=3 cmd_line='(null)' [available] + # name='arm/raspi2' type=0 cmd_line='-M raspi2 ' [UNAVAILABLE] + ... + # } + +The ``virtio-net-tests/announce-self`` test is listed as "available" in the +"ALL QGRAPH NODES" output. This means the test will execute. We can follow the +qgraph path in the "ALL QGRAPH EDGES" output as follows: '' -> 'x86_64/pc' -> +'i440FX-pcihost' -> 'pci-bus-pc' -> 'pci-bus' -> 'virtio-net-pci' -> +'virtio-net'. The root of the qgraph is '' and the depth first search begins +there. + +The ``arm/raspi`` machine node is listed as "UNAVAILABLE". Although it is +reachable from the root via '' -> 'arm/raspi2' the node is unavailable because +the QEMU binary did not list it when queried by the framework. This is expected +because we used the ``qemu-system-x86_64`` binary which does not support ARM +machine types. + +If a test is unexpectedly listed as "UNAVAILABLE", first check that the "ALL +QGRAPH EDGES" output reports edge connectivity from the root ('') to the test. +If there is no connectivity then the qgraph nodes were not set up correctly and +the driver or test code is incorrect. If there is connectivity, check the +availability of each node in the path in the "ALL QGRAPH NODES" output. The +first unavailable node in the path is the reason why the test is unavailable. +Typically this is because the QEMU binary lacks support for the necessary +machine type or device. + Creating a new driver and its interface """"""""""""""""""""""""""""""""""""""""" diff --git a/docs/devel/qom.rst b/docs/devel/qom.rst index 42d0dc4f4d..e5fe3597cd 100644 --- a/docs/devel/qom.rst +++ b/docs/devel/qom.rst @@ -87,6 +87,14 @@ specific type: #define MY_DEVICE(obj) \ OBJECT_CHECK(MyDevice, obj, TYPE_MY_DEVICE) +In case the ObjectClass implementation can be built as module a +module_obj() line must be added to make sure qemu loads the module +when the object is needed. + +.. code-block:: c + + module_obj(TYPE_MY_DEVICE); + Class Initialization ==================== diff --git a/docs/devel/secure-coding-practices.rst b/docs/devel/secure-coding-practices.rst index cbfc8af67e..0454cc527e 100644 --- a/docs/devel/secure-coding-practices.rst +++ b/docs/devel/secure-coding-practices.rst @@ -104,3 +104,12 @@ structures and only process the local copy. This prevents time-of-check-to-time-of-use (TOCTOU) race conditions that could cause QEMU to crash when a vCPU thread modifies guest RAM while device emulation is processing it. + +Use of null-co block drivers +---------------------------- + +The ``null-co`` block driver is designed for performance: its read accesses are +not initialized by default. In case this driver has to be used for security +research, it must be used with the ``read-zeroes=on`` option which fills read +buffers with zeroes. Security issues reported with the default +(``read-zeroes=off``) will be discarded. diff --git a/docs/devel/tcg-plugins.rst b/docs/devel/tcg-plugins.rst index 18c6581d85..047bf4ada7 100644 --- a/docs/devel/tcg-plugins.rst +++ b/docs/devel/tcg-plugins.rst @@ -34,11 +34,11 @@ version they were built against. This can be done simply by:: QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION; The core code will refuse to load a plugin that doesn't export a -`qemu_plugin_version` symbol or if plugin version is outside of QEMU's +``qemu_plugin_version`` symbol or if plugin version is outside of QEMU's supported range of API versions. -Additionally the `qemu_info_t` structure which is passed to the -`qemu_plugin_install` method of a plugin will detail the minimum and +Additionally the ``qemu_info_t`` structure which is passed to the +``qemu_plugin_install`` method of a plugin will detail the minimum and current API versions supported by QEMU. The API version will be incremented if new APIs are added. The minimum API version will be incremented if existing APIs are changed or removed. @@ -71,7 +71,8 @@ API Usage ===== -The QEMU binary needs to be compiled for plugin support:: +Any QEMU binary with TCG support has plugins enabled by default. +Earlier releases needed to be explicitly enabled with:: configure --enable-plugins @@ -145,12 +146,12 @@ Example Plugins There are a number of plugins included with QEMU and you are encouraged to contribute your own plugins plugins upstream. There is a -`contrib/plugins` directory where they can go. +``contrib/plugins`` directory where they can go. - tests/plugins These are some basic plugins that are used to test and exercise the -API during the `make check-tcg` target. +API during the ``make check-tcg`` target. - contrib/plugins/hotblocks.c @@ -162,7 +163,7 @@ with linux-user execution as system emulation tends to generate re-translations as blocks from different programs get swapped in and out of system memory. -If your program is single-threaded you can use the `inline` option for +If your program is single-threaded you can use the ``inline`` option for slightly faster (but not thread safe) counters. Example:: @@ -250,7 +251,7 @@ which will lead to a sorted list after the class breakdown:: ... To find the argument shorthand for the class you need to examine the -source code of the plugin at the moment, specifically the `*opt` +source code of the plugin at the moment, specifically the ``*opt`` argument in the InsnClassExecCount tables. - contrib/plugins/lockstep.c @@ -319,3 +320,86 @@ the user to see what hardware is accessed how often. It has a number of options: off:0000001c, 1, 2 off:00000020, 1, 2 ... + +- contrib/plugins/execlog.c + +The execlog tool traces executed instructions with memory access. It can be used +for debugging and security analysis purposes. +Please be aware that this will generate a lot of output. + +The plugin takes no argument:: + + qemu-system-arm $(QEMU_ARGS) \ + -plugin ./contrib/plugins/libexeclog.so -d plugin + +which will output an execution trace following this structure:: + + # vCPU, vAddr, opcode, disassembly[, load/store, memory addr, device]... + 0, 0xa12, 0xf8012400, "movs r4, #0" + 0, 0xa14, 0xf87f42b4, "cmp r4, r6" + 0, 0xa16, 0xd206, "bhs #0xa26" + 0, 0xa18, 0xfff94803, "ldr r0, [pc, #0xc]", load, 0x00010a28, RAM + 0, 0xa1a, 0xf989f000, "bl #0xd30" + 0, 0xd30, 0xfff9b510, "push {r4, lr}", store, 0x20003ee0, RAM, store, 0x20003ee4, RAM + 0, 0xd32, 0xf9893014, "adds r0, #0x14" + 0, 0xd34, 0xf9c8f000, "bl #0x10c8" + 0, 0x10c8, 0xfff96c43, "ldr r3, [r0, #0x44]", load, 0x200000e4, RAM + +- contrib/plugins/cache + +Cache modelling plugin that measures the performance of a given cache +configuration when a given working set is run:: + + qemu-x86_64 -plugin ./contrib/plugins/libcache.so \ + -d plugin -D cache.log ./tests/tcg/x86_64-linux-user/float_convs + +will report the following:: + + Data accesses: 996479, Misses: 507 + Miss rate: 0.050879% + + Instruction accesses: 2641737, Misses: 18617 + Miss rate: 0.704726% + + address, data misses, instruction + 0x424f1e (_int_malloc), 109, movq %rax, 8(%rcx) + 0x41f395 (_IO_default_xsputn), 49, movb %dl, (%rdi, %rax) + 0x42584d (ptmalloc_init.part.0), 33, movaps %xmm0, (%rax) + 0x454d48 (__tunables_init), 20, cmpb $0, (%r8) + ... + + address, fetch misses, instruction + 0x4160a0 (__vfprintf_internal), 744, movl $1, %ebx + 0x41f0a0 (_IO_setb), 744, endbr64 + 0x415882 (__vfprintf_internal), 744, movq %r12, %rdi + 0x4268a0 (__malloc), 696, andq $0xfffffffffffffff0, %rax + ... + +The plugin has a number of arguments, all of them are optional: + + * arg="limit=N" + + Print top N icache and dcache thrashing instructions along with their + address, number of misses, and its disassembly. (default: 32) + + * arg="icachesize=N" + * arg="iblksize=B" + * arg="iassoc=A" + + Instruction cache configuration arguments. They specify the cache size, block + size, and associativity of the instruction cache, respectively. + (default: N = 16384, B = 64, A = 8) + + * arg="dcachesize=N" + * arg="dblksize=B" + * arg="dassoc=A" + + Data cache configuration arguments. They specify the cache size, block size, + and associativity of the data cache, respectively. + (default: N = 16384, B = 64, A = 8) + + * arg="evict=POLICY" + + Sets the eviction policy to POLICY. Available policies are: :code:`lru`, + :code:`fifo`, and :code:`rand`. The plugin will use the specified policy for + both instruction and data caches. (default: POLICY = :code:`lru`) diff --git a/docs/devel/tcg.rst b/docs/devel/tcg.rst index 4ebde44b9d..a65fb7b1c4 100644 --- a/docs/devel/tcg.rst +++ b/docs/devel/tcg.rst @@ -11,13 +11,14 @@ performances. QEMU's dynamic translation backend is called TCG, for "Tiny Code Generator". For more information, please take a look at ``tcg/README``. -Some notable features of QEMU's dynamic translator are: +The following sections outline some notable features and implementation +details of QEMU's dynamic translator. CPU state optimisations ----------------------- -The target CPUs have many internal states which change the way it -evaluates instructions. In order to achieve a good speed, the +The target CPUs have many internal states which change the way they +evaluate instructions. In order to achieve a good speed, the translation phase considers that some state information of the virtual CPU cannot change in it. The state is recorded in the Translation Block (TB). If the state changes (e.g. privilege level), a new TB will @@ -31,17 +32,95 @@ Direct block chaining --------------------- After each translated basic block is executed, QEMU uses the simulated -Program Counter (PC) and other cpu state information (such as the CS +Program Counter (PC) and other CPU state information (such as the CS segment base value) to find the next basic block. -In order to accelerate the most common cases where the new simulated PC -is known, QEMU can patch a basic block so that it jumps directly to the -next one. +In its simplest, less optimized form, this is done by exiting from the +current TB, going through the TB epilogue, and then back to the +main loop. That’s where QEMU looks for the next TB to execute, +translating it from the guest architecture if it isn’t already available +in memory. Then QEMU proceeds to execute this next TB, starting at the +prologue and then moving on to the translated instructions. -The most portable code uses an indirect jump. An indirect jump makes -it easier to make the jump target modification atomic. On some host -architectures (such as x86 or PowerPC), the ``JUMP`` opcode is -directly patched so that the block chaining has no overhead. +Exiting from the TB this way will cause the ``cpu_exec_interrupt()`` +callback to be re-evaluated before executing additional instructions. +It is mandatory to exit this way after any CPU state changes that may +unmask interrupts. + +In order to accelerate the cases where the TB for the new +simulated PC is already available, QEMU has mechanisms that allow +multiple TBs to be chained directly, without having to go back to the +main loop as described above. These mechanisms are: + +``lookup_and_goto_ptr`` +^^^^^^^^^^^^^^^^^^^^^^^ + +Calling ``tcg_gen_lookup_and_goto_ptr()`` will emit a call to +``helper_lookup_tb_ptr``. This helper will look for an existing TB that +matches the current CPU state. If the destination TB is available its +code address is returned, otherwise the address of the JIT epilogue is +returned. The call to the helper is always followed by the tcg ``goto_ptr`` +opcode, which branches to the returned address. In this way, we either +branch to the next TB or return to the main loop. + +``goto_tb + exit_tb`` +^^^^^^^^^^^^^^^^^^^^^ + +The translation code usually implements branching by performing the +following steps: + +1. Call ``tcg_gen_goto_tb()`` passing a jump slot index (either 0 or 1) + as a parameter. + +2. Emit TCG instructions to update the CPU state with any information + that has been assumed constant and is required by the main loop to + correctly locate and execute the next TB. For most guests, this is + just the PC of the branch destination, but others may store additional + data. The information updated in this step must be inferable from both + ``cpu_get_tb_cpu_state()`` and ``cpu_restore_state()``. + +3. Call ``tcg_gen_exit_tb()`` passing the address of the current TB and + the jump slot index again. + +Step 1, ``tcg_gen_goto_tb()``, will emit a ``goto_tb`` TCG +instruction that later on gets translated to a jump to an address +associated with the specified jump slot. Initially, this is the address +of step 2's instructions, which update the CPU state information. Step 3, +``tcg_gen_exit_tb()``, exits from the current TB returning a tagged +pointer composed of the last executed TB’s address and the jump slot +index. + +The first time this whole sequence is executed, step 1 simply jumps +to step 2. Then the CPU state information gets updated and we exit from +the current TB. As a result, the behavior is very similar to the less +optimized form described earlier in this section. + +Next, the main loop looks for the next TB to execute using the +current CPU state information (creating the TB if it wasn’t already +available) and, before starting to execute the new TB’s instructions, +patches the previously executed TB by associating one of its jump +slots (the one specified in the call to ``tcg_gen_exit_tb()``) with the +address of the new TB. + +The next time this previous TB is executed and we get to that same +``goto_tb`` step, it will already be patched (assuming the destination TB +is still in memory) and will jump directly to the first instruction of +the destination TB, without going back to the main loop. + +For the ``goto_tb + exit_tb`` mechanism to be used, the following +conditions need to be satisfied: + +* The change in CPU state must be constant, e.g., a direct branch and + not an indirect branch. + +* The direct branch cannot cross a page boundary. Memory mappings + may change, causing the code at the destination address to change. + +Note that, on step 3 (``tcg_gen_exit_tb()``), in addition to the +jump slot index, the address of the TB just executed is also returned. +This address corresponds to the TB that will be patched; it may be +different than the one that was directly executed from the main loop +if the latter had already been chained to other TBs. Self-modifying code and translated code invalidation ---------------------------------------------------- diff --git a/docs/devel/testing.rst b/docs/devel/testing.rst index 1da4c4e4c4..8a9cda33a5 100644 --- a/docs/devel/testing.rst +++ b/docs/devel/testing.rst @@ -775,7 +775,7 @@ The base test class has also support for tests with more than one QEMUMachine. The way to get machines is through the ``self.get_vm()`` method which will return a QEMUMachine instance. The ``self.get_vm()`` method accepts arguments that will be passed to the QEMUMachine creation -and also an optional `name` attribute so you can identify a specific +and also an optional ``name`` attribute so you can identify a specific machine and get it more than once through the tests methods. A simple and hypothetical example follows: @@ -810,6 +810,32 @@ and hypothetical example follows: At test "tear down", ``avocado_qemu.Test`` handles all the QEMUMachines shutdown. +The ``avocado_qemu.LinuxTest`` base test class +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The ``avocado_qemu.LinuxTest`` is further specialization of the +``avocado_qemu.Test`` class, so it contains all the characteristics of +the later plus some extra features. + +First of all, this base class is intended for tests that need to +interact with a fully booted and operational Linux guest. At this +time, it uses a Fedora 31 guest image. The most basic example looks +like this: + +.. code:: + + from avocado_qemu import LinuxTest + + + class SomeTest(LinuxTest): + + def test(self): + self.launch_and_wait() + self.ssh_command('some_command_to_be_run_in_the_guest') + +Please refer to tests that use ``avocado_qemu.LinuxTest`` under +``tests/acceptance`` for more examples. + QEMUMachine ~~~~~~~~~~~ @@ -878,6 +904,17 @@ name. If one is not given explicitly, it will either be set to ``None``, or, if the test is tagged with one (and only one) ``:avocado: tags=arch:VALUE`` tag, it will be set to ``VALUE``. +cpu +~~~ + +The cpu model that will be set to all QEMUMachine instances created +by the test. + +The ``cpu`` attribute will be set to the test parameter of the same +name. If one is not given explicitly, it will either be set to +``None ``, or, if the test is tagged with one (and only one) +``:avocado: tags=cpu:VALUE`` tag, it will be set to ``VALUE``. + machine ~~~~~~~ @@ -896,6 +933,39 @@ The preserved value of the ``qemu_bin`` parameter or the result of the dynamic probe for a QEMU binary in the current working directory or source tree. +LinuxTest +~~~~~~~~~ + +Besides the attributes present on the ``avocado_qemu.Test`` base +class, the ``avocado_qemu.LinuxTest`` adds the following attributes: + +distro +...... + +The name of the Linux distribution used as the guest image for the +test. The name should match the **Provider** column on the list +of images supported by the avocado.utils.vmimage library: + +https://avocado-framework.readthedocs.io/en/latest/guides/writer/libs/vmimage.html#supported-images + +distro_version +.............. + +The version of the Linux distribution as the guest image for the +test. The name should match the **Version** column on the list +of images supported by the avocado.utils.vmimage library: + +https://avocado-framework.readthedocs.io/en/latest/guides/writer/libs/vmimage.html#supported-images + +distro_checksum +............... + +The sha256 hash of the guest image file used for the test. + +If this value is not set in the code or by a test parameter (with the +same name), no validation on the integrity of the image will be +performed. + Parameter reference ------------------- @@ -924,6 +994,12 @@ architecture of a kernel or disk image to boot a VM with. This parameter has a direct relation with the ``arch`` attribute. If not given, it will default to None. +cpu +~~~ + +The cpu model that will be set to all QEMUMachine instances created +by the test. + machine ~~~~~~~ @@ -936,6 +1012,38 @@ qemu_bin The exact QEMU binary to be used on QEMUMachine. +LinuxTest +~~~~~~~~~ + +Besides the parameters present on the ``avocado_qemu.Test`` base +class, the ``avocado_qemu.LinuxTest`` adds the following parameters: + +distro +...... + +The name of the Linux distribution used as the guest image for the +test. The name should match the **Provider** column on the list +of images supported by the avocado.utils.vmimage library: + +https://avocado-framework.readthedocs.io/en/latest/guides/writer/libs/vmimage.html#supported-images + +distro_version +.............. + +The version of the Linux distribution as the guest image for the +test. The name should match the **Version** column on the list +of images supported by the avocado.utils.vmimage library: + +https://avocado-framework.readthedocs.io/en/latest/guides/writer/libs/vmimage.html#supported-images + +distro_checksum +............... + +The sha256 hash of the guest image file used for the test. + +If this value is not set in the code or by this parameter no +validation on the integrity of the image will be performed. + Skipping tests -------------- The Avocado framework provides Python decorators which allow for easily skip @@ -954,7 +1062,7 @@ Here is a list of the most used variables: AVOCADO_ALLOW_LARGE_STORAGE ~~~~~~~~~~~~~~~~~~~~~~~~~~~ Tests which are going to fetch or produce assets considered *large* are not -going to run unless that `AVOCADO_ALLOW_LARGE_STORAGE=1` is exported on +going to run unless that ``AVOCADO_ALLOW_LARGE_STORAGE=1`` is exported on the environment. The definition of *large* is a bit arbitrary here, but it usually means an @@ -968,7 +1076,7 @@ skipped by default. The definition of *not safe* is also arbitrary but usually it means a blob which either its source or build process aren't public available. -You should export `AVOCADO_ALLOW_UNTRUSTED_CODE=1` on the environment in +You should export ``AVOCADO_ALLOW_UNTRUSTED_CODE=1`` on the environment in order to allow tests which make use of those kind of assets. AVOCADO_TIMEOUT_EXPECTED @@ -982,7 +1090,7 @@ property defined in the test class, for further details:: Even though the timeout can be set by the test developer, there are some tests that may not have a well-defined limit of time to finish under certain conditions. For example, tests that take longer to execute when QEMU is -compiled with debug flags. Therefore, the `AVOCADO_TIMEOUT_EXPECTED` variable +compiled with debug flags. Therefore, the ``AVOCADO_TIMEOUT_EXPECTED`` variable has been used to determine whether those tests should run or not. GITLAB_CI diff --git a/docs/devel/ui.rst b/docs/devel/ui.rst new file mode 100644 index 0000000000..06c7d622ce --- /dev/null +++ b/docs/devel/ui.rst @@ -0,0 +1,8 @@ +================= +Qemu UI subsystem +================= + +Qemu Clipboard +-------------- + +.. kernel-doc:: include/ui/clipboard.h diff --git a/docs/devel/vfio-migration.rst b/docs/devel/vfio-migration.rst new file mode 100644 index 0000000000..9ff6163c88 --- /dev/null +++ b/docs/devel/vfio-migration.rst @@ -0,0 +1,150 @@ +===================== +VFIO device Migration +===================== + +Migration of virtual machine involves saving the state for each device that +the guest is running on source host and restoring this saved state on the +destination host. This document details how saving and restoring of VFIO +devices is done in QEMU. + +Migration of VFIO devices consists of two phases: the optional pre-copy phase, +and the stop-and-copy phase. The pre-copy phase is iterative and allows to +accommodate VFIO devices that have a large amount of data that needs to be +transferred. The iterative pre-copy phase of migration allows for the guest to +continue whilst the VFIO device state is transferred to the destination, this +helps to reduce the total downtime of the VM. VFIO devices can choose to skip +the pre-copy phase of migration by returning pending_bytes as zero during the +pre-copy phase. + +A detailed description of the UAPI for VFIO device migration can be found in +the comment for the ``vfio_device_migration_info`` structure in the header +file linux-headers/linux/vfio.h. + +VFIO implements the device hooks for the iterative approach as follows: + +* A ``save_setup`` function that sets up the migration region and sets _SAVING + flag in the VFIO device state. + +* A ``load_setup`` function that sets up the migration region on the + destination and sets _RESUMING flag in the VFIO device state. + +* A ``save_live_pending`` function that reads pending_bytes from the vendor + driver, which indicates the amount of data that the vendor driver has yet to + save for the VFIO device. + +* A ``save_live_iterate`` function that reads the VFIO device's data from the + vendor driver through the migration region during iterative phase. + +* A ``save_state`` function to save the device config space if it is present. + +* A ``save_live_complete_precopy`` function that resets _RUNNING flag from the + VFIO device state and iteratively copies the remaining data for the VFIO + device until the vendor driver indicates that no data remains (pending bytes + is zero). + +* A ``load_state`` function that loads the config section and the data + sections that are generated by the save functions above + +* ``cleanup`` functions for both save and load that perform any migration + related cleanup, including unmapping the migration region + + +The VFIO migration code uses a VM state change handler to change the VFIO +device state when the VM state changes from running to not-running, and +vice versa. + +Similarly, a migration state change handler is used to trigger a transition of +the VFIO device state when certain changes of the migration state occur. For +example, the VFIO device state is transitioned back to _RUNNING in case a +migration failed or was canceled. + +System memory dirty pages tracking +---------------------------------- + +A ``log_global_start`` and ``log_global_stop`` memory listener callback informs +the VFIO IOMMU module to start and stop dirty page tracking. A ``log_sync`` +memory listener callback marks those system memory pages as dirty which are +used for DMA by the VFIO device. The dirty pages bitmap is queried per +container. All pages pinned by the vendor driver through external APIs have to +be marked as dirty during migration. When there are CPU writes, CPU dirty page +tracking can identify dirtied pages, but any page pinned by the vendor driver +can also be written by the device. There is currently no device or IOMMU +support for dirty page tracking in hardware. + +By default, dirty pages are tracked when the device is in pre-copy as well as +stop-and-copy phase. So, a page pinned by the vendor driver will be copied to +the destination in both phases. Copying dirty pages in pre-copy phase helps +QEMU to predict if it can achieve its downtime tolerances. If QEMU during +pre-copy phase keeps finding dirty pages continuously, then it understands +that even in stop-and-copy phase, it is likely to find dirty pages and can +predict the downtime accordingly. + +QEMU also provides a per device opt-out option ``pre-copy-dirty-page-tracking`` +which disables querying the dirty bitmap during pre-copy phase. If it is set to +off, all dirty pages will be copied to the destination in stop-and-copy phase +only. + +System memory dirty pages tracking when vIOMMU is enabled +--------------------------------------------------------- + +With vIOMMU, an IO virtual address range can get unmapped while in pre-copy +phase of migration. In that case, the unmap ioctl returns any dirty pages in +that range and QEMU reports corresponding guest physical pages dirty. During +stop-and-copy phase, an IOMMU notifier is used to get a callback for mapped +pages and then dirty pages bitmap is fetched from VFIO IOMMU modules for those +mapped ranges. + +Flow of state changes during Live migration +=========================================== + +Below is the flow of state change during live migration. +The values in the brackets represent the VM state, the migration state, and +the VFIO device state, respectively. + +Live migration save path +------------------------ + +:: + + QEMU normal running state + (RUNNING, _NONE, _RUNNING) + | + migrate_init spawns migration_thread + Migration thread then calls each device's .save_setup() + (RUNNING, _SETUP, _RUNNING|_SAVING) + | + (RUNNING, _ACTIVE, _RUNNING|_SAVING) + If device is active, get pending_bytes by .save_live_pending() + If total pending_bytes >= threshold_size, call .save_live_iterate() + Data of VFIO device for pre-copy phase is copied + Iterate till total pending bytes converge and are less than threshold + | + On migration completion, vCPU stops and calls .save_live_complete_precopy for + each active device. The VFIO device is then transitioned into _SAVING state + (FINISH_MIGRATE, _DEVICE, _SAVING) + | + For the VFIO device, iterate in .save_live_complete_precopy until + pending data is 0 + (FINISH_MIGRATE, _DEVICE, _STOPPED) + | + (FINISH_MIGRATE, _COMPLETED, _STOPPED) + Migraton thread schedules cleanup bottom half and exits + +Live migration resume path +-------------------------- + +:: + + Incoming migration calls .load_setup for each device + (RESTORE_VM, _ACTIVE, _STOPPED) + | + For each device, .load_state is called for that device section data + (RESTORE_VM, _ACTIVE, _RESUMING) + | + At the end, .load_cleanup is called for each device and vCPUs are started + (RUNNING, _NONE, _RUNNING) + +Postcopy +======== + +Postcopy migration is currently not supported for VFIO devices. diff --git a/docs/devel/writing-qmp-commands.txt b/docs/devel/writing-qmp-commands.rst similarity index 61% rename from docs/devel/writing-qmp-commands.txt rename to docs/devel/writing-qmp-commands.rst index b1e31d56c0..6a10a06c48 100644 --- a/docs/devel/writing-qmp-commands.txt +++ b/docs/devel/writing-qmp-commands.rst @@ -1,4 +1,5 @@ -= How to write QMP commands using the QAPI framework = +How to write QMP commands using the QAPI framework +================================================== This document is a step-by-step guide on how to write new QMP commands using the QAPI framework. It also shows how to implement new style HMP commands. @@ -10,7 +11,9 @@ For an in-depth introduction to the QAPI framework, please refer to docs/devel/qapi-code-gen.txt. For documentation about the QMP protocol, start with docs/interop/qmp-intro.txt. -== Overview == + +Overview +-------- Generally speaking, the following steps should be taken in order to write a new QMP command. @@ -31,55 +34,59 @@ new QMP command. The following sections will demonstrate each of the steps above. We will start very simple and get more complex as we progress. -=== Testing === + +Testing +------- For all the examples in the next sections, the test setup is the same and is shown here. -First, QEMU should be started like this: +First, QEMU should be started like this:: -# qemu-system-TARGET [...] \ - -chardev socket,id=qmp,port=4444,host=localhost,server=on \ - -mon chardev=qmp,mode=control,pretty=on + # qemu-system-TARGET [...] \ + -chardev socket,id=qmp,port=4444,host=localhost,server=on \ + -mon chardev=qmp,mode=control,pretty=on -Then, in a different terminal: +Then, in a different terminal:: -$ telnet localhost 4444 -Trying 127.0.0.1... -Connected to localhost. -Escape character is '^]'. -{ - "QMP": { - "version": { - "qemu": { - "micro": 50, - "minor": 15, - "major": 0 - }, - "package": "" - }, - "capabilities": [ - ] - } -} + $ telnet localhost 4444 + Trying 127.0.0.1... + Connected to localhost. + Escape character is '^]'. + { + "QMP": { + "version": { + "qemu": { + "micro": 50, + "minor": 15, + "major": 0 + }, + "package": "" + }, + "capabilities": [ + ] + } + } The above output is the QMP server saying you're connected. The server is -actually in capabilities negotiation mode. To enter in command mode type: +actually in capabilities negotiation mode. To enter in command mode type:: -{ "execute": "qmp_capabilities" } + { "execute": "qmp_capabilities" } -Then the server should respond: +Then the server should respond:: -{ - "return": { - } -} + { + "return": { + } + } Which is QMP's way of saying "the latest command executed OK and didn't return any data". Now you're ready to enter the QMP example commands as explained in the following sections. -== Writing a command that doesn't return data == + +Writing a command that doesn't return data +------------------------------------------ That's the most simple QMP command that can be written. Usually, this kind of command carries some meaningful action in QEMU but here it will just print @@ -90,9 +97,9 @@ return any data. The first step is defining the command in the appropriate QAPI schema module. We pick module qapi/misc.json, and add the following line at -the bottom: +the bottom:: -{ 'command': 'hello-world' } + { 'command': 'hello-world' } The "command" keyword defines a new QMP command. It's an JSON object. All schema entries are JSON objects. The line above will instruct the QAPI to @@ -102,19 +109,19 @@ protocol data. The next step is to write the "hello-world" implementation. As explained earlier, it's preferable for commands to live in QEMU subsystems. But "hello-world" doesn't pertain to any, so we put its implementation in -monitor/qmp-cmds.c: +monitor/qmp-cmds.c:: -void qmp_hello_world(Error **errp) -{ - printf("Hello, world!\n"); -} + void qmp_hello_world(Error **errp) + { + printf("Hello, world!\n"); + } There are a few things to be noticed: -1. QMP command implementation functions must be prefixed with "qmp_" +1. QMP command implementation functions must be prefixed with "qmp\_" 2. qmp_hello_world() returns void, this is in accordance with the fact that the command doesn't return any data -3. It takes an "Error **" argument. This is required. Later we will see how to +3. It takes an "Error \*\*" argument. This is required. Later we will see how to return errors and take additional arguments. The Error argument should not be touched if the command doesn't return errors 4. We won't add the function's prototype. That's automatically done by the QAPI @@ -122,23 +129,25 @@ There are a few things to be noticed: because it's the easiest way to demonstrate a QMP command You're done. Now build qemu, run it as suggested in the "Testing" section, -and then type the following QMP command: +and then type the following QMP command:: -{ "execute": "hello-world" } + { "execute": "hello-world" } Then check the terminal running qemu and look for the "Hello, world" string. If you don't see it then something went wrong. -=== Arguments === + +Arguments +~~~~~~~~~ Let's add an argument called "message" to our "hello-world" command. The new argument will contain the string to be printed to stdout. It's an optional argument, if it's not present we print our default "Hello, World" string. The first change we have to do is to modify the command specification in the -schema file to the following: +schema file to the following:: -{ 'command': 'hello-world', 'data': { '*message': 'str' } } + { 'command': 'hello-world', 'data': { '*message': 'str' } } Notice the new 'data' member in the schema. It's an JSON object whose each element is an argument to the command in question. Also notice the asterisk, @@ -147,80 +156,82 @@ for mandatory arguments). Finally, 'str' is the argument's type, which stands for "string". The QAPI also supports integers, booleans, enumerations and user defined types. -Now, let's update our C implementation in monitor/qmp-cmds.c: +Now, let's update our C implementation in monitor/qmp-cmds.c:: -void qmp_hello_world(bool has_message, const char *message, Error **errp) -{ - if (has_message) { - printf("%s\n", message); - } else { - printf("Hello, world\n"); - } -} + void qmp_hello_world(bool has_message, const char *message, Error **errp) + { + if (has_message) { + printf("%s\n", message); + } else { + printf("Hello, world\n"); + } + } There are two important details to be noticed: -1. All optional arguments are accompanied by a 'has_' boolean, which is set +1. All optional arguments are accompanied by a 'has\_' boolean, which is set if the optional argument is present or false otherwise 2. The C implementation signature must follow the schema's argument ordering, which is defined by the "data" member Time to test our new version of the "hello-world" command. Build qemu, run it as -described in the "Testing" section and then send two commands: +described in the "Testing" section and then send two commands:: -{ "execute": "hello-world" } -{ - "return": { - } -} + { "execute": "hello-world" } + { + "return": { + } + } -{ "execute": "hello-world", "arguments": { "message": "We love qemu" } } -{ - "return": { - } -} + { "execute": "hello-world", "arguments": { "message": "We love qemu" } } + { + "return": { + } + } You should see "Hello, world" and "We love qemu" in the terminal running qemu, if you don't see these strings, then something went wrong. -=== Errors === + +Errors +~~~~~~ QMP commands should use the error interface exported by the error.h header file. Basically, most errors are set by calling the error_setg() function. Let's say we don't accept the string "message" to contain the word "love". If -it does contain it, we want the "hello-world" command to return an error: +it does contain it, we want the "hello-world" command to return an error:: -void qmp_hello_world(bool has_message, const char *message, Error **errp) -{ - if (has_message) { - if (strstr(message, "love")) { - error_setg(errp, "the word 'love' is not allowed"); - return; - } - printf("%s\n", message); - } else { - printf("Hello, world\n"); - } -} + void qmp_hello_world(bool has_message, const char *message, Error **errp) + { + if (has_message) { + if (strstr(message, "love")) { + error_setg(errp, "the word 'love' is not allowed"); + return; + } + printf("%s\n", message); + } else { + printf("Hello, world\n"); + } + } The first argument to the error_setg() function is the Error pointer to pointer, which is passed to all QMP functions. The next argument is a human description of the error, this is a free-form printf-like string. Let's test the example above. Build qemu, run it as defined in the "Testing" -section, and then issue the following command: +section, and then issue the following command:: -{ "execute": "hello-world", "arguments": { "message": "all you need is love" } } + { "execute": "hello-world", "arguments": { "message": "all you need is love" } } -The QMP server's response should be: +The QMP server's response should be:: -{ - "error": { - "class": "GenericError", - "desc": "the word 'love' is not allowed" - } -} + { + "error": { + "class": "GenericError", + "desc": "the word 'love' is not allowed" + } + } Note that error_setg() produces a "GenericError" class. In general, all QMP errors should have that error class. There are two exceptions @@ -234,34 +245,38 @@ to this rule: If the failure you want to report falls into one of the two cases above, use error_set() with a second argument of an ErrorClass value. -=== Command Documentation === + +Command Documentation +~~~~~~~~~~~~~~~~~~~~~ There's only one step missing to make "hello-world"'s implementation complete, and that's its documentation in the schema file. There are many examples of such documentation in the schema file already, but -here goes "hello-world"'s new entry for qapi/misc.json: +here goes "hello-world"'s new entry for qapi/misc.json:: -## -# @hello-world: -# -# Print a client provided string to the standard output stream. -# -# @message: string to be printed -# -# Returns: Nothing on success. -# -# Notes: if @message is not provided, the "Hello, world" string will -# be printed instead -# -# Since: -## -{ 'command': 'hello-world', 'data': { '*message': 'str' } } + ## + # @hello-world: + # + # Print a client provided string to the standard output stream. + # + # @message: string to be printed + # + # Returns: Nothing on success. + # + # Notes: if @message is not provided, the "Hello, world" string will + # be printed instead + # + # Since: + ## + { 'command': 'hello-world', 'data': { '*message': 'str' } } Please, note that the "Returns" clause is optional if a command doesn't return any data nor any errors. -=== Implementing the HMP command === + +Implementing the HMP command +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Now that the QMP command is in place, we can also make it available in the human monitor (HMP). @@ -270,20 +285,20 @@ With the introduction of the QAPI, HMP commands make QMP calls. Most of the time HMP commands are simple wrappers. All HMP commands implementation exist in the monitor/hmp-cmds.c file. -Here's the implementation of the "hello-world" HMP command: +Here's the implementation of the "hello-world" HMP command:: -void hmp_hello_world(Monitor *mon, const QDict *qdict) -{ - const char *message = qdict_get_try_str(qdict, "message"); - Error *err = NULL; + void hmp_hello_world(Monitor *mon, const QDict *qdict) + { + const char *message = qdict_get_try_str(qdict, "message"); + Error *err = NULL; - qmp_hello_world(!!message, message, &err); - if (err) { - monitor_printf(mon, "%s\n", error_get_pretty(err)); - error_free(err); - return; - } -} + qmp_hello_world(!!message, message, &err); + if (err) { + monitor_printf(mon, "%s\n", error_get_pretty(err)); + error_free(err); + return; + } + } Also, you have to add the function's prototype to the hmp.h file. @@ -299,7 +314,7 @@ There are three important points to be noticed: QMP call There's one last step to actually make the command available to monitor users, -we should add it to the hmp-commands.hx file: +we should add it to the hmp-commands.hx file:: { .name = "hello-world", @@ -309,11 +324,13 @@ we should add it to the hmp-commands.hx file: .cmd = hmp_hello_world, }, -STEXI -@item hello_world @var{message} -@findex hello_world -Print message to the standard output -ETEXI +:: + + STEXI + @item hello_world @var{message} + @findex hello_world + Print message to the standard output + ETEXI To test this you have to open a user monitor and issue the "hello-world" command. It might be instructive to check the command's documentation with @@ -322,7 +339,9 @@ HMP's "help" command. Please, check the "-monitor" command-line option to know how to open a user monitor. -== Writing a command that returns data == + +Writing a command that returns data +----------------------------------- A QMP command is capable of returning any data the QAPI supports like integers, strings, booleans, enumerations and user defined types. @@ -330,7 +349,9 @@ strings, booleans, enumerations and user defined types. In this section we will focus on user defined types. Please, check the QAPI documentation for information about the other types. -=== User Defined Types === + +User Defined Types +~~~~~~~~~~~~~~~~~~ FIXME This example needs to be redone after commit 6d32717 @@ -344,63 +365,63 @@ returned as a string, the latter is an integer in nanoseconds (which is not very useful in practice, as the timer has probably already fired when the information reaches the client). -The best way to return that data is to create a new QAPI type, as shown below: +The best way to return that data is to create a new QAPI type, as shown below:: -## -# @QemuAlarmClock -# -# QEMU alarm clock information. -# -# @clock-name: The alarm clock method's name. -# -# @next-deadline: The time (in nanoseconds) the next alarm will fire. -# -# Since: 1.0 -## -{ 'type': 'QemuAlarmClock', - 'data': { 'clock-name': 'str', '*next-deadline': 'int' } } + ## + # @QemuAlarmClock + # + # QEMU alarm clock information. + # + # @clock-name: The alarm clock method's name. + # + # @next-deadline: The time (in nanoseconds) the next alarm will fire. + # + # Since: 1.0 + ## + { 'type': 'QemuAlarmClock', + 'data': { 'clock-name': 'str', '*next-deadline': 'int' } } The "type" keyword defines a new QAPI type. Its "data" member contains the type's members. In this example our members are the "clock-name" and the "next-deadline" one, which is optional. -Now let's define the query-alarm-clock command: +Now let's define the query-alarm-clock command:: -## -# @query-alarm-clock -# -# Return information about QEMU's alarm clock. -# -# Returns a @QemuAlarmClock instance describing the alarm clock method -# being currently used by QEMU (this is usually set by the '-clock' -# command-line option). -# -# Since: 1.0 -## -{ 'command': 'query-alarm-clock', 'returns': 'QemuAlarmClock' } + ## + # @query-alarm-clock + # + # Return information about QEMU's alarm clock. + # + # Returns a @QemuAlarmClock instance describing the alarm clock method + # being currently used by QEMU (this is usually set by the '-clock' + # command-line option). + # + # Since: 1.0 + ## + { 'command': 'query-alarm-clock', 'returns': 'QemuAlarmClock' } Notice the "returns" keyword. As its name suggests, it's used to define the data returned by a command. It's time to implement the qmp_query_alarm_clock() function, you can put it -in the qemu-timer.c file: +in the qemu-timer.c file:: -QemuAlarmClock *qmp_query_alarm_clock(Error **errp) -{ - QemuAlarmClock *clock; - int64_t deadline; + QemuAlarmClock *qmp_query_alarm_clock(Error **errp) + { + QemuAlarmClock *clock; + int64_t deadline; - clock = g_malloc0(sizeof(*clock)); + clock = g_malloc0(sizeof(*clock)); - deadline = qemu_next_alarm_deadline(); - if (deadline > 0) { - clock->has_next_deadline = true; - clock->next_deadline = deadline; - } - clock->clock_name = g_strdup(alarm_timer->name); + deadline = qemu_next_alarm_deadline(); + if (deadline > 0) { + clock->has_next_deadline = true; + clock->next_deadline = deadline; + } + clock->clock_name = g_strdup(alarm_timer->name); - return clock; -} + return clock; + } There are a number of things to be noticed: @@ -423,40 +444,42 @@ There are a number of things to be noticed: 6. You have to include "qapi/qapi-commands-misc.h" in qemu-timer.c Time to test the new command. Build qemu, run it as described in the "Testing" -section and try this: +section and try this:: -{ "execute": "query-alarm-clock" } -{ - "return": { - "next-deadline": 2368219, - "clock-name": "dynticks" - } -} + { "execute": "query-alarm-clock" } + { + "return": { + "next-deadline": 2368219, + "clock-name": "dynticks" + } + } -==== The HMP command ==== -Here's the HMP counterpart of the query-alarm-clock command: +The HMP command +~~~~~~~~~~~~~~~ -void hmp_info_alarm_clock(Monitor *mon) -{ - QemuAlarmClock *clock; - Error *err = NULL; +Here's the HMP counterpart of the query-alarm-clock command:: - clock = qmp_query_alarm_clock(&err); - if (err) { - monitor_printf(mon, "Could not query alarm clock information\n"); - error_free(err); - return; - } + void hmp_info_alarm_clock(Monitor *mon) + { + QemuAlarmClock *clock; + Error *err = NULL; - monitor_printf(mon, "Alarm clock method in use: '%s'\n", clock->clock_name); - if (clock->has_next_deadline) { - monitor_printf(mon, "Next alarm will fire in %" PRId64 " nanoseconds\n", - clock->next_deadline); - } + clock = qmp_query_alarm_clock(&err); + if (err) { + monitor_printf(mon, "Could not query alarm clock information\n"); + error_free(err); + return; + } - qapi_free_QemuAlarmClock(clock); -} + monitor_printf(mon, "Alarm clock method in use: '%s'\n", clock->clock_name); + if (clock->has_next_deadline) { + monitor_printf(mon, "Next alarm will fire in %" PRId64 " nanoseconds\n", + clock->next_deadline); + } + + qapi_free_QemuAlarmClock(clock); + } It's important to notice that hmp_info_alarm_clock() calls qapi_free_QemuAlarmClock() to free the data returned by qmp_query_alarm_clock(). @@ -471,7 +494,7 @@ it's good practice to always check for errors. Another important detail is that HMP's "info" commands don't go into the hmp-commands.hx. Instead, they go into the info_cmds[] table, which is defined -in the monitor/misc.c file. The entry for the "info alarmclock" follows: +in the monitor/misc.c file. The entry for the "info alarmclock" follows:: { .name = "alarmclock", @@ -483,63 +506,65 @@ in the monitor/misc.c file. The entry for the "info alarmclock" follows: To test this, run qemu and type "info alarmclock" in the user monitor. -=== Returning Lists === + +Returning Lists +~~~~~~~~~~~~~~~ For this example, we're going to return all available methods for the timer alarm, which is pretty much what the command-line option "-clock ?" does, except that we're also going to inform which method is in use. -This first step is to define a new type: +This first step is to define a new type:: -## -# @TimerAlarmMethod -# -# Timer alarm method information. -# -# @method-name: The method's name. -# -# @current: true if this alarm method is currently in use, false otherwise -# -# Since: 1.0 -## -{ 'type': 'TimerAlarmMethod', - 'data': { 'method-name': 'str', 'current': 'bool' } } + ## + # @TimerAlarmMethod + # + # Timer alarm method information. + # + # @method-name: The method's name. + # + # @current: true if this alarm method is currently in use, false otherwise + # + # Since: 1.0 + ## + { 'type': 'TimerAlarmMethod', + 'data': { 'method-name': 'str', 'current': 'bool' } } The command will be called "query-alarm-methods", here is its schema -specification: +specification:: -## -# @query-alarm-methods -# -# Returns information about available alarm methods. -# -# Returns: a list of @TimerAlarmMethod for each method -# -# Since: 1.0 -## -{ 'command': 'query-alarm-methods', 'returns': ['TimerAlarmMethod'] } + ## + # @query-alarm-methods + # + # Returns information about available alarm methods. + # + # Returns: a list of @TimerAlarmMethod for each method + # + # Since: 1.0 + ## + { 'command': 'query-alarm-methods', 'returns': ['TimerAlarmMethod'] } Notice the syntax for returning lists "'returns': ['TimerAlarmMethod']", this should be read as "returns a list of TimerAlarmMethod instances". -The C implementation follows: +The C implementation follows:: -TimerAlarmMethodList *qmp_query_alarm_methods(Error **errp) -{ - TimerAlarmMethodList *method_list = NULL; - const struct qemu_alarm_timer *p; - bool current = true; + TimerAlarmMethodList *qmp_query_alarm_methods(Error **errp) + { + TimerAlarmMethodList *method_list = NULL; + const struct qemu_alarm_timer *p; + bool current = true; - for (p = alarm_timers; p->name; p++) { - TimerAlarmMethod *value = g_malloc0(*value); - value->method_name = g_strdup(p->name); - value->current = current; - QAPI_LIST_PREPEND(method_list, value); - current = false; - } + for (p = alarm_timers; p->name; p++) { + TimerAlarmMethod *value = g_malloc0(*value); + value->method_name = g_strdup(p->name); + value->current = current; + QAPI_LIST_PREPEND(method_list, value); + current = false; + } - return method_list; -} + return method_list; + } The most important difference from the previous examples is the TimerAlarmMethodList type, which is automatically generated by the QAPI from @@ -557,41 +582,41 @@ first element of the alarm_timers array. Also notice that QAPI lists are handled by hand and we return the head of the list. Now Build qemu, run it as explained in the "Testing" section and try our new -command: +command:: -{ "execute": "query-alarm-methods" } -{ - "return": [ - { - "current": false, - "method-name": "unix" - }, - { - "current": true, - "method-name": "dynticks" - } - ] -} + { "execute": "query-alarm-methods" } + { + "return": [ + { + "current": false, + "method-name": "unix" + }, + { + "current": true, + "method-name": "dynticks" + } + ] + } The HMP counterpart is a bit more complex than previous examples because it -has to traverse the list, it's shown below for reference: +has to traverse the list, it's shown below for reference:: -void hmp_info_alarm_methods(Monitor *mon) -{ - TimerAlarmMethodList *method_list, *method; - Error *err = NULL; + void hmp_info_alarm_methods(Monitor *mon) + { + TimerAlarmMethodList *method_list, *method; + Error *err = NULL; - method_list = qmp_query_alarm_methods(&err); - if (err) { - monitor_printf(mon, "Could not query alarm methods\n"); - error_free(err); - return; - } + method_list = qmp_query_alarm_methods(&err); + if (err) { + monitor_printf(mon, "Could not query alarm methods\n"); + error_free(err); + return; + } - for (method = method_list; method; method = method->next) { - monitor_printf(mon, "%c %s\n", method->value->current ? '*' : ' ', - method->value->method_name); - } + for (method = method_list; method; method = method->next) { + monitor_printf(mon, "%c %s\n", method->value->current ? '*' : ' ', + method->value->method_name); + } - qapi_free_TimerAlarmMethodList(method_list); -} + qapi_free_TimerAlarmMethodList(method_list); + } diff --git a/docs/hyperv.txt b/docs/hyperv.txt index e53c581f45..000638a2fd 100644 --- a/docs/hyperv.txt +++ b/docs/hyperv.txt @@ -170,7 +170,7 @@ Recommended: hv-frequencies 3.16. hv-evmcs =============== The enlightenment is nested specific, it targets Hyper-V on KVM guests. When -enabled, it provides Enlightened VMCS feature to the guest. The feature +enabled, it provides Enlightened VMCS version 1 feature to the guest. The feature implements paravirtualized protocol between L0 (KVM) and L1 (Hyper-V) hypervisors making L2 exits to the hypervisor faster. The feature is Intel-only. Note: some virtualization features (e.g. Posted Interrupts) are disabled when @@ -209,8 +209,11 @@ In some cases (e.g. during development) it may make sense to use QEMU in 'pass-through' mode and give Windows guests all enlightenments currently supported by KVM. This pass-through mode is enabled by "hv-passthrough" CPU flag. -Note: enabling this flag effectively prevents migration as supported features -may differ between target and destination. +Note: "hv-passthrough" flag only enables enlightenments which are known to QEMU +(have corresponding "hv-*" flag) and copies "hv-spinlocks="/"hv-vendor-id=" +values from KVM to QEMU. "hv-passthrough" overrides all other "hv-*" settings on +the command line. Also, enabling this flag effectively prevents migration as the +list of enabled enlightenments may differ between target and destination hosts. 4. Useful links diff --git a/docs/index.rst b/docs/index.rst index 763e3d0426..5f7eaaa632 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -10,6 +10,7 @@ Welcome to QEMU's documentation! :maxdepth: 2 :caption: Contents: + about/index system/index user/index tools/index diff --git a/docs/interop/_templates/editpage.html b/docs/interop/_templates/editpage.html deleted file mode 100644 index 215e562681..0000000000 --- a/docs/interop/_templates/editpage.html +++ /dev/null @@ -1,5 +0,0 @@ -
- -
diff --git a/docs/interop/barrier.rst b/docs/interop/barrier.rst new file mode 100644 index 0000000000..055f2c1aef --- /dev/null +++ b/docs/interop/barrier.rst @@ -0,0 +1,426 @@ +Barrier client protocol +======================= + +QEMU's ``input-barrier`` device implements the client end of +the KVM (Keyboard-Video-Mouse) software +`Barrier `__. + +This document briefly describes the protocol as we implement it. + +Message format +-------------- + +Message format between the server and client is in two parts: + +#. the payload length, a 32bit integer in network endianness +#. the payload + +The payload starts with a 4byte string (without NUL) which is the +command. The first command between the server and the client +is the only command not encoded on 4 bytes ("Barrier"). +The remaining part of the payload is decoded according to the command. + +Protocol Description +-------------------- + +This comes from ``barrier/src/lib/barrier/protocol_types.h``. + +barrierCmdHello "Barrier" +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int16_t minor, int16_t major }`` +Description: + Say hello to client + + ``minor`` = protocol major version number supported by server + + ``major`` = protocol minor version number supported by server + +barrierCmdHelloBack "Barrier" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + client ->server +Parameters: + ``{ int16_t minor, int16_t major, char *name}`` +Description: + Respond to hello from server + + ``minor`` = protocol major version number supported by client + + ``major`` = protocol minor version number supported by client + + ``name`` = client name + +barrierCmdDInfo "DINF" +^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + client ->server +Parameters: + ``{ int16_t x_origin, int16_t y_origin, int16_t width, int16_t height, int16_t x, int16_t y}`` +Description: + The client screen must send this message in response to the + barrierCmdQInfo message. It must also send this message when the + screen's resolution changes. In this case, the client screen should + ignore any barrierCmdDMouseMove messages until it receives a + barrierCmdCInfoAck in order to prevent attempts to move the mouse off + the new screen area. + +barrierCmdCNoop "CNOP" +^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + client -> server +Parameters: + None +Description: + No operation + +barrierCmdCClose "CBYE" +^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + None +Description: + Close connection + +barrierCmdCEnter "CINN" +^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int16_t x, int16_t y, int32_t seq, int16_t modifier }`` +Description: + Enter screen. + + ``x``, ``y`` = entering screen absolute coordinates + + ``seq`` = sequence number, which is used to order messages between + screens. the secondary screen must return this number + with some messages + + ``modifier`` = modifier key mask. this will have bits set for each + toggle modifier key that is activated on entry to the + screen. the secondary screen should adjust its toggle + modifiers to reflect that state. + +barrierCmdCLeave "COUT" +^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + None +Description: + Leaving screen. the secondary screen should send clipboard data in + response to this message for those clipboards that it has grabbed + (i.e. has sent a barrierCmdCClipboard for and has not received a + barrierCmdCClipboard for with a greater sequence number) and that + were grabbed or have changed since the last leave. + +barrierCmdCClipboard "CCLP" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int8_t id, int32_t seq }`` +Description: + Grab clipboard. Sent by screen when some other app on that screen + grabs a clipboard. + + ``id`` = the clipboard identifier + + ``seq`` = sequence number. Client must use the sequence number passed in + the most recent barrierCmdCEnter. the server always sends 0. + +barrierCmdCScreenSaver "CSEC" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int8_t started }`` +Description: + Screensaver change. + + ``started`` = Screensaver on primary has started (1) or closed (0) + +barrierCmdCResetOptions "CROP" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + None +Description: + Reset options. Client should reset all of its options to their + defaults. + +barrierCmdCInfoAck "CIAK" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + None +Description: + Resolution change acknowledgment. Sent by server in response to a + client screen's barrierCmdDInfo. This is sent for every + barrierCmdDInfo, whether or not the server had sent a barrierCmdQInfo. + +barrierCmdCKeepAlive "CALV" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + None +Description: + Keep connection alive. Sent by the server periodically to verify + that connections are still up and running. clients must reply in + kind on receipt. if the server gets an error sending the message or + does not receive a reply within a reasonable time then the server + disconnects the client. if the client doesn't receive these (or any + message) periodically then it should disconnect from the server. the + appropriate interval is defined by an option. + +barrierCmdDKeyDown "DKDN" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int16_t keyid, int16_t modifier [,int16_t button] }`` +Description: + Key pressed. + + ``keyid`` = X11 key id + + ``modified`` = modified mask + + ``button`` = X11 Xkb keycode (optional) + +barrierCmdDKeyRepeat "DKRP" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int16_t keyid, int16_t modifier, int16_t repeat [,int16_t button] }`` +Description: + Key auto-repeat. + + ``keyid`` = X11 key id + + ``modified`` = modified mask + + ``repeat`` = number of repeats + + ``button`` = X11 Xkb keycode (optional) + +barrierCmdDKeyUp "DKUP" +^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int16_t keyid, int16_t modifier [,int16_t button] }`` +Description: + Key released. + + ``keyid`` = X11 key id + + ``modified`` = modified mask + + ``button`` = X11 Xkb keycode (optional) + +barrierCmdDMouseDown "DMDN" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int8_t button }`` +Description: + Mouse button pressed. + + ``button`` = button id + +barrierCmdDMouseUp "DMUP" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int8_t button }`` +Description: + Mouse button release. + + ``button`` = button id + +barrierCmdDMouseMove "DMMV" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int16_t x, int16_t y }`` +Description: + Absolute mouse moved. + + ``x``, ``y`` = absolute screen coordinates + +barrierCmdDMouseRelMove "DMRM" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int16_t x, int16_t y }`` +Description: + Relative mouse moved. + + ``x``, ``y`` = r relative screen coordinates + +barrierCmdDMouseWheel "DMWM" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int16_t x , int16_t y }`` or ``{ int16_t y }`` +Description: + Mouse scroll. The delta should be +120 for one tick forward (away + from the user) or right and -120 for one tick backward (toward the + user) or left. + + ``x`` = x delta + + ``y`` = y delta + +barrierCmdDClipboard "DCLP" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int8_t id, int32_t seq, int8_t mark, char *data }`` +Description: + Clipboard data. + + ``id`` = clipboard id + + ``seq`` = sequence number. The sequence number is 0 when sent by the + server. Client screens should use the/ sequence number from + the most recent barrierCmdCEnter. + +barrierCmdDSetOptions "DSOP" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int32 t nb, { int32_t id, int32_t val }[] }`` +Description: + Set options. Client should set the given option/value pairs. + + ``nb`` = numbers of ``{ id, val }`` entries + + ``id`` = option id + + ``val`` = option new value + +barrierCmdDFileTransfer "DFTR" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int8_t mark, char *content }`` +Description: + Transfer file data. + + * ``mark`` = 0 means the content followed is the file size + * 1 means the content followed is the chunk data + * 2 means the file transfer is finished + +barrierCmdDDragInfo "DDRG" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int16_t nb, char *content }`` +Description: + Drag information. + + ``nb`` = number of dragging objects + + ``content`` = object's directory + +barrierCmdQInfo "QINF" +^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + None +Description: + Query screen info + + Client should reply with a barrierCmdDInfo + +barrierCmdEIncompatible "EICV" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + ``{ int16_t nb, major *minor }`` +Description: + Incompatible version. + + ``major`` = major version + + ``minor`` = minor version + +barrierCmdEBusy "EBSY" +^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + None +Description: + Name provided when connecting is already in use. + +barrierCmdEUnknown "EUNK" +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + None +Description: + Unknown client. Name provided when connecting is not in primary's + screen configuration map. + +barrierCmdEBad "EBAD" +^^^^^^^^^^^^^^^^^^^^^^^ + +Direction: + server -> client +Parameters: + None +Description: + Protocol violation. Server should disconnect after sending this + message. + diff --git a/docs/interop/firmware.json b/docs/interop/firmware.json index 9d94ccafa9..8d8b0be030 100644 --- a/docs/interop/firmware.json +++ b/docs/interop/firmware.json @@ -115,6 +115,12 @@ # this feature are documented in # "docs/amd-memory-encryption.txt". # +# @amd-sev-es: The firmware supports running under AMD Secure Encrypted +# Virtualization - Encrypted State, as specified in the AMD64 +# Architecture Programmer's Manual. QEMU command line options +# related to this feature are documented in +# "docs/amd-memory-encryption.txt". +# # @enrolled-keys: The variable store (NVRAM) template associated with # the firmware binary has the UEFI Secure Boot # operational mode turned on, with certificates @@ -179,7 +185,7 @@ # Since: 3.0 ## { 'enum' : 'FirmwareFeature', - 'data' : [ 'acpi-s3', 'acpi-s4', 'amd-sev', 'enrolled-keys', + 'data' : [ 'acpi-s3', 'acpi-s4', 'amd-sev', 'amd-sev-es', 'enrolled-keys', 'requires-smm', 'secure-boot', 'verbose-dynamic', 'verbose-static' ] } @@ -504,6 +510,45 @@ # } # # { +# "description": "OVMF with SEV-ES support", +# "interface-types": [ +# "uefi" +# ], +# "mapping": { +# "device": "flash", +# "executable": { +# "filename": "/usr/share/OVMF/OVMF_CODE.fd", +# "format": "raw" +# }, +# "nvram-template": { +# "filename": "/usr/share/OVMF/OVMF_VARS.fd", +# "format": "raw" +# } +# }, +# "targets": [ +# { +# "architecture": "x86_64", +# "machines": [ +# "pc-q35-*" +# ] +# } +# ], +# "features": [ +# "acpi-s3", +# "amd-sev", +# "amd-sev-es", +# "verbose-dynamic" +# ], +# "tags": [ +# "-a X64", +# "-p OvmfPkg/OvmfPkgX64.dsc", +# "-t GCC48", +# "-b DEBUG", +# "-D FD_SIZE_4MB" +# ] +# } +# +# { # "description": "UEFI firmware for ARM64 virtual machines", # "interface-types": [ # "uefi" diff --git a/docs/interop/index.rst b/docs/interop/index.rst index 219a5e5fc5..f9801a9c20 100644 --- a/docs/interop/index.rst +++ b/docs/interop/index.rst @@ -1,17 +1,13 @@ -.. This is the top level page for the 'interop' manual. - - System Emulation Management and Interoperability ================================================ -This manual contains documents and specifications that are useful -for making QEMU interoperate with other software. - -Contents: +This section of the manual contains documents and specifications that +are useful for making QEMU interoperate with other software. .. toctree:: :maxdepth: 2 + barrier bitmaps dbus dbus-vmstate diff --git a/docs/interop/live-block-operations.rst b/docs/interop/live-block-operations.rst index 1073b930dc..9e3635b233 100644 --- a/docs/interop/live-block-operations.rst +++ b/docs/interop/live-block-operations.rst @@ -127,13 +127,15 @@ Interacting with a QEMU instance To show some example invocations of command-line, we will use the following invocation of QEMU, with a QMP server running over UNIX -socket:: +socket: - $ ./qemu-system-x86_64 -display none -no-user-config \ - -M q35 -nodefaults -m 512 \ - -blockdev node-name=node-A,driver=qcow2,file.driver=file,file.node-name=file,file.filename=./a.qcow2 \ - -device virtio-blk,drive=node-A,id=virtio0 \ - -monitor stdio -qmp unix:/tmp/qmp-sock,server=on,wait=off +.. parsed-literal:: + + $ |qemu_system| -display none -no-user-config -nodefaults \\ + -m 512 -blockdev \\ + node-name=node-A,driver=qcow2,file.driver=file,file.node-name=file,file.filename=./a.qcow2 \\ + -device virtio-blk,drive=node-A,id=virtio0 \\ + -monitor stdio -qmp unix:/tmp/qmp-sock,server=on,wait=off The ``-blockdev`` command-line option, used above, is available from QEMU 2.9 onwards. In the above invocation, notice the ``node-name`` @@ -692,14 +694,16 @@ And start the destination QEMU (we already have the source QEMU running -- discussed in the section: `Interacting with a QEMU instance`_) instance, with the following invocation. (As noted earlier, for simplicity's sake, the destination QEMU is started on the same host, but -it could be located elsewhere):: +it could be located elsewhere): - $ ./qemu-system-x86_64 -display none -no-user-config \ - -M q35 -nodefaults -m 512 \ - -blockdev node-name=node-TargetDisk,driver=qcow2,file.driver=file,file.node-name=file,file.filename=./target-disk.qcow2 \ - -device virtio-blk,drive=node-TargetDisk,id=virtio0 \ - -S -monitor stdio -qmp unix:./qmp-sock2,server=on,wait=off \ - -incoming tcp:localhost:6666 +.. parsed-literal:: + + $ |qemu_system| -display none -no-user-config -nodefaults \\ + -m 512 -blockdev \\ + node-name=node-TargetDisk,driver=qcow2,file.driver=file,file.node-name=file,file.filename=./target-disk.qcow2 \\ + -device virtio-blk,drive=node-TargetDisk,id=virtio0 \\ + -S -monitor stdio -qmp unix:./qmp-sock2,server=on,wait=off \\ + -incoming tcp:localhost:6666 Given the disk image chain on source QEMU:: @@ -777,7 +781,7 @@ the content of image [D]. } (6) [On *destination* QEMU] Finally, resume the guest vCPUs by issuing the - QMP command `cont`:: + QMP command ``cont``:: (QEMU) cont { diff --git a/docs/interop/qemu-ga-ref.rst b/docs/interop/qemu-ga-ref.rst index 3f1c4f908f..032d492455 100644 --- a/docs/interop/qemu-ga-ref.rst +++ b/docs/interop/qemu-ga-ref.rst @@ -1,13 +1,7 @@ QEMU Guest Agent Protocol Reference =================================== -.. - TODO: the old Texinfo manual used to note that this manual - is GPL-v2-or-later. We should make that reader-visible - both here and in our Sphinx manuals more generally. - -.. - TODO: display the QEMU version, both here and in our Sphinx manuals - more generally. +.. contents:: + :depth: 3 .. qapi-doc:: qga/qapi-schema.json diff --git a/docs/interop/qemu-qmp-ref.rst b/docs/interop/qemu-qmp-ref.rst index c8abaaf8e3..357effd64f 100644 --- a/docs/interop/qemu-qmp-ref.rst +++ b/docs/interop/qemu-qmp-ref.rst @@ -1,13 +1,7 @@ QEMU QMP Reference Manual ========================= -.. - TODO: the old Texinfo manual used to note that this manual - is GPL-v2-or-later. We should make that reader-visible - both here and in our Sphinx manuals more generally. - -.. - TODO: display the QEMU version, both here and in our Sphinx manuals - more generally. +.. contents:: + :depth: 3 .. qapi-doc:: qapi/qapi-schema.json diff --git a/docs/interop/qemu-storage-daemon-qmp-ref.rst b/docs/interop/qemu-storage-daemon-qmp-ref.rst index caf9dad23a..9fed68152f 100644 --- a/docs/interop/qemu-storage-daemon-qmp-ref.rst +++ b/docs/interop/qemu-storage-daemon-qmp-ref.rst @@ -1,13 +1,7 @@ QEMU Storage Daemon QMP Reference Manual ======================================== -.. - TODO: the old Texinfo manual used to note that this manual - is GPL-v2-or-later. We should make that reader-visible - both here and in our Sphinx manuals more generally. - -.. - TODO: display the QEMU version, both here and in our Sphinx manuals - more generally. +.. contents:: + :depth: 3 .. qapi-doc:: storage-daemon/qapi/qapi-schema.json diff --git a/docs/interop/vhost-user-gpu.rst b/docs/interop/vhost-user-gpu.rst index 3268bf405c..71a2c52b31 100644 --- a/docs/interop/vhost-user-gpu.rst +++ b/docs/interop/vhost-user-gpu.rst @@ -2,9 +2,10 @@ Vhost-user-gpu Protocol ======================= -:Licence: This work is licensed under the terms of the GNU GPL, - version 2 or later. See the COPYING file in the top-level - directory. +.. + Licence: This work is licensed under the terms of the GNU GPL, + version 2 or later. See the COPYING file in the top-level + directory. .. contents:: Table of Contents diff --git a/docs/interop/vhost-user.rst b/docs/interop/vhost-user.rst index d6085f7045..edc3ad84a3 100644 --- a/docs/interop/vhost-user.rst +++ b/docs/interop/vhost-user.rst @@ -1,11 +1,15 @@ +.. _vhost_user_proto: + =================== Vhost-user Protocol =================== -:Copyright: 2014 Virtual Open Systems Sarl. -:Copyright: 2019 Intel Corporation -:Licence: This work is licensed under the terms of the GNU GPL, - version 2 or later. See the COPYING file in the top-level - directory. + +.. + Copyright 2014 Virtual Open Systems Sarl. + Copyright 2019 Intel Corporation + Licence: This work is licensed under the terms of the GNU GPL, + version 2 or later. See the COPYING file in the top-level + directory. .. contents:: Table of Contents diff --git a/docs/meson.build b/docs/meson.build index f84306ba7e..300b134329 100644 --- a/docs/meson.build +++ b/docs/meson.build @@ -27,10 +27,9 @@ if sphinx_build.found() build_docs = (sphinx_build_test_out.returncode() == 0) if not build_docs - warning('@0@ is either too old or uses too old a Python version' - .format(sphinx_build.full_path())) + warning('@0@: @1@'.format(sphinx_build.full_path(), sphinx_build_test_out.stderr())) if get_option('docs').enabled() - error('Install a Python 3 version of python-sphinx') + error('Install a Python 3 version of python-sphinx and the readthedoc theme') endif endif endif @@ -45,6 +44,7 @@ if build_docs meson.source_root() / 'docs/sphinx/qapidoc.py', meson.source_root() / 'docs/sphinx/qmp_lexer.py', qapi_gen_depends ] + sphinx_template_files = [ meson.source_root() / 'docs/_templates/footer.html' ] have_ga = have_tools and config_host.has_key('CONFIG_GUEST_AGENT') @@ -77,7 +77,7 @@ if build_docs output: 'docs.stamp', input: files('conf.py'), depfile: 'docs.d', - depend_files: sphinx_extn_depends, + depend_files: [ sphinx_extn_depends, sphinx_template_files ], command: [SPHINX_ARGS, '-Ddepfile=@DEPFILE@', '-Ddepfile_stamp=@OUTPUT0@', '-b', 'html', '-d', private_dir, diff --git a/docs/pcie_pci_bridge.txt b/docs/pcie_pci_bridge.txt index ab35ebf3ca..1aa08fc5f0 100644 --- a/docs/pcie_pci_bridge.txt +++ b/docs/pcie_pci_bridge.txt @@ -70,9 +70,9 @@ A detailed command line would be: [qemu-bin + storage options] \ -m 2G \ --device pcie-root-port,bus=pcie.0,id=rp1 \ --device pcie-root-port,bus=pcie.0,id=rp2 \ --device pcie-root-port,bus=pcie.0,id=rp3,bus-reserve=1 \ +-device pcie-root-port,bus=pcie.0,id=rp1,slot=1 \ +-device pcie-root-port,bus=pcie.0,id=rp2,slot=2 \ +-device pcie-root-port,bus=pcie.0,id=rp3,slot=3,bus-reserve=1 \ -device pcie-pci-bridge,id=br1,bus=rp1 \ -device pcie-pci-bridge,id=br2,bus=rp2 \ -device e1000,bus=br1,addr=8 diff --git a/docs/specs/_templates/editpage.html b/docs/specs/_templates/editpage.html deleted file mode 100644 index aaa468aa98..0000000000 --- a/docs/specs/_templates/editpage.html +++ /dev/null @@ -1,5 +0,0 @@ -
- -
diff --git a/docs/specs/index.rst b/docs/specs/index.rst index 7b08314d33..b7b08ea30d 100644 --- a/docs/specs/index.rst +++ b/docs/specs/index.rst @@ -1,11 +1,8 @@ -.. This is the top level page for the 'specs' manual - - System Emulation Guest Hardware Specifications ============================================== - -Contents: +This section of the manual contains specifications of +guest hardware that is specific to QEMU. .. toctree:: :maxdepth: 2 diff --git a/docs/sphinx-static/theme_overrides.css b/docs/sphinx-static/theme_overrides.css new file mode 100644 index 0000000000..c70ef95128 --- /dev/null +++ b/docs/sphinx-static/theme_overrides.css @@ -0,0 +1,161 @@ +/* -*- coding: utf-8; mode: css -*- + * + * Sphinx HTML theme customization: read the doc + * Based on Linux Documentation/sphinx-static/theme_overrides.css + */ + +/* Improve contrast and increase size for easier reading. */ + +body { + font-family: serif; + color: black; + font-size: 100%; +} + +h1, h2, .rst-content .toctree-wrapper p.caption, h3, h4, h5, h6, legend { + font-family: sans-serif; +} + +.rst-content dl:not(.docutils) dt { + border-top: none; + border-left: solid 3px #ccc; + background-color: #f0f0f0; + color: black; +} + +.wy-nav-top { + background: #802400; +} + +.wy-side-nav-search input[type="text"] { + border-color: #f60; +} + +.wy-menu-vertical p.caption { + color: white; +} + +.wy-menu-vertical li.current a { + color: #505050; +} + +.wy-menu-vertical li.on a, .wy-menu-vertical li.current > a { + color: #303030; +} + +.fa-gitlab { + box-shadow: 0 4px 8px 0 rgba(0,0,0,0.2), 0 3px 10px 0 rgba(0,0,0,0.19); + border-radius: 5px; +} + +div[class^="highlight"] pre { + font-family: monospace; + color: black; + font-size: 100%; +} + +.wy-menu-vertical { + font-family: sans-serif; +} + +.c { + font-style: normal; +} + +p { + font-size: 100%; +} + +/* Interim: Code-blocks with line nos - lines and line numbers don't line up. + * see: https://github.com/rtfd/sphinx_rtd_theme/issues/419 + */ + +div[class^="highlight"] pre { + line-height: normal; +} +.rst-content .highlight > pre { + line-height: normal; +} + +/* Keep fields from being strangely far apart due to inheirited table CSS. */ +.rst-content table.field-list th.field-name { + padding-top: 1px; + padding-bottom: 1px; +} +.rst-content table.field-list td.field-body { + padding-top: 1px; + padding-bottom: 1px; +} + +@media screen { + + /* content column + * + * RTD theme's default is 800px as max width for the content, but we have + * tables with tons of columns, which need the full width of the view-port. + */ + + .wy-nav-content{max-width: none; } + + /* table: + * + * - Sequences of whitespace should collapse into a single whitespace. + * - make the overflow auto (scrollbar if needed) + * - align caption "left" ("center" is unsuitable on vast tables) + */ + + .wy-table-responsive table td { white-space: normal; } + .wy-table-responsive { overflow: auto; } + .rst-content table.docutils caption { text-align: left; font-size: 100%; } + + /* captions: + * + * - captions should have 100% (not 85%) font size + * - hide the permalink symbol as long as link is not hovered + */ + + .toc-title { + font-size: 150%; + font-weight: bold; + } + + caption, .wy-table caption, .rst-content table.field-list caption { + font-size: 100%; + } + caption a.headerlink { opacity: 0; } + caption a.headerlink:hover { opacity: 1; } + + /* Menu selection and keystrokes */ + + span.menuselection { + color: blue; + font-family: "Courier New", Courier, monospace + } + + code.kbd, code.kbd span { + color: white; + background-color: darkblue; + font-weight: bold; + font-family: "Courier New", Courier, monospace + } + + /* fix bottom margin of lists items */ + + .rst-content .section ul li:last-child, .rst-content .section ul li p:last-child { + margin-bottom: 12px; + } + + /* inline literal: drop the borderbox, padding and red color */ + + code, .rst-content tt, .rst-content code { + color: inherit; + border: none; + padding: unset; + background: inherit; + font-size: 85%; + } + + .rst-content tt.literal,.rst-content tt.literal,.rst-content code.literal { + color: inherit; + } +} diff --git a/docs/sphinx/qapidoc.py b/docs/sphinx/qapidoc.py index b7a2d39c10..87c67ab23f 100644 --- a/docs/sphinx/qapidoc.py +++ b/docs/sphinx/qapidoc.py @@ -34,7 +34,8 @@ from sphinx.errors import ExtensionError from sphinx.util.nodes import nested_parse_with_titles import sphinx from qapi.gen import QAPISchemaVisitor -from qapi.schema import QAPIError, QAPISemError, QAPISchema +from qapi.error import QAPIError, QAPISemError +from qapi.schema import QAPISchema # Sphinx up to 1.6 uses AutodocReporter; 1.7 and later diff --git a/docs/system/_templates/editpage.html b/docs/system/_templates/editpage.html deleted file mode 100644 index 6586b2e257..0000000000 --- a/docs/system/_templates/editpage.html +++ /dev/null @@ -1,5 +0,0 @@ -
- -
diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst index d1fb8f25b3..cec87e3743 100644 --- a/docs/system/arm/aspeed.rst +++ b/docs/system/arm/aspeed.rst @@ -5,7 +5,7 @@ The QEMU Aspeed machines model BMCs of various OpenPOWER systems and Aspeed evaluation boards. They are based on different releases of the Aspeed SoC : the AST2400 integrating an ARM926EJ-S CPU (400MHz), the AST2500 with an ARM1176JZS CPU (800MHz) and more recently the AST2600 -with dual cores ARM Cortex A7 CPUs (1.2GHz). +with dual cores ARM Cortex-A7 CPUs (1.2GHz). The SoC comes with RAM, Gigabit ethernet, USB, SD/MMC, USB, SPI, I2C, etc. @@ -13,6 +13,7 @@ etc. AST2400 SoC based machines : - ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC +- ``quanta-q71l-bmc`` OpenBMC Quanta BMC AST2500 SoC based machines : @@ -24,7 +25,7 @@ AST2500 SoC based machines : AST2600 SoC based machines : -- ``ast2600-evb`` Aspeed AST2600 Evaluation board (Cortex A7) +- ``ast2600-evb`` Aspeed AST2600 Evaluation board (Cortex-A7) - ``tacoma-bmc`` OpenPOWER Witherspoon POWER9 AST2600 BMC Supported devices @@ -49,6 +50,7 @@ Supported devices * Ethernet controllers * Front LEDs (PCA9552 on I2C bus) * LPC Peripheral Controller (a subset of subdevices are supported) + * Hash/Crypto Engine (HACE) - Hash support only. TODO: HMAC and RSA Missing devices @@ -59,7 +61,6 @@ Missing devices * PWM and Fan Controller * Slave GPIO Controller * Super I/O Controller - * Hash/Crypto Engine * PCI-Express 1 Controller * Graphic Display Controller * PECI Controller diff --git a/docs/system/arm/cpu-features.rst b/docs/system/arm/cpu-features.rst index c455442eaf..584eb17097 100644 --- a/docs/system/arm/cpu-features.rst +++ b/docs/system/arm/cpu-features.rst @@ -10,22 +10,22 @@ is the Performance Monitoring Unit (PMU). CPU types such as the Cortex-A15 and the Cortex-A57, which respectively implement Arm architecture reference manuals ARMv7-A and ARMv8-A, may both optionally implement PMUs. For example, if a user wants to use a Cortex-A15 without -a PMU, then the `-cpu` parameter should contain `pmu=off` on the QEMU -command line, i.e. `-cpu cortex-a15,pmu=off`. +a PMU, then the ``-cpu`` parameter should contain ``pmu=off`` on the QEMU +command line, i.e. ``-cpu cortex-a15,pmu=off``. As not all CPU types support all optional CPU features, then whether or not a CPU property exists depends on the CPU type. For example, CPUs that implement the ARMv8-A architecture reference manual may optionally support the AArch32 CPU feature, which may be enabled by disabling the -`aarch64` CPU property. A CPU type such as the Cortex-A15, which does -not implement ARMv8-A, will not have the `aarch64` CPU property. +``aarch64`` CPU property. A CPU type such as the Cortex-A15, which does +not implement ARMv8-A, will not have the ``aarch64`` CPU property. QEMU's support may be limited for some CPU features, only partially supporting the feature or only supporting the feature under certain -configurations. For example, the `aarch64` CPU feature, which, when +configurations. For example, the ``aarch64`` CPU feature, which, when disabled, enables the optional AArch32 CPU feature, is only supported when using the KVM accelerator and when running on a host CPU type that -supports the feature. While `aarch64` currently only works with KVM, +supports the feature. While ``aarch64`` currently only works with KVM, it could work with TCG. CPU features that are specific to KVM are prefixed with "kvm-" and are described in "KVM VCPU Features". @@ -33,12 +33,12 @@ CPU Feature Probing =================== Determining which CPU features are available and functional for a given -CPU type is possible with the `query-cpu-model-expansion` QMP command. -Below are some examples where `scripts/qmp/qmp-shell` (see the top comment +CPU type is possible with the ``query-cpu-model-expansion`` QMP command. +Below are some examples where ``scripts/qmp/qmp-shell`` (see the top comment block in the script for usage) is used to issue the QMP commands. -1. Determine which CPU features are available for the `max` CPU type - (Note, we started QEMU with qemu-system-aarch64, so `max` is +1. Determine which CPU features are available for the ``max`` CPU type + (Note, we started QEMU with qemu-system-aarch64, so ``max`` is implementing the ARMv8-A reference manual in this case):: (QEMU) query-cpu-model-expansion type=full model={"name":"max"} @@ -51,9 +51,9 @@ block in the script for usage) is used to issue the QMP commands. "sve896": true, "sve1280": true, "sve2048": true }}}} -We see that the `max` CPU type has the `pmu`, `aarch64`, `sve`, and many -`sve` CPU features. We also see that all the CPU features are -enabled, as they are all `true`. (The `sve` CPU features are all +We see that the ``max`` CPU type has the ``pmu``, ``aarch64``, ``sve``, and many +``sve`` CPU features. We also see that all the CPU features are +enabled, as they are all ``true``. (The ``sve`` CPU features are all optional SVE vector lengths (see "SVE CPU Properties"). While with TCG all SVE vector lengths can be supported, when KVM is in use it's more likely that only a few lengths will be supported, if SVE is supported at @@ -71,9 +71,9 @@ all.) "sve896": true, "sve1280": true, "sve2048": true }}}} -We see it worked, as `pmu` is now `false`. +We see it worked, as ``pmu`` is now ``false``. -(3) Let's try to disable `aarch64`, which enables the AArch32 CPU feature:: +(3) Let's try to disable ``aarch64``, which enables the AArch32 CPU feature:: (QEMU) query-cpu-model-expansion type=full model={"name":"max","props":{"aarch64":false}} {"error": { @@ -84,7 +84,7 @@ We see it worked, as `pmu` is now `false`. It looks like this feature is limited to a configuration we do not currently have. -(4) Let's disable `sve` and see what happens to all the optional SVE +(4) Let's disable ``sve`` and see what happens to all the optional SVE vector lengths:: (QEMU) query-cpu-model-expansion type=full model={"name":"max","props":{"sve":false}} @@ -97,14 +97,14 @@ currently have. "sve896": false, "sve1280": false, "sve2048": false }}}} -As expected they are now all `false`. +As expected they are now all ``false``. (5) Let's try probing CPU features for the Cortex-A15 CPU type:: (QEMU) query-cpu-model-expansion type=full model={"name":"cortex-a15"} {"return": {"model": {"name": "cortex-a15", "props": {"pmu": true}}}} -Only the `pmu` CPU feature is available. +Only the ``pmu`` CPU feature is available. A note about CPU feature dependencies ------------------------------------- @@ -123,29 +123,29 @@ A note about CPU models and KVM ------------------------------- Named CPU models generally do not work with KVM. There are a few cases -that do work, e.g. using the named CPU model `cortex-a57` with KVM on a -seattle host, but mostly if KVM is enabled the `host` CPU type must be +that do work, e.g. using the named CPU model ``cortex-a57`` with KVM on a +seattle host, but mostly if KVM is enabled the ``host`` CPU type must be used. This means the guest is provided all the same CPU features as the -host CPU type has. And, for this reason, the `host` CPU type should +host CPU type has. And, for this reason, the ``host`` CPU type should enable all CPU features that the host has by default. Indeed it's even a bit strange to allow disabling CPU features that the host has when using -the `host` CPU type, but in the absence of CPU models it's the best we can +the ``host`` CPU type, but in the absence of CPU models it's the best we can do if we want to launch guests without all the host's CPU features enabled. -Enabling KVM also affects the `query-cpu-model-expansion` QMP command. The +Enabling KVM also affects the ``query-cpu-model-expansion`` QMP command. The affect is not only limited to specific features, as pointed out in example (3) of "CPU Feature Probing", but also to which CPU types may be expanded. -When KVM is enabled, only the `max`, `host`, and current CPU type may be +When KVM is enabled, only the ``max``, ``host``, and current CPU type may be expanded. This restriction is necessary as it's not possible to know all CPU types that may work with KVM, but it does impose a small risk of users experiencing unexpected errors. For example on a seattle, as mentioned -above, the `cortex-a57` CPU type is also valid when KVM is enabled. -Therefore a user could use the `host` CPU type for the current type, but -then attempt to query `cortex-a57`, however that query will fail with our +above, the ``cortex-a57`` CPU type is also valid when KVM is enabled. +Therefore a user could use the ``host`` CPU type for the current type, but +then attempt to query ``cortex-a57``, however that query will fail with our restrictions. This shouldn't be an issue though as management layers and -users have been preferring the `host` CPU type for use with KVM for quite +users have been preferring the ``host`` CPU type for use with KVM for quite some time. Additionally, if the KVM-enabled QEMU instance running on a -seattle host is using the `cortex-a57` CPU type, then querying `cortex-a57` +seattle host is using the ``cortex-a57`` CPU type, then querying ``cortex-a57`` will work. Using CPU Features @@ -158,12 +158,12 @@ QEMU command line with that CPU type:: $ qemu-system-aarch64 -M virt -cpu max,pmu=off,sve=on,sve128=on,sve256=on The example above disables the PMU and enables the first two SVE vector -lengths for the `max` CPU type. Note, the `sve=on` isn't actually -necessary, because, as we observed above with our probe of the `max` CPU -type, `sve` is already on by default. Also, based on our probe of +lengths for the ``max`` CPU type. Note, the ``sve=on`` isn't actually +necessary, because, as we observed above with our probe of the ``max`` CPU +type, ``sve`` is already on by default. Also, based on our probe of defaults, it would seem we need to disable many SVE vector lengths, rather than only enabling the two we want. This isn't the case, because, as -disabling many SVE vector lengths would be quite verbose, the `sve` CPU +disabling many SVE vector lengths would be quite verbose, the ``sve`` CPU properties have special semantics (see "SVE CPU Property Parsing Semantics"). @@ -217,11 +217,11 @@ TCG VCPU Features TCG VCPU features are CPU features that are specific to TCG. Below is the list of TCG VCPU features and their descriptions. - pauth Enable or disable `FEAT_Pauth`, pointer + pauth Enable or disable ``FEAT_Pauth``, pointer authentication. By default, the feature is - enabled with `-cpu max`. + enabled with ``-cpu max``. - pauth-impdef When `FEAT_Pauth` is enabled, either the + pauth-impdef When ``FEAT_Pauth`` is enabled, either the *impdef* (Implementation Defined) algorithm is enabled or the *architected* QARMA algorithm is enabled. By default the impdef algorithm @@ -235,49 +235,49 @@ Below is the list of TCG VCPU features and their descriptions. SVE CPU Properties ================== -There are two types of SVE CPU properties: `sve` and `sve`. The first -is used to enable or disable the entire SVE feature, just as the `pmu` +There are two types of SVE CPU properties: ``sve`` and ``sve``. The first +is used to enable or disable the entire SVE feature, just as the ``pmu`` CPU property completely enables or disables the PMU. The second type -is used to enable or disable specific vector lengths, where `N` is the -number of bits of the length. The `sve` CPU properties have special +is used to enable or disable specific vector lengths, where ``N`` is the +number of bits of the length. The ``sve`` CPU properties have special dependencies and constraints, see "SVE CPU Property Dependencies and Constraints" below. Additionally, as we want all supported vector lengths to be enabled by default, then, in order to avoid overly verbose command -lines (command lines full of `sve=off`, for all `N` not wanted), we +lines (command lines full of ``sve=off``, for all ``N`` not wanted), we provide the parsing semantics listed in "SVE CPU Property Parsing Semantics". SVE CPU Property Dependencies and Constraints --------------------------------------------- - 1) At least one vector length must be enabled when `sve` is enabled. + 1) At least one vector length must be enabled when ``sve`` is enabled. - 2) If a vector length `N` is enabled, then, when KVM is enabled, all + 2) If a vector length ``N`` is enabled, then, when KVM is enabled, all smaller, host supported vector lengths must also be enabled. If KVM is not enabled, then only all the smaller, power-of-two vector lengths must be enabled. E.g. with KVM if the host supports all - vector lengths up to 512-bits (128, 256, 384, 512), then if `sve512` + vector lengths up to 512-bits (128, 256, 384, 512), then if ``sve512`` is enabled, the 128-bit vector length, 256-bit vector length, and 384-bit vector length must also be enabled. Without KVM, the 384-bit vector length would not be required. 3) If KVM is enabled then only vector lengths that the host CPU type support may be enabled. If SVE is not supported by the host, then - no `sve*` properties may be enabled. + no ``sve*`` properties may be enabled. SVE CPU Property Parsing Semantics ---------------------------------- - 1) If SVE is disabled (`sve=off`), then which SVE vector lengths + 1) If SVE is disabled (``sve=off``), then which SVE vector lengths are enabled or disabled is irrelevant to the guest, as the entire SVE feature is disabled and that disables all vector lengths for - the guest. However QEMU will still track any `sve` CPU - properties provided by the user. If later an `sve=on` is provided, - then the guest will get only the enabled lengths. If no `sve=on` + the guest. However QEMU will still track any ``sve`` CPU + properties provided by the user. If later an ``sve=on`` is provided, + then the guest will get only the enabled lengths. If no ``sve=on`` is provided and there are explicitly enabled vector lengths, then an error is generated. - 2) If SVE is enabled (`sve=on`), but no `sve` CPU properties are + 2) If SVE is enabled (``sve=on``), but no ``sve`` CPU properties are provided, then all supported vector lengths are enabled, which when KVM is not in use means including the non-power-of-two lengths, and, when KVM is in use, it means all vector lengths supported by the host @@ -293,7 +293,7 @@ SVE CPU Property Parsing Semantics constraint (2) of "SVE CPU Property Dependencies and Constraints"). 5) When KVM is enabled, if the host does not support SVE, then an error - is generated when attempting to enable any `sve*` properties (see + is generated when attempting to enable any ``sve*`` properties (see constraint (3) of "SVE CPU Property Dependencies and Constraints"). 6) When KVM is enabled, if the host does support SVE, then an error is @@ -301,8 +301,8 @@ SVE CPU Property Parsing Semantics by the host (see constraint (3) of "SVE CPU Property Dependencies and Constraints"). - 7) If one or more `sve` CPU properties are set `off`, but no `sve`, - CPU properties are set `on`, then the specified vector lengths are + 7) If one or more ``sve`` CPU properties are set ``off``, but no ``sve``, + CPU properties are set ``on``, then the specified vector lengths are disabled but the default for any unspecified lengths remains enabled. When KVM is not enabled, disabling a power-of-two vector length also disables all vector lengths larger than the power-of-two length. @@ -310,15 +310,15 @@ SVE CPU Property Parsing Semantics disables all larger vector lengths (see constraint (2) of "SVE CPU Property Dependencies and Constraints"). - 8) If one or more `sve` CPU properties are set to `on`, then they + 8) If one or more ``sve`` CPU properties are set to ``on``, then they are enabled and all unspecified lengths default to disabled, except for the required lengths per constraint (2) of "SVE CPU Property Dependencies and Constraints", which will even be auto-enabled if they were not explicitly enabled. - 9) If SVE was disabled (`sve=off`), allowing all vector lengths to be + 9) If SVE was disabled (``sve=off``), allowing all vector lengths to be explicitly disabled (i.e. avoiding the error specified in (3) of - "SVE CPU Property Parsing Semantics"), then if later an `sve=on` is + "SVE CPU Property Parsing Semantics"), then if later an ``sve=on`` is provided an error will be generated. To avoid this error, one must enable at least one vector length prior to enabling SVE. @@ -329,12 +329,12 @@ SVE CPU Property Examples $ qemu-system-aarch64 -M virt -cpu max,sve=off - 2) Implicitly enable all vector lengths for the `max` CPU type:: + 2) Implicitly enable all vector lengths for the ``max`` CPU type:: $ qemu-system-aarch64 -M virt -cpu max 3) When KVM is enabled, implicitly enable all host CPU supported vector - lengths with the `host` CPU type:: + lengths with the ``host`` CPU type:: $ qemu-system-aarch64 -M virt,accel=kvm -cpu host @@ -376,3 +376,18 @@ verbose command lines. However, the recommended way to select vector lengths is to explicitly enable each desired length. Therefore only example's (1), (4), and (6) exhibit recommended uses of the properties. +SVE User-mode Default Vector Length Property +-------------------------------------------- + +For qemu-aarch64, the cpu property ``sve-default-vector-length=N`` is +defined to mirror the Linux kernel parameter file +``/proc/sys/abi/sve_default_vector_length``. The default length, ``N``, +is in units of bytes and must be between 16 and 8192. +If not specified, the default vector length is 64. + +If the default length is larger than the maximum vector length enabled, +the actual vector length will be reduced. Note that the maximum vector +length supported by QEMU is 256. + +If this property is set to ``-1`` then the default vector length +is set to the maximum possible length. diff --git a/docs/system/arm/cubieboard.rst b/docs/system/arm/cubieboard.rst new file mode 100644 index 0000000000..344ff8cef9 --- /dev/null +++ b/docs/system/arm/cubieboard.rst @@ -0,0 +1,16 @@ +Cubietech Cubieboard (``cubieboard``) +===================================== + +The ``cubieboard`` model emulates the Cubietech Cubieboard, +which is a Cortex-A8 based single-board computer using +the AllWinner A10 SoC. + +Emulated devices: + +- Timer +- UART +- RTC +- EMAC +- SDHCI +- USB controller +- SATA controller diff --git a/docs/system/arm/emcraft-sf2.rst b/docs/system/arm/emcraft-sf2.rst new file mode 100644 index 0000000000..377e248720 --- /dev/null +++ b/docs/system/arm/emcraft-sf2.rst @@ -0,0 +1,15 @@ +Emcraft SmartFusion2 SOM kit (``emcraft-sf2``) +============================================== + +The ``emcraft-sf2`` board emulates the SmartFusion2 SOM kit from +Emcraft (M2S010). This is a System-on-Module from EmCraft systems, +based on the SmartFusion2 SoC FPGA from Microsemi Corporation. +The SoC is based on a Cortex-M4 processor. + +Emulated devices: + +- System timer +- System registers +- SPI controller +- UART +- EMAC diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst new file mode 100644 index 0000000000..144dc491d9 --- /dev/null +++ b/docs/system/arm/emulation.rst @@ -0,0 +1,103 @@ +A-profile CPU architecture support +================================== + +QEMU's TCG emulation includes support for the Armv5, Armv6, Armv7 and +Armv8 versions of the A-profile architecture. It also has support for +the following architecture extensions: + +- FEAT_AA32BF16 (AArch32 BFloat16 instructions) +- FEAT_AA32HPD (AArch32 hierarchical permission disables) +- FEAT_AA32I8MM (AArch32 Int8 matrix multiplication instructions) +- FEAT_AES (AESD and AESE instructions) +- FEAT_BF16 (AArch64 BFloat16 instructions) +- FEAT_BTI (Branch Target Identification) +- FEAT_DIT (Data Independent Timing instructions) +- FEAT_DPB (DC CVAP instruction) +- FEAT_DotProd (Advanced SIMD dot product instructions) +- FEAT_FCMA (Floating-point complex number instructions) +- FEAT_FHM (Floating-point half-precision multiplication instructions) +- FEAT_FP16 (Half-precision floating-point data processing) +- FEAT_FRINTTS (Floating-point to integer instructions) +- FEAT_FlagM (Flag manipulation instructions v2) +- FEAT_FlagM2 (Enhancements to flag manipulation instructions) +- FEAT_HPDS (Hierarchical permission disables) +- FEAT_I8MM (AArch64 Int8 matrix multiplication instructions) +- FEAT_JSCVT (JavaScript conversion instructions) +- FEAT_LOR (Limited ordering regions) +- FEAT_LRCPC (Load-acquire RCpc instructions) +- FEAT_LRCPC2 (Load-acquire RCpc instructions v2) +- FEAT_LSE (Large System Extensions) +- FEAT_MTE (Memory Tagging Extension) +- FEAT_MTE2 (Memory Tagging Extension) +- FEAT_MTE3 (MTE Asymmetric Fault Handling) +- FEAT_PAN (Privileged access never) +- FEAT_PAN2 (AT S1E1R and AT S1E1W instruction variants affected by PSTATE.PAN) +- FEAT_PAuth (Pointer authentication) +- FEAT_PMULL (PMULL, PMULL2 instructions) +- FEAT_PMUv3p1 (PMU Extensions v3.1) +- FEAT_PMUv3p4 (PMU Extensions v3.4) +- FEAT_RDM (Advanced SIMD rounding double multiply accumulate instructions) +- FEAT_RNG (Random number generator) +- FEAT_SB (Speculation Barrier) +- FEAT_SEL2 (Secure EL2) +- FEAT_SHA1 (SHA1 instructions) +- FEAT_SHA256 (SHA256 instructions) +- FEAT_SHA3 (Advanced SIMD SHA3 instructions) +- FEAT_SHA512 (Advanced SIMD SHA512 instructions) +- FEAT_SM3 (Advanced SIMD SM3 instructions) +- FEAT_SM4 (Advanced SIMD SM4 instructions) +- FEAT_SPECRES (Speculation restriction instructions) +- FEAT_SSBS (Speculative Store Bypass Safe) +- FEAT_TLBIOS (TLB invalidate instructions in Outer Shareable domain) +- FEAT_TLBIRANGE (TLB invalidate range instructions) +- FEAT_TTCNP (Translation table Common not private translations) +- FEAT_TTST (Small translation tables) +- FEAT_UAO (Unprivileged Access Override control) +- FEAT_VHE (Virtualization Host Extensions) +- FEAT_VMID16 (16-bit VMID) +- FEAT_XNX (Translation table stage 2 Unprivileged Execute-never) +- SVE (The Scalable Vector Extension) +- SVE2 (The Scalable Vector Extension v2) + +For information on the specifics of these extensions, please refer +to the `Armv8-A Arm Architecture Reference Manual +`_. + +When a specific named CPU is being emulated, only those features which +are present in hardware for that CPU are emulated. (If a feature is +not in the list above then it is not supported, even if the real +hardware should have it.) The ``max`` CPU enables all features. + +R-profile CPU architecture support +================================== + +QEMU's TCG emulation support for R-profile CPUs is currently limited. +We emulate only the Cortex-R5 and Cortex-R5F CPUs. + +M-profile CPU architecture support +================================== + +QEMU's TCG emulation includes support for Armv6-M, Armv7-M, Armv8-M, and +Armv8.1-M versions of the M-profile architucture. It also has support +for the following architecture extensions: + +- FP (Floating-point Extension) +- FPCXT (FPCXT access instructions) +- HP (Half-precision floating-point instructions) +- LOB (Low Overhead loops and Branch future) +- M (Main Extension) +- MPU (Memory Protection Unit Extension) +- PXN (Privileged Execute Never) +- RAS (Reliability, Serviceability and Availability): "minimum RAS Extension" only +- S (Security Extension) +- ST (System Timer Extension) + +For information on the specifics of these extensions, please refer +to the `Armv8-M Arm Architecture Reference Manual +`_. + +When a specific named CPU is being emulated, only those features which +are present in hardware for that CPU are emulated. (If a feature is +not in the list above then it is not supported, even if the real +hardware should have it.) There is no equivalent of the ``max`` CPU for +M-profile. diff --git a/docs/system/arm/highbank.rst b/docs/system/arm/highbank.rst new file mode 100644 index 0000000000..bb4965b367 --- /dev/null +++ b/docs/system/arm/highbank.rst @@ -0,0 +1,19 @@ +Calxeda Highbank and Midway (``highbank``, ``midway``) +====================================================== + +``highbank`` is a model of the Calxeda Highbank (ECX-1000) system, +which has four Cortex-A9 cores. + +``midway`` is a model of the Calxeda Midway (ECX-2000) system, +which has four Cortex-A15 cores. + +Emulated devices: + +- L2x0 cache controller +- SP804 dual timer +- PL011 UART +- PL061 GPIOs +- PL031 RTC +- PL022 synchronous serial port controller +- AHCI +- XGMAC ethernet controllers diff --git a/docs/system/arm/imx25-pdk.rst b/docs/system/arm/imx25-pdk.rst new file mode 100644 index 0000000000..2a9711e8a7 --- /dev/null +++ b/docs/system/arm/imx25-pdk.rst @@ -0,0 +1,19 @@ +NXP i.MX25 PDK board (``imx25-pdk``) +==================================== + +The ``imx25-pdk`` board emulates the NXP i.MX25 Product Development Kit +board, which is based on an i.MX25 SoC which uses an ARM926 CPU. + +Emulated devices: + +- SD controller +- AVIC +- CCM +- GPT +- EPIT timers +- FEC +- RNGC +- I2C +- GPIO controllers +- Watchdog timer +- USB controllers diff --git a/docs/system/arm/kzm.rst b/docs/system/arm/kzm.rst new file mode 100644 index 0000000000..bb018fbdf7 --- /dev/null +++ b/docs/system/arm/kzm.rst @@ -0,0 +1,18 @@ +Kyoto Microcomputer KZM-ARM11-01 (``kzm``) +========================================== + +The ``kzm`` board emulates the Kyoto Microcomputer KZM-ARM11-01 +evaluation board, which is based on an NXP i.MX32 SoC +which uses an ARM1136 CPU. + +Emulated devices: + +- UARTs +- LAN9118 ethernet +- AVIC +- CCM +- GPT +- EPIT timers +- I2C +- GPIO controllers +- Watchdog timer diff --git a/docs/system/arm/mainstone.rst b/docs/system/arm/mainstone.rst new file mode 100644 index 0000000000..05310f42c7 --- /dev/null +++ b/docs/system/arm/mainstone.rst @@ -0,0 +1,25 @@ +Intel Mainstone II board (``mainstone``) +======================================== + +The ``mainstone`` board emulates the Intel Mainstone II development +board, which uses a PXA270 CPU. + +Emulated devices: + +- Flash memory +- Keypad +- MMC controller +- 91C111 ethernet +- PIC +- Timer +- DMA +- GPIO +- FIR +- Serial +- LCD controller +- SSP +- USB controller +- RTC +- PCMCIA +- I2C +- I2S diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index f83b151787..8a75beb3a0 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -45,3 +45,13 @@ Differences between QEMU and real hardware: flash, but only as simple ROM, so attempting to rewrite the flash from the guest will fail - QEMU does not model the USB controller in MPS3 boards + +Machine-specific options +"""""""""""""""""""""""" + +The following machine-specific options are supported: + +remap + Supported for ``mps3-an524`` only. + Set ``BRAM``/``QSPI`` to select the initial memory mapping. The + default is ``BRAM``. diff --git a/docs/system/arm/nrf.rst b/docs/system/arm/nrf.rst new file mode 100644 index 0000000000..eda87bd760 --- /dev/null +++ b/docs/system/arm/nrf.rst @@ -0,0 +1,51 @@ +Nordic nRF boards (``microbit``) +================================ + +The `Nordic nRF`_ chips are a family of ARM-based System-on-Chip that +are designed to be used for low-power and short-range wireless solutions. + +.. _Nordic nRF: https://www.nordicsemi.com/Products + +The nRF51 series is the first series for short range wireless applications. +It is superseded by the nRF52 series. +The following machines are based on this chip : + +- ``microbit`` BBC micro:bit board with nRF51822 SoC + +There are other series such as nRF52, nRF53 and nRF91 which are currently not +supported by QEMU. + +Supported devices +----------------- + + * ARM Cortex-M0 (ARMv6-M) + * Serial ports (UART) + * Clock controller + * Timers + * Random Number Generator (RNG) + * GPIO controller + * NVMC + * SWI + +Missing devices +--------------- + + * Watchdog + * Real-Time Clock (RTC) controller + * TWI (i2c) + * SPI controller + * Analog to Digital Converter (ADC) + * Quadrature decoder + * Radio + +Boot options +------------ + +The Micro:bit machine can be started using the ``-device`` option to load a +firmware in `ihex format`_. Example: + +.. _ihex format: https://en.wikipedia.org/wiki/Intel_HEX + +.. code-block:: bash + + $ qemu-system-arm -M microbit -device loader,file=test.hex diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index d3cf2d9cd7..69f57c2886 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -1,23 +1,24 @@ -Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``) -===================================================== +Nuvoton iBMC boards (``*-bmc``, ``npcm750-evb``, ``quanta-gsj``) +================================================================ The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are designed to be used as Baseboard Management Controllers (BMCs) in various -servers. They all feature one or two ARM Cortex A9 CPU cores, as well as an +servers. They all feature one or two ARM Cortex-A9 CPU cores, as well as an assortment of peripherals targeted for either Enterprise or Data Center / Hyperscale applications. The former is a superset of the latter, so NPCM750 has all the peripherals of NPCM730 and more. .. _Nuvoton iBMC: https://www.nuvoton.com/products/cloud-computing/ibmc/ -The NPCM750 SoC has two Cortex A9 cores and is targeted for the Enterprise +The NPCM750 SoC has two Cortex-A9 cores and is targeted for the Enterprise segment. The following machines are based on this chip : - ``npcm750-evb`` Nuvoton NPCM750 Evaluation board -The NPCM730 SoC has two Cortex A9 cores and is targeted for Data Center and +The NPCM730 SoC has two Cortex-A9 cores and is targeted for Data Center and Hyperscale applications. The following machines are based on this chip : +- ``quanta-gbs-bmc`` Quanta GBS server BMC - ``quanta-gsj`` Quanta GSJ server BMC There are also two more SoCs, NPCM710 and NPCM705, which are single-core @@ -78,7 +79,7 @@ Boot options ------------ The Nuvoton machines can boot from an OpenBMC firmware image, or directly into -a kernel using the ``-kernel`` option. OpenBMC images for `quanta-gsj` and +a kernel using the ``-kernel`` option. OpenBMC images for ``quanta-gsj`` and possibly others can be downloaded from the OpenPOWER jenkins : https://openpower.xyz/ diff --git a/docs/system/arm/sabrelite.rst b/docs/system/arm/sabrelite.rst index 71713310e3..4ccb0560af 100644 --- a/docs/system/arm/sabrelite.rst +++ b/docs/system/arm/sabrelite.rst @@ -10,7 +10,7 @@ Supported devices The SABRE Lite machine supports the following devices: - * Up to 4 Cortex A9 cores + * Up to 4 Cortex-A9 cores * Generic Interrupt Controller * 1 Clock Controller Module * 1 System Reset Controller diff --git a/docs/system/arm/sbsa.rst b/docs/system/arm/sbsa.rst index b8ecfdb62f..b499d7e927 100644 --- a/docs/system/arm/sbsa.rst +++ b/docs/system/arm/sbsa.rst @@ -1,10 +1,10 @@ Arm Server Base System Architecture Reference board (``sbsa-ref``) ================================================================== -While the `virt` board is a generic board platform that doesn't match -any real hardware the `sbsa-ref` board intends to look like real +While the ``virt`` board is a generic board platform that doesn't match +any real hardware the ``sbsa-ref`` board intends to look like real hardware. The `Server Base System Architecture -` defines a +`_ defines a minimum base line of hardware support and importantly how the firmware reports that to any operating system. It is a static system that reports a very minimal DT to the firmware for non-discoverable diff --git a/docs/system/arm/stm32.rst b/docs/system/arm/stm32.rst new file mode 100644 index 0000000000..508b92cf86 --- /dev/null +++ b/docs/system/arm/stm32.rst @@ -0,0 +1,66 @@ +STMicroelectronics STM32 boards (``netduino2``, ``netduinoplus2``, ``stm32vldiscovery``) +======================================================================================== + +The `STM32`_ chips are a family of 32-bit ARM-based microcontroller by +STMicroelectronics. + +.. _STM32: https://www.st.com/en/microcontrollers-microprocessors/stm32-32-bit-arm-cortex-mcus.html + +The STM32F1 series is based on ARM Cortex-M3 core. The following machines are +based on this chip : + +- ``stm32vldiscovery`` STM32VLDISCOVERY board with STM32F100RBT6 microcontroller + +The STM32F2 series is based on ARM Cortex-M3 core. The following machines are +based on this chip : + +- ``netduino2`` Netduino 2 board with STM32F205RFT6 microcontroller + +The STM32F4 series is based on ARM Cortex-M4F core. This series is pin-to-pin +compatible with STM32F2 series. The following machines are based on this chip : + +- ``netduinoplus2`` Netduino Plus 2 board with STM32F405RGT6 microcontroller + +There are many other STM32 series that are currently not supported by QEMU. + +Supported devices +----------------- + + * ARM Cortex-M3, Cortex M4F + * Analog to Digital Converter (ADC) + * EXTI interrupt + * Serial ports (USART) + * SPI controller + * System configuration (SYSCFG) + * Timer controller (TIMER) + +Missing devices +--------------- + + * Camera interface (DCMI) + * Controller Area Network (CAN) + * Cycle Redundancy Check (CRC) calculation unit + * Digital to Analog Converter (DAC) + * DMA controller + * Ethernet controller + * Flash Interface Unit + * GPIO controller + * I2C controller + * Inter-Integrated Sound (I2S) controller + * Power supply configuration (PWR) + * Random Number Generator (RNG) + * Real-Time Clock (RTC) controller + * Reset and Clock Controller (RCC) + * Secure Digital Input/Output (SDIO) interface + * USB OTG + * Watchdog controller (IWDG, WWDG) + +Boot options +------------ + +The STM32 machines can be started using the ``-kernel`` option to load a +firmware. Example: + +.. code-block:: bash + + $ qemu-system-arm -M stm32vldiscovery -kernel firmware.bin diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index 27652adfae..59acf0eeaf 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -1,7 +1,7 @@ 'virt' generic virtual platform (``virt``) ========================================== -The `virt` board is a platform which does not correspond to any +The ``virt`` board is a platform which does not correspond to any real hardware; it is designed for use in virtual machines. It is the recommended board type if you simply want to run a guest such as Linux and do not care about reproducing the diff --git a/docs/system/authz.rst b/docs/system/authz.rst new file mode 100644 index 0000000000..942af39602 --- /dev/null +++ b/docs/system/authz.rst @@ -0,0 +1,263 @@ +.. _client authorization: + +Client authorization +-------------------- + +When configuring a QEMU network backend with either TLS certificates or SASL +authentication, access will be granted if the client successfully proves +their identity. If the authorization identity database is scoped to the QEMU +client this may be sufficient. It is common, however, for the identity database +to be much broader and thus authentication alone does not enable sufficient +access control. In this case QEMU provides a flexible system for enforcing +finer grained authorization on clients post-authentication. + +Identity providers +~~~~~~~~~~~~~~~~~~ + +At the time of writing there are two authentication frameworks used by QEMU +that emit an identity upon completion. + + * TLS x509 certificate distinguished name. + + When configuring the QEMU backend as a network server with TLS, there + are a choice of credentials to use. The most common scenario is to utilize + x509 certificates. The simplest configuration only involves issuing + certificates to the servers, allowing the client to avoid a MITM attack + against their intended server. + + It is possible, however, to enable mutual verification by requiring that + the client provide a certificate to the server to prove its own identity. + This is done by setting the property ``verify-peer=yes`` on the + ``tls-creds-x509`` object, which is in fact the default. + + When peer verification is enabled, client will need to be issued with a + certificate by the same certificate authority as the server. If this is + still not sufficiently strong access control the Distinguished Name of + the certificate can be used as an identity in the QEMU authorization + framework. + + * SASL username. + + When configuring the QEMU backend as a network server with SASL, upon + completion of the SASL authentication mechanism, a username will be + provided. The format of this username will vary depending on the choice + of mechanism configured for SASL. It might be a simple UNIX style user + ``joebloggs``, while if using Kerberos/GSSAPI it can have a realm + attached ``joebloggs@QEMU.ORG``. Whatever format the username is presented + in, it can be used with the QEMU authorization framework. + +Authorization drivers +~~~~~~~~~~~~~~~~~~~~~ + +The QEMU authorization framework is a general purpose design with choice of +user customizable drivers. These are provided as objects that can be +created at startup using the ``-object`` argument, or at runtime using the +``object_add`` monitor command. + +Simple +^^^^^^ + +This authorization driver provides a simple mechanism for granting access +based on an exact match against a single identity. This is useful when it is +known that only a single client is to be allowed access. + +A possible use case would be when configuring QEMU for an incoming live +migration. It is known exactly which source QEMU the migration is expected +to arrive from. The x509 certificate associated with this source QEMU would +thus be used as the identity to match against. Alternatively if the virtual +machine is dedicated to a specific tenant, then the VNC server would be +configured with SASL and the username of only that tenant listed. + +To create an instance of this driver via QMP: + +:: + + { + "execute": "object-add", + "arguments": { + "qom-type": "authz-simple", + "id": "authz0", + "props": { + "identity": "fred" + } + } + } + + +Or via the command line + +:: + + -object authz-simple,id=authz0,identity=fred + + +List +^^^^ + +In some network backends it will be desirable to grant access to a range of +clients. This authorization driver provides a list mechanism for granting +access by matching identities against a list of permitted one. Each match +rule has an associated policy and a catch all policy applies if no rule +matches. The match can either be done as an exact string comparison, or can +use the shell-like glob syntax, which allows for use of wildcards. + +To create an instance of this class via QMP: + +:: + + { + "execute": "object-add", + "arguments": { + "qom-type": "authz-list", + "id": "authz0", + "props": { + "rules": [ + { "match": "fred", "policy": "allow", "format": "exact" }, + { "match": "bob", "policy": "allow", "format": "exact" }, + { "match": "danb", "policy": "deny", "format": "exact" }, + { "match": "dan*", "policy": "allow", "format": "glob" } + ], + "policy": "deny" + } + } + } + + +Due to the way this driver requires setting nested properties, creating +it on the command line will require use of the JSON syntax for ``-object``. +In most cases, however, the next driver will be more suitable. + +List file +^^^^^^^^^ + +This is a variant on the previous driver that allows for a more dynamic +access control policy by storing the match rules in a standalone file +that can be reloaded automatically upon change. + +To create an instance of this class via QMP: + +:: + + { + "execute": "object-add", + "arguments": { + "qom-type": "authz-list-file", + "id": "authz0", + "props": { + "filename": "/etc/qemu/myvm-vnc.acl", + "refresh": true + } + } + } + + +If ``refresh`` is ``yes``, inotify is used to monitor for changes +to the file and auto-reload the rules. + +The ``myvm-vnc.acl`` file should contain the match rules in a format that +closely matches the previous driver: + +:: + + { + "rules": [ + { "match": "fred", "policy": "allow", "format": "exact" }, + { "match": "bob", "policy": "allow", "format": "exact" }, + { "match": "danb", "policy": "deny", "format": "exact" }, + { "match": "dan*", "policy": "allow", "format": "glob" } + ], + "policy": "deny" + } + + +The object can be created on the command line using + +:: + + -object authz-list-file,id=authz0,\ + filename=/etc/qemu/myvm-vnc.acl,refresh=on + + +PAM +^^^ + +In some scenarios it might be desirable to integrate with authorization +mechanisms that are implemented outside of QEMU. In order to allow maximum +flexibility, QEMU provides a driver that uses the ``PAM`` framework. + +To create an instance of this class via QMP: + +:: + + { + "execute": "object-add", + "arguments": { + "qom-type": "authz-pam", + "id": "authz0", + "parameters": { + "service": "qemu-vnc-tls" + } + } + } + + +The driver only uses the PAM "account" verification +subsystem. The above config would require a config +file /etc/pam.d/qemu-vnc-tls. For a simple file +lookup it would contain + +:: + + account requisite pam_listfile.so item=user sense=allow \ + file=/etc/qemu/vnc.allow + + +The external file would then contain a list of usernames. +If x509 cert was being used as the username, a suitable +entry would match the distinguished name: + +:: + + CN=laptop.berrange.com,O=Berrange Home,L=London,ST=London,C=GB + + +On the command line it can be created using + +:: + + -object authz-pam,id=authz0,service=qemu-vnc-tls + + +There are a variety of PAM plugins that can be used which are not illustrated +here, and it is possible to implement brand new plugins using the PAM API. + + +Connecting backends +~~~~~~~~~~~~~~~~~~~ + +The authorization driver is created using the ``-object`` argument and then +needs to be associated with a network service. The authorization driver object +will be given a unique ID that needs to be referenced. + +The property to set in the network service will vary depending on the type of +identity to verify. By convention, any network server backend that uses TLS +will provide ``tls-authz`` property, while any server using SASL will provide +a ``sasl-authz`` property. + +Thus an example using SASL and authorization for the VNC server would look +like: + +:: + + $QEMU --object authz-simple,id=authz0,identity=fred \ + --vnc 0.0.0.0:1,sasl,sasl-authz=authz0 + +While to validate both the x509 certificate and SASL username: + +:: + + echo "CN=laptop.qemu.org,O=QEMU Project,L=London,ST=London,C=GB" >> tls.acl + $QEMU --object authz-simple,id=authz0,identity=fred \ + --object authz-list-file,id=authz1,filename=tls.acl \ + --object tls-creds-x509,id=tls0,dir=/etc/qemu/tls,verify-peer=yes \ + --vnc 0.0.0.0:1,sasl,sasl-authz=auth0,tls-creds=tls0,tls-authz=authz1 diff --git a/docs/system/barrier.rst b/docs/system/barrier.rst new file mode 100644 index 0000000000..155d7d2901 --- /dev/null +++ b/docs/system/barrier.rst @@ -0,0 +1,44 @@ +QEMU Barrier Client +=================== + +Generally, mouse and keyboard are grabbed through the QEMU video +interface emulation. + +But when we want to use a video graphic adapter via a PCI passthrough +there is no way to provide the keyboard and mouse inputs to the VM +except by plugging a second set of mouse and keyboard to the host +or by installing a KVM software in the guest OS. + +The QEMU Barrier client avoids this by implementing directly the Barrier +protocol into QEMU. + +`Barrier `__ +is a KVM (Keyboard-Video-Mouse) software forked from Symless's +synergy 1.9 codebase. + +This protocol is enabled by adding an input-barrier object to QEMU. + +Syntax:: + + input-barrier,id=,name= + [,server=][,port=] + [,x-origin=][,y-origin=] + [,width=][,height=] + +The object can be added on the QEMU command line, for instance with:: + + -object input-barrier,id=barrier0,name=VM-1 + +where VM-1 is the name the display configured in the Barrier server +on the host providing the mouse and the keyboard events. + +by default ```` is ``localhost``, +```` is ``24800``, ```` and ```` are set to ``0``, +```` and ```` to ``1920`` and ``1080``. + +If the Barrier server is stopped QEMU needs to be reconnected manually, +by removing and re-adding the input-barrier object, for instance +with the help of the HMP monitor:: + + (qemu) object_del barrier0 + (qemu) object_add input-barrier,id=barrier0,name=VM-1 diff --git a/docs/system/bootindex.rst b/docs/system/bootindex.rst new file mode 100644 index 0000000000..8b057f812f --- /dev/null +++ b/docs/system/bootindex.rst @@ -0,0 +1,76 @@ +Managing device boot order with bootindex properties +==================================================== + +QEMU can tell QEMU-aware guest firmware (like the x86 PC BIOS) +which order it should look for a bootable OS on which devices. +A simple way to set this order is to use the ``-boot order=`` option, +but you can also do this more flexibly, by setting a ``bootindex`` +property on the individual block or net devices you specify +on the QEMU command line. + +The ``bootindex`` properties are used to determine the order in which +firmware will consider devices for booting the guest OS. If the +``bootindex`` property is not set for a device, it gets the lowest +boot priority. There is no particular order in which devices with no +``bootindex`` property set will be considered for booting, but they +will still be bootable. + +Some guest machine types (for instance the s390x machines) do +not support ``-boot order=``; on those machines you must always +use ``bootindex`` properties. + +There is no way to set a ``bootindex`` property if you are using +a short-form option like ``-hda`` or ``-cdrom``, so to use +``bootindex`` properties you will need to expand out those options +into long-form ``-drive`` and ``-device`` option pairs. + +Example +------- + +Let's assume we have a QEMU machine with two NICs (virtio, e1000) and two +disks (IDE, virtio): + +.. parsed-literal:: + + |qemu_system| -drive file=disk1.img,if=none,id=disk1 \\ + -device ide-hd,drive=disk1,bootindex=4 \\ + -drive file=disk2.img,if=none,id=disk2 \\ + -device virtio-blk-pci,drive=disk2,bootindex=3 \\ + -netdev type=user,id=net0 \\ + -device virtio-net-pci,netdev=net0,bootindex=2 \\ + -netdev type=user,id=net1 \\ + -device e1000,netdev=net1,bootindex=1 + +Given the command above, firmware should try to boot from the e1000 NIC +first. If this fails, it should try the virtio NIC next; if this fails +too, it should try the virtio disk, and then the IDE disk. + +Limitations +----------- + +Some firmware has limitations on which devices can be considered for +booting. For instance, the PC BIOS boot specification allows only one +disk to be bootable. If boot from disk fails for some reason, the BIOS +won't retry booting from other disk. It can still try to boot from +floppy or net, though. + +Sometimes, firmware cannot map the device path QEMU wants firmware to +boot from to a boot method. It doesn't happen for devices the firmware +can natively boot from, but if firmware relies on an option ROM for +booting, and the same option ROM is used for booting from more then one +device, the firmware may not be able to ask the option ROM to boot from +a particular device reliably. For instance with the PC BIOS, if a SCSI HBA +has three bootable devices target1, target3, target5 connected to it, +the option ROM will have a boot method for each of them, but it is not +possible to map from boot method back to a specific target. This is a +shortcoming of the PC BIOS boot specification. + +Mixing bootindex and boot order parameters +------------------------------------------ + +Note that it does not make sense to use the bootindex property together +with the ``-boot order=...`` (or ``-boot once=...``) parameter. The guest +firmware implementations normally either support the one or the other, +but not both parameters at the same time. Mixing them will result in +undefined behavior, and thus the guest firmware will likely not boot +from the expected devices. diff --git a/docs/system/cpu-hotplug.rst b/docs/system/cpu-hotplug.rst index bd0663616e..015ce2b6ec 100644 --- a/docs/system/cpu-hotplug.rst +++ b/docs/system/cpu-hotplug.rst @@ -78,7 +78,7 @@ vCPU hotplug } (QEMU) -(5) Optionally, run QMP `query-cpus-fast` for some details about the +(5) Optionally, run QMP ``query-cpus-fast`` for some details about the vCPUs:: (QEMU) query-cpus-fast diff --git a/docs/system/cpu-models-x86-abi.csv b/docs/system/cpu-models-x86-abi.csv new file mode 100644 index 0000000000..f3f3b60be1 --- /dev/null +++ b/docs/system/cpu-models-x86-abi.csv @@ -0,0 +1,67 @@ +Model,baseline,v2,v3,v4 +486-v1,,,, +Broadwell-v1,✅,✅,✅, +Broadwell-v2,✅,✅,✅, +Broadwell-v3,✅,✅,✅, +Broadwell-v4,✅,✅,✅, +Cascadelake-Server-v1,✅,✅,✅,✅ +Cascadelake-Server-v2,✅,✅,✅,✅ +Cascadelake-Server-v3,✅,✅,✅,✅ +Cascadelake-Server-v4,✅,✅,✅,✅ +Conroe-v1,✅,,, +Cooperlake-v1,✅,✅,✅,✅ +Denverton-v1,✅,✅,, +Denverton-v2,✅,✅,, +Dhyana-v1,✅,✅,✅, +EPYC-Milan-v1,✅,✅,✅, +EPYC-Rome-v1,✅,✅,✅, +EPYC-Rome-v2,✅,✅,✅, +EPYC-v1,✅,✅,✅, +EPYC-v2,✅,✅,✅, +EPYC-v3,✅,✅,✅, +Haswell-v1,✅,✅,✅, +Haswell-v2,✅,✅,✅, +Haswell-v3,✅,✅,✅, +Haswell-v4,✅,✅,✅, +Icelake-Client-v1,✅,✅,✅, +Icelake-Client-v2,✅,✅,✅, +Icelake-Server-v1,✅,✅,✅,✅ +Icelake-Server-v2,✅,✅,✅,✅ +Icelake-Server-v3,✅,✅,✅,✅ +Icelake-Server-v4,✅,✅,✅,✅ +IvyBridge-v1,✅,✅,, +IvyBridge-v2,✅,✅,, +KnightsMill-v1,✅,✅,✅, +Nehalem-v1,✅,✅,, +Nehalem-v2,✅,✅,, +Opteron_G1-v1,✅,,, +Opteron_G2-v1,✅,,, +Opteron_G3-v1,✅,,, +Opteron_G4-v1,✅,✅,, +Opteron_G5-v1,✅,✅,, +Penryn-v1,✅,,, +SandyBridge-v1,✅,✅,, +SandyBridge-v2,✅,✅,, +Skylake-Client-v1,✅,✅,✅, +Skylake-Client-v2,✅,✅,✅, +Skylake-Client-v3,✅,✅,✅, +Skylake-Server-v1,✅,✅,✅,✅ +Skylake-Server-v2,✅,✅,✅,✅ +Skylake-Server-v3,✅,✅,✅,✅ +Skylake-Server-v4,✅,✅,✅,✅ +Snowridge-v1,✅,✅,, +Snowridge-v2,✅,✅,, +Westmere-v1,✅,✅,, +Westmere-v2,✅,✅,, +athlon-v1,,,, +core2duo-v1,✅,,, +coreduo-v1,,,, +kvm32-v1,,,, +kvm64-v1,✅,,, +n270-v1,,,, +pentium-v1,,,, +pentium2-v1,,,, +pentium3-v1,,,, +phenom-v1,✅,,, +qemu32-v1,,,, +qemu64-v1,✅,,, diff --git a/docs/system/cpu-models-x86.rst.inc b/docs/system/cpu-models-x86.rst.inc index 867c8216b5..9119f5dff5 100644 --- a/docs/system/cpu-models-x86.rst.inc +++ b/docs/system/cpu-models-x86.rst.inc @@ -39,6 +39,28 @@ CPU, as they would with "Host passthrough", but gives much of the benefit of passthrough, while making live migration safe. +ABI compatibility levels for CPU models +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The x86_64 architecture has a number of `ABI compatibility levels`_ +defined. Traditionally most operating systems and toolchains would +only target the original baseline ABI. It is expected that in +future OS and toolchains are likely to target newer ABIs. The +table that follows illustrates which ABI compatibility levels +can be satisfied by the QEMU CPU models. Note that the table only +lists the long term stable CPU model versions (eg Haswell-v4). +In addition to whats listed, there are also many CPU model +aliases which resolve to a different CPU model version, +depending on the machine type is in use. + +.. _ABI compatibility levels: https://gitlab.com/x86-psABIs/x86-64-ABI/ + +.. csv-table:: x86-64 ABI compatibility levels + :file: cpu-models-x86-abi.csv + :widths: 40,15,15,15,15 + :header-rows: 2 + + Preferred CPU models for Intel x86 hosts ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ @@ -205,7 +227,7 @@ features are included if using "Host passthrough" or "Host model". Preferred CPU models for AMD x86 hosts ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -The following CPU models are preferred for use on Intel hosts. +The following CPU models are preferred for use on AMD hosts. Administrators / applications are recommended to use the CPU model that matches the generation of the host CPUs in use. In a deployment with a mixture of host CPU models between machines, if live migration diff --git a/docs/system/device-emulation.rst b/docs/system/device-emulation.rst new file mode 100644 index 0000000000..7afcfd8064 --- /dev/null +++ b/docs/system/device-emulation.rst @@ -0,0 +1,90 @@ +.. _device-emulation: + +Device Emulation +---------------- + +QEMU supports the emulation of a large number of devices from +peripherals such network cards and USB devices to integrated systems +on a chip (SoCs). Configuration of these is often a source of +confusion so it helps to have an understanding of some of the terms +used to describes devices within QEMU. + +Common Terms +~~~~~~~~~~~~ + +Device Front End +================ + +A device front end is how a device is presented to the guest. The type +of device presented should match the hardware that the guest operating +system is expecting to see. All devices can be specified with the +``--device`` command line option. Running QEMU with the command line +options ``--device help`` will list all devices it is aware of. Using +the command line ``--device foo,help`` will list the additional +configuration options available for that device. + +A front end is often paired with a back end, which describes how the +host's resources are used in the emulation. + +Device Buses +============ + +Most devices will exist on a BUS of some sort. Depending on the +machine model you choose (``-M foo``) a number of buses will have been +automatically created. In most cases the BUS a device is attached to +can be inferred, for example PCI devices are generally automatically +allocated to the next free address of first PCI bus found. However in +complicated configurations you can explicitly specify what bus +(``bus=ID``) a device is attached to along with its address +(``addr=N``). + +Some devices, for example a PCI SCSI host controller, will add an +additional buses to the system that other devices can be attached to. +A hypothetical chain of devices might look like: + + --device foo,bus=pci.0,addr=0,id=foo + --device bar,bus=foo.0,addr=1,id=baz + +which would be a bar device (with the ID of baz) which is attached to +the first foo bus (foo.0) at address 1. The foo device which provides +that bus is itself is attached to the first PCI bus (pci.0). + + +Device Back End +=============== + +The back end describes how the data from the emulated device will be +processed by QEMU. The configuration of the back end is usually +specific to the class of device being emulated. For example serial +devices will be backed by a ``--chardev`` which can redirect the data +to a file or socket or some other system. Storage devices are handled +by ``--blockdev`` which will specify how blocks are handled, for +example being stored in a qcow2 file or accessing a raw host disk +partition. Back ends can sometimes be stacked to implement features +like snapshots. + +While the choice of back end is generally transparent to the guest, +there are cases where features will not be reported to the guest if +the back end is unable to support it. + +Device Pass Through +=================== + +Device pass through is where the device is actually given access to +the underlying hardware. This can be as simple as exposing a single +USB device on the host system to the guest or dedicating a video card +in a PCI slot to the exclusive use of the guest. + + +Emulated Devices +~~~~~~~~~~~~~~~~ + +.. toctree:: + :maxdepth: 1 + + devices/ivshmem.rst + devices/net.rst + devices/nvme.rst + devices/usb.rst + devices/vhost-user.rst + devices/virtio-pmem.rst diff --git a/docs/system/device-url-syntax.rst.inc b/docs/system/device-url-syntax.rst.inc index 6f6ec8366b..d15a021508 100644 --- a/docs/system/device-url-syntax.rst.inc +++ b/docs/system/device-url-syntax.rst.inc @@ -85,24 +85,6 @@ These are specified using a special URL syntax. Currently authentication must be done using ssh-agent. Other authentication methods may be supported in future. -``Sheepdog`` - Sheepdog is a distributed storage system for QEMU. QEMU supports - using either local sheepdog devices or remote networked devices. - - Syntax for specifying a sheepdog device - - :: - - sheepdog[+tcp|+unix]://[host:port]/vdiname[?socket=path][#snapid|#tag] - - Example - - .. parsed-literal:: - - |qemu_system| --drive file=sheepdog://192.0.2.1:30000/MyVirtualMachine - - See also https://sheepdog.github.io/sheepdog/. - ``GlusterFS`` GlusterFS is a user space distributed file system. QEMU supports the use of GlusterFS volumes for hosting VM disk images using TCP, Unix diff --git a/docs/system/ivshmem.rst b/docs/system/devices/ivshmem.rst similarity index 100% rename from docs/system/ivshmem.rst rename to docs/system/devices/ivshmem.rst diff --git a/docs/system/net.rst b/docs/system/devices/net.rst similarity index 100% rename from docs/system/net.rst rename to docs/system/devices/net.rst diff --git a/docs/system/nvme.rst b/docs/system/devices/nvme.rst similarity index 92% rename from docs/system/nvme.rst rename to docs/system/devices/nvme.rst index f7f63d6bf6..bff72d1c24 100644 --- a/docs/system/nvme.rst +++ b/docs/system/devices/nvme.rst @@ -81,6 +81,12 @@ There are a number of parameters available: Set the UUID of the namespace. This will be reported as a "Namespace UUID" descriptor in the Namespace Identification Descriptor List. +``eui64`` + Set the EUI-64 of the namespace. This will be reported as a "IEEE Extended + Unique Identifier" descriptor in the Namespace Identification Descriptor List. + Since machine type 6.1 a non-zero default value is used if the parameter + is not provided. For earlier machine types the field defaults to 0. + ``bus`` If there are more ``nvme`` devices defined, this parameter may be used to attach the namespace to a specific ``nvme`` device (identified by an ``id`` @@ -196,6 +202,12 @@ The namespace may be configured with additional parameters allows all zones to be open. If ``zoned.max_active`` is specified, this value must be less than or equal to that. +``zoned.zasl=UINT8`` (default: ``0``) + Set the maximum data transfer size for the Zone Append command. Like + ``mdts``, the value is specified as a power of two (2^n) and is in units of + the minimum memory page size (CAP.MPSMIN). The default value (``0``) + has this property inherit the ``mdts`` value. + Metadata -------- diff --git a/docs/system/devices/usb.rst b/docs/system/devices/usb.rst new file mode 100644 index 0000000000..afb7d6c226 --- /dev/null +++ b/docs/system/devices/usb.rst @@ -0,0 +1,351 @@ +.. _pcsys_005fusb: + +USB emulation +------------- + +QEMU can emulate a PCI UHCI, OHCI, EHCI or XHCI USB controller. You can +plug virtual USB devices or real host USB devices (only works with +certain host operating systems). QEMU will automatically create and +connect virtual USB hubs as necessary to connect multiple USB devices. + +USB controllers +~~~~~~~~~~~~~~~ + +XHCI controller support +^^^^^^^^^^^^^^^^^^^^^^^ + +QEMU has XHCI host adapter support. The XHCI hardware design is much +more virtualization-friendly when compared to EHCI and UHCI, thus XHCI +emulation uses less resources (especially CPU). So if your guest +supports XHCI (which should be the case for any operating system +released around 2010 or later) we recommend using it: + + qemu -device qemu-xhci + +XHCI supports USB 1.1, USB 2.0 and USB 3.0 devices, so this is the +only controller you need. With only a single USB controller (and +therefore only a single USB bus) present in the system there is no +need to use the bus= parameter when adding USB devices. + + +EHCI controller support +^^^^^^^^^^^^^^^^^^^^^^^ + +The QEMU EHCI Adapter supports USB 2.0 devices. It can be used either +standalone or with companion controllers (UHCI, OHCI) for USB 1.1 +devices. The companion controller setup is more convenient to use +because it provides a single USB bus supporting both USB 2.0 and USB +1.1 devices. See next section for details. + +When running EHCI in standalone mode you can add UHCI or OHCI +controllers for USB 1.1 devices too. Each controller creates its own +bus though, so there are two completely separate USB buses: One USB +1.1 bus driven by the UHCI controller and one USB 2.0 bus driven by +the EHCI controller. Devices must be attached to the correct +controller manually. + +The easiest way to add a UHCI controller to a ``pc`` machine is the +``-usb`` switch. QEMU will create the UHCI controller as function of +the PIIX3 chipset. The USB 1.1 bus will carry the name ``usb-bus.0``. + +You can use the standard ``-device`` switch to add a EHCI controller to +your virtual machine. It is strongly recommended to specify an ID for +the controller so the USB 2.0 bus gets an individual name, for example +``-device usb-ehci,id=ehci``. This will give you a USB 2.0 bus named +``ehci.0``. + +When adding USB devices using the ``-device`` switch you can specify the +bus they should be attached to. Here is a complete example: + +.. parsed-literal:: + + |qemu_system| -M pc ${otheroptions} \\ + -drive if=none,id=usbstick,format=raw,file=/path/to/image \\ + -usb \\ + -device usb-ehci,id=ehci \\ + -device usb-tablet,bus=usb-bus.0 \\ + -device usb-storage,bus=ehci.0,drive=usbstick + +This attaches a USB tablet to the UHCI adapter and a USB mass storage +device to the EHCI adapter. + + +Companion controller support +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The UHCI and OHCI controllers can attach to a USB bus created by EHCI +as companion controllers. This is done by specifying the ``masterbus`` +and ``firstport`` properties. ``masterbus`` specifies the bus name the +controller should attach to. ``firstport`` specifies the first port the +controller should attach to, which is needed as usually one EHCI +controller with six ports has three UHCI companion controllers with +two ports each. + +There is a config file in docs which will do all this for +you, which you can use like this: + +.. parsed-literal:: + + |qemu_system| -readconfig docs/config/ich9-ehci-uhci.cfg + +Then use ``bus=ehci.0`` to assign your USB devices to that bus. + +Using the ``-usb`` switch for ``q35`` machines will create a similar +USB controller configuration. + + +.. _Connecting USB devices: + +Connecting USB devices +~~~~~~~~~~~~~~~~~~~~~~ + +USB devices can be connected with the ``-device usb-...`` command line +option or the ``device_add`` monitor command. Available devices are: + +``usb-mouse`` + Virtual Mouse. This will override the PS/2 mouse emulation when + activated. + +``usb-tablet`` + Pointer device that uses absolute coordinates (like a touchscreen). + This means QEMU is able to report the mouse position without having + to grab the mouse. Also overrides the PS/2 mouse emulation when + activated. + +``usb-storage,drive=drive_id`` + Mass storage device backed by drive_id (see the :ref:`disk images` + chapter in the System Emulation Users Guide). This is the classic + bulk-only transport protocol used by 99% of USB sticks. This + example shows it connected to an XHCI USB controller and with + a drive backed by a raw format disk image: + + .. parsed-literal:: + + |qemu_system| [...] \\ + -drive if=none,id=stick,format=raw,file=/path/to/file.img \\ + -device nec-usb-xhci,id=xhci \\ + -device usb-storage,bus=xhci.0,drive=stick + +``usb-uas`` + USB attached SCSI device. This does not create a SCSI disk, so + you need to explicitly create a ``scsi-hd`` or ``scsi-cd`` device + on the command line, as well as using the ``-drive`` option to + specify what those disks are backed by. One ``usb-uas`` device can + handle multiple logical units (disks). This example creates three + logical units: two disks and one cdrom drive: + + .. parsed-literal:: + + |qemu_system| [...] \\ + -drive if=none,id=uas-disk1,format=raw,file=/path/to/file1.img \\ + -drive if=none,id=uas-disk2,format=raw,file=/path/to/file2.img \\ + -drive if=none,id=uas-cdrom,media=cdrom,format=raw,file=/path/to/image.iso \\ + -device nec-usb-xhci,id=xhci \\ + -device usb-uas,id=uas,bus=xhci.0 \\ + -device scsi-hd,bus=uas.0,scsi-id=0,lun=0,drive=uas-disk1 \\ + -device scsi-hd,bus=uas.0,scsi-id=0,lun=1,drive=uas-disk2 \\ + -device scsi-cd,bus=uas.0,scsi-id=0,lun=5,drive=uas-cdrom + +``usb-bot`` + Bulk-only transport storage device. This presents the guest with the + same USB bulk-only transport protocol interface as ``usb-storage``, but + the QEMU command line option works like ``usb-uas`` and does not + automatically create SCSI disks for you. ``usb-bot`` supports up to + 16 LUNs. Unlike ``usb-uas``, the LUN numbers must be continuous, + i.e. for three devices you must use 0+1+2. The 0+1+5 numbering from the + ``usb-uas`` example above won't work with ``usb-bot``. + +``usb-mtp,rootdir=dir`` + Media transfer protocol device, using dir as root of the file tree + that is presented to the guest. + +``usb-host,hostbus=bus,hostaddr=addr`` + Pass through the host device identified by bus and addr + +``usb-host,vendorid=vendor,productid=product`` + Pass through the host device identified by vendor and product ID + +``usb-wacom-tablet`` + Virtual Wacom PenPartner tablet. This device is similar to the + ``tablet`` above but it can be used with the tslib library because in + addition to touch coordinates it reports touch pressure. + +``usb-kbd`` + Standard USB keyboard. Will override the PS/2 keyboard (if present). + +``usb-serial,chardev=id`` + Serial converter. This emulates an FTDI FT232BM chip connected to + host character device id. + +``usb-braille,chardev=id`` + Braille device. This will use BrlAPI to display the braille output on + a real or fake device referenced by id. + +``usb-net[,netdev=id]`` + Network adapter that supports CDC ethernet and RNDIS protocols. id + specifies a netdev defined with ``-netdev …,id=id``. For instance, + user-mode networking can be used with + + .. parsed-literal:: + + |qemu_system| [...] -netdev user,id=net0 -device usb-net,netdev=net0 + +``usb-ccid`` + Smartcard reader device + +``usb-audio`` + USB audio device + +``u2f-{emulated,passthru}`` + Universal Second Factor device + +Physical port addressing +^^^^^^^^^^^^^^^^^^^^^^^^ + +For all the above USB devices, by default QEMU will plug the device +into the next available port on the specified USB bus, or onto +some available USB bus if you didn't specify one explicitly. +If you need to, you can also specify the physical port where +the device will show up in the guest. This can be done using the +``port`` property. UHCI has two root ports (1,2). EHCI has six root +ports (1-6), and the emulated (1.1) USB hub has eight ports. + +Plugging a tablet into UHCI port 1 works like this:: + + -device usb-tablet,bus=usb-bus.0,port=1 + +Plugging a hub into UHCI port 2 works like this:: + + -device usb-hub,bus=usb-bus.0,port=2 + +Plugging a virtual USB stick into port 4 of the hub just plugged works +this way:: + + -device usb-storage,bus=usb-bus.0,port=2.4,drive=... + +In the monitor, the ``device_add` command also accepts a ``port`` +property specification. If you want to unplug devices too you should +specify some unique id which you can use to refer to the device. +You can then use ``device_del`` to unplug the device later. +For example:: + + (qemu) device_add usb-tablet,bus=usb-bus.0,port=1,id=my-tablet + (qemu) device_del my-tablet + +Hotplugging USB storage +~~~~~~~~~~~~~~~~~~~~~~~ + +The ``usb-bot`` and ``usb-uas`` devices can be hotplugged. In the hotplug +case they are added with ``attached = false`` so the guest will not see +the device until the ``attached`` property is explicitly set to true. +That allows you to attach one or more scsi devices before making the +device visible to the guest. The workflow looks like this: + +#. ``device-add usb-bot,id=foo`` +#. ``device-add scsi-{hd,cd},bus=foo.0,lun=0`` +#. optionally add more devices (luns 1 ... 15) +#. ``scripts/qmp/qom-set foo.attached = true`` + +.. _host_005fusb_005fdevices: + +Using host USB devices on a Linux host +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +WARNING: this is an experimental feature. QEMU will slow down when using +it. USB devices requiring real time streaming (i.e. USB Video Cameras) +are not supported yet. + +1. If you use an early Linux 2.4 kernel, verify that no Linux driver is + actually using the USB device. A simple way to do that is simply to + disable the corresponding kernel module by renaming it from + ``mydriver.o`` to ``mydriver.o.disabled``. + +2. Verify that ``/proc/bus/usb`` is working (most Linux distributions + should enable it by default). You should see something like that: + + :: + + ls /proc/bus/usb + 001 devices drivers + +3. Since only root can access to the USB devices directly, you can + either launch QEMU as root or change the permissions of the USB + devices you want to use. For testing, the following suffices: + + :: + + chown -R myuid /proc/bus/usb + +4. Launch QEMU and do in the monitor: + + :: + + info usbhost + Device 1.2, speed 480 Mb/s + Class 00: USB device 1234:5678, USB DISK + + You should see the list of the devices you can use (Never try to use + hubs, it won't work). + +5. Add the device in QEMU by using: + + :: + + device_add usb-host,vendorid=0x1234,productid=0x5678 + + Normally the guest OS should report that a new USB device is plugged. + You can use the option ``-device usb-host,...`` to do the same. + +6. Now you can try to use the host USB device in QEMU. + +When relaunching QEMU, you may have to unplug and plug again the USB +device to make it work again (this is a bug). + +``usb-host`` properties for specifying the host device +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The example above uses the ``vendorid`` and ``productid`` to +specify which host device to pass through, but this is not +the only way to specify the host device. ``usb-host`` supports +the following properties: + +``hostbus=`` + Specifies the bus number the device must be attached to +``hostaddr=`` + Specifies the device address the device got assigned by the guest os +``hostport=`` + Specifies the physical port the device is attached to +``vendorid=`` + Specifies the vendor ID of the device +``productid=`` + Specifies the product ID of the device. + +In theory you can combine all these properties as you like. In +practice only a few combinations are useful: + +- ``vendorid`` and ``productid`` -- match for a specific device, pass it to + the guest when it shows up somewhere in the host. + +- ``hostbus`` and ``hostport`` -- match for a specific physical port in the + host, any device which is plugged in there gets passed to the + guest. + +- ``hostbus`` and ``hostaddr`` -- most useful for ad-hoc pass through as the + hostaddr isn't stable. The next time you plug the device into the host it + will get a new hostaddr. + +Note that on the host USB 1.1 devices are handled by UHCI/OHCI and USB +2.0 by EHCI. That means different USB devices plugged into the very +same physical port on the host may show up on different host buses +depending on the speed. Supposing that devices plugged into a given +physical port appear as bus 1 + port 1 for 2.0 devices and bus 3 + port 1 +for 1.1 devices, you can pass through any device plugged into that port +and also assign it to the correct USB bus in QEMU like this: + +.. parsed-literal:: + + |qemu_system| -M pc [...] \\ + -usb \\ + -device usb-ehci,id=ehci \\ + -device usb-host,bus=usb-bus.0,hostbus=3,hostport=1 \\ + -device usb-host,bus=ehci.0,hostbus=1,hostport=1 diff --git a/docs/system/devices/vhost-user.rst b/docs/system/devices/vhost-user.rst new file mode 100644 index 0000000000..86128114fa --- /dev/null +++ b/docs/system/devices/vhost-user.rst @@ -0,0 +1,59 @@ +.. _vhost_user: + +vhost-user back ends +-------------------- + +vhost-user back ends are way to service the request of VirtIO devices +outside of QEMU itself. To do this there are a number of things +required. + +vhost-user device +=================== + +These are simple stub devices that ensure the VirtIO device is visible +to the guest. The code is mostly boilerplate although each device has +a ``chardev`` option which specifies the ID of the ``--chardev`` +device that connects via a socket to the vhost-user *daemon*. + +vhost-user daemon +================= + +This is a separate process that is connected to by QEMU via a socket +following the :ref:`vhost_user_proto`. There are a number of daemons +that can be built when enabled by the project although any daemon that +meets the specification for a given device can be used. + +Shared memory object +==================== + +In order for the daemon to access the VirtIO queues to process the +requests it needs access to the guest's address space. This is +achieved via the ``memory-backend-file`` or ``memory-backend-memfd`` +objects. A reference to a file-descriptor which can access this object +will be passed via the socket as part of the protocol negotiation. + +Currently the shared memory object needs to match the size of the main +system memory as defined by the ``-m`` argument. + +Example +======= + +First start you daemon. + +.. parsed-literal:: + + $ virtio-foo --socket-path=/var/run/foo.sock $OTHER_ARGS + +The you start your QEMU instance specifying the device, chardev and +memory objects. + +.. parsed-literal:: + + $ |qemu_system| \\ + -m 4096 \\ + -chardev socket,id=ba1,path=/var/run/foo.sock \\ + -device vhost-user-foo,chardev=ba1,$OTHER_ARGS \\ + -object memory-backend-memfd,id=mem,size=4G,share=on \\ + -numa node,memdev=mem \\ + ... + diff --git a/docs/system/virtio-pmem.rst b/docs/system/devices/virtio-pmem.rst similarity index 100% rename from docs/system/virtio-pmem.rst rename to docs/system/devices/virtio-pmem.rst diff --git a/docs/system/generic-loader.rst b/docs/system/generic-loader.rst index 6bf8a4eb48..4f9fb005f1 100644 --- a/docs/system/generic-loader.rst +++ b/docs/system/generic-loader.rst @@ -1,8 +1,8 @@ .. Copyright (c) 2016, Xilinx Inc. -This work is licensed under the terms of the GNU GPL, version 2 or later. See -the COPYING file in the top-level directory. + This work is licensed under the terms of the GNU GPL, version 2 or later. See + the COPYING file in the top-level directory. Generic Loader -------------- @@ -92,9 +92,12 @@ shown below: specified in the executable format header. This option should only be used for the boot image. This will also cause the image to be written to the specified CPU's address space. If not specified, the - default is CPU 0. - Setting force-raw=on forces the file - to be treated as a raw image. This can be used to load supported - executable formats as if they were raw. + default is CPU 0. + +```` + Setting 'force-raw=on' forces the file to be treated as a raw image. + This can be used to load supported executable formats as if they + were raw. All values are parsed using the standard QemuOpts parsing. This allows the user to specify any values in any format supported. By default the values diff --git a/docs/system/guest-loader.rst b/docs/system/guest-loader.rst index 37d03cbd89..4320d1183f 100644 --- a/docs/system/guest-loader.rst +++ b/docs/system/guest-loader.rst @@ -4,7 +4,7 @@ Guest Loader ------------ -The guest loader is similar to the `generic-loader` although it is +The guest loader is similar to the ``generic-loader`` although it is aimed at a particular use case of loading hypervisor guests. This is useful for debugging hypervisors without having to jump through the hoops of firmware and boot-loaders. @@ -27,12 +27,12 @@ multi-boot capability. A typical example would look like: In the above example the Xen hypervisor is loaded by the -kernel parameter and passed it's boot arguments via -append. The Dom0 guest is loaded into the areas of memory. Each blob will get -`/chosen/module@` entry in the FDT to indicate it's location and +``/chosen/module@`` entry in the FDT to indicate it's location and size. Additional information can be passed with by using additional arguments. Currently the only supported machines which use FDT data to boot are -the ARM and RiscV `virt` machines. +the ARM and RiscV ``virt`` machines. Arguments ^^^^^^^^^ diff --git a/docs/system/index.rst b/docs/system/index.rst index b05af716a9..7b9276c05f 100644 --- a/docs/system/index.rst +++ b/docs/system/index.rst @@ -1,44 +1,35 @@ -.. This is the top level page for the 'system' manual. - - System Emulation ================ -This manual is the overall guide for users using QEMU +This section of the manual is the overall guide for users using QEMU for full system emulation (as opposed to user-mode emulation). This includes working with hypervisors such as KVM, Xen, Hax or Hypervisor.Framework. -Contents: - .. toctree:: :maxdepth: 3 quickstart invocation + device-emulation keys mux-chardev monitor images - net virtio-net-failover - usb - nvme - ivshmem linuxboot generic-loader guest-loader + barrier vnc-security tls + secrets + authz gdb managed-startup + bootindex cpu-hotplug - virtio-pmem pr-manager targets security multi-process - deprecated - removed-features - build-platforms - license diff --git a/docs/system/ppc/powernv.rst b/docs/system/ppc/powernv.rst index 43c58bc32e..4c4cdea527 100644 --- a/docs/system/ppc/powernv.rst +++ b/docs/system/ppc/powernv.rst @@ -48,15 +48,15 @@ Firmware -------- The OPAL firmware (OpenPower Abstraction Layer) for OpenPower systems -includes the runtime services `skiboot` and the bootloader kernel and -initramfs `skiroot`. Source code can be found on GitHub: +includes the runtime services ``skiboot`` and the bootloader kernel and +initramfs ``skiroot``. Source code can be found on GitHub: https://github.com/open-power. -Prebuilt images of `skiboot` and `skiboot` are made available on the `OpenPOWER `__ site. To boot a POWER9 machine, use the `witherspoon `__ images. For POWER8, use +Prebuilt images of ``skiboot`` and ``skiboot`` are made available on the `OpenPOWER `__ site. To boot a POWER9 machine, use the `witherspoon `__ images. For POWER8, use the `palmetto `__ images. -QEMU includes a prebuilt image of `skiboot` which is updated when a +QEMU includes a prebuilt image of ``skiboot`` which is updated when a more recent version is required by the models. Boot options diff --git a/docs/system/ppc/ppce500.rst b/docs/system/ppc/ppce500.rst new file mode 100644 index 0000000000..afc58f60f5 --- /dev/null +++ b/docs/system/ppc/ppce500.rst @@ -0,0 +1,164 @@ +ppce500 generic platform (``ppce500``) +====================================== + +QEMU for PPC supports a special ``ppce500`` machine designed for emulation and +virtualization purposes. + +Supported devices +----------------- + +The ``ppce500`` machine supports the following devices: + +* PowerPC e500 series core (e500v2/e500mc/e5500/e6500) +* Configuration, Control, and Status Register (CCSR) +* Multicore Programmable Interrupt Controller (MPIC) with MSI support +* 1 16550A UART device +* 1 Freescale MPC8xxx I2C controller +* 1 Pericom pt7c4338 RTC via I2C +* 1 Freescale MPC8xxx GPIO controller +* Power-off functionality via one GPIO pin +* 1 Freescale MPC8xxx PCI host controller +* VirtIO devices via PCI bus +* 1 Freescale Enhanced Triple Speed Ethernet controller (eTSEC) + +Hardware configuration information +---------------------------------- + +The ``ppce500`` machine automatically generates a device tree blob ("dtb") +which it passes to the guest, if there is no ``-dtb`` option. This provides +information about the addresses, interrupt lines and other configuration of +the various devices in the system. + +If users want to provide their own DTB, they can use the ``-dtb`` option. +These DTBs should have the following requirements: + +* The number of subnodes under /cpus node should match QEMU's ``-smp`` option +* The /memory reg size should match QEMU’s selected ram_size via ``-m`` + +Both ``qemu-system-ppc`` and ``qemu-system-ppc64`` provide emulation for the +following 32-bit PowerPC CPUs: + +* e500v2 +* e500mc + +Additionally ``qemu-system-ppc64`` provides support for the following 64-bit +PowerPC CPUs: + +* e5500 +* e6500 + +The CPU type can be specified via the ``-cpu`` command line. If not specified, +it creates a machine with e500v2 core. The following example shows an e6500 +based machine creation: + +.. code-block:: bash + + $ qemu-system-ppc64 -nographic -M ppce500 -cpu e6500 + +Boot options +------------ + +The ``ppce500`` machine can start using the standard -kernel functionality +for loading a payload like an OS kernel (e.g.: Linux), or U-Boot firmware. + +When -bios is omitted, the default pc-bios/u-boot.e500 firmware image is used +as the BIOS. QEMU follows below truth table to select which payload to execute: + +===== ========== ======= +-bios -kernel payload +===== ========== ======= + N N u-boot + N Y kernel + Y don't care u-boot +===== ========== ======= + +When both -bios and -kernel are present, QEMU loads U-Boot and U-Boot in turns +automatically loads the kernel image specified by the -kernel parameter via +U-Boot's built-in "bootm" command, hence a legacy uImage format is required in +such senario. + +Running Linux kernel +-------------------- + +Linux mainline v5.11 release is tested at the time of writing. To build a +Linux mainline kernel that can be booted by the ``ppce500`` machine in +64-bit mode, simply configure the kernel using the defconfig configuration: + +.. code-block:: bash + + $ export ARCH=powerpc + $ export CROSS_COMPILE=powerpc-linux- + $ make corenet64_smp_defconfig + $ make menuconfig + +then manually select the following configuration: + + Platform support > Freescale Book-E Machine Type > QEMU generic e500 platform + +To boot the newly built Linux kernel in QEMU with the ``ppce500`` machine: + +.. code-block:: bash + + $ qemu-system-ppc64 -M ppce500 -cpu e5500 -smp 4 -m 2G \ + -display none -serial stdio \ + -kernel vmlinux \ + -initrd /path/to/rootfs.cpio \ + -append "root=/dev/ram" + +To build a Linux mainline kernel that can be booted by the ``ppce500`` machine +in 32-bit mode, use the same 64-bit configuration steps except the defconfig +file should use corenet32_smp_defconfig. + +To boot the 32-bit Linux kernel: + +.. code-block:: bash + + $ qemu-system-ppc{64|32} -M ppce500 -cpu e500mc -smp 4 -m 2G \ + -display none -serial stdio \ + -kernel vmlinux \ + -initrd /path/to/rootfs.cpio \ + -append "root=/dev/ram" + +Running U-Boot +-------------- + +U-Boot mainline v2021.07 release is tested at the time of writing. To build a +U-Boot mainline bootloader that can be booted by the ``ppce500`` machine, use +the qemu-ppce500_defconfig with similar commands as described above for Linux: + +.. code-block:: bash + + $ export CROSS_COMPILE=powerpc-linux- + $ make qemu-ppce500_defconfig + +You will get u-boot file in the build tree. + +When U-Boot boots, you will notice the following if using with ``-cpu e6500``: + +.. code-block:: none + + CPU: Unknown, Version: 0.0, (0x00000000) + Core: e6500, Version: 2.0, (0x80400020) + +This is because we only specified a core name to QEMU and it does not have a +meaningful SVR value which represents an actual SoC that integrates such core. +You can specify a real world SoC device that QEMU has built-in support but all +these SoCs are e500v2 based MPC85xx series, hence you cannot test anything +built for P4080 (e500mc), P5020 (e5500) and T2080 (e6500). + +By default a VirtIO standard PCI networking device is connected as an ethernet +interface at PCI address 0.1.0, but we can switch that to an e1000 NIC by: + +.. code-block:: bash + + $ qemu-system-ppc -M ppce500 -smp 4 -m 2G \ + -display none -serial stdio \ + -bios u-boot \ + -nic tap,ifname=tap0,script=no,downscript=no,model=e1000 + +The QEMU ``ppce500`` machine can also dynamically instantiate an eTSEC device +if “-device eTSEC” is given to QEMU: + +.. code-block:: bash + + -netdev tap,ifname=tap0,script=no,downscript=no,id=net0 -device eTSEC,netdev=net0 diff --git a/docs/system/qemu-block-drivers.rst.inc b/docs/system/qemu-block-drivers.rst.inc index 60a064b232..16225710eb 100644 --- a/docs/system/qemu-block-drivers.rst.inc +++ b/docs/system/qemu-block-drivers.rst.inc @@ -547,75 +547,6 @@ also available. Here are some example of the older syntax: |qemu_system| linux2.img -hdb nbd:unix:/tmp/my_socket |qemu_system| -cdrom nbd:localhost:10809:exportname=debian-500-ppc-netinst - - -Sheepdog disk images -~~~~~~~~~~~~~~~~~~~~ - -Sheepdog is a distributed storage system for QEMU. It provides highly -available block level storage volumes that can be attached to -QEMU-based virtual machines. - -You can create a Sheepdog disk image with the command: - -.. parsed-literal:: - - qemu-img create sheepdog:///IMAGE SIZE - -where *IMAGE* is the Sheepdog image name and *SIZE* is its -size. - -To import the existing *FILENAME* to Sheepdog, you can use a -convert command. - -.. parsed-literal:: - - qemu-img convert FILENAME sheepdog:///IMAGE - -You can boot from the Sheepdog disk image with the command: - -.. parsed-literal:: - - |qemu_system| sheepdog:///IMAGE - -You can also create a snapshot of the Sheepdog image like qcow2. - -.. parsed-literal:: - - qemu-img snapshot -c TAG sheepdog:///IMAGE - -where *TAG* is a tag name of the newly created snapshot. - -To boot from the Sheepdog snapshot, specify the tag name of the -snapshot. - -.. parsed-literal:: - - |qemu_system| sheepdog:///IMAGE#TAG - -You can create a cloned image from the existing snapshot. - -.. parsed-literal:: - - qemu-img create -b sheepdog:///BASE#TAG sheepdog:///IMAGE - -where *BASE* is an image name of the source snapshot and *TAG* -is its tag name. - -You can use an unix socket instead of an inet socket: - -.. parsed-literal:: - - |qemu_system| sheepdog+unix:///IMAGE?socket=PATH - -If the Sheepdog daemon doesn't run on the local host, you need to -specify one of the Sheepdog servers to connect to. - -.. parsed-literal:: - - qemu-img create sheepdog://HOSTNAME:PORT/IMAGE SIZE - |qemu_system| sheepdog://HOSTNAME:PORT/IMAGE - iSCSI LUNs ~~~~~~~~~~ diff --git a/docs/system/riscv/microchip-icicle-kit.rst b/docs/system/riscv/microchip-icicle-kit.rst index 4fe97bce3f..40798b1aae 100644 --- a/docs/system/riscv/microchip-icicle-kit.rst +++ b/docs/system/riscv/microchip-icicle-kit.rst @@ -15,33 +15,53 @@ Supported devices The ``microchip-icicle-kit`` machine supports the following devices: - * 1 E51 core - * 4 U54 cores - * Core Level Interruptor (CLINT) - * Platform-Level Interrupt Controller (PLIC) - * L2 Loosely Integrated Memory (L2-LIM) - * DDR memory controller - * 5 MMUARTs - * 1 DMA controller - * 2 GEM Ethernet controllers - * 1 SDHC storage controller +* 1 E51 core +* 4 U54 cores +* Core Level Interruptor (CLINT) +* Platform-Level Interrupt Controller (PLIC) +* L2 Loosely Integrated Memory (L2-LIM) +* DDR memory controller +* 5 MMUARTs +* 1 DMA controller +* 2 GEM Ethernet controllers +* 1 SDHC storage controller Boot options ------------ The ``microchip-icicle-kit`` machine can start using the standard -bios functionality for loading its BIOS image, aka Hart Software Services (HSS_). -HSS loads the second stage bootloader U-Boot from an SD card. It does not -support direct kernel loading via the -kernel option. One has to load kernel -from U-Boot. +HSS loads the second stage bootloader U-Boot from an SD card. Then a kernel +can be loaded from U-Boot. It also supports direct kernel booting via the +-kernel option along with the device tree blob via -dtb. When direct kernel +boot is used, the OpenSBI fw_dynamic BIOS image is used to boot a payload +like U-Boot or OS kernel directly. + +The user provided DTB should have the following requirements: + +* The /cpus node should contain at least one subnode for E51 and the number + of subnodes should match QEMU's ``-smp`` option +* The /memory reg size should match QEMU’s selected ram_size via ``-m`` +* Should contain a node for the CLINT device with a compatible string + "riscv,clint0" + +QEMU follows below truth table to select which payload to execute: + +===== ========== ========== ======= +-bios -kernel -dtb payload +===== ========== ========== ======= + N N don't care HSS + Y don't care don't care HSS + N Y Y kernel +===== ========== ========== ======= The memory is set to 1537 MiB by default which is the minimum required high memory size by HSS. A sanity check on ram size is performed in the machine init routine to prompt user to increase the RAM size to > 1537 MiB when less than 1537 MiB ram is detected. -Boot the machine ----------------- +Running HSS +----------- HSS 2020.12 release is tested at the time of writing. To build an HSS image that can be booted by the ``microchip-icicle-kit`` machine, type the following @@ -75,7 +95,7 @@ Then we can boot the machine by: -serial chardev:serial1 With above command line, current terminal session will be used for the first -serial port. Open another terminal window, and use `minicom` to connect the +serial port. Open another terminal window, and use ``minicom`` to connect the second serial port. .. code-block:: bash @@ -86,4 +106,44 @@ HSS output is on the first serial port (stdio) and U-Boot outputs on the second serial port. U-Boot will automatically load the Linux kernel from the SD card image. +Direct Kernel Boot +------------------ + +Sometimes we just want to test booting a new kernel, and transforming the +kernel image to the format required by the HSS bootflow is tedious. We can +use '-kernel' for direct kernel booting just like other RISC-V machines do. + +In this mode, the OpenSBI fw_dynamic BIOS image for 'generic' platform is +used to boot an S-mode payload like U-Boot or OS kernel directly. + +For example, the following commands show building a U-Boot image from U-Boot +mainline v2021.07 for the Microchip Icicle Kit board: + +.. code-block:: bash + + $ export CROSS_COMPILE=riscv64-linux- + $ make microchip_mpfs_icicle_defconfig + +Then we can boot the machine by: + +.. code-block:: bash + + $ qemu-system-riscv64 -M microchip-icicle-kit -smp 5 -m 2G \ + -sd path/to/sdcard.img \ + -nic user,model=cadence_gem \ + -nic tap,ifname=tap,model=cadence_gem,script=no \ + -display none -serial stdio \ + -kernel path/to/u-boot/build/dir/u-boot.bin \ + -dtb path/to/u-boot/build/dir/u-boot.dtb + +CAVEATS: + +* Check the "stdout-path" property in the /chosen node in the DTB to determine + which serial port is used for the serial console, e.g.: if the console is set + to the second serial port, change to use "-serial null -serial stdio". +* The default U-Boot configuration uses CONFIG_OF_SEPARATE hence the ELF image + ``u-boot`` cannot be passed to "-kernel" as it does not contain the DTB hence + ``u-boot.bin`` has to be used which does contain one. To use the ELF image, + we need to change to CONFIG_OF_EMBED or CONFIG_OF_PRIOR_STAGE. + .. _HSS: https://github.com/polarfire-soc/hart-software-services diff --git a/docs/system/riscv/shakti-c.rst b/docs/system/riscv/shakti-c.rst new file mode 100644 index 0000000000..a6035d42b0 --- /dev/null +++ b/docs/system/riscv/shakti-c.rst @@ -0,0 +1,82 @@ +Shakti C Reference Platform (``shakti_c``) +========================================== + +Shakti C Reference Platform is a reference platform based on arty a7 100t +for the Shakti SoC. + +Shakti SoC is a SoC based on the Shakti C-class processor core. Shakti C +is a 64bit RV64GCSUN processor core. + +For more details on Shakti SoC, please see: +https://gitlab.com/shaktiproject/cores/shakti-soc/-/blob/master/fpga/boards/artya7-100t/c-class/README.rst + +For more info on the Shakti C-class core, please see: +https://c-class.readthedocs.io/en/latest/ + +Supported devices +----------------- + +The ``shakti_c`` machine supports the following devices: + + * 1 C-class core + * Core Level Interruptor (CLINT) + * Platform-Level Interrupt Controller (PLIC) + * 1 UART + +Boot options +------------ + +The ``shakti_c`` machine can start using the standard -bios +functionality for loading the baremetal application or opensbi. + +Boot the machine +---------------- + +Shakti SDK +~~~~~~~~~~ +Shakti SDK can be used to generate the baremetal example UART applications. + +.. code-block:: bash + + $ git clone https://gitlab.com/behindbytes/shakti-sdk.git + $ cd shakti-sdk + $ make software PROGRAM=loopback TARGET=artix7_100t + +Binary would be generated in: + software/examples/uart_applns/loopback/output/loopback.shakti + +You could also download the precompiled example applicatons using below +commands. + +.. code-block:: bash + + $ wget -c https://gitlab.com/behindbytes/shakti-binaries/-/raw/master/sdk/shakti_sdk_qemu.zip + $ unzip shakti_sdk_qemu.zip + +Then we can run the UART example using: + +.. code-block:: bash + + $ qemu-system-riscv64 -M shakti_c -nographic \ + -bios path/to/shakti_sdk_qemu/loopback.shakti + +OpenSBI +~~~~~~~ +We can also run OpenSBI with Test Payload. + +.. code-block:: bash + + $ git clone https://github.com/riscv/opensbi.git -b v0.9 + $ cd opensbi + $ wget -c https://gitlab.com/behindbytes/shakti-binaries/-/raw/master/dts/shakti.dtb + $ export CROSS_COMPILE=riscv64-unknown-elf- + $ export FW_FDT_PATH=./shakti.dtb + $ make PLATFORM=generic + +fw_payload.elf would be generated in build/platform/generic/firmware/fw_payload.elf. +Boot it using the below qemu command. + +.. code-block:: bash + + $ qemu-system-riscv64 -M shakti_c -nographic \ + -bios path/to/fw_payload.elf diff --git a/docs/system/riscv/sifive_u.rst b/docs/system/riscv/sifive_u.rst index 98e7562848..01108b5ecc 100644 --- a/docs/system/riscv/sifive_u.rst +++ b/docs/system/riscv/sifive_u.rst @@ -9,21 +9,21 @@ Supported devices The ``sifive_u`` machine supports the following devices: - * 1 E51 / E31 core - * Up to 4 U54 / U34 cores - * Core Level Interruptor (CLINT) - * Platform-Level Interrupt Controller (PLIC) - * Power, Reset, Clock, Interrupt (PRCI) - * L2 Loosely Integrated Memory (L2-LIM) - * DDR memory controller - * 2 UARTs - * 1 GEM Ethernet controller - * 1 GPIO controller - * 1 One-Time Programmable (OTP) memory with stored serial number - * 1 DMA controller - * 2 QSPI controllers - * 1 ISSI 25WP256 flash - * 1 SD card in SPI mode +* 1 E51 / E31 core +* Up to 4 U54 / U34 cores +* Core Local Interruptor (CLINT) +* Platform-Level Interrupt Controller (PLIC) +* Power, Reset, Clock, Interrupt (PRCI) +* L2 Loosely Integrated Memory (L2-LIM) +* DDR memory controller +* 2 UARTs +* 1 GEM Ethernet controller +* 1 GPIO controller +* 1 One-Time Programmable (OTP) memory with stored serial number +* 1 DMA controller +* 2 QSPI controllers +* 1 ISSI 25WP256 flash +* 1 SD card in SPI mode Please note the real world HiFive Unleashed board has a fixed configuration of 1 E51 core and 4 U54 core combination and the RISC-V core boots in 64-bit mode. @@ -36,12 +36,21 @@ Hardware configuration information ---------------------------------- The ``sifive_u`` machine automatically generates a device tree blob ("dtb") -which it passes to the guest. This provides information about the addresses, -interrupt lines and other configuration of the various devices in the system. -Guest software should discover the devices that are present in the generated -DTB instead of using a DTB for the real hardware, as some of the devices are -not modeled by QEMU and trying to access these devices may cause unexpected -behavior. +which it passes to the guest, if there is no ``-dtb`` option. This provides +information about the addresses, interrupt lines and other configuration of +the various devices in the system. Guest software should discover the devices +that are present in the generated DTB instead of using a DTB for the real +hardware, as some of the devices are not modeled by QEMU and trying to access +these devices may cause unexpected behavior. + +If users want to provide their own DTB, they can use the ``-dtb`` option. +These DTBs should have the following requirements: + +* The /cpus node should contain at least one subnode for E51 and the number + of subnodes should match QEMU's ``-smp`` option +* The /memory reg size should match QEMU’s selected ram_size via ``-m`` +* Should contain a node for the CLINT device with a compatible string + "riscv,clint0" if using with OpenSBI BIOS images Boot options ------------ @@ -122,6 +131,32 @@ To boot the newly built Linux kernel in QEMU with the ``sifive_u`` machine: -initrd /path/to/rootfs.ext4 \ -append "root=/dev/ram" +Alternatively, we can use a custom DTB to boot the machine by inserting a CLINT +node in fu540-c000.dtsi in the Linux kernel, + +.. code-block:: none + + clint: clint@2000000 { + compatible = "riscv,clint0"; + interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7 + &cpu1_intc 3 &cpu1_intc 7 + &cpu2_intc 3 &cpu2_intc 7 + &cpu3_intc 3 &cpu3_intc 7 + &cpu4_intc 3 &cpu4_intc 7>; + reg = <0x00 0x2000000 0x00 0x10000>; + }; + +with the following command line options: + +.. code-block:: bash + + $ qemu-system-riscv64 -M sifive_u -smp 5 -m 8G \ + -display none -serial stdio \ + -kernel arch/riscv/boot/Image \ + -dtb arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dtb \ + -initrd /path/to/rootfs.ext4 \ + -append "root=/dev/ram" + To build a Linux mainline kernel that can be booted by the ``sifive_u`` machine in 32-bit mode, use the rv32_defconfig configuration. A patch is required to fix the 32-bit boot issue for Linux kernel v5.10. diff --git a/docs/system/riscv/virt.rst b/docs/system/riscv/virt.rst new file mode 100644 index 0000000000..321d77e07d --- /dev/null +++ b/docs/system/riscv/virt.rst @@ -0,0 +1,138 @@ +'virt' Generic Virtual Platform (``virt``) +========================================== + +The ``virt`` board is a platform which does not correspond to any real hardware; +it is designed for use in virtual machines. It is the recommended board type +if you simply want to run a guest such as Linux and do not care about +reproducing the idiosyncrasies and limitations of a particular bit of +real-world hardware. + +Supported devices +----------------- + +The ``virt`` machine supports the following devices: + +* Up to 8 generic RV32GC/RV64GC cores, with optional extensions +* Core Local Interruptor (CLINT) +* Platform-Level Interrupt Controller (PLIC) +* CFI parallel NOR flash memory +* 1 NS16550 compatible UART +* 1 Google Goldfish RTC +* 1 SiFive Test device +* 8 virtio-mmio transport devices +* 1 generic PCIe host bridge +* The fw_cfg device that allows a guest to obtain data from QEMU + +Note that the default CPU is a generic RV32GC/RV64GC. Optional extensions +can be enabled via command line parameters, e.g.: ``-cpu rv64,x-h=true`` +enables the hypervisor extension for RV64. + +Hardware configuration information +---------------------------------- + +The ``virt`` machine automatically generates a device tree blob ("dtb") +which it passes to the guest, if there is no ``-dtb`` option. This provides +information about the addresses, interrupt lines and other configuration of +the various devices in the system. Guest software should discover the devices +that are present in the generated DTB. + +If users want to provide their own DTB, they can use the ``-dtb`` option. +These DTBs should have the following requirements: + +* The number of subnodes of the /cpus node should match QEMU's ``-smp`` option +* The /memory reg size should match QEMU’s selected ram_size via ``-m`` +* Should contain a node for the CLINT device with a compatible string + "riscv,clint0" if using with OpenSBI BIOS images + +Boot options +------------ + +The ``virt`` machine can start using the standard -kernel functionality +for loading a Linux kernel, a VxWorks kernel, an S-mode U-Boot bootloader +with the default OpenSBI firmware image as the -bios. It also supports +the recommended RISC-V bootflow: U-Boot SPL (M-mode) loads OpenSBI fw_dynamic +firmware and U-Boot proper (S-mode), using the standard -bios functionality. + +Running Linux kernel +-------------------- + +Linux mainline v5.12 release is tested at the time of writing. To build a +Linux mainline kernel that can be booted by the ``virt`` machine in +64-bit mode, simply configure the kernel using the defconfig configuration: + +.. code-block:: bash + + $ export ARCH=riscv + $ export CROSS_COMPILE=riscv64-linux- + $ make defconfig + $ make + +To boot the newly built Linux kernel in QEMU with the ``virt`` machine: + +.. code-block:: bash + + $ qemu-system-riscv64 -M virt -smp 4 -m 2G \ + -display none -serial stdio \ + -kernel arch/riscv/boot/Image \ + -initrd /path/to/rootfs.cpio \ + -append "root=/dev/ram" + +To build a Linux mainline kernel that can be booted by the ``virt`` machine +in 32-bit mode, use the rv32_defconfig configuration. A patch is required to +fix the 32-bit boot issue for Linux kernel v5.12. + +.. code-block:: bash + + $ export ARCH=riscv + $ export CROSS_COMPILE=riscv64-linux- + $ curl https://patchwork.kernel.org/project/linux-riscv/patch/20210627135117.28641-1-bmeng.cn@gmail.com/mbox/ > riscv.patch + $ git am riscv.patch + $ make rv32_defconfig + $ make + +Replace ``qemu-system-riscv64`` with ``qemu-system-riscv32`` in the command +line above to boot the 32-bit Linux kernel. A rootfs image containing 32-bit +applications shall be used in order for kernel to boot to user space. + +Running U-Boot +-------------- + +U-Boot mainline v2021.04 release is tested at the time of writing. To build an +S-mode U-Boot bootloader that can be booted by the ``virt`` machine, use +the qemu-riscv64_smode_defconfig with similar commands as described above for Linux: + +.. code-block:: bash + + $ export CROSS_COMPILE=riscv64-linux- + $ make qemu-riscv64_smode_defconfig + +Boot the 64-bit U-Boot S-mode image directly: + +.. code-block:: bash + + $ qemu-system-riscv64 -M virt -smp 4 -m 2G \ + -display none -serial stdio \ + -kernel /path/to/u-boot.bin + +To test booting U-Boot SPL which in M-mode, which in turn loads a FIT image +that bundles OpenSBI fw_dynamic firmware and U-Boot proper (S-mode) together, +build the U-Boot images using riscv64_spl_defconfig: + +.. code-block:: bash + + $ export CROSS_COMPILE=riscv64-linux- + $ export OPENSBI=/path/to/opensbi-riscv64-generic-fw_dynamic.bin + $ make qemu-riscv64_spl_defconfig + +The minimal QEMU commands to run U-Boot SPL are: + +.. code-block:: bash + + $ qemu-system-riscv64 -M virt -smp 4 -m 2G \ + -display none -serial stdio \ + -bios /path/to/u-boot-spl \ + -device loader,file=/path/to/u-boot.itb,addr=0x80200000 + +To test 32-bit U-Boot images, switch to use qemu-riscv32_smode_defconfig and +riscv32_spl_defconfig builds, and replace ``qemu-system-riscv64`` with +``qemu-system-riscv32`` in the command lines above to boot the 32-bit U-Boot. diff --git a/docs/system/s390x/protvirt.rst b/docs/system/s390x/protvirt.rst index 0f481043d9..aee63ed7ec 100644 --- a/docs/system/s390x/protvirt.rst +++ b/docs/system/s390x/protvirt.rst @@ -14,11 +14,11 @@ Prerequisites To run PVMs, a machine with the Protected Virtualization feature, as indicated by the Ultravisor Call facility (stfle bit 158), is required. The Ultravisor needs to be initialized at boot by setting -`prot_virt=1` on the host's kernel command line. +``prot_virt=1`` on the host's kernel command line. Running PVMs requires using the KVM hypervisor. -If those requirements are met, the capability `KVM_CAP_S390_PROTECTED` +If those requirements are met, the capability ``KVM_CAP_S390_PROTECTED`` will indicate that KVM can support PVMs on that LPAR. @@ -26,15 +26,15 @@ Running a Protected Virtual Machine ----------------------------------- To run a PVM you will need to select a CPU model which includes the -`Unpack facility` (stfle bit 161 represented by the feature -`unpack`/`S390_FEAT_UNPACK`), and add these options to the command line:: +``Unpack facility`` (stfle bit 161 represented by the feature +``unpack``/``S390_FEAT_UNPACK``), and add these options to the command line:: -object s390-pv-guest,id=pv0 \ -machine confidential-guest-support=pv0 Adding these options will: -* Ensure the `unpack` facility is available +* Ensure the ``unpack`` facility is available * Enable the IOMMU by default for all I/O devices * Initialize the PV mechanism @@ -63,5 +63,5 @@ from the disk boot. This memory layout includes the encrypted components (kernel, initrd, cmdline), the stage3a loader and metadata. In case this boot method is used, the command line options -initrd and -cmdline are ineffective. The preparation of a PVM -image is done via the `genprotimg` tool from the s390-tools +image is done via the ``genprotimg`` tool from the s390-tools collection. diff --git a/docs/system/secrets.rst b/docs/system/secrets.rst new file mode 100644 index 0000000000..4a177369b6 --- /dev/null +++ b/docs/system/secrets.rst @@ -0,0 +1,162 @@ +.. _secret data: + +Providing secret data to QEMU +----------------------------- + +There are a variety of objects in QEMU which require secret data to be provided +by the administrator or management application. For example, network block +devices often require a password, LUKS block devices require a passphrase to +unlock key material, remote desktop services require an access password. +QEMU has a general purpose mechanism for providing secret data to QEMU in a +secure manner, using the ``secret`` object type. + +At startup this can be done using the ``-object secret,...`` command line +argument. At runtime this can be done using the ``object_add`` QMP / HMP +monitor commands. The examples that follow will illustrate use of ``-object`` +command lines, but they all apply equivalentely in QMP / HMP. When creating +a ``secret`` object it must be given a unique ID string. This ID is then +used to identify the object when configuring the thing which need the data. + + +INSECURE: Passing secrets as clear text inline +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +**The following should never be done in a production environment or on a +multi-user host. Command line arguments are usually visible in the process +listings and are often collected in log files by system monitoring agents +or bug reporting tools. QMP/HMP commands and their arguments are also often +logged and attached to bug reports. This all risks compromising secrets that +are passed inline.** + +For the convenience of people debugging / developing with QEMU, it is possible +to pass secret data inline on the command line. + +:: + + -object secret,id=secvnc0,data=87539319 + + +Again it is possible to provide the data in base64 encoded format, which is +particularly useful if the data contains binary characters that would clash +with argument parsing. + +:: + + -object secret,id=secvnc0,data=ODc1MzkzMTk=,format=base64 + + +**Note: base64 encoding does not provide any security benefit.** + +Passing secrets as clear text via a file +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The simplest approach to providing data securely is to use a file to store +the secret: + +:: + + -object secret,id=secvnc0,file=vnc-password.txt + + +In this example the file ``vnc-password.txt`` contains the plain text secret +data. It is important to note that the contents of the file are treated as an +opaque blob. The entire raw file contents is used as the value, thus it is +important not to mistakenly add any trailing newline character in the file if +this newline is not intended to be part of the secret data. + +In some cases it might be more convenient to pass the secret data in base64 +format and have QEMU decode to get the raw bytes before use: + +:: + + -object secret,id=sec0,file=vnc-password.txt,format=base64 + + +The file should generally be given mode ``0600`` or ``0400`` permissions, and +have its user/group ownership set to the same account that the QEMU process +will be launched under. If using mandatory access control such as SELinux, then +the file should be labelled to only grant access to the specific QEMU process +that needs access. This will prevent other processes/users from compromising the +secret data. + + +Passing secrets as cipher text inline +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +To address the insecurity of passing secrets inline as clear text, it is +possible to configure a second secret as an AES key to use for decrypting +the data. + +The secret used as the AES key must always be configured using the file based +storage mechanism: + +:: + + -object secret,id=secmaster,file=masterkey.data,format=base64 + + +In this case the ``masterkey.data`` file would be initialized with 32 +cryptographically secure random bytes, which are then base64 encoded. +The contents of this file will by used as an AES-256 key to encrypt the +real secret that can now be safely passed to QEMU inline as cipher text + +:: + + -object secret,id=secvnc0,keyid=secmaster,data=BASE64-CIPHERTEXT,iv=BASE64-IV,format=base64 + + +In this example ``BASE64-CIPHERTEXT`` is the result of AES-256-CBC encrypting +the secret with ``masterkey.data`` and then base64 encoding the ciphertext. +The ``BASE64-IV`` data is 16 random bytes which have been base64 encrypted. +These bytes are used as the initialization vector for the AES-256-CBC value. + +A single master key can be used to encrypt all subsequent secrets, **but it is +critical that a different initialization vector is used for every secret**. + +Passing secrets via the Linux keyring +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The earlier mechanisms described are platform agnostic. If using QEMU on a Linux +host, it is further possible to pass secrets to QEMU using the Linux keyring: + +:: + + -object secret_keyring,id=secvnc0,serial=1729 + + +This instructs QEMU to load data from the Linux keyring secret identified by +the serial number ``1729``. It is possible to combine use of the keyring with +other features mentioned earlier such as base64 encoding: + +:: + + -object secret_keyring,id=secvnc0,serial=1729,format=base64 + + +and also encryption with a master key: + +:: + + -object secret_keyring,id=secvnc0,keyid=secmaster,serial=1729,iv=BASE64-IV + + +Best practice +~~~~~~~~~~~~~ + +It is recommended for production deployments to use a master key secret, and +then pass all subsequent inline secrets encrypted with the master key. + +Each QEMU instance must have a distinct master key, and that must be generated +from a cryptographically secure random data source. The master key should be +deleted immediately upon QEMU shutdown. If passing the master key as a file, +the key file must have access control rules applied that restrict access to +just the one QEMU process that is intended to use it. Alternatively the Linux +keyring can be used to pass the master key to QEMU. + +The secrets for individual QEMU device backends must all then be encrypted +with this master key. + +This procedure helps ensure that the individual secrets for QEMU backends will +not be compromised, even if ``-object`` CLI args or ``object_add`` monitor +commands are collected in log files and attached to public bug support tickets. +The only item that needs strongly protecting is the master key file. diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index edd013c7bb..91ebc26c6d 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -85,10 +85,17 @@ undocumented; you can get a complete list by running arm/aspeed arm/sabrelite arm/digic + arm/cubieboard + arm/emcraft-sf2 + arm/highbank arm/musicpal arm/gumstix + arm/mainstone + arm/kzm + arm/nrf arm/nseries arm/nuvoton + arm/imx25-pdk arm/orangepi arm/palm arm/raspi @@ -96,9 +103,16 @@ undocumented; you can get a complete list by running arm/collie arm/sx1 arm/stellaris + arm/stm32 arm/virt arm/xlnx-versal-virt +Emulated CPU architecture support +================================= + +.. toctree:: + arm/emulation + Arm CPU features ================ diff --git a/docs/system/target-ppc.rst b/docs/system/target-ppc.rst index 67905b8f2a..4f6eb93b17 100644 --- a/docs/system/target-ppc.rst +++ b/docs/system/target-ppc.rst @@ -20,5 +20,6 @@ help``. ppc/embedded ppc/powermac ppc/powernv + ppc/ppce500 ppc/prep ppc/pseries diff --git a/docs/system/target-riscv.rst b/docs/system/target-riscv.rst index 8d5946fbbb..89a866e4f4 100644 --- a/docs/system/target-riscv.rst +++ b/docs/system/target-riscv.rst @@ -67,7 +67,20 @@ undocumented; you can get a complete list by running :maxdepth: 1 riscv/microchip-icicle-kit + riscv/shakti-c riscv/sifive_u + riscv/virt -RISC-V CPU features +RISC-V CPU firmware ------------------- + +When using the ``sifive_u`` or ``virt`` machine there are three different +firmware boot options: +1. ``-bios default`` - This is the default behaviour if no -bios option +is included. This option will load the default OpenSBI firmware automatically. +The firmware is included with the QEMU release and no user interaction is +required. All a user needs to do is specify the kernel they want to boot +with the -kernel option +2. ``-bios none`` - QEMU will not automatically load any firmware. It is up +to the user to load all the images they need. +3. ``-bios `` - Tells QEMU to load the specified file as the firmware. diff --git a/docs/system/usb.rst b/docs/system/usb.rst deleted file mode 100644 index eeab78dcfb..0000000000 --- a/docs/system/usb.rst +++ /dev/null @@ -1,140 +0,0 @@ -.. _pcsys_005fusb: - -USB emulation -------------- - -QEMU can emulate a PCI UHCI, OHCI, EHCI or XHCI USB controller. You can -plug virtual USB devices or real host USB devices (only works with -certain host operating systems). QEMU will automatically create and -connect virtual USB hubs as necessary to connect multiple USB devices. - -.. _Connecting USB devices: - -Connecting USB devices -~~~~~~~~~~~~~~~~~~~~~~ - -USB devices can be connected with the ``-device usb-...`` command line -option or the ``device_add`` monitor command. Available devices are: - -``usb-mouse`` - Virtual Mouse. This will override the PS/2 mouse emulation when - activated. - -``usb-tablet`` - Pointer device that uses absolute coordinates (like a touchscreen). - This means QEMU is able to report the mouse position without having - to grab the mouse. Also overrides the PS/2 mouse emulation when - activated. - -``usb-storage,drive=drive_id`` - Mass storage device backed by drive_id (see the :ref:`disk images` - chapter in the System Emulation Users Guide) - -``usb-uas`` - USB attached SCSI device, see - `usb-storage.txt `__ - for details - -``usb-bot`` - Bulk-only transport storage device, see - `usb-storage.txt `__ - for details here, too - -``usb-mtp,rootdir=dir`` - Media transfer protocol device, using dir as root of the file tree - that is presented to the guest. - -``usb-host,hostbus=bus,hostaddr=addr`` - Pass through the host device identified by bus and addr - -``usb-host,vendorid=vendor,productid=product`` - Pass through the host device identified by vendor and product ID - -``usb-wacom-tablet`` - Virtual Wacom PenPartner tablet. This device is similar to the - ``tablet`` above but it can be used with the tslib library because in - addition to touch coordinates it reports touch pressure. - -``usb-kbd`` - Standard USB keyboard. Will override the PS/2 keyboard (if present). - -``usb-serial,chardev=id`` - Serial converter. This emulates an FTDI FT232BM chip connected to - host character device id. - -``usb-braille,chardev=id`` - Braille device. This will use BrlAPI to display the braille output on - a real or fake device referenced by id. - -``usb-net[,netdev=id]`` - Network adapter that supports CDC ethernet and RNDIS protocols. id - specifies a netdev defined with ``-netdev …,id=id``. For instance, - user-mode networking can be used with - - .. parsed-literal:: - - |qemu_system| [...] -netdev user,id=net0 -device usb-net,netdev=net0 - -``usb-ccid`` - Smartcard reader device - -``usb-audio`` - USB audio device - -``u2f-{emulated,passthru}`` - Universal Second Factor device - -.. _host_005fusb_005fdevices: - -Using host USB devices on a Linux host -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -WARNING: this is an experimental feature. QEMU will slow down when using -it. USB devices requiring real time streaming (i.e. USB Video Cameras) -are not supported yet. - -1. If you use an early Linux 2.4 kernel, verify that no Linux driver is - actually using the USB device. A simple way to do that is simply to - disable the corresponding kernel module by renaming it from - ``mydriver.o`` to ``mydriver.o.disabled``. - -2. Verify that ``/proc/bus/usb`` is working (most Linux distributions - should enable it by default). You should see something like that: - - :: - - ls /proc/bus/usb - 001 devices drivers - -3. Since only root can access to the USB devices directly, you can - either launch QEMU as root or change the permissions of the USB - devices you want to use. For testing, the following suffices: - - :: - - chown -R myuid /proc/bus/usb - -4. Launch QEMU and do in the monitor: - - :: - - info usbhost - Device 1.2, speed 480 Mb/s - Class 00: USB device 1234:5678, USB DISK - - You should see the list of the devices you can use (Never try to use - hubs, it won't work). - -5. Add the device in QEMU by using: - - :: - - device_add usb-host,vendorid=0x1234,productid=0x5678 - - Normally the guest OS should report that a new USB device is plugged. - You can use the option ``-device usb-host,...`` to do the same. - -6. Now you can try to use the host USB device in QEMU. - -When relaunching QEMU, you may have to unplug and plug again the USB -device to make it work again (this is a bug). diff --git a/docs/system/vnc-security.rst b/docs/system/vnc-security.rst index 830f6acc73..4c1769eeb8 100644 --- a/docs/system/vnc-security.rst +++ b/docs/system/vnc-security.rst @@ -168,7 +168,7 @@ used is drastically reduced. In fact only the GSSAPI SASL mechanism provides an acceptable level of security by modern standards. Previous versions of QEMU referred to the DIGEST-MD5 mechanism, however, it has multiple serious flaws described in detail in RFC 6331 and thus should -never be used any more. The SCRAM-SHA-1 mechanism provides a simple +never be used any more. The SCRAM-SHA-256 mechanism provides a simple username/password auth facility similar to DIGEST-MD5, but does not support session encryption, so can only be used in combination with TLS. @@ -191,11 +191,12 @@ reasonable configuration is :: - mech_list: scram-sha-1 + mech_list: scram-sha-256 sasldb_path: /etc/qemu/passwd.db The ``saslpasswd2`` program can be used to populate the ``passwd.db`` -file with accounts. +file with accounts. Note that the ``passwd.db`` file stores passwords +in clear text. Other SASL configurations will be left as an exercise for the reader. Note that all mechanisms, except GSSAPI, should be combined with use of diff --git a/docs/tools/_templates/editpage.html b/docs/tools/_templates/editpage.html deleted file mode 100644 index 2a9c8fc92b..0000000000 --- a/docs/tools/_templates/editpage.html +++ /dev/null @@ -1,5 +0,0 @@ -
- -
diff --git a/docs/tools/index.rst b/docs/tools/index.rst index d923834a73..ef6041a490 100644 --- a/docs/tools/index.rst +++ b/docs/tools/index.rst @@ -1,11 +1,8 @@ -.. This is the top level page for the 'tools' manual - - Tools ===== - -Contents: +This section of the manual documents QEMU's "tools": its +command line utilities and other standalone programs. .. toctree:: :maxdepth: 2 diff --git a/docs/tools/qemu-img.rst b/docs/tools/qemu-img.rst index c9efcfaefc..b7d602a288 100644 --- a/docs/tools/qemu-img.rst +++ b/docs/tools/qemu-img.rst @@ -414,7 +414,7 @@ Command description: 4 Error on reading data -.. option:: convert [--object OBJECTDEF] [--image-opts] [--target-image-opts] [--target-is-zero] [--bitmaps] [-U] [-C] [-c] [-p] [-q] [-n] [-f FMT] [-t CACHE] [-T SRC_CACHE] [-O OUTPUT_FMT] [-B BACKING_FILE] [-o OPTIONS] [-l SNAPSHOT_PARAM] [-S SPARSE_SIZE] [-r RATE_LIMIT] [-m NUM_COROUTINES] [-W] FILENAME [FILENAME2 [...]] OUTPUT_FILENAME +.. option:: convert [--object OBJECTDEF] [--image-opts] [--target-image-opts] [--target-is-zero] [--bitmaps [--skip-broken-bitmaps]] [-U] [-C] [-c] [-p] [-q] [-n] [-f FMT] [-t CACHE] [-T SRC_CACHE] [-O OUTPUT_FMT] [-B BACKING_FILE] [-o OPTIONS] [-l SNAPSHOT_PARAM] [-S SPARSE_SIZE] [-r RATE_LIMIT] [-m NUM_COROUTINES] [-W] FILENAME [FILENAME2 [...]] OUTPUT_FILENAME Convert the disk image *FILENAME* or a snapshot *SNAPSHOT_PARAM* to disk image *OUTPUT_FILENAME* using format *OUTPUT_FMT*. It can @@ -456,6 +456,12 @@ Command description: *NUM_COROUTINES* specifies how many coroutines work in parallel during the convert process (defaults to 8). + Use of ``--bitmaps`` requests that any persistent bitmaps present in + the original are also copied to the destination. If any bitmap is + inconsistent in the source, the conversion will fail unless + ``--skip-broken-bitmaps`` is also specified to copy only the + consistent bitmaps. + .. option:: create [--object OBJECTDEF] [-q] [-f FMT] [-b BACKING_FILE] [-F BACKING_FMT] [-u] [-o OPTIONS] FILENAME [SIZE] Create the new disk image *FILENAME* of size *SIZE* and format @@ -593,13 +599,16 @@ Command description: the ``start``, ``length``, ``offset`` fields; it will also include other more specific information: - - whether the sectors contain actual data or not (boolean field ``data``; - if false, the sectors are either unallocated or stored as optimized - all-zero clusters); - - whether the data is known to read as zero (boolean field ``zero``); - - in order to make the output shorter, the target file is expressed as - a ``depth``; for example, a depth of 2 refers to the backing file - of the backing file of *FILENAME*. + - boolean field ``data``: true if the sectors contain actual data, + false if the sectors are either unallocated or stored as optimized + all-zero clusters + - boolean field ``zero``: true if the data is known to read as zero + - boolean field ``present``: true if the data belongs to the backing + chain, false if rebasing the backing chain onto a deeper file + would pick up data from the deeper file; + - integer field ``depth``: the depth within the backing chain at + which the data was resolved; for example, a depth of 2 refers to + the backing file of the backing file of *FILENAME*. In JSON format, the ``offset`` field is optional; it is absent in cases where ``human`` format would omit the entry or exit with an error. @@ -866,6 +875,37 @@ Supported image file formats: issue ``lsattr filename`` to check if the NOCOW flag is set or not (Capital 'C' is NOCOW flag). + ``data_file`` + Filename where all guest data will be stored. If this option is used, + the qcow2 file will only contain the image's metadata. + + Note: Data loss will occur if the given filename already exists when + using this option with ``qemu-img create`` since ``qemu-img`` will create + the data file anew, overwriting the file's original contents. To simply + update the reference to point to the given pre-existing file, use + ``qemu-img amend``. + + ``data_file_raw`` + If this option is set to ``on``, QEMU will always keep the external data + file consistent as a standalone read-only raw image. + + It does this by forwarding all write accesses to the qcow2 file through to + the raw data file, including their offsets. Therefore, data that is visible + on the qcow2 node (i.e., to the guest) at some offset is visible at the same + offset in the raw data file. This results in a read-only raw image. Writes + that bypass the qcow2 metadata may corrupt the qcow2 metadata because the + out-of-band writes may result in the metadata falling out of sync with the + raw image. + + If this option is ``off``, QEMU will use the data file to store data in an + arbitrary manner. The file’s content will not make sense without the + accompanying qcow2 metadata. Where data is written will have no relation to + its offset as seen by the guest, and some writes (specifically zero writes) + may not be forwarded to the data file at all, but will only be handled by + modifying qcow2 metadata. + + This option can only be enabled if ``data_file`` is set. + ``Other`` QEMU also supports various other image file formats for diff --git a/docs/tools/virtiofsd.rst b/docs/tools/virtiofsd.rst index 00554c75bd..b208f2a6f0 100644 --- a/docs/tools/virtiofsd.rst +++ b/docs/tools/virtiofsd.rst @@ -101,6 +101,9 @@ Options Enable/disable extended attributes (xattr) on files and directories. The default is ``no_xattr``. + * posix_acl|no_posix_acl - + Enable/disable posix acl support. Posix ACLs are disabled by default. + .. option:: --socket-path=PATH Listen on vhost-user UNIX domain socket at PATH. @@ -127,8 +130,8 @@ Options timeout. ``always`` sets a long cache lifetime at the expense of coherency. The default is ``auto``. -xattr-mapping -------------- +Extended attribute (xattr) mapping +---------------------------------- By default the name of xattr's used by the client are passed through to the server file system. This can be a problem where either those xattr names are used @@ -136,6 +139,9 @@ by something on the server (e.g. selinux client/server confusion) or if the virtiofsd is running in a container with restricted privileges where it cannot access some attributes. +Mapping syntax +~~~~~~~~~~~~~~ + A mapping of xattr names can be made using -o xattrmap=mapping where the ``mapping`` string consists of a series of rules. @@ -232,14 +238,54 @@ Note: When the 'security.capability' xattr is remapped, the daemon has to do extra work to remove it during many operations, which the host kernel normally does itself. -xattr-mapping Examples ----------------------- +Security considerations +~~~~~~~~~~~~~~~~~~~~~~~ + +Operating systems typically partition the xattr namespace using +well defined name prefixes. Each partition may have different +access controls applied. For example, on Linux there are multiple +partitions + + * ``system.*`` - access varies depending on attribute & filesystem + * ``security.*`` - only processes with CAP_SYS_ADMIN + * ``trusted.*`` - only processes with CAP_SYS_ADMIN + * ``user.*`` - any process granted by file permissions / ownership + +While other OS such as FreeBSD have different name prefixes +and access control rules. + +When remapping attributes on the host, it is important to +ensure that the remapping does not allow a guest user to +evade the guest access control rules. + +Consider if ``trusted.*`` from the guest was remapped to +``user.virtiofs.trusted*`` in the host. An unprivileged +user in a Linux guest has the ability to write to xattrs +under ``user.*``. Thus the user can evade the access +control restriction on ``trusted.*`` by instead writing +to ``user.virtiofs.trusted.*``. + +As noted above, the partitions used and access controls +applied, will vary across guest OS, so it is not wise to +try to predict what the guest OS will use. + +The simplest way to avoid an insecure configuration is +to remap all xattrs at once, to a given fixed prefix. +This is shown in example (1) below. + +If selectively mapping only a subset of xattr prefixes, +then rules must be added to explicitly block direct +access to the target of the remapping. This is shown +in example (2) below. + +Mapping examples +~~~~~~~~~~~~~~~~ 1) Prefix all attributes with 'user.virtiofs.' :: --o xattrmap=":prefix:all::user.virtiofs.::bad:all:::" + -o xattrmap=":prefix:all::user.virtiofs.::bad:all:::" This uses two rules, using : as the field separator; @@ -250,7 +296,8 @@ the host set. This is equivalent to the 'map' rule: :: --o xattrmap=":map::user.virtiofs.:" + + -o xattrmap=":map::user.virtiofs.:" 2) Prefix 'trusted.' attributes, allow others through @@ -270,14 +317,17 @@ stripping of 'user.virtiofs.'. The second rule hides unprefixed 'trusted.' attributes on the host. The third rule stops a guest from explicitly setting -the 'user.virtiofs.' path directly. +the 'user.virtiofs.' path directly to prevent access +control bypass on the target of the earlier prefix +remapping. Finally, the fourth rule lets all remaining attributes through. This is equivalent to the 'map' rule: :: --o xattrmap="/map/trusted./user.virtiofs./" + + -o xattrmap="/map/trusted./user.virtiofs./" 3) Hide 'security.' attributes, and allow everything else @@ -298,13 +348,13 @@ Examples Export ``/var/lib/fs/vm001/`` on vhost-user UNIX domain socket ``/var/run/vm001-vhost-fs.sock``: -:: +.. parsed-literal:: host# virtiofsd --socket-path=/var/run/vm001-vhost-fs.sock -o source=/var/lib/fs/vm001 - host# qemu-system-x86_64 \ - -chardev socket,id=char0,path=/var/run/vm001-vhost-fs.sock \ - -device vhost-user-fs-pci,chardev=char0,tag=myfs \ - -object memory-backend-memfd,id=mem,size=4G,share=on \ - -numa node,memdev=mem \ - ... + host# |qemu_system| \\ + -chardev socket,id=char0,path=/var/run/vm001-vhost-fs.sock \\ + -device vhost-user-fs-pci,chardev=char0,tag=myfs \\ + -object memory-backend-memfd,id=mem,size=4G,share=on \\ + -numa node,memdev=mem \\ + ... guest# mount -t virtiofs myfs /mnt diff --git a/docs/usb-storage.txt b/docs/usb-storage.txt deleted file mode 100644 index 551af6f88b..0000000000 --- a/docs/usb-storage.txt +++ /dev/null @@ -1,59 +0,0 @@ - -qemu usb storage emulation --------------------------- - -QEMU has three devices for usb storage emulation. - -Number one emulates the classic bulk-only transport protocol which is -used by 99% of the usb sticks on the market today and is called -"usb-storage". Usage (hooking up to xhci, other host controllers work -too): - - qemu ${other_vm_args} \ - -drive if=none,id=stick,file=/path/to/file.img \ - -device nec-usb-xhci,id=xhci \ - -device usb-storage,bus=xhci.0,drive=stick - - -Number two is the newer usb attached scsi transport. This one doesn't -automagically create a scsi disk, so you have to explicitly attach one -manually. Multiple logical units are supported. Here is an example -with tree logical units: - - qemu ${other_vm_args} \ - -drive if=none,id=uas-disk1,file=/path/to/file1.img \ - -drive if=none,id=uas-disk2,file=/path/to/file2.img \ - -drive if=none,id=uas-cdrom,media=cdrom,file=/path/to/image.iso \ - -device nec-usb-xhci,id=xhci \ - -device usb-uas,id=uas,bus=xhci.0 \ - -device scsi-hd,bus=uas.0,scsi-id=0,lun=0,drive=uas-disk1 \ - -device scsi-hd,bus=uas.0,scsi-id=0,lun=1,drive=uas-disk2 \ - -device scsi-cd,bus=uas.0,scsi-id=0,lun=5,drive=uas-cdrom - - -Number three emulates the classic bulk-only transport protocol too. -It's called "usb-bot". It shares most code with "usb-storage", and -the guest will not be able to see the difference. The qemu command -line interface is similar to usb-uas though, i.e. no automatic scsi -disk creation. It also features support for up to 16 LUNs. The LUN -numbers must be continuous, i.e. for three devices you must use 0+1+2. -The 0+1+5 numbering from the "usb-uas" example isn't going to work -with "usb-bot". - -Starting with qemu version 2.7 usb-bot and usb-uas devices can be -hotplugged. In the hotplug case they are added with "attached = -false" so the guest will not see the device until the "attached" -property is explicitly set to true. That allows to attach one or more -scsi devices before making the device visible to the guest, i.e. the -workflow looks like this: - - (1) device-add usb-bot,id=foo - (2) device-add scsi-{hd,cd},bus=foo.0,lun=0 - (2b) optionally add more devices (luns 1 ... 15). - (3) scripts/qmp/qom-set foo.attached = true - -enjoy, - Gerd - --- -Gerd Hoffmann diff --git a/docs/usb2.txt b/docs/usb2.txt deleted file mode 100644 index 172614d3a7..0000000000 --- a/docs/usb2.txt +++ /dev/null @@ -1,172 +0,0 @@ - -USB Quick Start -=============== - -XHCI controller support ------------------------ - -QEMU has XHCI host adapter support. The XHCI hardware design is much -more virtualization-friendly when compared to EHCI and UHCI, thus XHCI -emulation uses less resources (especially cpu). So if your guest -supports XHCI (which should be the case for any operating system -released around 2010 or later) we recommend using it: - - qemu -device qemu-xhci - -XHCI supports USB 1.1, USB 2.0 and USB 3.0 devices, so this is the -only controller you need. With only a single USB controller (and -therefore only a single USB bus) present in the system there is no -need to use the bus= parameter when adding USB devices. - - -EHCI controller support ------------------------ - -The QEMU EHCI Adapter supports USB 2.0 devices. It can be used either -standalone or with companion controllers (UHCI, OHCI) for USB 1.1 -devices. The companion controller setup is more convenient to use -because it provides a single USB bus supporting both USB 2.0 and USB -1.1 devices. See next section for details. - -When running EHCI in standalone mode you can add UHCI or OHCI -controllers for USB 1.1 devices too. Each controller creates its own -bus though, so there are two completely separate USB buses: One USB -1.1 bus driven by the UHCI controller and one USB 2.0 bus driven by -the EHCI controller. Devices must be attached to the correct -controller manually. - -The easiest way to add a UHCI controller to a 'pc' machine is the -'-usb' switch. QEMU will create the UHCI controller as function of -the PIIX3 chipset. The USB 1.1 bus will carry the name "usb-bus.0". - -You can use the standard -device switch to add a EHCI controller to -your virtual machine. It is strongly recommended to specify an ID for -the controller so the USB 2.0 bus gets an individual name, for example -'-device usb-ehci,id=ehci". This will give you a USB 2.0 bus named -"ehci.0". - -When adding USB devices using the -device switch you can specify the -bus they should be attached to. Here is a complete example: - - qemu -M pc ${otheroptions} \ - -drive if=none,id=usbstick,file=/path/to/image \ - -usb \ - -device usb-ehci,id=ehci \ - -device usb-tablet,bus=usb-bus.0 \ - -device usb-storage,bus=ehci.0,drive=usbstick - -This attaches a USB tablet to the UHCI adapter and a USB mass storage -device to the EHCI adapter. - - -Companion controller support ----------------------------- - -The UHCI and OHCI controllers can attach to a USB bus created by EHCI -as companion controllers. This is done by specifying the masterbus -and firstport properties. masterbus specifies the bus name the -controller should attach to. firstport specifies the first port the -controller should attach to, which is needed as usually one EHCI -controller with six ports has three UHCI companion controllers with -two ports each. - -There is a config file in docs which will do all this for -you, just try ... - - qemu -readconfig docs/config/ich9-ehci-uhci.cfg - -... then use "bus=ehci.0" to assign your USB devices to that bus. - -Using the '-usb' switch for 'q35' machines will create a similar -USB controller configuration. - - -More USB tips & tricks -====================== - -Recently the USB pass through driver (also known as usb-host) and the -QEMU USB subsystem gained a few capabilities which are available only -via qdev properties, i,e. when using '-device'. - - -physical port addressing ------------------------- - -First you can (for all USB devices) specify the physical port where -the device will show up in the guest. This can be done using the -"port" property. UHCI has two root ports (1,2). EHCI has six root -ports (1-6), the emulated (1.1) USB hub has eight ports. - -Plugging a tablet into UHCI port 1 works like this: - - -device usb-tablet,bus=usb-bus.0,port=1 - -Plugging a hub into UHCI port 2 works like this: - - -device usb-hub,bus=usb-bus.0,port=2 - -Plugging a virtual USB stick into port 4 of the hub just plugged works -this way: - - -device usb-storage,bus=usb-bus.0,port=2.4,drive=... - -You can do basically the same in the monitor using the device_add -command. If you want to unplug devices too you should specify some -unique id which you can use to refer to the device ... - - (qemu) device_add usb-tablet,bus=usb-bus.0,port=1,id=my-tablet - (qemu) device_del my-tablet - -... when unplugging it with device_del. - - -USB pass through hints ----------------------- - -The usb-host driver has a bunch of properties to specify the device -which should be passed to the guest: - - hostbus= -- Specifies the bus number the device must be attached - to. - - hostaddr= -- Specifies the device address the device got - assigned by the guest os. - - hostport= -- Specifies the physical port the device is attached - to. - - vendorid= -- Specifies the vendor ID of the device. - productid= -- Specifies the product ID of the device. - -In theory you can combine all these properties as you like. In -practice only a few combinations are useful: - - (1) vendorid+productid -- match for a specific device, pass it to - the guest when it shows up somewhere in the host. - - (2) hostbus+hostport -- match for a specific physical port in the - host, any device which is plugged in there gets passed to the - guest. - - (3) hostbus+hostaddr -- most useful for ad-hoc pass through as the - hostaddr isn't stable, the next time you plug in the device it - gets a new one ... - -Note that USB 1.1 devices are handled by UHCI/OHCI and USB 2.0 by -EHCI. That means a device plugged into the very same physical port -may show up on different buses depending on the speed. The port I'm -using for testing is bus 1 + port 1 for 2.0 devices and bus 3 + port 1 -for 1.1 devices. Passing through any device plugged into that port -and also assign them to the correct bus can be done this way: - - qemu -M pc ${otheroptions} \ - -usb \ - -device usb-ehci,id=ehci \ - -device usb-host,bus=usb-bus.0,hostbus=3,hostport=1 \ - -device usb-host,bus=ehci.0,hostbus=1,hostport=1 - -enjoy, - Gerd - --- -Gerd Hoffmann diff --git a/docs/user/_templates/editpage.html b/docs/user/_templates/editpage.html deleted file mode 100644 index 1f5ee01e60..0000000000 --- a/docs/user/_templates/editpage.html +++ /dev/null @@ -1,5 +0,0 @@ -
- -
diff --git a/docs/user/index.rst b/docs/user/index.rst index a5b47459ec..9faa4badd7 100644 --- a/docs/user/index.rst +++ b/docs/user/index.rst @@ -1,15 +1,10 @@ -.. This is the top level page for the 'user' manual. - - User Mode Emulation =================== -This manual is the overall guide for users using QEMU +This section of the manual is the overall guide for users using QEMU for user-mode emulation. In this mode, QEMU can launch processes compiled for one CPU on another CPU. -Contents: - .. toctree:: :maxdepth: 2 diff --git a/dump/dump.c b/dump/dump.c index 929138e91d..ab625909f3 100644 --- a/dump/dump.c +++ b/dump/dump.c @@ -15,7 +15,6 @@ #include "qemu-common.h" #include "qemu/cutils.h" #include "elf.h" -#include "cpu.h" #include "exec/hwaddr.h" #include "monitor/monitor.h" #include "sysemu/kvm.h" diff --git a/dump/win_dump.c b/dump/win_dump.c index 652c7bad99..c5eb5a9aac 100644 --- a/dump/win_dump.c +++ b/dump/win_dump.c @@ -12,7 +12,6 @@ #include "qemu-common.h" #include "qemu/cutils.h" #include "elf.h" -#include "cpu.h" #include "exec/hwaddr.h" #include "monitor/monitor.h" #include "sysemu/kvm.h" diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c new file mode 100644 index 0000000000..e71e229190 --- /dev/null +++ b/ebpf/ebpf_rss-stub.c @@ -0,0 +1,40 @@ +/* + * eBPF RSS stub file + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Yuri Benditovich + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "ebpf/ebpf_rss.h" + +void ebpf_rss_init(struct EBPFRSSContext *ctx) +{ + +} + +bool ebpf_rss_is_loaded(struct EBPFRSSContext *ctx) +{ + return false; +} + +bool ebpf_rss_load(struct EBPFRSSContext *ctx) +{ + return false; +} + +bool ebpf_rss_set_all(struct EBPFRSSContext *ctx, struct EBPFRSSConfig *config, + uint16_t *indirections_table, uint8_t *toeplitz_key) +{ + return false; +} + +void ebpf_rss_unload(struct EBPFRSSContext *ctx) +{ + +} diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c new file mode 100644 index 0000000000..118c68da83 --- /dev/null +++ b/ebpf/ebpf_rss.c @@ -0,0 +1,165 @@ +/* + * eBPF RSS loader + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Andrew Melnychenko + * Yuri Benditovich + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" + +#include +#include + +#include "hw/virtio/virtio-net.h" /* VIRTIO_NET_RSS_MAX_TABLE_LEN */ + +#include "ebpf/ebpf_rss.h" +#include "ebpf/rss.bpf.skeleton.h" +#include "trace.h" + +void ebpf_rss_init(struct EBPFRSSContext *ctx) +{ + if (ctx != NULL) { + ctx->obj = NULL; + } +} + +bool ebpf_rss_is_loaded(struct EBPFRSSContext *ctx) +{ + return ctx != NULL && ctx->obj != NULL; +} + +bool ebpf_rss_load(struct EBPFRSSContext *ctx) +{ + struct rss_bpf *rss_bpf_ctx; + + if (ctx == NULL) { + return false; + } + + rss_bpf_ctx = rss_bpf__open(); + if (rss_bpf_ctx == NULL) { + trace_ebpf_error("eBPF RSS", "can not open eBPF RSS object"); + goto error; + } + + bpf_program__set_socket_filter(rss_bpf_ctx->progs.tun_rss_steering_prog); + + if (rss_bpf__load(rss_bpf_ctx)) { + trace_ebpf_error("eBPF RSS", "can not load RSS program"); + goto error; + } + + ctx->obj = rss_bpf_ctx; + ctx->program_fd = bpf_program__fd( + rss_bpf_ctx->progs.tun_rss_steering_prog); + ctx->map_configuration = bpf_map__fd( + rss_bpf_ctx->maps.tap_rss_map_configurations); + ctx->map_indirections_table = bpf_map__fd( + rss_bpf_ctx->maps.tap_rss_map_indirection_table); + ctx->map_toeplitz_key = bpf_map__fd( + rss_bpf_ctx->maps.tap_rss_map_toeplitz_key); + + return true; +error: + rss_bpf__destroy(rss_bpf_ctx); + ctx->obj = NULL; + + return false; +} + +static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx, + struct EBPFRSSConfig *config) +{ + uint32_t map_key = 0; + + if (!ebpf_rss_is_loaded(ctx)) { + return false; + } + if (bpf_map_update_elem(ctx->map_configuration, + &map_key, config, 0) < 0) { + return false; + } + return true; +} + +static bool ebpf_rss_set_indirections_table(struct EBPFRSSContext *ctx, + uint16_t *indirections_table, + size_t len) +{ + uint32_t i = 0; + + if (!ebpf_rss_is_loaded(ctx) || indirections_table == NULL || + len > VIRTIO_NET_RSS_MAX_TABLE_LEN) { + return false; + } + + for (; i < len; ++i) { + if (bpf_map_update_elem(ctx->map_indirections_table, &i, + indirections_table + i, 0) < 0) { + return false; + } + } + return true; +} + +static bool ebpf_rss_set_toepliz_key(struct EBPFRSSContext *ctx, + uint8_t *toeplitz_key) +{ + uint32_t map_key = 0; + + /* prepare toeplitz key */ + uint8_t toe[VIRTIO_NET_RSS_MAX_KEY_SIZE] = {}; + + if (!ebpf_rss_is_loaded(ctx) || toeplitz_key == NULL) { + return false; + } + memcpy(toe, toeplitz_key, VIRTIO_NET_RSS_MAX_KEY_SIZE); + *(uint32_t *)toe = ntohl(*(uint32_t *)toe); + + if (bpf_map_update_elem(ctx->map_toeplitz_key, &map_key, toe, + 0) < 0) { + return false; + } + return true; +} + +bool ebpf_rss_set_all(struct EBPFRSSContext *ctx, struct EBPFRSSConfig *config, + uint16_t *indirections_table, uint8_t *toeplitz_key) +{ + if (!ebpf_rss_is_loaded(ctx) || config == NULL || + indirections_table == NULL || toeplitz_key == NULL) { + return false; + } + + if (!ebpf_rss_set_config(ctx, config)) { + return false; + } + + if (!ebpf_rss_set_indirections_table(ctx, indirections_table, + config->indirections_len)) { + return false; + } + + if (!ebpf_rss_set_toepliz_key(ctx, toeplitz_key)) { + return false; + } + + return true; +} + +void ebpf_rss_unload(struct EBPFRSSContext *ctx) +{ + if (!ebpf_rss_is_loaded(ctx)) { + return; + } + + rss_bpf__destroy(ctx->obj); + ctx->obj = NULL; +} diff --git a/ebpf/ebpf_rss.h b/ebpf/ebpf_rss.h new file mode 100644 index 0000000000..bf3f2572c7 --- /dev/null +++ b/ebpf/ebpf_rss.h @@ -0,0 +1,44 @@ +/* + * eBPF RSS header + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Andrew Melnychenko + * Yuri Benditovich + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#ifndef QEMU_EBPF_RSS_H +#define QEMU_EBPF_RSS_H + +struct EBPFRSSContext { + void *obj; + int program_fd; + int map_configuration; + int map_toeplitz_key; + int map_indirections_table; +}; + +struct EBPFRSSConfig { + uint8_t redirect; + uint8_t populate_hash; + uint32_t hash_types; + uint16_t indirections_len; + uint16_t default_queue; +} __attribute__((packed)); + +void ebpf_rss_init(struct EBPFRSSContext *ctx); + +bool ebpf_rss_is_loaded(struct EBPFRSSContext *ctx); + +bool ebpf_rss_load(struct EBPFRSSContext *ctx); + +bool ebpf_rss_set_all(struct EBPFRSSContext *ctx, struct EBPFRSSConfig *config, + uint16_t *indirections_table, uint8_t *toeplitz_key); + +void ebpf_rss_unload(struct EBPFRSSContext *ctx); + +#endif /* QEMU_EBPF_RSS_H */ diff --git a/ebpf/meson.build b/ebpf/meson.build new file mode 100644 index 0000000000..9cd0635370 --- /dev/null +++ b/ebpf/meson.build @@ -0,0 +1 @@ +common_ss.add(when: libbpf, if_true: files('ebpf_rss.c'), if_false: files('ebpf_rss-stub.c')) diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h new file mode 100644 index 0000000000..126683eb87 --- /dev/null +++ b/ebpf/rss.bpf.skeleton.h @@ -0,0 +1,431 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* THIS FILE IS AUTOGENERATED! */ +#ifndef __RSS_BPF_SKEL_H__ +#define __RSS_BPF_SKEL_H__ + +#include +#include + +struct rss_bpf { + struct bpf_object_skeleton *skeleton; + struct bpf_object *obj; + struct { + struct bpf_map *tap_rss_map_configurations; + struct bpf_map *tap_rss_map_indirection_table; + struct bpf_map *tap_rss_map_toeplitz_key; + } maps; + struct { + struct bpf_program *tun_rss_steering_prog; + } progs; + struct { + struct bpf_link *tun_rss_steering_prog; + } links; +}; + +static void +rss_bpf__destroy(struct rss_bpf *obj) +{ + if (!obj) + return; + if (obj->skeleton) + bpf_object__destroy_skeleton(obj->skeleton); + free(obj); +} + +static inline int +rss_bpf__create_skeleton(struct rss_bpf *obj); + +static inline struct rss_bpf * +rss_bpf__open_opts(const struct bpf_object_open_opts *opts) +{ + struct rss_bpf *obj; + + obj = (struct rss_bpf *)calloc(1, sizeof(*obj)); + if (!obj) + return NULL; + if (rss_bpf__create_skeleton(obj)) + goto err; + if (bpf_object__open_skeleton(obj->skeleton, opts)) + goto err; + + return obj; +err: + rss_bpf__destroy(obj); + return NULL; +} + +static inline struct rss_bpf * +rss_bpf__open(void) +{ + return rss_bpf__open_opts(NULL); +} + +static inline int +rss_bpf__load(struct rss_bpf *obj) +{ + return bpf_object__load_skeleton(obj->skeleton); +} + +static inline struct rss_bpf * +rss_bpf__open_and_load(void) +{ + struct rss_bpf *obj; + + obj = rss_bpf__open(); + if (!obj) + return NULL; + if (rss_bpf__load(obj)) { + rss_bpf__destroy(obj); + return NULL; + } + return obj; +} + +static inline int +rss_bpf__attach(struct rss_bpf *obj) +{ + return bpf_object__attach_skeleton(obj->skeleton); +} + +static inline void +rss_bpf__detach(struct rss_bpf *obj) +{ + return bpf_object__detach_skeleton(obj->skeleton); +} + +static inline int +rss_bpf__create_skeleton(struct rss_bpf *obj) +{ + struct bpf_object_skeleton *s; + + s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s)); + if (!s) + return -1; + obj->skeleton = s; + + s->sz = sizeof(*s); + s->name = "rss_bpf"; + s->obj = &obj->obj; + + /* maps */ + s->map_cnt = 3; + s->map_skel_sz = sizeof(*s->maps); + s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz); + if (!s->maps) + goto err; + + s->maps[0].name = "tap_rss_map_configurations"; + s->maps[0].map = &obj->maps.tap_rss_map_configurations; + + s->maps[1].name = "tap_rss_map_indirection_table"; + s->maps[1].map = &obj->maps.tap_rss_map_indirection_table; + + s->maps[2].name = "tap_rss_map_toeplitz_key"; + s->maps[2].map = &obj->maps.tap_rss_map_toeplitz_key; + + /* programs */ + s->prog_cnt = 1; + s->prog_skel_sz = sizeof(*s->progs); + s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz); + if (!s->progs) + goto err; + + s->progs[0].name = "tun_rss_steering_prog"; + s->progs[0].prog = &obj->progs.tun_rss_steering_prog; + s->progs[0].link = &obj->links.tun_rss_steering_prog; + + s->data_sz = 8088; + s->data = (void *)"\ +\x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x18\x1d\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0a\0\ +\x01\0\xbf\x18\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\ +\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x07\0\0\0\0\0\0\ +\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x66\x02\0\0\0\0\xbf\x79\0\0\ +\0\0\0\0\x15\x09\x64\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\ +\0\x5d\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\ +\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\ +\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\ +\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\ +\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\ +\xff\0\0\0\0\x15\x08\x4c\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\ +\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x81\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\ +\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\ +\x77\0\0\0\x20\0\0\0\x55\0\x11\0\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\xff\ +\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\x55\ +\x03\x0c\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\ +\xd0\xff\xff\xff\xbf\x81\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\ +\x85\0\0\0\x44\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\ +\0\0\0\x15\0\x01\0\0\0\0\0\x05\0\x2f\x02\0\0\0\0\x15\x01\x2e\x02\0\0\0\0\x7b\ +\x9a\x30\xff\0\0\0\0\x15\x01\x57\0\x86\xdd\0\0\x55\x01\x3b\0\x08\0\0\0\x7b\x7a\ +\x20\xff\0\0\0\0\xb7\x07\0\0\x01\0\0\0\x73\x7a\x50\xff\0\0\0\0\xb7\x01\0\0\0\0\ +\0\0\x63\x1a\xe0\xff\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\ +\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x81\0\0\0\0\0\0\xb7\x02\0\ +\0\0\0\0\0\xb7\x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\ +\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x1a\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\ +\0\0\x55\x01\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\ +\x5c\xff\0\0\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x60\xff\0\0\0\0\x73\x7a\x56\ +\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\ +\0\0\x57\x01\0\0\x3c\0\0\0\x7b\x1a\x40\xff\0\0\0\0\x79\xa7\x20\xff\0\0\0\0\xbf\ +\x91\0\0\0\0\0\0\x57\x01\0\0\xff\0\0\0\x15\x01\x19\0\0\0\0\0\x71\xa1\x56\xff\0\ +\0\0\0\x55\x01\x17\0\0\0\0\0\x57\x09\0\0\xff\0\0\0\x15\x09\x7a\x01\x11\0\0\0\ +\x55\x09\x14\0\x06\0\0\0\xb7\x01\0\0\x01\0\0\0\x73\x1a\x53\xff\0\0\0\0\xb7\x01\ +\0\0\0\0\0\0\x63\x1a\xe0\xff\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\ +\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x81\0\0\0\0\0\0\x79\ +\xa2\x40\xff\0\0\0\0\xb7\x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\ +\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\xf4\x01\0\0\0\0\x69\xa1\ +\xd0\xff\0\0\0\0\x6b\x1a\x58\xff\0\0\0\0\x69\xa1\xd2\xff\0\0\0\0\x6b\x1a\x5a\ +\xff\0\0\0\0\x71\xa1\x50\xff\0\0\0\0\x15\x01\xd4\0\0\0\0\0\x71\x62\x03\0\0\0\0\ +\0\x67\x02\0\0\x08\0\0\0\x71\x61\x02\0\0\0\0\0\x4f\x12\0\0\0\0\0\0\x71\x63\x04\ +\0\0\0\0\0\x71\x61\x05\0\0\0\0\0\x67\x01\0\0\x08\0\0\0\x4f\x31\0\0\0\0\0\0\x67\ +\x01\0\0\x10\0\0\0\x4f\x21\0\0\0\0\0\0\x71\xa2\x53\xff\0\0\0\0\x79\xa0\x30\xff\ +\0\0\0\0\x15\x02\x06\x01\0\0\0\0\xbf\x12\0\0\0\0\0\0\x57\x02\0\0\x02\0\0\0\x15\ +\x02\x03\x01\0\0\0\0\x61\xa1\x5c\xff\0\0\0\0\x63\x1a\xa0\xff\0\0\0\0\x61\xa1\ +\x60\xff\0\0\0\0\x63\x1a\xa4\xff\0\0\0\0\x69\xa1\x58\xff\0\0\0\0\x6b\x1a\xa8\ +\xff\0\0\0\0\x69\xa1\x5a\xff\0\0\0\0\x6b\x1a\xaa\xff\0\0\0\0\x05\0\x65\x01\0\0\ +\0\0\xb7\x01\0\0\x01\0\0\0\x73\x1a\x51\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x7b\x1a\ +\xf0\xff\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\x7b\x1a\xe0\xff\0\0\0\0\x7b\x1a\xd8\ +\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\xd0\xff\ +\xff\xff\xb7\x01\0\0\x28\0\0\0\x7b\x1a\x40\xff\0\0\0\0\xbf\x81\0\0\0\0\0\0\xb7\ +\x02\0\0\0\0\0\0\xb7\x04\0\0\x28\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\ +\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x10\x01\0\0\0\0\x79\xa1\xe0\ +\xff\0\0\0\0\x63\x1a\x64\xff\0\0\0\0\x77\x01\0\0\x20\0\0\0\x63\x1a\x68\xff\0\0\ +\0\0\x79\xa1\xd8\xff\0\0\0\0\x63\x1a\x5c\xff\0\0\0\0\x77\x01\0\0\x20\0\0\0\x63\ +\x1a\x60\xff\0\0\0\0\x79\xa1\xe8\xff\0\0\0\0\x63\x1a\x6c\xff\0\0\0\0\x77\x01\0\ +\0\x20\0\0\0\x63\x1a\x70\xff\0\0\0\0\x79\xa1\xf0\xff\0\0\0\0\x63\x1a\x74\xff\0\ +\0\0\0\x77\x01\0\0\x20\0\0\0\x63\x1a\x78\xff\0\0\0\0\x71\xa9\xd6\xff\0\0\0\0\ +\x25\x09\xff\0\x3c\0\0\0\xb7\x01\0\0\x01\0\0\0\x6f\x91\0\0\0\0\0\0\x18\x02\0\0\ +\x01\0\0\0\0\0\0\0\0\x18\0\x1c\x5f\x21\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\0\ +\xf8\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x6b\x1a\xfe\xff\0\0\0\0\xb7\x01\0\0\x28\0\0\ +\0\x7b\x1a\x40\xff\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\x8c\xff\xff\xff\x7b\ +\x1a\x18\xff\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\x7c\xff\xff\xff\x7b\x1a\ +\x10\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x7b\x1a\x28\xff\0\0\0\0\x7b\x7a\x20\xff\0\ +\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\xfe\xff\xff\xff\xbf\x81\0\0\0\0\0\0\x79\ +\xa2\x40\xff\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\ +\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x15\0\x01\0\0\0\0\0\x05\0\x90\ +\x01\0\0\0\0\xbf\x91\0\0\0\0\0\0\x15\x01\x23\0\x3c\0\0\0\x15\x01\x59\0\x2c\0\0\ +\0\x55\x01\x5a\0\x2b\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xf8\xff\0\0\0\0\xbf\xa3\ +\0\0\0\0\0\0\x07\x03\0\0\xf8\xff\xff\xff\xbf\x81\0\0\0\0\0\0\x79\xa2\x40\xff\0\ +\0\0\0\xb7\x04\0\0\x04\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\xbf\x01\ +\0\0\0\0\0\0\x67\x01\0\0\x20\0\0\0\x77\x01\0\0\x20\0\0\0\x55\x01\x03\x01\0\0\0\ +\0\x71\xa1\xfa\xff\0\0\0\0\x55\x01\x4b\0\x02\0\0\0\x71\xa1\xf9\xff\0\0\0\0\x55\ +\x01\x49\0\x02\0\0\0\x71\xa1\xfb\xff\0\0\0\0\x55\x01\x47\0\x01\0\0\0\x79\xa2\ +\x40\xff\0\0\0\0\x07\x02\0\0\x08\0\0\0\xbf\x81\0\0\0\0\0\0\x79\xa3\x18\xff\0\0\ +\0\0\xb7\x04\0\0\x10\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\xbf\x01\0\ +\0\0\0\0\0\x67\x01\0\0\x20\0\0\0\x77\x01\0\0\x20\0\0\0\x55\x01\xf2\0\0\0\0\0\ +\xb7\x01\0\0\x01\0\0\0\x73\x1a\x55\xff\0\0\0\0\x05\0\x39\0\0\0\0\0\xb7\x01\0\0\ +\0\0\0\0\x6b\x1a\xf8\xff\0\0\0\0\xb7\x09\0\0\x02\0\0\0\xb7\x07\0\0\x1e\0\0\0\ +\x05\0\x0e\0\0\0\0\0\x79\xa2\x38\xff\0\0\0\0\x0f\x29\0\0\0\0\0\0\xbf\x92\0\0\0\ +\0\0\0\x07\x02\0\0\x01\0\0\0\x71\xa3\xff\xff\0\0\0\0\x67\x03\0\0\x03\0\0\0\x2d\ +\x23\x02\0\0\0\0\0\x79\xa7\x20\xff\0\0\0\0\x05\0\x2b\0\0\0\0\0\x07\x07\0\0\xff\ +\xff\xff\xff\xbf\x72\0\0\0\0\0\0\x67\x02\0\0\x20\0\0\0\x77\x02\0\0\x20\0\0\0\ +\x15\x02\xf9\xff\0\0\0\0\x7b\x9a\x38\xff\0\0\0\0\x79\xa1\x40\xff\0\0\0\0\x0f\ +\x19\0\0\0\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\xf8\xff\xff\xff\xbf\x81\0\0\0\ +\0\0\0\xbf\x92\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\ +\0\x44\0\0\0\xbf\x01\0\0\0\0\0\0\x67\x01\0\0\x20\0\0\0\x77\x01\0\0\x20\0\0\0\ +\x55\x01\x94\0\0\0\0\0\x71\xa2\xf8\xff\0\0\0\0\x55\x02\x0f\0\xc9\0\0\0\x07\x09\ +\0\0\x02\0\0\0\xbf\x81\0\0\0\0\0\0\xbf\x92\0\0\0\0\0\0\x79\xa3\x10\xff\0\0\0\0\ +\xb7\x04\0\0\x10\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\xbf\x01\0\0\0\ +\0\0\0\x67\x01\0\0\x20\0\0\0\x77\x01\0\0\x20\0\0\0\x55\x01\x87\0\0\0\0\0\xb7\ +\x01\0\0\x01\0\0\0\x73\x1a\x54\xff\0\0\0\0\x79\xa7\x20\xff\0\0\0\0\x05\0\x07\0\ +\0\0\0\0\xb7\x09\0\0\x01\0\0\0\x15\x02\xd1\xff\0\0\0\0\x71\xa9\xf9\xff\0\0\0\0\ +\x07\x09\0\0\x02\0\0\0\x05\0\xce\xff\0\0\0\0\xb7\x01\0\0\x01\0\0\0\x73\x1a\x56\ +\xff\0\0\0\0\x71\xa1\xff\xff\0\0\0\0\x67\x01\0\0\x03\0\0\0\x79\xa2\x40\xff\0\0\ +\0\0\x0f\x12\0\0\0\0\0\0\x07\x02\0\0\x08\0\0\0\x7b\x2a\x40\xff\0\0\0\0\x71\xa9\ +\xfe\xff\0\0\0\0\x25\x09\x0e\0\x3c\0\0\0\xb7\x01\0\0\x01\0\0\0\x6f\x91\0\0\0\0\ +\0\0\x18\x02\0\0\x01\0\0\0\0\0\0\0\0\x18\0\x1c\x5f\x21\0\0\0\0\0\0\x55\x01\x01\ +\0\0\0\0\0\x05\0\x07\0\0\0\0\0\x79\xa1\x28\xff\0\0\0\0\x07\x01\0\0\x01\0\0\0\ +\x7b\x1a\x28\xff\0\0\0\0\x67\x01\0\0\x20\0\0\0\x77\x01\0\0\x20\0\0\0\x55\x01\ +\x82\xff\x0b\0\0\0\x05\0\x10\xff\0\0\0\0\x15\x09\xf8\xff\x87\0\0\0\x05\0\xfd\ +\xff\0\0\0\0\x71\xa1\x51\xff\0\0\0\0\x79\xa0\x30\xff\0\0\0\0\x15\x01\x17\x01\0\ +\0\0\0\x71\x62\x03\0\0\0\0\0\x67\x02\0\0\x08\0\0\0\x71\x61\x02\0\0\0\0\0\x4f\ +\x12\0\0\0\0\0\0\x71\x63\x04\0\0\0\0\0\x71\x61\x05\0\0\0\0\0\x67\x01\0\0\x08\0\ +\0\0\x4f\x31\0\0\0\0\0\0\x67\x01\0\0\x10\0\0\0\x4f\x21\0\0\0\0\0\0\x71\xa2\x53\ +\xff\0\0\0\0\x15\x02\x3d\0\0\0\0\0\xbf\x12\0\0\0\0\0\0\x57\x02\0\0\x10\0\0\0\ +\x15\x02\x3a\0\0\0\0\0\xbf\xa2\0\0\0\0\0\0\x07\x02\0\0\x5c\xff\xff\xff\x71\xa4\ +\x54\xff\0\0\0\0\xbf\x23\0\0\0\0\0\0\x15\x04\x02\0\0\0\0\0\xbf\xa3\0\0\0\0\0\0\ +\x07\x03\0\0\x7c\xff\xff\xff\x67\x01\0\0\x38\0\0\0\xc7\x01\0\0\x38\0\0\0\x65\ +\x01\x01\0\xff\xff\xff\xff\xbf\x32\0\0\0\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\ +\x6c\xff\xff\xff\x71\xa5\x55\xff\0\0\0\0\xbf\x34\0\0\0\0\0\0\x15\x05\x02\0\0\0\ +\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\x8c\xff\xff\xff\x65\x01\x01\0\xff\xff\xff\ +\xff\xbf\x43\0\0\0\0\0\0\x61\x21\x04\0\0\0\0\0\x67\x01\0\0\x20\0\0\0\x61\x24\0\ +\0\0\0\0\0\x4f\x41\0\0\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\0\x61\x21\x08\0\0\0\0\0\ +\x61\x22\x0c\0\0\0\0\0\x67\x02\0\0\x20\0\0\0\x4f\x12\0\0\0\0\0\0\x7b\x2a\xa8\ +\xff\0\0\0\0\x61\x31\0\0\0\0\0\0\x61\x32\x04\0\0\0\0\0\x61\x34\x08\0\0\0\0\0\ +\x61\x33\x0c\0\0\0\0\0\x69\xa5\x5a\xff\0\0\0\0\x6b\x5a\xc2\xff\0\0\0\0\x69\xa5\ +\x58\xff\0\0\0\0\x6b\x5a\xc0\xff\0\0\0\0\x67\x03\0\0\x20\0\0\0\x4f\x43\0\0\0\0\ +\0\0\x7b\x3a\xb8\xff\0\0\0\0\x67\x02\0\0\x20\0\0\0\x4f\x12\0\0\0\0\0\0\x7b\x2a\ +\xb0\xff\0\0\0\0\x05\0\x6b\0\0\0\0\0\x71\xa2\x52\xff\0\0\0\0\x15\x02\x04\0\0\0\ +\0\0\xbf\x12\0\0\0\0\0\0\x57\x02\0\0\x04\0\0\0\x15\x02\x01\0\0\0\0\0\x05\0\xf7\ +\xfe\0\0\0\0\x57\x01\0\0\x01\0\0\0\x15\x01\xd3\0\0\0\0\0\x61\xa1\x5c\xff\0\0\0\ +\0\x63\x1a\xa0\xff\0\0\0\0\x61\xa1\x60\xff\0\0\0\0\x63\x1a\xa4\xff\0\0\0\0\x05\ +\0\x5e\0\0\0\0\0\x71\xa2\x52\xff\0\0\0\0\x15\x02\x1e\0\0\0\0\0\xbf\x12\0\0\0\0\ +\0\0\x57\x02\0\0\x20\0\0\0\x15\x02\x1b\0\0\0\0\0\xbf\xa2\0\0\0\0\0\0\x07\x02\0\ +\0\x5c\xff\xff\xff\x71\xa4\x54\xff\0\0\0\0\xbf\x23\0\0\0\0\0\0\x15\x04\x02\0\0\ +\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\x7c\xff\xff\xff\x57\x01\0\0\0\x01\0\0\ +\x15\x01\x01\0\0\0\0\0\xbf\x32\0\0\0\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\x6c\ +\xff\xff\xff\x71\xa5\x55\xff\0\0\0\0\xbf\x34\0\0\0\0\0\0\x15\x05\x02\0\0\0\0\0\ +\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\x8c\xff\xff\xff\x15\x01\xc3\xff\0\0\0\0\x05\0\ +\xc1\xff\0\0\0\0\xb7\x09\0\0\x3c\0\0\0\x79\xa7\x20\xff\0\0\0\0\x67\0\0\0\x20\0\ +\0\0\x77\0\0\0\x20\0\0\0\x15\0\xa5\xfe\0\0\0\0\x05\0\xb0\0\0\0\0\0\x15\x09\x07\ +\xff\x87\0\0\0\x05\0\xa2\xfe\0\0\0\0\xbf\x12\0\0\0\0\0\0\x57\x02\0\0\x08\0\0\0\ +\x15\x02\xab\0\0\0\0\0\xbf\xa2\0\0\0\0\0\0\x07\x02\0\0\x5c\xff\xff\xff\x71\xa4\ +\x54\xff\0\0\0\0\xbf\x23\0\0\0\0\0\0\x15\x04\x02\0\0\0\0\0\xbf\xa3\0\0\0\0\0\0\ +\x07\x03\0\0\x7c\xff\xff\xff\x57\x01\0\0\x40\0\0\0\x15\x01\x01\0\0\0\0\0\xbf\ +\x32\0\0\0\0\0\0\x61\x23\x04\0\0\0\0\0\x67\x03\0\0\x20\0\0\0\x61\x24\0\0\0\0\0\ +\0\x4f\x43\0\0\0\0\0\0\x7b\x3a\xa0\xff\0\0\0\0\x61\x23\x08\0\0\0\0\0\x61\x22\ +\x0c\0\0\0\0\0\x67\x02\0\0\x20\0\0\0\x4f\x32\0\0\0\0\0\0\x7b\x2a\xa8\xff\0\0\0\ +\0\x15\x01\x1c\0\0\0\0\0\x71\xa1\x55\xff\0\0\0\0\x15\x01\x1a\0\0\0\0\0\x61\xa1\ +\x98\xff\0\0\0\0\x67\x01\0\0\x20\0\0\0\x61\xa2\x94\xff\0\0\0\0\x4f\x21\0\0\0\0\ +\0\0\x7b\x1a\xb8\xff\0\0\0\0\x61\xa1\x90\xff\0\0\0\0\x67\x01\0\0\x20\0\0\0\x61\ +\xa2\x8c\xff\0\0\0\0\x05\0\x19\0\0\0\0\0\xb7\x01\0\0\x01\0\0\0\x73\x1a\x52\xff\ +\0\0\0\0\xb7\x01\0\0\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\ +\x03\0\0\xd0\xff\xff\xff\xbf\x81\0\0\0\0\0\0\x79\xa2\x40\xff\0\0\0\0\xb7\x04\0\ +\0\x08\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\ +\0\0\0\x20\0\0\0\x55\0\x7d\0\0\0\0\0\x05\0\x88\xfe\0\0\0\0\xb7\x09\0\0\x2b\0\0\ +\0\x05\0\xc6\xff\0\0\0\0\x61\xa1\x78\xff\0\0\0\0\x67\x01\0\0\x20\0\0\0\x61\xa2\ +\x74\xff\0\0\0\0\x4f\x21\0\0\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x61\xa1\x70\xff\0\ +\0\0\0\x67\x01\0\0\x20\0\0\0\x61\xa2\x6c\xff\0\0\0\0\x4f\x21\0\0\0\0\0\0\x7b\ +\x1a\xb0\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x07\x07\0\0\x04\0\0\0\x61\x03\0\0\0\0\ +\0\0\xb7\x05\0\0\0\0\0\0\x05\0\x4e\0\0\0\0\0\xaf\x52\0\0\0\0\0\0\xbf\x75\0\0\0\ +\0\0\0\x0f\x15\0\0\0\0\0\0\x71\x55\0\0\0\0\0\0\x67\x03\0\0\x01\0\0\0\xbf\x50\0\ +\0\0\0\0\0\x77\0\0\0\x07\0\0\0\x4f\x03\0\0\0\0\0\0\xbf\x40\0\0\0\0\0\0\x67\0\0\ +\0\x39\0\0\0\xc7\0\0\0\x3f\0\0\0\x5f\x30\0\0\0\0\0\0\xaf\x02\0\0\0\0\0\0\xbf\ +\x50\0\0\0\0\0\0\x77\0\0\0\x06\0\0\0\x57\0\0\0\x01\0\0\0\x67\x03\0\0\x01\0\0\0\ +\x4f\x03\0\0\0\0\0\0\xbf\x40\0\0\0\0\0\0\x67\0\0\0\x3a\0\0\0\xc7\0\0\0\x3f\0\0\ +\0\x5f\x30\0\0\0\0\0\0\xaf\x02\0\0\0\0\0\0\x67\x03\0\0\x01\0\0\0\xbf\x50\0\0\0\ +\0\0\0\x77\0\0\0\x05\0\0\0\x57\0\0\0\x01\0\0\0\x4f\x03\0\0\0\0\0\0\xbf\x40\0\0\ +\0\0\0\0\x67\0\0\0\x3b\0\0\0\xc7\0\0\0\x3f\0\0\0\x5f\x30\0\0\0\0\0\0\xaf\x02\0\ +\0\0\0\0\0\x67\x03\0\0\x01\0\0\0\xbf\x50\0\0\0\0\0\0\x77\0\0\0\x04\0\0\0\x57\0\ +\0\0\x01\0\0\0\x4f\x03\0\0\0\0\0\0\xbf\x40\0\0\0\0\0\0\x67\0\0\0\x3c\0\0\0\xc7\ +\0\0\0\x3f\0\0\0\x5f\x30\0\0\0\0\0\0\xaf\x02\0\0\0\0\0\0\xbf\x50\0\0\0\0\0\0\ +\x77\0\0\0\x03\0\0\0\x57\0\0\0\x01\0\0\0\x67\x03\0\0\x01\0\0\0\x4f\x03\0\0\0\0\ +\0\0\xbf\x40\0\0\0\0\0\0\x67\0\0\0\x3d\0\0\0\xc7\0\0\0\x3f\0\0\0\x5f\x30\0\0\0\ +\0\0\0\xaf\x02\0\0\0\0\0\0\xbf\x50\0\0\0\0\0\0\x77\0\0\0\x02\0\0\0\x57\0\0\0\ +\x01\0\0\0\x67\x03\0\0\x01\0\0\0\x4f\x03\0\0\0\0\0\0\xbf\x40\0\0\0\0\0\0\x67\0\ +\0\0\x3e\0\0\0\xc7\0\0\0\x3f\0\0\0\x5f\x30\0\0\0\0\0\0\xaf\x02\0\0\0\0\0\0\xbf\ +\x50\0\0\0\0\0\0\x77\0\0\0\x01\0\0\0\x57\0\0\0\x01\0\0\0\x67\x03\0\0\x01\0\0\0\ +\x4f\x03\0\0\0\0\0\0\x57\x04\0\0\x01\0\0\0\x87\x04\0\0\0\0\0\0\x5f\x34\0\0\0\0\ +\0\0\xaf\x42\0\0\0\0\0\0\x57\x05\0\0\x01\0\0\0\x67\x03\0\0\x01\0\0\0\x4f\x53\0\ +\0\0\0\0\0\x07\x01\0\0\x01\0\0\0\xbf\x25\0\0\0\0\0\0\x15\x01\x0b\0\x24\0\0\0\ +\xbf\xa2\0\0\0\0\0\0\x07\x02\0\0\xa0\xff\xff\xff\x0f\x12\0\0\0\0\0\0\x71\x24\0\ +\0\0\0\0\0\xbf\x40\0\0\0\0\0\0\x67\0\0\0\x38\0\0\0\xc7\0\0\0\x38\0\0\0\xb7\x02\ +\0\0\0\0\0\0\x65\0\xa9\xff\xff\xff\xff\xff\xbf\x32\0\0\0\0\0\0\x05\0\xa7\xff\0\ +\0\0\0\xbf\x21\0\0\0\0\0\0\x67\x01\0\0\x20\0\0\0\x77\x01\0\0\x20\0\0\0\x15\x01\ +\x0e\0\0\0\0\0\x71\x63\x06\0\0\0\0\0\x71\x64\x07\0\0\0\0\0\x67\x04\0\0\x08\0\0\ +\0\x4f\x34\0\0\0\0\0\0\x3f\x41\0\0\0\0\0\0\x2f\x41\0\0\0\0\0\0\x1f\x12\0\0\0\0\ +\0\0\x63\x2a\x50\xff\0\0\0\0\xbf\xa2\0\0\0\0\0\0\x07\x02\0\0\x50\xff\xff\xff\ +\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\x55\0\x05\0\0\0\0\0\ +\x71\x61\x08\0\0\0\0\0\x71\x60\x09\0\0\0\0\0\x67\0\0\0\x08\0\0\0\x4f\x10\0\0\0\ +\0\0\0\x95\0\0\0\0\0\0\0\x69\0\0\0\0\0\0\0\x05\0\xfd\xff\0\0\0\0\x02\0\0\0\x04\ +\0\0\0\x0a\0\0\0\x01\0\0\0\0\0\0\0\x02\0\0\0\x04\0\0\0\x28\0\0\0\x01\0\0\0\0\0\ +\0\0\x02\0\0\0\x04\0\0\0\x02\0\0\0\x80\0\0\0\0\0\0\0\x47\x50\x4c\x20\x76\x32\0\ +\0\0\0\0\0\x10\0\0\0\0\0\0\0\x01\x7a\x52\0\x08\x7c\x0b\x01\x0c\0\0\0\x18\0\0\0\ +\x18\0\0\0\0\0\0\0\0\0\0\0\xd8\x13\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\xa0\0\0\0\x04\0\xf1\xff\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\x60\x02\0\0\0\0\x03\0\x20\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x3f\x02\0\0\0\0\ +\x03\0\xd0\x0f\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xed\x01\0\0\0\0\x03\0\x10\x10\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\xd4\x01\0\0\0\0\x03\0\x20\x10\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\xa3\x01\0\0\0\0\x03\0\xb8\x12\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x63\x01\0\0\0\0\ +\x03\0\x48\x10\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x2a\x01\0\0\0\0\x03\0\x10\x13\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\xe1\0\0\0\0\0\x03\0\xa0\x13\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\x2e\x02\0\0\0\0\x03\0\x28\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x68\x02\0\0\0\0\x03\ +\0\xc0\x13\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x36\x02\0\0\0\0\x03\0\xc8\x13\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\x22\x01\0\0\0\0\x03\0\xe8\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\x02\x01\0\0\0\0\x03\0\x40\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd9\0\0\0\0\0\x03\0\ +\xf8\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x26\x02\0\0\0\0\x03\0\x20\x0e\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\xcc\x01\0\0\0\0\x03\0\x60\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x9b\ +\x01\0\0\0\0\x03\0\xc8\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x5b\x01\0\0\0\0\x03\0\ +\x20\x07\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x7c\x01\0\0\0\0\x03\0\x48\x08\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\x53\x01\0\0\0\0\x03\0\xb8\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x1a\ +\x01\0\0\0\0\x03\0\xe0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x84\x01\0\0\0\0\x03\0\ +\xb8\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x1e\x02\0\0\0\0\x03\0\xd8\x09\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\xc4\x01\0\0\0\0\x03\0\x70\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x93\ +\x01\0\0\0\0\x03\0\xa8\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x74\x01\0\0\0\0\x03\0\ +\xf0\x0d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x4b\x01\0\0\0\0\x03\0\0\x0a\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x12\x01\0\0\0\0\x03\0\x10\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xfa\0\ +\0\0\0\0\x03\0\xc0\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x58\x02\0\0\0\0\x03\0\x88\ +\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x16\x02\0\0\0\0\x03\0\xb8\x0a\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\xe5\x01\0\0\0\0\x03\0\xc0\x0f\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xbc\x01\ +\0\0\0\0\x03\0\0\x0e\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x8b\x01\0\0\0\0\x03\0\x18\x0e\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd1\0\0\0\0\0\x03\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\x50\x02\0\0\0\0\x03\0\x20\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x0e\x02\0\0\0\0\ +\x03\0\x48\x0f\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x6c\x01\0\0\0\0\x03\0\xb0\x04\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x43\x01\0\0\0\0\x03\0\xc8\x0c\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\xc9\0\0\0\0\0\x03\0\xf8\x0c\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x06\x02\0\0\0\0\x03\ +\0\xd0\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x3b\x01\0\0\0\0\x03\0\x98\x0b\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\xf2\0\0\0\0\0\x03\0\xb8\x0b\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x48\ +\x02\0\0\0\0\x03\0\xf0\x0b\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xfe\x01\0\0\0\0\x03\0\ +\xf8\x0b\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xdd\x01\0\0\0\0\x03\0\0\x0c\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\xb4\x01\0\0\0\0\x03\0\x30\x0d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x0a\ +\x01\0\0\0\0\x03\0\x90\x0d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xc1\0\0\0\0\0\x03\0\xa8\ +\x0d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xba\0\0\0\0\0\x03\0\xd0\x01\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\xf6\x01\0\0\0\0\x03\0\xe0\x0d\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xac\x01\0\ +\0\0\0\x03\0\x30\x0e\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x33\x01\0\0\0\0\x03\0\x80\x0e\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xea\0\0\0\0\0\x03\0\x98\x0e\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x03\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x6b\0\0\0\x11\0\x06\ +\0\0\0\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\x25\0\0\0\x11\0\x05\0\0\0\0\0\0\0\0\0\x14\ +\0\0\0\0\0\0\0\x82\0\0\0\x11\0\x05\0\x28\0\0\0\0\0\0\0\x14\0\0\0\0\0\0\0\x01\0\ +\0\0\x11\0\x05\0\x14\0\0\0\0\0\0\0\x14\0\0\0\0\0\0\0\x40\0\0\0\x12\0\x03\0\0\0\ +\0\0\0\0\0\0\xd8\x13\0\0\0\0\0\0\x28\0\0\0\0\0\0\0\x01\0\0\0\x3a\0\0\0\x50\0\0\ +\0\0\0\0\0\x01\0\0\0\x3c\0\0\0\x80\x13\0\0\0\0\0\0\x01\0\0\0\x3b\0\0\0\x1c\0\0\ +\0\0\0\0\0\x01\0\0\0\x38\0\0\0\0\x74\x61\x70\x5f\x72\x73\x73\x5f\x6d\x61\x70\ +\x5f\x74\x6f\x65\x70\x6c\x69\x74\x7a\x5f\x6b\x65\x79\0\x2e\x74\x65\x78\x74\0\ +\x6d\x61\x70\x73\0\x74\x61\x70\x5f\x72\x73\x73\x5f\x6d\x61\x70\x5f\x63\x6f\x6e\ +\x66\x69\x67\x75\x72\x61\x74\x69\x6f\x6e\x73\0\x74\x75\x6e\x5f\x72\x73\x73\x5f\ +\x73\x74\x65\x65\x72\x69\x6e\x67\x5f\x70\x72\x6f\x67\0\x2e\x72\x65\x6c\x74\x75\ +\x6e\x5f\x72\x73\x73\x5f\x73\x74\x65\x65\x72\x69\x6e\x67\0\x5f\x6c\x69\x63\x65\ +\x6e\x73\x65\0\x2e\x72\x65\x6c\x2e\x65\x68\x5f\x66\x72\x61\x6d\x65\0\x74\x61\ +\x70\x5f\x72\x73\x73\x5f\x6d\x61\x70\x5f\x69\x6e\x64\x69\x72\x65\x63\x74\x69\ +\x6f\x6e\x5f\x74\x61\x62\x6c\x65\0\x72\x73\x73\x2e\x62\x70\x66\x2e\x63\0\x2e\ +\x73\x74\x72\x74\x61\x62\0\x2e\x73\x79\x6d\x74\x61\x62\0\x4c\x42\x42\x30\x5f\ +\x39\0\x4c\x42\x42\x30\x5f\x38\x39\0\x4c\x42\x42\x30\x5f\x36\x39\0\x4c\x42\x42\ +\x30\x5f\x35\x39\0\x4c\x42\x42\x30\x5f\x31\x39\0\x4c\x42\x42\x30\x5f\x31\x30\ +\x39\0\x4c\x42\x42\x30\x5f\x39\x38\0\x4c\x42\x42\x30\x5f\x37\x38\0\x4c\x42\x42\ +\x30\x5f\x34\x38\0\x4c\x42\x42\x30\x5f\x31\x38\0\x4c\x42\x42\x30\x5f\x38\x37\0\ +\x4c\x42\x42\x30\x5f\x34\x37\0\x4c\x42\x42\x30\x5f\x33\x37\0\x4c\x42\x42\x30\ +\x5f\x31\x37\0\x4c\x42\x42\x30\x5f\x31\x30\x37\0\x4c\x42\x42\x30\x5f\x39\x36\0\ +\x4c\x42\x42\x30\x5f\x37\x36\0\x4c\x42\x42\x30\x5f\x36\x36\0\x4c\x42\x42\x30\ +\x5f\x34\x36\0\x4c\x42\x42\x30\x5f\x33\x36\0\x4c\x42\x42\x30\x5f\x32\x36\0\x4c\ +\x42\x42\x30\x5f\x31\x30\x36\0\x4c\x42\x42\x30\x5f\x36\x35\0\x4c\x42\x42\x30\ +\x5f\x34\x35\0\x4c\x42\x42\x30\x5f\x33\x35\0\x4c\x42\x42\x30\x5f\x34\0\x4c\x42\ +\x42\x30\x5f\x35\x34\0\x4c\x42\x42\x30\x5f\x34\x34\0\x4c\x42\x42\x30\x5f\x32\ +\x34\0\x4c\x42\x42\x30\x5f\x31\x30\x34\0\x4c\x42\x42\x30\x5f\x39\x33\0\x4c\x42\ +\x42\x30\x5f\x38\x33\0\x4c\x42\x42\x30\x5f\x35\x33\0\x4c\x42\x42\x30\x5f\x34\ +\x33\0\x4c\x42\x42\x30\x5f\x32\x33\0\x4c\x42\x42\x30\x5f\x31\x30\x33\0\x4c\x42\ +\x42\x30\x5f\x38\x32\0\x4c\x42\x42\x30\x5f\x35\x32\0\x4c\x42\x42\x30\x5f\x31\ +\x30\x32\0\x4c\x42\x42\x30\x5f\x39\x31\0\x4c\x42\x42\x30\x5f\x38\x31\0\x4c\x42\ +\x42\x30\x5f\x37\x31\0\x4c\x42\x42\x30\x5f\x36\x31\0\x4c\x42\x42\x30\x5f\x35\ +\x31\0\x4c\x42\x42\x30\x5f\x34\x31\0\x4c\x42\x42\x30\x5f\x32\x31\0\x4c\x42\x42\ +\x30\x5f\x31\x31\0\x4c\x42\x42\x30\x5f\x31\x31\x31\0\x4c\x42\x42\x30\x5f\x31\ +\x30\x31\0\x4c\x42\x42\x30\x5f\x38\x30\0\x4c\x42\x42\x30\x5f\x36\x30\0\x4c\x42\ +\x42\x30\x5f\x35\x30\0\x4c\x42\x42\x30\x5f\x31\x30\0\x4c\x42\x42\x30\x5f\x31\ +\x31\x30\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xaa\ +\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa0\x1a\0\0\0\0\0\0\x71\x02\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x1a\0\0\0\x01\0\0\ +\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x5a\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\0\0\xd8\x13\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x56\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\x60\x1a\0\0\0\0\0\0\x30\0\0\0\0\0\0\0\x09\0\0\0\x03\0\0\0\x08\0\0\0\0\0\0\0\ +\x10\0\0\0\0\0\0\0\x20\0\0\0\x01\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x18\ +\x14\0\0\0\0\0\0\x3c\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\x6c\0\0\0\x01\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x54\x14\0\0\0\0\0\ +\0\x07\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x78\0\0\ +\0\x01\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x60\x14\0\0\0\0\0\0\x30\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x74\0\0\0\x09\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x90\x1a\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x09\0\0\0\ +\x07\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\xb2\0\0\0\x02\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\x90\x14\0\0\0\0\0\0\xd0\x05\0\0\0\0\0\0\x01\0\0\0\x39\0\0\ +\0\x08\0\0\0\0\0\0\0\x18\0\0\0\0\0\0\0"; + + return 0; +err: + bpf_object__destroy_skeleton(s); + return -1; +} + +#endif /* __RSS_BPF_SKEL_H__ */ diff --git a/ebpf/trace-events b/ebpf/trace-events new file mode 100644 index 0000000000..411b1e2be3 --- /dev/null +++ b/ebpf/trace-events @@ -0,0 +1,4 @@ +# See docs/devel/tracing.txt for syntax documentation. + +# ebpf-rss.c +ebpf_error(const char *s1, const char *s2) "error in %s: %s" diff --git a/ebpf/trace.h b/ebpf/trace.h new file mode 100644 index 0000000000..abefc46ab1 --- /dev/null +++ b/ebpf/trace.h @@ -0,0 +1 @@ +#include "trace/trace-ebpf.h" diff --git a/fpu/meson.build b/fpu/meson.build new file mode 100644 index 0000000000..1a9992ded5 --- /dev/null +++ b/fpu/meson.build @@ -0,0 +1 @@ +specific_ss.add(when: 'CONFIG_TCG', if_true: files('softfloat.c')) diff --git a/fpu/softfloat-parts-addsub.c.inc b/fpu/softfloat-parts-addsub.c.inc new file mode 100644 index 0000000000..ae5c1017c5 --- /dev/null +++ b/fpu/softfloat-parts-addsub.c.inc @@ -0,0 +1,62 @@ +/* + * Floating point arithmetic implementation + * + * The code in this source file is derived from release 2a of the SoftFloat + * IEC/IEEE Floating-point Arithmetic Package. Those parts of the code (and + * some later contributions) are provided under that license, as detailed below. + * It has subsequently been modified by contributors to the QEMU Project, + * so some portions are provided under: + * the SoftFloat-2a license + * the BSD license + * GPL-v2-or-later + * + * Any future contributions to this file after December 1st 2014 will be + * taken to be licensed under the Softfloat-2a license unless specifically + * indicated otherwise. + */ + +static void partsN(add_normal)(FloatPartsN *a, FloatPartsN *b) +{ + int exp_diff = a->exp - b->exp; + + if (exp_diff > 0) { + frac_shrjam(b, exp_diff); + } else if (exp_diff < 0) { + frac_shrjam(a, -exp_diff); + a->exp = b->exp; + } + + if (frac_add(a, a, b)) { + frac_shrjam(a, 1); + a->frac_hi |= DECOMPOSED_IMPLICIT_BIT; + a->exp += 1; + } +} + +static bool partsN(sub_normal)(FloatPartsN *a, FloatPartsN *b) +{ + int exp_diff = a->exp - b->exp; + int shift; + + if (exp_diff > 0) { + frac_shrjam(b, exp_diff); + frac_sub(a, a, b); + } else if (exp_diff < 0) { + a->exp = b->exp; + a->sign ^= 1; + frac_shrjam(a, -exp_diff); + frac_sub(a, b, a); + } else if (frac_sub(a, a, b)) { + /* Overflow means that A was less than B. */ + frac_neg(a); + a->sign ^= 1; + } + + shift = frac_normalize(a); + if (likely(shift < N)) { + a->exp -= shift; + return true; + } + a->cls = float_class_zero; + return false; +} diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc new file mode 100644 index 0000000000..dddee92d6e --- /dev/null +++ b/fpu/softfloat-parts.c.inc @@ -0,0 +1,1492 @@ +/* + * QEMU float support + * + * The code in this source file is derived from release 2a of the SoftFloat + * IEC/IEEE Floating-point Arithmetic Package. Those parts of the code (and + * some later contributions) are provided under that license, as detailed below. + * It has subsequently been modified by contributors to the QEMU Project, + * so some portions are provided under: + * the SoftFloat-2a license + * the BSD license + * GPL-v2-or-later + * + * Any future contributions to this file after December 1st 2014 will be + * taken to be licensed under the Softfloat-2a license unless specifically + * indicated otherwise. + */ + +static void partsN(return_nan)(FloatPartsN *a, float_status *s) +{ + switch (a->cls) { + case float_class_snan: + float_raise(float_flag_invalid, s); + if (s->default_nan_mode) { + parts_default_nan(a, s); + } else { + parts_silence_nan(a, s); + } + break; + case float_class_qnan: + if (s->default_nan_mode) { + parts_default_nan(a, s); + } + break; + default: + g_assert_not_reached(); + } +} + +static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, + float_status *s) +{ + if (is_snan(a->cls) || is_snan(b->cls)) { + float_raise(float_flag_invalid, s); + } + + if (s->default_nan_mode) { + parts_default_nan(a, s); + } else { + int cmp = frac_cmp(a, b); + if (cmp == 0) { + cmp = a->sign < b->sign; + } + + if (pickNaN(a->cls, b->cls, cmp > 0, s)) { + a = b; + } + if (is_snan(a->cls)) { + parts_silence_nan(a, s); + } + } + return a; +} + +static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, + FloatPartsN *c, float_status *s, + int ab_mask, int abc_mask) +{ + int which; + + if (unlikely(abc_mask & float_cmask_snan)) { + float_raise(float_flag_invalid, s); + } + + which = pickNaNMulAdd(a->cls, b->cls, c->cls, + ab_mask == float_cmask_infzero, s); + + if (s->default_nan_mode || which == 3) { + /* + * Note that this check is after pickNaNMulAdd so that function + * has an opportunity to set the Invalid flag for infzero. + */ + parts_default_nan(a, s); + return a; + } + + switch (which) { + case 0: + break; + case 1: + a = b; + break; + case 2: + a = c; + break; + default: + g_assert_not_reached(); + } + if (is_snan(a->cls)) { + parts_silence_nan(a, s); + } + return a; +} + +/* + * Canonicalize the FloatParts structure. Determine the class, + * unbias the exponent, and normalize the fraction. + */ +static void partsN(canonicalize)(FloatPartsN *p, float_status *status, + const FloatFmt *fmt) +{ + if (unlikely(p->exp == 0)) { + if (likely(frac_eqz(p))) { + p->cls = float_class_zero; + } else if (status->flush_inputs_to_zero) { + float_raise(float_flag_input_denormal, status); + p->cls = float_class_zero; + frac_clear(p); + } else { + int shift = frac_normalize(p); + p->cls = float_class_normal; + p->exp = fmt->frac_shift - fmt->exp_bias - shift + 1; + } + } else if (likely(p->exp < fmt->exp_max) || fmt->arm_althp) { + p->cls = float_class_normal; + p->exp -= fmt->exp_bias; + frac_shl(p, fmt->frac_shift); + p->frac_hi |= DECOMPOSED_IMPLICIT_BIT; + } else if (likely(frac_eqz(p))) { + p->cls = float_class_inf; + } else { + frac_shl(p, fmt->frac_shift); + p->cls = (parts_is_snan_frac(p->frac_hi, status) + ? float_class_snan : float_class_qnan); + } +} + +/* + * Round and uncanonicalize a floating-point number by parts. There + * are FRAC_SHIFT bits that may require rounding at the bottom of the + * fraction; these bits will be removed. The exponent will be biased + * by EXP_BIAS and must be bounded by [EXP_MAX-1, 0]. + */ +static void partsN(uncanon_normal)(FloatPartsN *p, float_status *s, + const FloatFmt *fmt) +{ + const int exp_max = fmt->exp_max; + const int frac_shift = fmt->frac_shift; + const uint64_t round_mask = fmt->round_mask; + const uint64_t frac_lsb = round_mask + 1; + const uint64_t frac_lsbm1 = round_mask ^ (round_mask >> 1); + const uint64_t roundeven_mask = round_mask | frac_lsb; + uint64_t inc; + bool overflow_norm = false; + int exp, flags = 0; + + switch (s->float_rounding_mode) { + case float_round_nearest_even: + if (N > 64 && frac_lsb == 0) { + inc = ((p->frac_hi & 1) || (p->frac_lo & round_mask) != frac_lsbm1 + ? frac_lsbm1 : 0); + } else { + inc = ((p->frac_lo & roundeven_mask) != frac_lsbm1 + ? frac_lsbm1 : 0); + } + break; + case float_round_ties_away: + inc = frac_lsbm1; + break; + case float_round_to_zero: + overflow_norm = true; + inc = 0; + break; + case float_round_up: + inc = p->sign ? 0 : round_mask; + overflow_norm = p->sign; + break; + case float_round_down: + inc = p->sign ? round_mask : 0; + overflow_norm = !p->sign; + break; + case float_round_to_odd: + overflow_norm = true; + /* fall through */ + case float_round_to_odd_inf: + if (N > 64 && frac_lsb == 0) { + inc = p->frac_hi & 1 ? 0 : round_mask; + } else { + inc = p->frac_lo & frac_lsb ? 0 : round_mask; + } + break; + default: + g_assert_not_reached(); + } + + exp = p->exp + fmt->exp_bias; + if (likely(exp > 0)) { + if (p->frac_lo & round_mask) { + flags |= float_flag_inexact; + if (frac_addi(p, p, inc)) { + frac_shr(p, 1); + p->frac_hi |= DECOMPOSED_IMPLICIT_BIT; + exp++; + } + p->frac_lo &= ~round_mask; + } + + if (fmt->arm_althp) { + /* ARM Alt HP eschews Inf and NaN for a wider exponent. */ + if (unlikely(exp > exp_max)) { + /* Overflow. Return the maximum normal. */ + flags = float_flag_invalid; + exp = exp_max; + frac_allones(p); + p->frac_lo &= ~round_mask; + } + } else if (unlikely(exp >= exp_max)) { + flags |= float_flag_overflow | float_flag_inexact; + if (overflow_norm) { + exp = exp_max - 1; + frac_allones(p); + p->frac_lo &= ~round_mask; + } else { + p->cls = float_class_inf; + exp = exp_max; + frac_clear(p); + } + } + frac_shr(p, frac_shift); + } else if (s->flush_to_zero) { + flags |= float_flag_output_denormal; + p->cls = float_class_zero; + exp = 0; + frac_clear(p); + } else { + bool is_tiny = s->tininess_before_rounding || exp < 0; + + if (!is_tiny) { + FloatPartsN discard; + is_tiny = !frac_addi(&discard, p, inc); + } + + frac_shrjam(p, 1 - exp); + + if (p->frac_lo & round_mask) { + /* Need to recompute round-to-even/round-to-odd. */ + switch (s->float_rounding_mode) { + case float_round_nearest_even: + if (N > 64 && frac_lsb == 0) { + inc = ((p->frac_hi & 1) || + (p->frac_lo & round_mask) != frac_lsbm1 + ? frac_lsbm1 : 0); + } else { + inc = ((p->frac_lo & roundeven_mask) != frac_lsbm1 + ? frac_lsbm1 : 0); + } + break; + case float_round_to_odd: + case float_round_to_odd_inf: + if (N > 64 && frac_lsb == 0) { + inc = p->frac_hi & 1 ? 0 : round_mask; + } else { + inc = p->frac_lo & frac_lsb ? 0 : round_mask; + } + break; + default: + break; + } + flags |= float_flag_inexact; + frac_addi(p, p, inc); + p->frac_lo &= ~round_mask; + } + + exp = (p->frac_hi & DECOMPOSED_IMPLICIT_BIT) != 0; + frac_shr(p, frac_shift); + + if (is_tiny && (flags & float_flag_inexact)) { + flags |= float_flag_underflow; + } + if (exp == 0 && frac_eqz(p)) { + p->cls = float_class_zero; + } + } + p->exp = exp; + float_raise(flags, s); +} + +static void partsN(uncanon)(FloatPartsN *p, float_status *s, + const FloatFmt *fmt) +{ + if (likely(p->cls == float_class_normal)) { + parts_uncanon_normal(p, s, fmt); + } else { + switch (p->cls) { + case float_class_zero: + p->exp = 0; + frac_clear(p); + return; + case float_class_inf: + g_assert(!fmt->arm_althp); + p->exp = fmt->exp_max; + frac_clear(p); + return; + case float_class_qnan: + case float_class_snan: + g_assert(!fmt->arm_althp); + p->exp = fmt->exp_max; + frac_shr(p, fmt->frac_shift); + return; + default: + break; + } + g_assert_not_reached(); + } +} + +/* + * Returns the result of adding or subtracting the values of the + * floating-point values `a' and `b'. The operation is performed + * according to the IEC/IEEE Standard for Binary Floating-Point + * Arithmetic. + */ +static FloatPartsN *partsN(addsub)(FloatPartsN *a, FloatPartsN *b, + float_status *s, bool subtract) +{ + bool b_sign = b->sign ^ subtract; + int ab_mask = float_cmask(a->cls) | float_cmask(b->cls); + + if (a->sign != b_sign) { + /* Subtraction */ + if (likely(ab_mask == float_cmask_normal)) { + if (parts_sub_normal(a, b)) { + return a; + } + /* Subtract was exact, fall through to set sign. */ + ab_mask = float_cmask_zero; + } + + if (ab_mask == float_cmask_zero) { + a->sign = s->float_rounding_mode == float_round_down; + return a; + } + + if (unlikely(ab_mask & float_cmask_anynan)) { + goto p_nan; + } + + if (ab_mask & float_cmask_inf) { + if (a->cls != float_class_inf) { + /* N - Inf */ + goto return_b; + } + if (b->cls != float_class_inf) { + /* Inf - N */ + return a; + } + /* Inf - Inf */ + float_raise(float_flag_invalid, s); + parts_default_nan(a, s); + return a; + } + } else { + /* Addition */ + if (likely(ab_mask == float_cmask_normal)) { + parts_add_normal(a, b); + return a; + } + + if (ab_mask == float_cmask_zero) { + return a; + } + + if (unlikely(ab_mask & float_cmask_anynan)) { + goto p_nan; + } + + if (ab_mask & float_cmask_inf) { + a->cls = float_class_inf; + return a; + } + } + + if (b->cls == float_class_zero) { + g_assert(a->cls == float_class_normal); + return a; + } + + g_assert(a->cls == float_class_zero); + g_assert(b->cls == float_class_normal); + return_b: + b->sign = b_sign; + return b; + + p_nan: + return parts_pick_nan(a, b, s); +} + +/* + * Returns the result of multiplying the floating-point values `a' and + * `b'. The operation is performed according to the IEC/IEEE Standard + * for Binary Floating-Point Arithmetic. + */ +static FloatPartsN *partsN(mul)(FloatPartsN *a, FloatPartsN *b, + float_status *s) +{ + int ab_mask = float_cmask(a->cls) | float_cmask(b->cls); + bool sign = a->sign ^ b->sign; + + if (likely(ab_mask == float_cmask_normal)) { + FloatPartsW tmp; + + frac_mulw(&tmp, a, b); + frac_truncjam(a, &tmp); + + a->exp += b->exp + 1; + if (!(a->frac_hi & DECOMPOSED_IMPLICIT_BIT)) { + frac_add(a, a, a); + a->exp -= 1; + } + + a->sign = sign; + return a; + } + + /* Inf * Zero == NaN */ + if (unlikely(ab_mask == float_cmask_infzero)) { + float_raise(float_flag_invalid, s); + parts_default_nan(a, s); + return a; + } + + if (unlikely(ab_mask & float_cmask_anynan)) { + return parts_pick_nan(a, b, s); + } + + /* Multiply by 0 or Inf */ + if (ab_mask & float_cmask_inf) { + a->cls = float_class_inf; + a->sign = sign; + return a; + } + + g_assert(ab_mask & float_cmask_zero); + a->cls = float_class_zero; + a->sign = sign; + return a; +} + +/* + * Returns the result of multiplying the floating-point values `a' and + * `b' then adding 'c', with no intermediate rounding step after the + * multiplication. The operation is performed according to the + * IEC/IEEE Standard for Binary Floating-Point Arithmetic 754-2008. + * The flags argument allows the caller to select negation of the + * addend, the intermediate product, or the final result. (The + * difference between this and having the caller do a separate + * negation is that negating externally will flip the sign bit on NaNs.) + * + * Requires A and C extracted into a double-sized structure to provide the + * extra space for the widening multiply. + */ +static FloatPartsN *partsN(muladd)(FloatPartsN *a, FloatPartsN *b, + FloatPartsN *c, int flags, float_status *s) +{ + int ab_mask, abc_mask; + FloatPartsW p_widen, c_widen; + + ab_mask = float_cmask(a->cls) | float_cmask(b->cls); + abc_mask = float_cmask(c->cls) | ab_mask; + + /* + * It is implementation-defined whether the cases of (0,inf,qnan) + * and (inf,0,qnan) raise InvalidOperation or not (and what QNaN + * they return if they do), so we have to hand this information + * off to the target-specific pick-a-NaN routine. + */ + if (unlikely(abc_mask & float_cmask_anynan)) { + return parts_pick_nan_muladd(a, b, c, s, ab_mask, abc_mask); + } + + if (flags & float_muladd_negate_c) { + c->sign ^= 1; + } + + /* Compute the sign of the product into A. */ + a->sign ^= b->sign; + if (flags & float_muladd_negate_product) { + a->sign ^= 1; + } + + if (unlikely(ab_mask != float_cmask_normal)) { + if (unlikely(ab_mask == float_cmask_infzero)) { + goto d_nan; + } + + if (ab_mask & float_cmask_inf) { + if (c->cls == float_class_inf && a->sign != c->sign) { + goto d_nan; + } + goto return_inf; + } + + g_assert(ab_mask & float_cmask_zero); + if (c->cls == float_class_normal) { + *a = *c; + goto return_normal; + } + if (c->cls == float_class_zero) { + if (a->sign != c->sign) { + goto return_sub_zero; + } + goto return_zero; + } + g_assert(c->cls == float_class_inf); + } + + if (unlikely(c->cls == float_class_inf)) { + a->sign = c->sign; + goto return_inf; + } + + /* Perform the multiplication step. */ + p_widen.sign = a->sign; + p_widen.exp = a->exp + b->exp + 1; + frac_mulw(&p_widen, a, b); + if (!(p_widen.frac_hi & DECOMPOSED_IMPLICIT_BIT)) { + frac_add(&p_widen, &p_widen, &p_widen); + p_widen.exp -= 1; + } + + /* Perform the addition step. */ + if (c->cls != float_class_zero) { + /* Zero-extend C to less significant bits. */ + frac_widen(&c_widen, c); + c_widen.exp = c->exp; + + if (a->sign == c->sign) { + parts_add_normal(&p_widen, &c_widen); + } else if (!parts_sub_normal(&p_widen, &c_widen)) { + goto return_sub_zero; + } + } + + /* Narrow with sticky bit, for proper rounding later. */ + frac_truncjam(a, &p_widen); + a->sign = p_widen.sign; + a->exp = p_widen.exp; + + return_normal: + if (flags & float_muladd_halve_result) { + a->exp -= 1; + } + finish_sign: + if (flags & float_muladd_negate_result) { + a->sign ^= 1; + } + return a; + + return_sub_zero: + a->sign = s->float_rounding_mode == float_round_down; + return_zero: + a->cls = float_class_zero; + goto finish_sign; + + return_inf: + a->cls = float_class_inf; + goto finish_sign; + + d_nan: + float_raise(float_flag_invalid, s); + parts_default_nan(a, s); + return a; +} + +/* + * Returns the result of dividing the floating-point value `a' by the + * corresponding value `b'. The operation is performed according to + * the IEC/IEEE Standard for Binary Floating-Point Arithmetic. + */ +static FloatPartsN *partsN(div)(FloatPartsN *a, FloatPartsN *b, + float_status *s) +{ + int ab_mask = float_cmask(a->cls) | float_cmask(b->cls); + bool sign = a->sign ^ b->sign; + + if (likely(ab_mask == float_cmask_normal)) { + a->sign = sign; + a->exp -= b->exp + frac_div(a, b); + return a; + } + + /* 0/0 or Inf/Inf => NaN */ + if (unlikely(ab_mask == float_cmask_zero) || + unlikely(ab_mask == float_cmask_inf)) { + float_raise(float_flag_invalid, s); + parts_default_nan(a, s); + return a; + } + + /* All the NaN cases */ + if (unlikely(ab_mask & float_cmask_anynan)) { + return parts_pick_nan(a, b, s); + } + + a->sign = sign; + + /* Inf / X */ + if (a->cls == float_class_inf) { + return a; + } + + /* 0 / X */ + if (a->cls == float_class_zero) { + return a; + } + + /* X / Inf */ + if (b->cls == float_class_inf) { + a->cls = float_class_zero; + return a; + } + + /* X / 0 => Inf */ + g_assert(b->cls == float_class_zero); + float_raise(float_flag_divbyzero, s); + a->cls = float_class_inf; + return a; +} + +/* + * Floating point remainder, per IEC/IEEE, or modulus. + */ +static FloatPartsN *partsN(modrem)(FloatPartsN *a, FloatPartsN *b, + uint64_t *mod_quot, float_status *s) +{ + int ab_mask = float_cmask(a->cls) | float_cmask(b->cls); + + if (likely(ab_mask == float_cmask_normal)) { + frac_modrem(a, b, mod_quot); + return a; + } + + if (mod_quot) { + *mod_quot = 0; + } + + /* All the NaN cases */ + if (unlikely(ab_mask & float_cmask_anynan)) { + return parts_pick_nan(a, b, s); + } + + /* Inf % N; N % 0 */ + if (a->cls == float_class_inf || b->cls == float_class_zero) { + float_raise(float_flag_invalid, s); + parts_default_nan(a, s); + return a; + } + + /* N % Inf; 0 % N */ + g_assert(b->cls == float_class_inf || a->cls == float_class_zero); + return a; +} + +/* + * Square Root + * + * The base algorithm is lifted from + * https://git.musl-libc.org/cgit/musl/tree/src/math/sqrtf.c + * https://git.musl-libc.org/cgit/musl/tree/src/math/sqrt.c + * https://git.musl-libc.org/cgit/musl/tree/src/math/sqrtl.c + * and is thus MIT licenced. + */ +static void partsN(sqrt)(FloatPartsN *a, float_status *status, + const FloatFmt *fmt) +{ + const uint32_t three32 = 3u << 30; + const uint64_t three64 = 3ull << 62; + uint32_t d32, m32, r32, s32, u32; /* 32-bit computation */ + uint64_t d64, m64, r64, s64, u64; /* 64-bit computation */ + uint64_t dh, dl, rh, rl, sh, sl, uh, ul; /* 128-bit computation */ + uint64_t d0h, d0l, d1h, d1l, d2h, d2l; + uint64_t discard; + bool exp_odd; + size_t index; + + if (unlikely(a->cls != float_class_normal)) { + switch (a->cls) { + case float_class_snan: + case float_class_qnan: + parts_return_nan(a, status); + return; + case float_class_zero: + return; + case float_class_inf: + if (unlikely(a->sign)) { + goto d_nan; + } + return; + default: + g_assert_not_reached(); + } + } + + if (unlikely(a->sign)) { + goto d_nan; + } + + /* + * Argument reduction. + * x = 4^e frac; with integer e, and frac in [1, 4) + * m = frac fixed point at bit 62, since we're in base 4. + * If base-2 exponent is odd, exchange that for multiply by 2, + * which results in no shift. + */ + exp_odd = a->exp & 1; + index = extract64(a->frac_hi, 57, 6) | (!exp_odd << 6); + if (!exp_odd) { + frac_shr(a, 1); + } + + /* + * Approximate r ~= 1/sqrt(m) and s ~= sqrt(m) when m in [1, 4). + * + * Initial estimate: + * 7-bit lookup table (1-bit exponent and 6-bit significand). + * + * The relative error (e = r0*sqrt(m)-1) of a linear estimate + * (r0 = a*m + b) is |e| < 0.085955 ~ 0x1.6p-4 at best; + * a table lookup is faster and needs one less iteration. + * The 7-bit table gives |e| < 0x1.fdp-9. + * + * A Newton-Raphson iteration for r is + * s = m*r + * d = s*r + * u = 3 - d + * r = r*u/2 + * + * Fixed point representations: + * m, s, d, u, three are all 2.30; r is 0.32 + */ + m64 = a->frac_hi; + m32 = m64 >> 32; + + r32 = rsqrt_tab[index] << 16; + /* |r*sqrt(m) - 1| < 0x1.FDp-9 */ + + s32 = ((uint64_t)m32 * r32) >> 32; + d32 = ((uint64_t)s32 * r32) >> 32; + u32 = three32 - d32; + + if (N == 64) { + /* float64 or smaller */ + + r32 = ((uint64_t)r32 * u32) >> 31; + /* |r*sqrt(m) - 1| < 0x1.7Bp-16 */ + + s32 = ((uint64_t)m32 * r32) >> 32; + d32 = ((uint64_t)s32 * r32) >> 32; + u32 = three32 - d32; + + if (fmt->frac_size <= 23) { + /* float32 or smaller */ + + s32 = ((uint64_t)s32 * u32) >> 32; /* 3.29 */ + s32 = (s32 - 1) >> 6; /* 9.23 */ + /* s < sqrt(m) < s + 0x1.08p-23 */ + + /* compute nearest rounded result to 2.23 bits */ + uint32_t d0 = (m32 << 16) - s32 * s32; + uint32_t d1 = s32 - d0; + uint32_t d2 = d1 + s32 + 1; + s32 += d1 >> 31; + a->frac_hi = (uint64_t)s32 << (64 - 25); + + /* increment or decrement for inexact */ + if (d2 != 0) { + a->frac_hi += ((int32_t)(d1 ^ d2) < 0 ? -1 : 1); + } + goto done; + } + + /* float64 */ + + r64 = (uint64_t)r32 * u32 * 2; + /* |r*sqrt(m) - 1| < 0x1.37-p29; convert to 64-bit arithmetic */ + mul64To128(m64, r64, &s64, &discard); + mul64To128(s64, r64, &d64, &discard); + u64 = three64 - d64; + + mul64To128(s64, u64, &s64, &discard); /* 3.61 */ + s64 = (s64 - 2) >> 9; /* 12.52 */ + + /* Compute nearest rounded result */ + uint64_t d0 = (m64 << 42) - s64 * s64; + uint64_t d1 = s64 - d0; + uint64_t d2 = d1 + s64 + 1; + s64 += d1 >> 63; + a->frac_hi = s64 << (64 - 54); + + /* increment or decrement for inexact */ + if (d2 != 0) { + a->frac_hi += ((int64_t)(d1 ^ d2) < 0 ? -1 : 1); + } + goto done; + } + + r64 = (uint64_t)r32 * u32 * 2; + /* |r*sqrt(m) - 1| < 0x1.7Bp-16; convert to 64-bit arithmetic */ + + mul64To128(m64, r64, &s64, &discard); + mul64To128(s64, r64, &d64, &discard); + u64 = three64 - d64; + mul64To128(u64, r64, &r64, &discard); + r64 <<= 1; + /* |r*sqrt(m) - 1| < 0x1.a5p-31 */ + + mul64To128(m64, r64, &s64, &discard); + mul64To128(s64, r64, &d64, &discard); + u64 = three64 - d64; + mul64To128(u64, r64, &rh, &rl); + add128(rh, rl, rh, rl, &rh, &rl); + /* |r*sqrt(m) - 1| < 0x1.c001p-59; change to 128-bit arithmetic */ + + mul128To256(a->frac_hi, a->frac_lo, rh, rl, &sh, &sl, &discard, &discard); + mul128To256(sh, sl, rh, rl, &dh, &dl, &discard, &discard); + sub128(three64, 0, dh, dl, &uh, &ul); + mul128To256(uh, ul, sh, sl, &sh, &sl, &discard, &discard); /* 3.125 */ + /* -0x1p-116 < s - sqrt(m) < 0x3.8001p-125 */ + + sub128(sh, sl, 0, 4, &sh, &sl); + shift128Right(sh, sl, 13, &sh, &sl); /* 16.112 */ + /* s < sqrt(m) < s + 1ulp */ + + /* Compute nearest rounded result */ + mul64To128(sl, sl, &d0h, &d0l); + d0h += 2 * sh * sl; + sub128(a->frac_lo << 34, 0, d0h, d0l, &d0h, &d0l); + sub128(sh, sl, d0h, d0l, &d1h, &d1l); + add128(sh, sl, 0, 1, &d2h, &d2l); + add128(d2h, d2l, d1h, d1l, &d2h, &d2l); + add128(sh, sl, 0, d1h >> 63, &sh, &sl); + shift128Left(sh, sl, 128 - 114, &sh, &sl); + + /* increment or decrement for inexact */ + if (d2h | d2l) { + if ((int64_t)(d1h ^ d2h) < 0) { + sub128(sh, sl, 0, 1, &sh, &sl); + } else { + add128(sh, sl, 0, 1, &sh, &sl); + } + } + a->frac_lo = sl; + a->frac_hi = sh; + + done: + /* Convert back from base 4 to base 2. */ + a->exp >>= 1; + if (!(a->frac_hi & DECOMPOSED_IMPLICIT_BIT)) { + frac_add(a, a, a); + } else { + a->exp += 1; + } + return; + + d_nan: + float_raise(float_flag_invalid, status); + parts_default_nan(a, status); +} + +/* + * Rounds the floating-point value `a' to an integer, and returns the + * result as a floating-point value. The operation is performed + * according to the IEC/IEEE Standard for Binary Floating-Point + * Arithmetic. + * + * parts_round_to_int_normal is an internal helper function for + * normal numbers only, returning true for inexact but not directly + * raising float_flag_inexact. + */ +static bool partsN(round_to_int_normal)(FloatPartsN *a, FloatRoundMode rmode, + int scale, int frac_size) +{ + uint64_t frac_lsb, frac_lsbm1, rnd_even_mask, rnd_mask, inc; + int shift_adj; + + scale = MIN(MAX(scale, -0x10000), 0x10000); + a->exp += scale; + + if (a->exp < 0) { + bool one; + + /* All fractional */ + switch (rmode) { + case float_round_nearest_even: + one = false; + if (a->exp == -1) { + FloatPartsN tmp; + /* Shift left one, discarding DECOMPOSED_IMPLICIT_BIT */ + frac_add(&tmp, a, a); + /* Anything remaining means frac > 0.5. */ + one = !frac_eqz(&tmp); + } + break; + case float_round_ties_away: + one = a->exp == -1; + break; + case float_round_to_zero: + one = false; + break; + case float_round_up: + one = !a->sign; + break; + case float_round_down: + one = a->sign; + break; + case float_round_to_odd: + one = true; + break; + default: + g_assert_not_reached(); + } + + frac_clear(a); + a->exp = 0; + if (one) { + a->frac_hi = DECOMPOSED_IMPLICIT_BIT; + } else { + a->cls = float_class_zero; + } + return true; + } + + if (a->exp >= frac_size) { + /* All integral */ + return false; + } + + if (N > 64 && a->exp < N - 64) { + /* + * Rounding is not in the low word -- shift lsb to bit 2, + * which leaves room for sticky and rounding bit. + */ + shift_adj = (N - 1) - (a->exp + 2); + frac_shrjam(a, shift_adj); + frac_lsb = 1 << 2; + } else { + shift_adj = 0; + frac_lsb = DECOMPOSED_IMPLICIT_BIT >> (a->exp & 63); + } + + frac_lsbm1 = frac_lsb >> 1; + rnd_mask = frac_lsb - 1; + rnd_even_mask = rnd_mask | frac_lsb; + + if (!(a->frac_lo & rnd_mask)) { + /* Fractional bits already clear, undo the shift above. */ + frac_shl(a, shift_adj); + return false; + } + + switch (rmode) { + case float_round_nearest_even: + inc = ((a->frac_lo & rnd_even_mask) != frac_lsbm1 ? frac_lsbm1 : 0); + break; + case float_round_ties_away: + inc = frac_lsbm1; + break; + case float_round_to_zero: + inc = 0; + break; + case float_round_up: + inc = a->sign ? 0 : rnd_mask; + break; + case float_round_down: + inc = a->sign ? rnd_mask : 0; + break; + case float_round_to_odd: + inc = a->frac_lo & frac_lsb ? 0 : rnd_mask; + break; + default: + g_assert_not_reached(); + } + + if (shift_adj == 0) { + if (frac_addi(a, a, inc)) { + frac_shr(a, 1); + a->frac_hi |= DECOMPOSED_IMPLICIT_BIT; + a->exp++; + } + a->frac_lo &= ~rnd_mask; + } else { + frac_addi(a, a, inc); + a->frac_lo &= ~rnd_mask; + /* Be careful shifting back, not to overflow */ + frac_shl(a, shift_adj - 1); + if (a->frac_hi & DECOMPOSED_IMPLICIT_BIT) { + a->exp++; + } else { + frac_add(a, a, a); + } + } + return true; +} + +static void partsN(round_to_int)(FloatPartsN *a, FloatRoundMode rmode, + int scale, float_status *s, + const FloatFmt *fmt) +{ + switch (a->cls) { + case float_class_qnan: + case float_class_snan: + parts_return_nan(a, s); + break; + case float_class_zero: + case float_class_inf: + break; + case float_class_normal: + if (parts_round_to_int_normal(a, rmode, scale, fmt->frac_size)) { + float_raise(float_flag_inexact, s); + } + break; + default: + g_assert_not_reached(); + } +} + +/* + * Returns the result of converting the floating-point value `a' to + * the two's complement integer format. The conversion is performed + * according to the IEC/IEEE Standard for Binary Floating-Point + * Arithmetic---which means in particular that the conversion is + * rounded according to the current rounding mode. If `a' is a NaN, + * the largest positive integer is returned. Otherwise, if the + * conversion overflows, the largest integer with the same sign as `a' + * is returned. + */ +static int64_t partsN(float_to_sint)(FloatPartsN *p, FloatRoundMode rmode, + int scale, int64_t min, int64_t max, + float_status *s) +{ + int flags = 0; + uint64_t r; + + switch (p->cls) { + case float_class_snan: + case float_class_qnan: + flags = float_flag_invalid; + r = max; + break; + + case float_class_inf: + flags = float_flag_invalid; + r = p->sign ? min : max; + break; + + case float_class_zero: + return 0; + + case float_class_normal: + /* TODO: N - 2 is frac_size for rounding; could use input fmt. */ + if (parts_round_to_int_normal(p, rmode, scale, N - 2)) { + flags = float_flag_inexact; + } + + if (p->exp <= DECOMPOSED_BINARY_POINT) { + r = p->frac_hi >> (DECOMPOSED_BINARY_POINT - p->exp); + } else { + r = UINT64_MAX; + } + if (p->sign) { + if (r <= -(uint64_t)min) { + r = -r; + } else { + flags = float_flag_invalid; + r = min; + } + } else if (r > max) { + flags = float_flag_invalid; + r = max; + } + break; + + default: + g_assert_not_reached(); + } + + float_raise(flags, s); + return r; +} + +/* + * Returns the result of converting the floating-point value `a' to + * the unsigned integer format. The conversion is performed according + * to the IEC/IEEE Standard for Binary Floating-Point + * Arithmetic---which means in particular that the conversion is + * rounded according to the current rounding mode. If `a' is a NaN, + * the largest unsigned integer is returned. Otherwise, if the + * conversion overflows, the largest unsigned integer is returned. If + * the 'a' is negative, the result is rounded and zero is returned; + * values that do not round to zero will raise the inexact exception + * flag. + */ +static uint64_t partsN(float_to_uint)(FloatPartsN *p, FloatRoundMode rmode, + int scale, uint64_t max, float_status *s) +{ + int flags = 0; + uint64_t r; + + switch (p->cls) { + case float_class_snan: + case float_class_qnan: + flags = float_flag_invalid; + r = max; + break; + + case float_class_inf: + flags = float_flag_invalid; + r = p->sign ? 0 : max; + break; + + case float_class_zero: + return 0; + + case float_class_normal: + /* TODO: N - 2 is frac_size for rounding; could use input fmt. */ + if (parts_round_to_int_normal(p, rmode, scale, N - 2)) { + flags = float_flag_inexact; + if (p->cls == float_class_zero) { + r = 0; + break; + } + } + + if (p->sign) { + flags = float_flag_invalid; + r = 0; + } else if (p->exp > DECOMPOSED_BINARY_POINT) { + flags = float_flag_invalid; + r = max; + } else { + r = p->frac_hi >> (DECOMPOSED_BINARY_POINT - p->exp); + if (r > max) { + flags = float_flag_invalid; + r = max; + } + } + break; + + default: + g_assert_not_reached(); + } + + float_raise(flags, s); + return r; +} + +/* + * Integer to float conversions + * + * Returns the result of converting the two's complement integer `a' + * to the floating-point format. The conversion is performed according + * to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. + */ +static void partsN(sint_to_float)(FloatPartsN *p, int64_t a, + int scale, float_status *s) +{ + uint64_t f = a; + int shift; + + memset(p, 0, sizeof(*p)); + + if (a == 0) { + p->cls = float_class_zero; + return; + } + + p->cls = float_class_normal; + if (a < 0) { + f = -f; + p->sign = true; + } + shift = clz64(f); + scale = MIN(MAX(scale, -0x10000), 0x10000); + + p->exp = DECOMPOSED_BINARY_POINT - shift + scale; + p->frac_hi = f << shift; +} + +/* + * Unsigned Integer to float conversions + * + * Returns the result of converting the unsigned integer `a' to the + * floating-point format. The conversion is performed according to the + * IEC/IEEE Standard for Binary Floating-Point Arithmetic. + */ +static void partsN(uint_to_float)(FloatPartsN *p, uint64_t a, + int scale, float_status *status) +{ + memset(p, 0, sizeof(*p)); + + if (a == 0) { + p->cls = float_class_zero; + } else { + int shift = clz64(a); + scale = MIN(MAX(scale, -0x10000), 0x10000); + p->cls = float_class_normal; + p->exp = DECOMPOSED_BINARY_POINT - shift + scale; + p->frac_hi = a << shift; + } +} + +/* + * Float min/max. + */ +static FloatPartsN *partsN(minmax)(FloatPartsN *a, FloatPartsN *b, + float_status *s, int flags) +{ + int ab_mask = float_cmask(a->cls) | float_cmask(b->cls); + int a_exp, b_exp, cmp; + + if (unlikely(ab_mask & float_cmask_anynan)) { + /* + * For minnum/maxnum, if one operand is a QNaN, and the other + * operand is numerical, then return numerical argument. + */ + if ((flags & minmax_isnum) + && !(ab_mask & float_cmask_snan) + && (ab_mask & ~float_cmask_qnan)) { + return is_nan(a->cls) ? b : a; + } + return parts_pick_nan(a, b, s); + } + + a_exp = a->exp; + b_exp = b->exp; + + if (unlikely(ab_mask != float_cmask_normal)) { + switch (a->cls) { + case float_class_normal: + break; + case float_class_inf: + a_exp = INT16_MAX; + break; + case float_class_zero: + a_exp = INT16_MIN; + break; + default: + g_assert_not_reached(); + break; + } + switch (b->cls) { + case float_class_normal: + break; + case float_class_inf: + b_exp = INT16_MAX; + break; + case float_class_zero: + b_exp = INT16_MIN; + break; + default: + g_assert_not_reached(); + break; + } + } + + /* Compare magnitudes. */ + cmp = a_exp - b_exp; + if (cmp == 0) { + cmp = frac_cmp(a, b); + } + + /* + * Take the sign into account. + * For ismag, only do this if the magnitudes are equal. + */ + if (!(flags & minmax_ismag) || cmp == 0) { + if (a->sign != b->sign) { + /* For differing signs, the negative operand is less. */ + cmp = a->sign ? -1 : 1; + } else if (a->sign) { + /* For two negative operands, invert the magnitude comparison. */ + cmp = -cmp; + } + } + + if (flags & minmax_ismin) { + cmp = -cmp; + } + return cmp < 0 ? b : a; +} + +/* + * Floating point compare + */ +static FloatRelation partsN(compare)(FloatPartsN *a, FloatPartsN *b, + float_status *s, bool is_quiet) +{ + int ab_mask = float_cmask(a->cls) | float_cmask(b->cls); + int cmp; + + if (likely(ab_mask == float_cmask_normal)) { + if (a->sign != b->sign) { + goto a_sign; + } + if (a->exp != b->exp) { + cmp = a->exp < b->exp ? -1 : 1; + } else { + cmp = frac_cmp(a, b); + } + if (a->sign) { + cmp = -cmp; + } + return cmp; + } + + if (unlikely(ab_mask & float_cmask_anynan)) { + if (!is_quiet || (ab_mask & float_cmask_snan)) { + float_raise(float_flag_invalid, s); + } + return float_relation_unordered; + } + + if (ab_mask & float_cmask_zero) { + if (ab_mask == float_cmask_zero) { + return float_relation_equal; + } else if (a->cls == float_class_zero) { + goto b_sign; + } else { + goto a_sign; + } + } + + if (ab_mask == float_cmask_inf) { + if (a->sign == b->sign) { + return float_relation_equal; + } + } else if (b->cls == float_class_inf) { + goto b_sign; + } else { + g_assert(a->cls == float_class_inf); + } + + a_sign: + return a->sign ? float_relation_less : float_relation_greater; + b_sign: + return b->sign ? float_relation_greater : float_relation_less; +} + +/* + * Multiply A by 2 raised to the power N. + */ +static void partsN(scalbn)(FloatPartsN *a, int n, float_status *s) +{ + switch (a->cls) { + case float_class_snan: + case float_class_qnan: + parts_return_nan(a, s); + break; + case float_class_zero: + case float_class_inf: + break; + case float_class_normal: + a->exp += MIN(MAX(n, -0x10000), 0x10000); + break; + default: + g_assert_not_reached(); + } +} + +/* + * Return log2(A) + */ +static void partsN(log2)(FloatPartsN *a, float_status *s, const FloatFmt *fmt) +{ + uint64_t a0, a1, r, t, ign; + FloatPartsN f; + int i, n, a_exp, f_exp; + + if (unlikely(a->cls != float_class_normal)) { + switch (a->cls) { + case float_class_snan: + case float_class_qnan: + parts_return_nan(a, s); + return; + case float_class_zero: + /* log2(0) = -inf */ + a->cls = float_class_inf; + a->sign = 1; + return; + case float_class_inf: + if (unlikely(a->sign)) { + goto d_nan; + } + return; + default: + break; + } + g_assert_not_reached(); + } + if (unlikely(a->sign)) { + goto d_nan; + } + + /* TODO: This algorithm looses bits too quickly for float128. */ + g_assert(N == 64); + + a_exp = a->exp; + f_exp = -1; + + r = 0; + t = DECOMPOSED_IMPLICIT_BIT; + a0 = a->frac_hi; + a1 = 0; + + n = fmt->frac_size + 2; + if (unlikely(a_exp == -1)) { + /* + * When a_exp == -1, we're computing the log2 of a value [0.5,1.0). + * When the value is very close to 1.0, there are lots of 1's in + * the msb parts of the fraction. At the end, when we subtract + * this value from -1.0, we can see a catastrophic loss of precision, + * as 0x800..000 - 0x7ff..ffx becomes 0x000..00y, leaving only the + * bits of y in the final result. To minimize this, compute as many + * digits as we can. + * ??? This case needs another algorithm to avoid this. + */ + n = fmt->frac_size * 2 + 2; + /* Don't compute a value overlapping the sticky bit */ + n = MIN(n, 62); + } + + for (i = 0; i < n; i++) { + if (a1) { + mul128To256(a0, a1, a0, a1, &a0, &a1, &ign, &ign); + } else if (a0 & 0xffffffffull) { + mul64To128(a0, a0, &a0, &a1); + } else if (a0 & ~DECOMPOSED_IMPLICIT_BIT) { + a0 >>= 32; + a0 *= a0; + } else { + goto exact; + } + + if (a0 & DECOMPOSED_IMPLICIT_BIT) { + if (unlikely(a_exp == 0 && r == 0)) { + /* + * When a_exp == 0, we're computing the log2 of a value + * [1.0,2.0). When the value is very close to 1.0, there + * are lots of 0's in the msb parts of the fraction. + * We need to compute more digits to produce a correct + * result -- restart at the top of the fraction. + * ??? This is likely to lose precision quickly, as for + * float128; we may need another method. + */ + f_exp -= i; + t = r = DECOMPOSED_IMPLICIT_BIT; + i = 0; + } else { + r |= t; + } + } else { + add128(a0, a1, a0, a1, &a0, &a1); + } + t >>= 1; + } + + /* Set sticky for inexact. */ + r |= (a1 || a0 & ~DECOMPOSED_IMPLICIT_BIT); + + exact: + parts_sint_to_float(a, a_exp, 0, s); + if (r == 0) { + return; + } + + memset(&f, 0, sizeof(f)); + f.cls = float_class_normal; + f.frac_hi = r; + f.exp = f_exp - frac_normalize(&f); + + if (a_exp < 0) { + parts_sub_normal(a, &f); + } else if (a_exp > 0) { + parts_add_normal(a, &f); + } else { + *a = f; + } + return; + + d_nan: + float_raise(float_flag_invalid, s); + parts_default_nan(a, s); +} diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index c2f87addb2..12467bb9bb 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -103,7 +103,7 @@ static inline bool snan_bit_is_one(float_status *status) { #if defined(TARGET_MIPS) return status->snan_bit_is_one; -#elif defined(TARGET_HPPA) || defined(TARGET_UNICORE32) || defined(TARGET_SH4) +#elif defined(TARGET_HPPA) || defined(TARGET_SH4) return 1; #else return 0; @@ -129,7 +129,7 @@ static bool parts_is_snan_frac(uint64_t frac, float_status *status) | The pattern for a default generated deconstructed floating-point NaN. *----------------------------------------------------------------------------*/ -static FloatParts parts_default_nan(float_status *status) +static void parts64_default_nan(FloatParts64 *p, float_status *status) { bool sign = 0; uint64_t frac; @@ -145,12 +145,14 @@ static FloatParts parts_default_nan(float_status *status) #elif defined(TARGET_HPPA) /* snan_bit_is_one, set msb-1. */ frac = 1ULL << (DECOMPOSED_BINARY_POINT - 2); +#elif defined(TARGET_HEXAGON) + sign = 1; + frac = ~0ULL; #else - /* This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, - * S390, SH4, TriCore, and Xtensa. I cannot find documentation - * for Unicore32; the choice from the original commit is unchanged. - * Our other supported targets, CRIS, LM32, Moxie, Nios2, and Tile, - * do not have floating-point. + /* + * This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, + * S390, SH4, TriCore, and Xtensa. Our other supported targets, + * CRIS, Nios2, and Tile, do not have floating-point. */ if (snan_bit_is_one(status)) { /* set all bits other than msb */ @@ -161,7 +163,7 @@ static FloatParts parts_default_nan(float_status *status) } #endif - return (FloatParts) { + *p = (FloatParts64) { .cls = float_class_qnan, .sign = sign, .exp = INT_MAX, @@ -169,26 +171,55 @@ static FloatParts parts_default_nan(float_status *status) }; } +static void parts128_default_nan(FloatParts128 *p, float_status *status) +{ + /* + * Extrapolate from the choices made by parts64_default_nan to fill + * in the quad-floating format. If the low bit is set, assume we + * want to set all non-snan bits. + */ + FloatParts64 p64; + parts64_default_nan(&p64, status); + + *p = (FloatParts128) { + .cls = float_class_qnan, + .sign = p64.sign, + .exp = INT_MAX, + .frac_hi = p64.frac, + .frac_lo = -(p64.frac & 1) + }; +} + /*---------------------------------------------------------------------------- | Returns a quiet NaN from a signalling NaN for the deconstructed | floating-point parts. *----------------------------------------------------------------------------*/ -static FloatParts parts_silence_nan(FloatParts a, float_status *status) +static uint64_t parts_silence_nan_frac(uint64_t frac, float_status *status) { g_assert(!no_signaling_nans(status)); -#if defined(TARGET_HPPA) - a.frac &= ~(1ULL << (DECOMPOSED_BINARY_POINT - 1)); - a.frac |= 1ULL << (DECOMPOSED_BINARY_POINT - 2); -#else + g_assert(!status->default_nan_mode); + + /* The only snan_bit_is_one target without default_nan_mode is HPPA. */ if (snan_bit_is_one(status)) { - return parts_default_nan(status); + frac &= ~(1ULL << (DECOMPOSED_BINARY_POINT - 1)); + frac |= 1ULL << (DECOMPOSED_BINARY_POINT - 2); } else { - a.frac |= 1ULL << (DECOMPOSED_BINARY_POINT - 1); + frac |= 1ULL << (DECOMPOSED_BINARY_POINT - 1); } -#endif - a.cls = float_class_qnan; - return a; + return frac; +} + +static void parts64_silence_nan(FloatParts64 *p, float_status *status) +{ + p->frac = parts_silence_nan_frac(p->frac, status); + p->cls = float_class_qnan; +} + +static void parts128_silence_nan(FloatParts128 *p, float_status *status) +{ + p->frac_hi = parts_silence_nan_frac(p->frac_hi, status); + p->cls = float_class_qnan; } /*---------------------------------------------------------------------------- @@ -225,26 +256,6 @@ floatx80 floatx80_default_nan(float_status *status) const floatx80 floatx80_infinity = make_floatx80_init(floatx80_infinity_high, floatx80_infinity_low); -/*---------------------------------------------------------------------------- -| Raises the exceptions specified by `flags'. Floating-point traps can be -| defined here if desired. It is currently not possible for such a trap -| to substitute a result value. If traps are not implemented, this routine -| should be simply `float_exception_flags |= flags;'. -*----------------------------------------------------------------------------*/ - -void float_raise(uint8_t flags, float_status *status) -{ - status->float_exception_flags |= flags; -} - -/*---------------------------------------------------------------------------- -| Internal canonical NaN format. -*----------------------------------------------------------------------------*/ -typedef struct { - bool sign; - uint64_t high, low; -} commonNaNT; - /*---------------------------------------------------------------------------- | Returns 1 if the half-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. @@ -360,46 +371,6 @@ bool float32_is_signaling_nan(float32 a_, float_status *status) } } -/*---------------------------------------------------------------------------- -| Returns the result of converting the single-precision floating-point NaN -| `a' to the canonical NaN format. If `a' is a signaling NaN, the invalid -| exception is raised. -*----------------------------------------------------------------------------*/ - -static commonNaNT float32ToCommonNaN(float32 a, float_status *status) -{ - commonNaNT z; - - if (float32_is_signaling_nan(a, status)) { - float_raise(float_flag_invalid, status); - } - z.sign = float32_val(a) >> 31; - z.low = 0; - z.high = ((uint64_t)float32_val(a)) << 41; - return z; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the canonical NaN `a' to the single- -| precision floating-point format. -*----------------------------------------------------------------------------*/ - -static float32 commonNaNToFloat32(commonNaNT a, float_status *status) -{ - uint32_t mantissa = a.high >> 41; - - if (status->default_nan_mode) { - return float32_default_nan(status); - } - - if (mantissa) { - return make_float32( - (((uint32_t)a.sign) << 31) | 0x7F800000 | (a.high >> 41)); - } else { - return float32_default_nan(status); - } -} - /*---------------------------------------------------------------------------- | Select which NaN to propagate for a two-input operation. | IEEE754 doesn't specify all the details of this, so the @@ -624,6 +595,12 @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { return 1; } +#elif defined(TARGET_RISCV) + /* For RISC-V, InvalidOp is set when multiplicands are Inf and zero */ + if (infzero) { + float_raise(float_flag_invalid, status); + } + return 3; /* default NaN */ #elif defined(TARGET_XTENSA) /* * For Xtensa, the (inf,zero,nan) case sets InvalidOp and returns @@ -664,62 +641,6 @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, #endif } -/*---------------------------------------------------------------------------- -| Takes two single-precision floating-point values `a' and `b', one of which -| is a NaN, and returns the appropriate NaN result. If either `a' or `b' is a -| signaling NaN, the invalid exception is raised. -*----------------------------------------------------------------------------*/ - -static float32 propagateFloat32NaN(float32 a, float32 b, float_status *status) -{ - bool aIsLargerSignificand; - uint32_t av, bv; - FloatClass a_cls, b_cls; - - /* This is not complete, but is good enough for pickNaN. */ - a_cls = (!float32_is_any_nan(a) - ? float_class_normal - : float32_is_signaling_nan(a, status) - ? float_class_snan - : float_class_qnan); - b_cls = (!float32_is_any_nan(b) - ? float_class_normal - : float32_is_signaling_nan(b, status) - ? float_class_snan - : float_class_qnan); - - av = float32_val(a); - bv = float32_val(b); - - if (is_snan(a_cls) || is_snan(b_cls)) { - float_raise(float_flag_invalid, status); - } - - if (status->default_nan_mode) { - return float32_default_nan(status); - } - - if ((uint32_t)(av << 1) < (uint32_t)(bv << 1)) { - aIsLargerSignificand = 0; - } else if ((uint32_t)(bv << 1) < (uint32_t)(av << 1)) { - aIsLargerSignificand = 1; - } else { - aIsLargerSignificand = (av < bv) ? 1 : 0; - } - - if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { - if (is_snan(b_cls)) { - return float32_silence_nan(b, status); - } - return b; - } else { - if (is_snan(a_cls)) { - return float32_silence_nan(a, status); - } - return a; - } -} - /*---------------------------------------------------------------------------- | Returns 1 if the double-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. @@ -760,104 +681,6 @@ bool float64_is_signaling_nan(float64 a_, float_status *status) } } -/*---------------------------------------------------------------------------- -| Returns the result of converting the double-precision floating-point NaN -| `a' to the canonical NaN format. If `a' is a signaling NaN, the invalid -| exception is raised. -*----------------------------------------------------------------------------*/ - -static commonNaNT float64ToCommonNaN(float64 a, float_status *status) -{ - commonNaNT z; - - if (float64_is_signaling_nan(a, status)) { - float_raise(float_flag_invalid, status); - } - z.sign = float64_val(a) >> 63; - z.low = 0; - z.high = float64_val(a) << 12; - return z; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the canonical NaN `a' to the double- -| precision floating-point format. -*----------------------------------------------------------------------------*/ - -static float64 commonNaNToFloat64(commonNaNT a, float_status *status) -{ - uint64_t mantissa = a.high >> 12; - - if (status->default_nan_mode) { - return float64_default_nan(status); - } - - if (mantissa) { - return make_float64( - (((uint64_t) a.sign) << 63) - | UINT64_C(0x7FF0000000000000) - | (a.high >> 12)); - } else { - return float64_default_nan(status); - } -} - -/*---------------------------------------------------------------------------- -| Takes two double-precision floating-point values `a' and `b', one of which -| is a NaN, and returns the appropriate NaN result. If either `a' or `b' is a -| signaling NaN, the invalid exception is raised. -*----------------------------------------------------------------------------*/ - -static float64 propagateFloat64NaN(float64 a, float64 b, float_status *status) -{ - bool aIsLargerSignificand; - uint64_t av, bv; - FloatClass a_cls, b_cls; - - /* This is not complete, but is good enough for pickNaN. */ - a_cls = (!float64_is_any_nan(a) - ? float_class_normal - : float64_is_signaling_nan(a, status) - ? float_class_snan - : float_class_qnan); - b_cls = (!float64_is_any_nan(b) - ? float_class_normal - : float64_is_signaling_nan(b, status) - ? float_class_snan - : float_class_qnan); - - av = float64_val(a); - bv = float64_val(b); - - if (is_snan(a_cls) || is_snan(b_cls)) { - float_raise(float_flag_invalid, status); - } - - if (status->default_nan_mode) { - return float64_default_nan(status); - } - - if ((uint64_t)(av << 1) < (uint64_t)(bv << 1)) { - aIsLargerSignificand = 0; - } else if ((uint64_t)(bv << 1) < (uint64_t)(av << 1)) { - aIsLargerSignificand = 1; - } else { - aIsLargerSignificand = (av < bv) ? 1 : 0; - } - - if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { - if (is_snan(b_cls)) { - return float64_silence_nan(b, status); - } - return b; - } else { - if (is_snan(a_cls)) { - return float64_silence_nan(a, status); - } - return a; - } -} - /*---------------------------------------------------------------------------- | Returns 1 if the extended double-precision floating-point value `a' is a | quiet NaN; otherwise returns 0. This slightly differs from the same @@ -921,55 +744,6 @@ floatx80 floatx80_silence_nan(floatx80 a, float_status *status) return a; } -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point NaN `a' to the canonical NaN format. If `a' is a signaling NaN, the -| invalid exception is raised. -*----------------------------------------------------------------------------*/ - -static commonNaNT floatx80ToCommonNaN(floatx80 a, float_status *status) -{ - floatx80 dflt; - commonNaNT z; - - if (floatx80_is_signaling_nan(a, status)) { - float_raise(float_flag_invalid, status); - } - if (a.low >> 63) { - z.sign = a.high >> 15; - z.low = 0; - z.high = a.low << 1; - } else { - dflt = floatx80_default_nan(status); - z.sign = dflt.high >> 15; - z.low = 0; - z.high = dflt.low << 1; - } - return z; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the canonical NaN `a' to the extended -| double-precision floating-point format. -*----------------------------------------------------------------------------*/ - -static floatx80 commonNaNToFloatx80(commonNaNT a, float_status *status) -{ - floatx80 z; - - if (status->default_nan_mode) { - return floatx80_default_nan(status); - } - - if (a.high >> 1) { - z.low = UINT64_C(0x8000000000000000) | a.high >> 1; - z.high = (((uint16_t)a.sign) << 15) | 0x7FFF; - } else { - z = floatx80_default_nan(status); - } - return z; -} - /*---------------------------------------------------------------------------- | Takes two extended double-precision floating-point values `a' and `b', one | of which is a NaN, and returns the appropriate NaN result. If either `a' or @@ -1061,111 +835,3 @@ bool float128_is_signaling_nan(float128 a, float_status *status) } } } - -/*---------------------------------------------------------------------------- -| Returns a quiet NaN from a signalling NaN for the quadruple-precision -| floating point value `a'. -*----------------------------------------------------------------------------*/ - -float128 float128_silence_nan(float128 a, float_status *status) -{ - if (no_signaling_nans(status)) { - g_assert_not_reached(); - } else { - if (snan_bit_is_one(status)) { - return float128_default_nan(status); - } else { - a.high |= UINT64_C(0x0000800000000000); - return a; - } - } -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point NaN -| `a' to the canonical NaN format. If `a' is a signaling NaN, the invalid -| exception is raised. -*----------------------------------------------------------------------------*/ - -static commonNaNT float128ToCommonNaN(float128 a, float_status *status) -{ - commonNaNT z; - - if (float128_is_signaling_nan(a, status)) { - float_raise(float_flag_invalid, status); - } - z.sign = a.high >> 63; - shortShift128Left(a.high, a.low, 16, &z.high, &z.low); - return z; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the canonical NaN `a' to the quadruple- -| precision floating-point format. -*----------------------------------------------------------------------------*/ - -static float128 commonNaNToFloat128(commonNaNT a, float_status *status) -{ - float128 z; - - if (status->default_nan_mode) { - return float128_default_nan(status); - } - - shift128Right(a.high, a.low, 16, &z.high, &z.low); - z.high |= (((uint64_t)a.sign) << 63) | UINT64_C(0x7FFF000000000000); - return z; -} - -/*---------------------------------------------------------------------------- -| Takes two quadruple-precision floating-point values `a' and `b', one of -| which is a NaN, and returns the appropriate NaN result. If either `a' or -| `b' is a signaling NaN, the invalid exception is raised. -*----------------------------------------------------------------------------*/ - -static float128 propagateFloat128NaN(float128 a, float128 b, - float_status *status) -{ - bool aIsLargerSignificand; - FloatClass a_cls, b_cls; - - /* This is not complete, but is good enough for pickNaN. */ - a_cls = (!float128_is_any_nan(a) - ? float_class_normal - : float128_is_signaling_nan(a, status) - ? float_class_snan - : float_class_qnan); - b_cls = (!float128_is_any_nan(b) - ? float_class_normal - : float128_is_signaling_nan(b, status) - ? float_class_snan - : float_class_qnan); - - if (is_snan(a_cls) || is_snan(b_cls)) { - float_raise(float_flag_invalid, status); - } - - if (status->default_nan_mode) { - return float128_default_nan(status); - } - - if (lt128(a.high << 1, a.low, b.high << 1, b.low)) { - aIsLargerSignificand = 0; - } else if (lt128(b.high << 1, b.low, a.high << 1, a.low)) { - aIsLargerSignificand = 1; - } else { - aIsLargerSignificand = (a.high < b.high) ? 1 : 0; - } - - if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { - if (is_snan(b_cls)) { - return float128_silence_nan(b, status); - } - return b; - } else { - if (is_snan(a_cls)) { - return float128_silence_nan(a, status); - } - return a; - } -} diff --git a/fpu/softfloat.c b/fpu/softfloat.c index 67cfa0fd82..6e769f990c 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -132,7 +132,7 @@ this code that are retained. if (unlikely(soft_t ## _is_denormal(*a))) { \ *a = soft_t ## _set_sign(soft_t ## _zero, \ soft_t ## _is_neg(*a)); \ - s->float_exception_flags |= float_flag_input_denormal; \ + float_raise(float_flag_input_denormal, s); \ } \ } @@ -360,7 +360,7 @@ float32_gen2(float32 xa, float32 xb, float_status *s, ur.h = hard(ua.h, ub.h); if (unlikely(f32_is_inf(ur))) { - s->float_exception_flags |= float_flag_overflow; + float_raise(float_flag_overflow, s); } else if (unlikely(fabsf(ur.h) <= FLT_MIN) && post(ua, ub)) { goto soft; } @@ -391,7 +391,7 @@ float64_gen2(float64 xa, float64 xb, float_status *s, ur.h = hard(ua.h, ub.h); if (unlikely(f64_is_inf(ur))) { - s->float_exception_flags |= float_flag_overflow; + float_raise(float_flag_overflow, s); } else if (unlikely(fabs(ur.h) <= DBL_MIN) && post(ua, ub)) { goto soft; } @@ -401,60 +401,6 @@ float64_gen2(float64 xa, float64 xb, float_status *s, return soft(ua.s, ub.s, s); } -/*---------------------------------------------------------------------------- -| Returns the fraction bits of the single-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline uint32_t extractFloat32Frac(float32 a) -{ - return float32_val(a) & 0x007FFFFF; -} - -/*---------------------------------------------------------------------------- -| Returns the exponent bits of the single-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline int extractFloat32Exp(float32 a) -{ - return (float32_val(a) >> 23) & 0xFF; -} - -/*---------------------------------------------------------------------------- -| Returns the sign bit of the single-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline bool extractFloat32Sign(float32 a) -{ - return float32_val(a) >> 31; -} - -/*---------------------------------------------------------------------------- -| Returns the fraction bits of the double-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline uint64_t extractFloat64Frac(float64 a) -{ - return float64_val(a) & UINT64_C(0x000FFFFFFFFFFFFF); -} - -/*---------------------------------------------------------------------------- -| Returns the exponent bits of the double-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline int extractFloat64Exp(float64 a) -{ - return (float64_val(a) >> 52) & 0x7FF; -} - -/*---------------------------------------------------------------------------- -| Returns the sign bit of the double-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline bool extractFloat64Sign(float64 a) -{ - return float64_val(a) >> 63; -} - /* * Classify a floating point number. Everything above float_class_qnan * is a NaN so cls >= float_class_qnan is any NaN. @@ -469,6 +415,29 @@ typedef enum __attribute__ ((__packed__)) { float_class_snan, } FloatClass; +#define float_cmask(bit) (1u << (bit)) + +enum { + float_cmask_zero = float_cmask(float_class_zero), + float_cmask_normal = float_cmask(float_class_normal), + float_cmask_inf = float_cmask(float_class_inf), + float_cmask_qnan = float_cmask(float_class_qnan), + float_cmask_snan = float_cmask(float_class_snan), + + float_cmask_infzero = float_cmask_zero | float_cmask_inf, + float_cmask_anynan = float_cmask_qnan | float_cmask_snan, +}; + +/* Flags for parts_minmax. */ +enum { + /* Set for minimum; clear for maximum. */ + minmax_ismin = 1, + /* Set for the IEEE 754-2008 minNum() and maxNum() operations. */ + minmax_isnum = 2, + /* Set for the IEEE 754-2008 minNumMag() and minNumMag() operations. */ + minmax_ismag = 4, +}; + /* Simple helpers for checking if, or what kind of, NaN we have */ static inline __attribute__((unused)) bool is_nan(FloatClass c) { @@ -486,26 +455,52 @@ static inline __attribute__((unused)) bool is_qnan(FloatClass c) } /* - * Structure holding all of the decomposed parts of a float. The - * exponent is unbiased and the fraction is normalized. All - * calculations are done with a 64 bit fraction and then rounded as - * appropriate for the final format. + * Structure holding all of the decomposed parts of a float. + * The exponent is unbiased and the fraction is normalized. * - * Thanks to the packed FloatClass a decent compiler should be able to - * fit the whole structure into registers and avoid using the stack - * for parameter passing. + * The fraction words are stored in big-endian word ordering, + * so that truncation from a larger format to a smaller format + * can be done simply by ignoring subsequent elements. */ typedef struct { - uint64_t frac; - int32_t exp; FloatClass cls; bool sign; -} FloatParts; + int32_t exp; + union { + /* Routines that know the structure may reference the singular name. */ + uint64_t frac; + /* + * Routines expanded with multiple structures reference "hi" and "lo" + * depending on the operation. In FloatParts64, "hi" and "lo" are + * both the same word and aliased here. + */ + uint64_t frac_hi; + uint64_t frac_lo; + }; +} FloatParts64; -#define DECOMPOSED_BINARY_POINT (64 - 2) +typedef struct { + FloatClass cls; + bool sign; + int32_t exp; + uint64_t frac_hi; + uint64_t frac_lo; +} FloatParts128; + +typedef struct { + FloatClass cls; + bool sign; + int32_t exp; + uint64_t frac_hi; + uint64_t frac_hm; /* high-middle */ + uint64_t frac_lm; /* low-middle */ + uint64_t frac_lo; +} FloatParts256; + +/* These apply to the most significant word of each FloatPartsN. */ +#define DECOMPOSED_BINARY_POINT 63 #define DECOMPOSED_IMPLICIT_BIT (1ull << DECOMPOSED_BINARY_POINT) -#define DECOMPOSED_OVERFLOW_BIT (DECOMPOSED_IMPLICIT_BIT << 1) /* Structure holding all of the relevant parameters for a format. * exp_size: the size of the exponent field @@ -514,9 +509,7 @@ typedef struct { * frac_size: the size of the fraction field * frac_shift: shift to normalise the fraction with DECOMPOSED_BINARY_POINT * The following are computed based the size of fraction - * frac_lsb: least significant bit of fraction - * frac_lsbm1: the bit below the least significant bit (for rounding) - * round_mask/roundeven_mask: masks used for rounding + * round_mask: bits below lsb which must be rounded * The following optional modifiers are available: * arm_althp: handle ARM Alternative Half Precision */ @@ -526,24 +519,21 @@ typedef struct { int exp_max; int frac_size; int frac_shift; - uint64_t frac_lsb; - uint64_t frac_lsbm1; - uint64_t round_mask; - uint64_t roundeven_mask; bool arm_althp; + uint64_t round_mask; } FloatFmt; /* Expand fields based on the size of exponent and fraction */ -#define FLOAT_PARAMS(E, F) \ - .exp_size = E, \ - .exp_bias = ((1 << E) - 1) >> 1, \ - .exp_max = (1 << E) - 1, \ - .frac_size = F, \ - .frac_shift = DECOMPOSED_BINARY_POINT - F, \ - .frac_lsb = 1ull << (DECOMPOSED_BINARY_POINT - F), \ - .frac_lsbm1 = 1ull << ((DECOMPOSED_BINARY_POINT - F) - 1), \ - .round_mask = (1ull << (DECOMPOSED_BINARY_POINT - F)) - 1, \ - .roundeven_mask = (2ull << (DECOMPOSED_BINARY_POINT - F)) - 1 +#define FLOAT_PARAMS_(E) \ + .exp_size = E, \ + .exp_bias = ((1 << E) - 1) >> 1, \ + .exp_max = (1 << E) - 1 + +#define FLOAT_PARAMS(E, F) \ + FLOAT_PARAMS_(E), \ + .frac_size = F, \ + .frac_shift = (-F - 1) & 63, \ + .round_mask = (1ull << ((-F - 1) & 63)) - 1 static const FloatFmt float16_params = { FLOAT_PARAMS(5, 10) @@ -566,65 +556,123 @@ static const FloatFmt float64_params = { FLOAT_PARAMS(11, 52) }; -/* Unpack a float to parts, but do not canonicalize. */ -static inline FloatParts unpack_raw(FloatFmt fmt, uint64_t raw) -{ - const int sign_pos = fmt.frac_size + fmt.exp_size; +static const FloatFmt float128_params = { + FLOAT_PARAMS(15, 112) +}; - return (FloatParts) { +#define FLOATX80_PARAMS(R) \ + FLOAT_PARAMS_(15), \ + .frac_size = R == 64 ? 63 : R, \ + .frac_shift = 0, \ + .round_mask = R == 64 ? -1 : (1ull << ((-R - 1) & 63)) - 1 + +static const FloatFmt floatx80_params[3] = { + [floatx80_precision_s] = { FLOATX80_PARAMS(23) }, + [floatx80_precision_d] = { FLOATX80_PARAMS(52) }, + [floatx80_precision_x] = { FLOATX80_PARAMS(64) }, +}; + +/* Unpack a float to parts, but do not canonicalize. */ +static void unpack_raw64(FloatParts64 *r, const FloatFmt *fmt, uint64_t raw) +{ + const int f_size = fmt->frac_size; + const int e_size = fmt->exp_size; + + *r = (FloatParts64) { .cls = float_class_unclassified, - .sign = extract64(raw, sign_pos, 1), - .exp = extract64(raw, fmt.frac_size, fmt.exp_size), - .frac = extract64(raw, 0, fmt.frac_size), + .sign = extract64(raw, f_size + e_size, 1), + .exp = extract64(raw, f_size, e_size), + .frac = extract64(raw, 0, f_size) }; } -static inline FloatParts float16_unpack_raw(float16 f) +static inline void float16_unpack_raw(FloatParts64 *p, float16 f) { - return unpack_raw(float16_params, f); + unpack_raw64(p, &float16_params, f); } -static inline FloatParts bfloat16_unpack_raw(bfloat16 f) +static inline void bfloat16_unpack_raw(FloatParts64 *p, bfloat16 f) { - return unpack_raw(bfloat16_params, f); + unpack_raw64(p, &bfloat16_params, f); } -static inline FloatParts float32_unpack_raw(float32 f) +static inline void float32_unpack_raw(FloatParts64 *p, float32 f) { - return unpack_raw(float32_params, f); + unpack_raw64(p, &float32_params, f); } -static inline FloatParts float64_unpack_raw(float64 f) +static inline void float64_unpack_raw(FloatParts64 *p, float64 f) { - return unpack_raw(float64_params, f); + unpack_raw64(p, &float64_params, f); +} + +static void floatx80_unpack_raw(FloatParts128 *p, floatx80 f) +{ + *p = (FloatParts128) { + .cls = float_class_unclassified, + .sign = extract32(f.high, 15, 1), + .exp = extract32(f.high, 0, 15), + .frac_hi = f.low + }; +} + +static void float128_unpack_raw(FloatParts128 *p, float128 f) +{ + const int f_size = float128_params.frac_size - 64; + const int e_size = float128_params.exp_size; + + *p = (FloatParts128) { + .cls = float_class_unclassified, + .sign = extract64(f.high, f_size + e_size, 1), + .exp = extract64(f.high, f_size, e_size), + .frac_hi = extract64(f.high, 0, f_size), + .frac_lo = f.low, + }; } /* Pack a float from parts, but do not canonicalize. */ -static inline uint64_t pack_raw(FloatFmt fmt, FloatParts p) +static uint64_t pack_raw64(const FloatParts64 *p, const FloatFmt *fmt) { - const int sign_pos = fmt.frac_size + fmt.exp_size; - uint64_t ret = deposit64(p.frac, fmt.frac_size, fmt.exp_size, p.exp); - return deposit64(ret, sign_pos, 1, p.sign); + const int f_size = fmt->frac_size; + const int e_size = fmt->exp_size; + uint64_t ret; + + ret = (uint64_t)p->sign << (f_size + e_size); + ret = deposit64(ret, f_size, e_size, p->exp); + ret = deposit64(ret, 0, f_size, p->frac); + return ret; } -static inline float16 float16_pack_raw(FloatParts p) +static inline float16 float16_pack_raw(const FloatParts64 *p) { - return make_float16(pack_raw(float16_params, p)); + return make_float16(pack_raw64(p, &float16_params)); } -static inline bfloat16 bfloat16_pack_raw(FloatParts p) +static inline bfloat16 bfloat16_pack_raw(const FloatParts64 *p) { - return pack_raw(bfloat16_params, p); + return pack_raw64(p, &bfloat16_params); } -static inline float32 float32_pack_raw(FloatParts p) +static inline float32 float32_pack_raw(const FloatParts64 *p) { - return make_float32(pack_raw(float32_params, p)); + return make_float32(pack_raw64(p, &float32_params)); } -static inline float64 float64_pack_raw(FloatParts p) +static inline float64 float64_pack_raw(const FloatParts64 *p) { - return make_float64(pack_raw(float64_params, p)); + return make_float64(pack_raw64(p, &float64_params)); +} + +static float128 float128_pack_raw(const FloatParts128 *p) +{ + const int f_size = float128_params.frac_size - 64; + const int e_size = float128_params.exp_size; + uint64_t hi; + + hi = (uint64_t)p->sign << (f_size + e_size); + hi = deposit64(hi, f_size, e_size, p->exp); + hi = deposit64(hi, 0, f_size, p->frac_hi); + return make_float128(hi, p->frac_lo); } /*---------------------------------------------------------------------------- @@ -637,474 +685,1177 @@ static inline float64 float64_pack_raw(FloatParts p) *----------------------------------------------------------------------------*/ #include "softfloat-specialize.c.inc" -/* Canonicalize EXP and FRAC, setting CLS. */ -static FloatParts sf_canonicalize(FloatParts part, const FloatFmt *parm, - float_status *status) -{ - if (part.exp == parm->exp_max && !parm->arm_althp) { - if (part.frac == 0) { - part.cls = float_class_inf; - } else { - part.frac <<= parm->frac_shift; - part.cls = (parts_is_snan_frac(part.frac, status) - ? float_class_snan : float_class_qnan); - } - } else if (part.exp == 0) { - if (likely(part.frac == 0)) { - part.cls = float_class_zero; - } else if (status->flush_inputs_to_zero) { - float_raise(float_flag_input_denormal, status); - part.cls = float_class_zero; - part.frac = 0; - } else { - int shift = clz64(part.frac) - 1; - part.cls = float_class_normal; - part.exp = parm->frac_shift - parm->exp_bias - shift + 1; - part.frac <<= shift; - } - } else { - part.cls = float_class_normal; - part.exp -= parm->exp_bias; - part.frac = DECOMPOSED_IMPLICIT_BIT + (part.frac << parm->frac_shift); - } - return part; -} +#define PARTS_GENERIC_64_128(NAME, P) \ + _Generic((P), FloatParts64 *: parts64_##NAME, \ + FloatParts128 *: parts128_##NAME) -/* Round and uncanonicalize a floating-point number by parts. There - * are FRAC_SHIFT bits that may require rounding at the bottom of the - * fraction; these bits will be removed. The exponent will be biased - * by EXP_BIAS and must be bounded by [EXP_MAX-1, 0]. +#define PARTS_GENERIC_64_128_256(NAME, P) \ + _Generic((P), FloatParts64 *: parts64_##NAME, \ + FloatParts128 *: parts128_##NAME, \ + FloatParts256 *: parts256_##NAME) + +#define parts_default_nan(P, S) PARTS_GENERIC_64_128(default_nan, P)(P, S) +#define parts_silence_nan(P, S) PARTS_GENERIC_64_128(silence_nan, P)(P, S) + +static void parts64_return_nan(FloatParts64 *a, float_status *s); +static void parts128_return_nan(FloatParts128 *a, float_status *s); + +#define parts_return_nan(P, S) PARTS_GENERIC_64_128(return_nan, P)(P, S) + +static FloatParts64 *parts64_pick_nan(FloatParts64 *a, FloatParts64 *b, + float_status *s); +static FloatParts128 *parts128_pick_nan(FloatParts128 *a, FloatParts128 *b, + float_status *s); + +#define parts_pick_nan(A, B, S) PARTS_GENERIC_64_128(pick_nan, A)(A, B, S) + +static FloatParts64 *parts64_pick_nan_muladd(FloatParts64 *a, FloatParts64 *b, + FloatParts64 *c, float_status *s, + int ab_mask, int abc_mask); +static FloatParts128 *parts128_pick_nan_muladd(FloatParts128 *a, + FloatParts128 *b, + FloatParts128 *c, + float_status *s, + int ab_mask, int abc_mask); + +#define parts_pick_nan_muladd(A, B, C, S, ABM, ABCM) \ + PARTS_GENERIC_64_128(pick_nan_muladd, A)(A, B, C, S, ABM, ABCM) + +static void parts64_canonicalize(FloatParts64 *p, float_status *status, + const FloatFmt *fmt); +static void parts128_canonicalize(FloatParts128 *p, float_status *status, + const FloatFmt *fmt); + +#define parts_canonicalize(A, S, F) \ + PARTS_GENERIC_64_128(canonicalize, A)(A, S, F) + +static void parts64_uncanon_normal(FloatParts64 *p, float_status *status, + const FloatFmt *fmt); +static void parts128_uncanon_normal(FloatParts128 *p, float_status *status, + const FloatFmt *fmt); + +#define parts_uncanon_normal(A, S, F) \ + PARTS_GENERIC_64_128(uncanon_normal, A)(A, S, F) + +static void parts64_uncanon(FloatParts64 *p, float_status *status, + const FloatFmt *fmt); +static void parts128_uncanon(FloatParts128 *p, float_status *status, + const FloatFmt *fmt); + +#define parts_uncanon(A, S, F) \ + PARTS_GENERIC_64_128(uncanon, A)(A, S, F) + +static void parts64_add_normal(FloatParts64 *a, FloatParts64 *b); +static void parts128_add_normal(FloatParts128 *a, FloatParts128 *b); +static void parts256_add_normal(FloatParts256 *a, FloatParts256 *b); + +#define parts_add_normal(A, B) \ + PARTS_GENERIC_64_128_256(add_normal, A)(A, B) + +static bool parts64_sub_normal(FloatParts64 *a, FloatParts64 *b); +static bool parts128_sub_normal(FloatParts128 *a, FloatParts128 *b); +static bool parts256_sub_normal(FloatParts256 *a, FloatParts256 *b); + +#define parts_sub_normal(A, B) \ + PARTS_GENERIC_64_128_256(sub_normal, A)(A, B) + +static FloatParts64 *parts64_addsub(FloatParts64 *a, FloatParts64 *b, + float_status *s, bool subtract); +static FloatParts128 *parts128_addsub(FloatParts128 *a, FloatParts128 *b, + float_status *s, bool subtract); + +#define parts_addsub(A, B, S, Z) \ + PARTS_GENERIC_64_128(addsub, A)(A, B, S, Z) + +static FloatParts64 *parts64_mul(FloatParts64 *a, FloatParts64 *b, + float_status *s); +static FloatParts128 *parts128_mul(FloatParts128 *a, FloatParts128 *b, + float_status *s); + +#define parts_mul(A, B, S) \ + PARTS_GENERIC_64_128(mul, A)(A, B, S) + +static FloatParts64 *parts64_muladd(FloatParts64 *a, FloatParts64 *b, + FloatParts64 *c, int flags, + float_status *s); +static FloatParts128 *parts128_muladd(FloatParts128 *a, FloatParts128 *b, + FloatParts128 *c, int flags, + float_status *s); + +#define parts_muladd(A, B, C, Z, S) \ + PARTS_GENERIC_64_128(muladd, A)(A, B, C, Z, S) + +static FloatParts64 *parts64_div(FloatParts64 *a, FloatParts64 *b, + float_status *s); +static FloatParts128 *parts128_div(FloatParts128 *a, FloatParts128 *b, + float_status *s); + +#define parts_div(A, B, S) \ + PARTS_GENERIC_64_128(div, A)(A, B, S) + +static FloatParts64 *parts64_modrem(FloatParts64 *a, FloatParts64 *b, + uint64_t *mod_quot, float_status *s); +static FloatParts128 *parts128_modrem(FloatParts128 *a, FloatParts128 *b, + uint64_t *mod_quot, float_status *s); + +#define parts_modrem(A, B, Q, S) \ + PARTS_GENERIC_64_128(modrem, A)(A, B, Q, S) + +static void parts64_sqrt(FloatParts64 *a, float_status *s, const FloatFmt *f); +static void parts128_sqrt(FloatParts128 *a, float_status *s, const FloatFmt *f); + +#define parts_sqrt(A, S, F) \ + PARTS_GENERIC_64_128(sqrt, A)(A, S, F) + +static bool parts64_round_to_int_normal(FloatParts64 *a, FloatRoundMode rm, + int scale, int frac_size); +static bool parts128_round_to_int_normal(FloatParts128 *a, FloatRoundMode r, + int scale, int frac_size); + +#define parts_round_to_int_normal(A, R, C, F) \ + PARTS_GENERIC_64_128(round_to_int_normal, A)(A, R, C, F) + +static void parts64_round_to_int(FloatParts64 *a, FloatRoundMode rm, + int scale, float_status *s, + const FloatFmt *fmt); +static void parts128_round_to_int(FloatParts128 *a, FloatRoundMode r, + int scale, float_status *s, + const FloatFmt *fmt); + +#define parts_round_to_int(A, R, C, S, F) \ + PARTS_GENERIC_64_128(round_to_int, A)(A, R, C, S, F) + +static int64_t parts64_float_to_sint(FloatParts64 *p, FloatRoundMode rmode, + int scale, int64_t min, int64_t max, + float_status *s); +static int64_t parts128_float_to_sint(FloatParts128 *p, FloatRoundMode rmode, + int scale, int64_t min, int64_t max, + float_status *s); + +#define parts_float_to_sint(P, R, Z, MN, MX, S) \ + PARTS_GENERIC_64_128(float_to_sint, P)(P, R, Z, MN, MX, S) + +static uint64_t parts64_float_to_uint(FloatParts64 *p, FloatRoundMode rmode, + int scale, uint64_t max, + float_status *s); +static uint64_t parts128_float_to_uint(FloatParts128 *p, FloatRoundMode rmode, + int scale, uint64_t max, + float_status *s); + +#define parts_float_to_uint(P, R, Z, M, S) \ + PARTS_GENERIC_64_128(float_to_uint, P)(P, R, Z, M, S) + +static void parts64_sint_to_float(FloatParts64 *p, int64_t a, + int scale, float_status *s); +static void parts128_sint_to_float(FloatParts128 *p, int64_t a, + int scale, float_status *s); + +#define parts_sint_to_float(P, I, Z, S) \ + PARTS_GENERIC_64_128(sint_to_float, P)(P, I, Z, S) + +static void parts64_uint_to_float(FloatParts64 *p, uint64_t a, + int scale, float_status *s); +static void parts128_uint_to_float(FloatParts128 *p, uint64_t a, + int scale, float_status *s); + +#define parts_uint_to_float(P, I, Z, S) \ + PARTS_GENERIC_64_128(uint_to_float, P)(P, I, Z, S) + +static FloatParts64 *parts64_minmax(FloatParts64 *a, FloatParts64 *b, + float_status *s, int flags); +static FloatParts128 *parts128_minmax(FloatParts128 *a, FloatParts128 *b, + float_status *s, int flags); + +#define parts_minmax(A, B, S, F) \ + PARTS_GENERIC_64_128(minmax, A)(A, B, S, F) + +static int parts64_compare(FloatParts64 *a, FloatParts64 *b, + float_status *s, bool q); +static int parts128_compare(FloatParts128 *a, FloatParts128 *b, + float_status *s, bool q); + +#define parts_compare(A, B, S, Q) \ + PARTS_GENERIC_64_128(compare, A)(A, B, S, Q) + +static void parts64_scalbn(FloatParts64 *a, int n, float_status *s); +static void parts128_scalbn(FloatParts128 *a, int n, float_status *s); + +#define parts_scalbn(A, N, S) \ + PARTS_GENERIC_64_128(scalbn, A)(A, N, S) + +static void parts64_log2(FloatParts64 *a, float_status *s, const FloatFmt *f); +static void parts128_log2(FloatParts128 *a, float_status *s, const FloatFmt *f); + +#define parts_log2(A, S, F) \ + PARTS_GENERIC_64_128(log2, A)(A, S, F) + +/* + * Helper functions for softfloat-parts.c.inc, per-size operations. */ -static FloatParts round_canonical(FloatParts p, float_status *s, - const FloatFmt *parm) +#define FRAC_GENERIC_64_128(NAME, P) \ + _Generic((P), FloatParts64 *: frac64_##NAME, \ + FloatParts128 *: frac128_##NAME) + +#define FRAC_GENERIC_64_128_256(NAME, P) \ + _Generic((P), FloatParts64 *: frac64_##NAME, \ + FloatParts128 *: frac128_##NAME, \ + FloatParts256 *: frac256_##NAME) + +static bool frac64_add(FloatParts64 *r, FloatParts64 *a, FloatParts64 *b) { - const uint64_t frac_lsb = parm->frac_lsb; - const uint64_t frac_lsbm1 = parm->frac_lsbm1; - const uint64_t round_mask = parm->round_mask; - const uint64_t roundeven_mask = parm->roundeven_mask; - const int exp_max = parm->exp_max; - const int frac_shift = parm->frac_shift; - uint64_t frac, inc; - int exp, flags = 0; - bool overflow_norm; + return uadd64_overflow(a->frac, b->frac, &r->frac); +} - frac = p.frac; - exp = p.exp; +static bool frac128_add(FloatParts128 *r, FloatParts128 *a, FloatParts128 *b) +{ + bool c = 0; + r->frac_lo = uadd64_carry(a->frac_lo, b->frac_lo, &c); + r->frac_hi = uadd64_carry(a->frac_hi, b->frac_hi, &c); + return c; +} - switch (p.cls) { - case float_class_normal: - switch (s->float_rounding_mode) { - case float_round_nearest_even: - overflow_norm = false; - inc = ((frac & roundeven_mask) != frac_lsbm1 ? frac_lsbm1 : 0); - break; - case float_round_ties_away: - overflow_norm = false; - inc = frac_lsbm1; - break; - case float_round_to_zero: - overflow_norm = true; - inc = 0; - break; - case float_round_up: - inc = p.sign ? 0 : round_mask; - overflow_norm = p.sign; - break; - case float_round_down: - inc = p.sign ? round_mask : 0; - overflow_norm = !p.sign; - break; - case float_round_to_odd: - overflow_norm = true; - inc = frac & frac_lsb ? 0 : round_mask; - break; - default: - g_assert_not_reached(); +static bool frac256_add(FloatParts256 *r, FloatParts256 *a, FloatParts256 *b) +{ + bool c = 0; + r->frac_lo = uadd64_carry(a->frac_lo, b->frac_lo, &c); + r->frac_lm = uadd64_carry(a->frac_lm, b->frac_lm, &c); + r->frac_hm = uadd64_carry(a->frac_hm, b->frac_hm, &c); + r->frac_hi = uadd64_carry(a->frac_hi, b->frac_hi, &c); + return c; +} + +#define frac_add(R, A, B) FRAC_GENERIC_64_128_256(add, R)(R, A, B) + +static bool frac64_addi(FloatParts64 *r, FloatParts64 *a, uint64_t c) +{ + return uadd64_overflow(a->frac, c, &r->frac); +} + +static bool frac128_addi(FloatParts128 *r, FloatParts128 *a, uint64_t c) +{ + c = uadd64_overflow(a->frac_lo, c, &r->frac_lo); + return uadd64_overflow(a->frac_hi, c, &r->frac_hi); +} + +#define frac_addi(R, A, C) FRAC_GENERIC_64_128(addi, R)(R, A, C) + +static void frac64_allones(FloatParts64 *a) +{ + a->frac = -1; +} + +static void frac128_allones(FloatParts128 *a) +{ + a->frac_hi = a->frac_lo = -1; +} + +#define frac_allones(A) FRAC_GENERIC_64_128(allones, A)(A) + +static int frac64_cmp(FloatParts64 *a, FloatParts64 *b) +{ + return a->frac == b->frac ? 0 : a->frac < b->frac ? -1 : 1; +} + +static int frac128_cmp(FloatParts128 *a, FloatParts128 *b) +{ + uint64_t ta = a->frac_hi, tb = b->frac_hi; + if (ta == tb) { + ta = a->frac_lo, tb = b->frac_lo; + if (ta == tb) { + return 0; } + } + return ta < tb ? -1 : 1; +} - exp += parm->exp_bias; - if (likely(exp > 0)) { - if (frac & round_mask) { - flags |= float_flag_inexact; - frac += inc; - if (frac & DECOMPOSED_OVERFLOW_BIT) { - frac >>= 1; - exp++; - } - } - frac >>= frac_shift; +#define frac_cmp(A, B) FRAC_GENERIC_64_128(cmp, A)(A, B) - if (parm->arm_althp) { - /* ARM Alt HP eschews Inf and NaN for a wider exponent. */ - if (unlikely(exp > exp_max)) { - /* Overflow. Return the maximum normal. */ - flags = float_flag_invalid; - exp = exp_max; - frac = -1; - } - } else if (unlikely(exp >= exp_max)) { - flags |= float_flag_overflow | float_flag_inexact; - if (overflow_norm) { - exp = exp_max - 1; - frac = -1; - } else { - p.cls = float_class_inf; - goto do_inf; - } - } - } else if (s->flush_to_zero) { - flags |= float_flag_output_denormal; - p.cls = float_class_zero; - goto do_zero; - } else { - bool is_tiny = s->tininess_before_rounding - || (exp < 0) - || !((frac + inc) & DECOMPOSED_OVERFLOW_BIT); +static void frac64_clear(FloatParts64 *a) +{ + a->frac = 0; +} - shift64RightJamming(frac, 1 - exp, &frac); - if (frac & round_mask) { - /* Need to recompute round-to-even. */ - switch (s->float_rounding_mode) { - case float_round_nearest_even: - inc = ((frac & roundeven_mask) != frac_lsbm1 - ? frac_lsbm1 : 0); - break; - case float_round_to_odd: - inc = frac & frac_lsb ? 0 : round_mask; - break; - default: - break; - } - flags |= float_flag_inexact; - frac += inc; - } +static void frac128_clear(FloatParts128 *a) +{ + a->frac_hi = a->frac_lo = 0; +} - exp = (frac & DECOMPOSED_IMPLICIT_BIT ? 1 : 0); - frac >>= frac_shift; +#define frac_clear(A) FRAC_GENERIC_64_128(clear, A)(A) - if (is_tiny && (flags & float_flag_inexact)) { - flags |= float_flag_underflow; - } - if (exp == 0 && frac == 0) { - p.cls = float_class_zero; - } - } - break; +static bool frac64_div(FloatParts64 *a, FloatParts64 *b) +{ + uint64_t n1, n0, r, q; + bool ret; - case float_class_zero: - do_zero: - exp = 0; - frac = 0; - break; + /* + * We want a 2*N / N-bit division to produce exactly an N-bit + * result, so that we do not lose any precision and so that we + * do not have to renormalize afterward. If A.frac < B.frac, + * then division would produce an (N-1)-bit result; shift A left + * by one to produce the an N-bit result, and return true to + * decrement the exponent to match. + * + * The udiv_qrnnd algorithm that we're using requires normalization, + * i.e. the msb of the denominator must be set, which is already true. + */ + ret = a->frac < b->frac; + if (ret) { + n0 = a->frac; + n1 = 0; + } else { + n0 = a->frac >> 1; + n1 = a->frac << 63; + } + q = udiv_qrnnd(&r, n0, n1, b->frac); - case float_class_inf: - do_inf: - assert(!parm->arm_althp); - exp = exp_max; - frac = 0; - break; + /* Set lsb if there is a remainder, to set inexact. */ + a->frac = q | (r != 0); - case float_class_qnan: - case float_class_snan: - assert(!parm->arm_althp); - exp = exp_max; - frac >>= parm->frac_shift; - break; + return ret; +} - default: - g_assert_not_reached(); +static bool frac128_div(FloatParts128 *a, FloatParts128 *b) +{ + uint64_t q0, q1, a0, a1, b0, b1; + uint64_t r0, r1, r2, r3, t0, t1, t2, t3; + bool ret = false; + + a0 = a->frac_hi, a1 = a->frac_lo; + b0 = b->frac_hi, b1 = b->frac_lo; + + ret = lt128(a0, a1, b0, b1); + if (!ret) { + a1 = shr_double(a0, a1, 1); + a0 = a0 >> 1; } - float_raise(flags, s); - p.exp = exp; - p.frac = frac; - return p; + /* Use 128/64 -> 64 division as estimate for 192/128 -> 128 division. */ + q0 = estimateDiv128To64(a0, a1, b0); + + /* + * Estimate is high because B1 was not included (unless B1 == 0). + * Reduce quotient and increase remainder until remainder is non-negative. + * This loop will execute 0 to 2 times. + */ + mul128By64To192(b0, b1, q0, &t0, &t1, &t2); + sub192(a0, a1, 0, t0, t1, t2, &r0, &r1, &r2); + while (r0 != 0) { + q0--; + add192(r0, r1, r2, 0, b0, b1, &r0, &r1, &r2); + } + + /* Repeat using the remainder, producing a second word of quotient. */ + q1 = estimateDiv128To64(r1, r2, b0); + mul128By64To192(b0, b1, q1, &t1, &t2, &t3); + sub192(r1, r2, 0, t1, t2, t3, &r1, &r2, &r3); + while (r1 != 0) { + q1--; + add192(r1, r2, r3, 0, b0, b1, &r1, &r2, &r3); + } + + /* Any remainder indicates inexact; set sticky bit. */ + q1 |= (r2 | r3) != 0; + + a->frac_hi = q0; + a->frac_lo = q1; + return ret; } -/* Explicit FloatFmt version */ -static FloatParts float16a_unpack_canonical(float16 f, float_status *s, - const FloatFmt *params) +#define frac_div(A, B) FRAC_GENERIC_64_128(div, A)(A, B) + +static bool frac64_eqz(FloatParts64 *a) { - return sf_canonicalize(float16_unpack_raw(f), params, s); + return a->frac == 0; } -static FloatParts float16_unpack_canonical(float16 f, float_status *s) +static bool frac128_eqz(FloatParts128 *a) { - return float16a_unpack_canonical(f, s, &float16_params); + return (a->frac_hi | a->frac_lo) == 0; } -static FloatParts bfloat16_unpack_canonical(bfloat16 f, float_status *s) +#define frac_eqz(A) FRAC_GENERIC_64_128(eqz, A)(A) + +static void frac64_mulw(FloatParts128 *r, FloatParts64 *a, FloatParts64 *b) { - return sf_canonicalize(bfloat16_unpack_raw(f), &bfloat16_params, s); + mulu64(&r->frac_lo, &r->frac_hi, a->frac, b->frac); } -static float16 float16a_round_pack_canonical(FloatParts p, float_status *s, +static void frac128_mulw(FloatParts256 *r, FloatParts128 *a, FloatParts128 *b) +{ + mul128To256(a->frac_hi, a->frac_lo, b->frac_hi, b->frac_lo, + &r->frac_hi, &r->frac_hm, &r->frac_lm, &r->frac_lo); +} + +#define frac_mulw(R, A, B) FRAC_GENERIC_64_128(mulw, A)(R, A, B) + +static void frac64_neg(FloatParts64 *a) +{ + a->frac = -a->frac; +} + +static void frac128_neg(FloatParts128 *a) +{ + bool c = 0; + a->frac_lo = usub64_borrow(0, a->frac_lo, &c); + a->frac_hi = usub64_borrow(0, a->frac_hi, &c); +} + +static void frac256_neg(FloatParts256 *a) +{ + bool c = 0; + a->frac_lo = usub64_borrow(0, a->frac_lo, &c); + a->frac_lm = usub64_borrow(0, a->frac_lm, &c); + a->frac_hm = usub64_borrow(0, a->frac_hm, &c); + a->frac_hi = usub64_borrow(0, a->frac_hi, &c); +} + +#define frac_neg(A) FRAC_GENERIC_64_128_256(neg, A)(A) + +static int frac64_normalize(FloatParts64 *a) +{ + if (a->frac) { + int shift = clz64(a->frac); + a->frac <<= shift; + return shift; + } + return 64; +} + +static int frac128_normalize(FloatParts128 *a) +{ + if (a->frac_hi) { + int shl = clz64(a->frac_hi); + a->frac_hi = shl_double(a->frac_hi, a->frac_lo, shl); + a->frac_lo <<= shl; + return shl; + } else if (a->frac_lo) { + int shl = clz64(a->frac_lo); + a->frac_hi = a->frac_lo << shl; + a->frac_lo = 0; + return shl + 64; + } + return 128; +} + +static int frac256_normalize(FloatParts256 *a) +{ + uint64_t a0 = a->frac_hi, a1 = a->frac_hm; + uint64_t a2 = a->frac_lm, a3 = a->frac_lo; + int ret, shl; + + if (likely(a0)) { + shl = clz64(a0); + if (shl == 0) { + return 0; + } + ret = shl; + } else { + if (a1) { + ret = 64; + a0 = a1, a1 = a2, a2 = a3, a3 = 0; + } else if (a2) { + ret = 128; + a0 = a2, a1 = a3, a2 = 0, a3 = 0; + } else if (a3) { + ret = 192; + a0 = a3, a1 = 0, a2 = 0, a3 = 0; + } else { + ret = 256; + a0 = 0, a1 = 0, a2 = 0, a3 = 0; + goto done; + } + shl = clz64(a0); + if (shl == 0) { + goto done; + } + ret += shl; + } + + a0 = shl_double(a0, a1, shl); + a1 = shl_double(a1, a2, shl); + a2 = shl_double(a2, a3, shl); + a3 <<= shl; + + done: + a->frac_hi = a0; + a->frac_hm = a1; + a->frac_lm = a2; + a->frac_lo = a3; + return ret; +} + +#define frac_normalize(A) FRAC_GENERIC_64_128_256(normalize, A)(A) + +static void frac64_modrem(FloatParts64 *a, FloatParts64 *b, uint64_t *mod_quot) +{ + uint64_t a0, a1, b0, t0, t1, q, quot; + int exp_diff = a->exp - b->exp; + int shift; + + a0 = a->frac; + a1 = 0; + + if (exp_diff < -1) { + if (mod_quot) { + *mod_quot = 0; + } + return; + } + if (exp_diff == -1) { + a0 >>= 1; + exp_diff = 0; + } + + b0 = b->frac; + quot = q = b0 <= a0; + if (q) { + a0 -= b0; + } + + exp_diff -= 64; + while (exp_diff > 0) { + q = estimateDiv128To64(a0, a1, b0); + q = q > 2 ? q - 2 : 0; + mul64To128(b0, q, &t0, &t1); + sub128(a0, a1, t0, t1, &a0, &a1); + shortShift128Left(a0, a1, 62, &a0, &a1); + exp_diff -= 62; + quot = (quot << 62) + q; + } + + exp_diff += 64; + if (exp_diff > 0) { + q = estimateDiv128To64(a0, a1, b0); + q = q > 2 ? (q - 2) >> (64 - exp_diff) : 0; + mul64To128(b0, q << (64 - exp_diff), &t0, &t1); + sub128(a0, a1, t0, t1, &a0, &a1); + shortShift128Left(0, b0, 64 - exp_diff, &t0, &t1); + while (le128(t0, t1, a0, a1)) { + ++q; + sub128(a0, a1, t0, t1, &a0, &a1); + } + quot = (exp_diff < 64 ? quot << exp_diff : 0) + q; + } else { + t0 = b0; + t1 = 0; + } + + if (mod_quot) { + *mod_quot = quot; + } else { + sub128(t0, t1, a0, a1, &t0, &t1); + if (lt128(t0, t1, a0, a1) || + (eq128(t0, t1, a0, a1) && (q & 1))) { + a0 = t0; + a1 = t1; + a->sign = !a->sign; + } + } + + if (likely(a0)) { + shift = clz64(a0); + shortShift128Left(a0, a1, shift, &a0, &a1); + } else if (likely(a1)) { + shift = clz64(a1); + a0 = a1 << shift; + a1 = 0; + shift += 64; + } else { + a->cls = float_class_zero; + return; + } + + a->exp = b->exp + exp_diff - shift; + a->frac = a0 | (a1 != 0); +} + +static void frac128_modrem(FloatParts128 *a, FloatParts128 *b, + uint64_t *mod_quot) +{ + uint64_t a0, a1, a2, b0, b1, t0, t1, t2, q, quot; + int exp_diff = a->exp - b->exp; + int shift; + + a0 = a->frac_hi; + a1 = a->frac_lo; + a2 = 0; + + if (exp_diff < -1) { + if (mod_quot) { + *mod_quot = 0; + } + return; + } + if (exp_diff == -1) { + shift128Right(a0, a1, 1, &a0, &a1); + exp_diff = 0; + } + + b0 = b->frac_hi; + b1 = b->frac_lo; + + quot = q = le128(b0, b1, a0, a1); + if (q) { + sub128(a0, a1, b0, b1, &a0, &a1); + } + + exp_diff -= 64; + while (exp_diff > 0) { + q = estimateDiv128To64(a0, a1, b0); + q = q > 4 ? q - 4 : 0; + mul128By64To192(b0, b1, q, &t0, &t1, &t2); + sub192(a0, a1, a2, t0, t1, t2, &a0, &a1, &a2); + shortShift192Left(a0, a1, a2, 61, &a0, &a1, &a2); + exp_diff -= 61; + quot = (quot << 61) + q; + } + + exp_diff += 64; + if (exp_diff > 0) { + q = estimateDiv128To64(a0, a1, b0); + q = q > 4 ? (q - 4) >> (64 - exp_diff) : 0; + mul128By64To192(b0, b1, q << (64 - exp_diff), &t0, &t1, &t2); + sub192(a0, a1, a2, t0, t1, t2, &a0, &a1, &a2); + shortShift192Left(0, b0, b1, 64 - exp_diff, &t0, &t1, &t2); + while (le192(t0, t1, t2, a0, a1, a2)) { + ++q; + sub192(a0, a1, a2, t0, t1, t2, &a0, &a1, &a2); + } + quot = (exp_diff < 64 ? quot << exp_diff : 0) + q; + } else { + t0 = b0; + t1 = b1; + t2 = 0; + } + + if (mod_quot) { + *mod_quot = quot; + } else { + sub192(t0, t1, t2, a0, a1, a2, &t0, &t1, &t2); + if (lt192(t0, t1, t2, a0, a1, a2) || + (eq192(t0, t1, t2, a0, a1, a2) && (q & 1))) { + a0 = t0; + a1 = t1; + a2 = t2; + a->sign = !a->sign; + } + } + + if (likely(a0)) { + shift = clz64(a0); + shortShift192Left(a0, a1, a2, shift, &a0, &a1, &a2); + } else if (likely(a1)) { + shift = clz64(a1); + shortShift128Left(a1, a2, shift, &a0, &a1); + a2 = 0; + shift += 64; + } else if (likely(a2)) { + shift = clz64(a2); + a0 = a2 << shift; + a1 = a2 = 0; + shift += 128; + } else { + a->cls = float_class_zero; + return; + } + + a->exp = b->exp + exp_diff - shift; + a->frac_hi = a0; + a->frac_lo = a1 | (a2 != 0); +} + +#define frac_modrem(A, B, Q) FRAC_GENERIC_64_128(modrem, A)(A, B, Q) + +static void frac64_shl(FloatParts64 *a, int c) +{ + a->frac <<= c; +} + +static void frac128_shl(FloatParts128 *a, int c) +{ + uint64_t a0 = a->frac_hi, a1 = a->frac_lo; + + if (c & 64) { + a0 = a1, a1 = 0; + } + + c &= 63; + if (c) { + a0 = shl_double(a0, a1, c); + a1 = a1 << c; + } + + a->frac_hi = a0; + a->frac_lo = a1; +} + +#define frac_shl(A, C) FRAC_GENERIC_64_128(shl, A)(A, C) + +static void frac64_shr(FloatParts64 *a, int c) +{ + a->frac >>= c; +} + +static void frac128_shr(FloatParts128 *a, int c) +{ + uint64_t a0 = a->frac_hi, a1 = a->frac_lo; + + if (c & 64) { + a1 = a0, a0 = 0; + } + + c &= 63; + if (c) { + a1 = shr_double(a0, a1, c); + a0 = a0 >> c; + } + + a->frac_hi = a0; + a->frac_lo = a1; +} + +#define frac_shr(A, C) FRAC_GENERIC_64_128(shr, A)(A, C) + +static void frac64_shrjam(FloatParts64 *a, int c) +{ + uint64_t a0 = a->frac; + + if (likely(c != 0)) { + if (likely(c < 64)) { + a0 = (a0 >> c) | (shr_double(a0, 0, c) != 0); + } else { + a0 = a0 != 0; + } + a->frac = a0; + } +} + +static void frac128_shrjam(FloatParts128 *a, int c) +{ + uint64_t a0 = a->frac_hi, a1 = a->frac_lo; + uint64_t sticky = 0; + + if (unlikely(c == 0)) { + return; + } else if (likely(c < 64)) { + /* nothing */ + } else if (likely(c < 128)) { + sticky = a1; + a1 = a0; + a0 = 0; + c &= 63; + if (c == 0) { + goto done; + } + } else { + sticky = a0 | a1; + a0 = a1 = 0; + goto done; + } + + sticky |= shr_double(a1, 0, c); + a1 = shr_double(a0, a1, c); + a0 = a0 >> c; + + done: + a->frac_lo = a1 | (sticky != 0); + a->frac_hi = a0; +} + +static void frac256_shrjam(FloatParts256 *a, int c) +{ + uint64_t a0 = a->frac_hi, a1 = a->frac_hm; + uint64_t a2 = a->frac_lm, a3 = a->frac_lo; + uint64_t sticky = 0; + + if (unlikely(c == 0)) { + return; + } else if (likely(c < 64)) { + /* nothing */ + } else if (likely(c < 256)) { + if (unlikely(c & 128)) { + sticky |= a2 | a3; + a3 = a1, a2 = a0, a1 = 0, a0 = 0; + } + if (unlikely(c & 64)) { + sticky |= a3; + a3 = a2, a2 = a1, a1 = a0, a0 = 0; + } + c &= 63; + if (c == 0) { + goto done; + } + } else { + sticky = a0 | a1 | a2 | a3; + a0 = a1 = a2 = a3 = 0; + goto done; + } + + sticky |= shr_double(a3, 0, c); + a3 = shr_double(a2, a3, c); + a2 = shr_double(a1, a2, c); + a1 = shr_double(a0, a1, c); + a0 = a0 >> c; + + done: + a->frac_lo = a3 | (sticky != 0); + a->frac_lm = a2; + a->frac_hm = a1; + a->frac_hi = a0; +} + +#define frac_shrjam(A, C) FRAC_GENERIC_64_128_256(shrjam, A)(A, C) + +static bool frac64_sub(FloatParts64 *r, FloatParts64 *a, FloatParts64 *b) +{ + return usub64_overflow(a->frac, b->frac, &r->frac); +} + +static bool frac128_sub(FloatParts128 *r, FloatParts128 *a, FloatParts128 *b) +{ + bool c = 0; + r->frac_lo = usub64_borrow(a->frac_lo, b->frac_lo, &c); + r->frac_hi = usub64_borrow(a->frac_hi, b->frac_hi, &c); + return c; +} + +static bool frac256_sub(FloatParts256 *r, FloatParts256 *a, FloatParts256 *b) +{ + bool c = 0; + r->frac_lo = usub64_borrow(a->frac_lo, b->frac_lo, &c); + r->frac_lm = usub64_borrow(a->frac_lm, b->frac_lm, &c); + r->frac_hm = usub64_borrow(a->frac_hm, b->frac_hm, &c); + r->frac_hi = usub64_borrow(a->frac_hi, b->frac_hi, &c); + return c; +} + +#define frac_sub(R, A, B) FRAC_GENERIC_64_128_256(sub, R)(R, A, B) + +static void frac64_truncjam(FloatParts64 *r, FloatParts128 *a) +{ + r->frac = a->frac_hi | (a->frac_lo != 0); +} + +static void frac128_truncjam(FloatParts128 *r, FloatParts256 *a) +{ + r->frac_hi = a->frac_hi; + r->frac_lo = a->frac_hm | ((a->frac_lm | a->frac_lo) != 0); +} + +#define frac_truncjam(R, A) FRAC_GENERIC_64_128(truncjam, R)(R, A) + +static void frac64_widen(FloatParts128 *r, FloatParts64 *a) +{ + r->frac_hi = a->frac; + r->frac_lo = 0; +} + +static void frac128_widen(FloatParts256 *r, FloatParts128 *a) +{ + r->frac_hi = a->frac_hi; + r->frac_hm = a->frac_lo; + r->frac_lm = 0; + r->frac_lo = 0; +} + +#define frac_widen(A, B) FRAC_GENERIC_64_128(widen, B)(A, B) + +/* + * Reciprocal sqrt table. 1 bit of exponent, 6-bits of mantessa. + * From https://git.musl-libc.org/cgit/musl/tree/src/math/sqrt_data.c + * and thus MIT licenced. + */ +static const uint16_t rsqrt_tab[128] = { + 0xb451, 0xb2f0, 0xb196, 0xb044, 0xaef9, 0xadb6, 0xac79, 0xab43, + 0xaa14, 0xa8eb, 0xa7c8, 0xa6aa, 0xa592, 0xa480, 0xa373, 0xa26b, + 0xa168, 0xa06a, 0x9f70, 0x9e7b, 0x9d8a, 0x9c9d, 0x9bb5, 0x9ad1, + 0x99f0, 0x9913, 0x983a, 0x9765, 0x9693, 0x95c4, 0x94f8, 0x9430, + 0x936b, 0x92a9, 0x91ea, 0x912e, 0x9075, 0x8fbe, 0x8f0a, 0x8e59, + 0x8daa, 0x8cfe, 0x8c54, 0x8bac, 0x8b07, 0x8a64, 0x89c4, 0x8925, + 0x8889, 0x87ee, 0x8756, 0x86c0, 0x862b, 0x8599, 0x8508, 0x8479, + 0x83ec, 0x8361, 0x82d8, 0x8250, 0x81c9, 0x8145, 0x80c2, 0x8040, + 0xff02, 0xfd0e, 0xfb25, 0xf947, 0xf773, 0xf5aa, 0xf3ea, 0xf234, + 0xf087, 0xeee3, 0xed47, 0xebb3, 0xea27, 0xe8a3, 0xe727, 0xe5b2, + 0xe443, 0xe2dc, 0xe17a, 0xe020, 0xdecb, 0xdd7d, 0xdc34, 0xdaf1, + 0xd9b3, 0xd87b, 0xd748, 0xd61a, 0xd4f1, 0xd3cd, 0xd2ad, 0xd192, + 0xd07b, 0xcf69, 0xce5b, 0xcd51, 0xcc4a, 0xcb48, 0xca4a, 0xc94f, + 0xc858, 0xc764, 0xc674, 0xc587, 0xc49d, 0xc3b7, 0xc2d4, 0xc1f4, + 0xc116, 0xc03c, 0xbf65, 0xbe90, 0xbdbe, 0xbcef, 0xbc23, 0xbb59, + 0xba91, 0xb9cc, 0xb90a, 0xb84a, 0xb78c, 0xb6d0, 0xb617, 0xb560, +}; + +#define partsN(NAME) glue(glue(glue(parts,N),_),NAME) +#define FloatPartsN glue(FloatParts,N) +#define FloatPartsW glue(FloatParts,W) + +#define N 64 +#define W 128 + +#include "softfloat-parts-addsub.c.inc" +#include "softfloat-parts.c.inc" + +#undef N +#undef W +#define N 128 +#define W 256 + +#include "softfloat-parts-addsub.c.inc" +#include "softfloat-parts.c.inc" + +#undef N +#undef W +#define N 256 + +#include "softfloat-parts-addsub.c.inc" + +#undef N +#undef W +#undef partsN +#undef FloatPartsN +#undef FloatPartsW + +/* + * Pack/unpack routines with a specific FloatFmt. + */ + +static void float16a_unpack_canonical(FloatParts64 *p, float16 f, + float_status *s, const FloatFmt *params) +{ + float16_unpack_raw(p, f); + parts_canonicalize(p, s, params); +} + +static void float16_unpack_canonical(FloatParts64 *p, float16 f, + float_status *s) +{ + float16a_unpack_canonical(p, f, s, &float16_params); +} + +static void bfloat16_unpack_canonical(FloatParts64 *p, bfloat16 f, + float_status *s) +{ + bfloat16_unpack_raw(p, f); + parts_canonicalize(p, s, &bfloat16_params); +} + +static float16 float16a_round_pack_canonical(FloatParts64 *p, + float_status *s, const FloatFmt *params) { - return float16_pack_raw(round_canonical(p, s, params)); + parts_uncanon(p, s, params); + return float16_pack_raw(p); } -static float16 float16_round_pack_canonical(FloatParts p, float_status *s) +static float16 float16_round_pack_canonical(FloatParts64 *p, + float_status *s) { return float16a_round_pack_canonical(p, s, &float16_params); } -static bfloat16 bfloat16_round_pack_canonical(FloatParts p, float_status *s) +static bfloat16 bfloat16_round_pack_canonical(FloatParts64 *p, + float_status *s) { - return bfloat16_pack_raw(round_canonical(p, s, &bfloat16_params)); + parts_uncanon(p, s, &bfloat16_params); + return bfloat16_pack_raw(p); } -static FloatParts float32_unpack_canonical(float32 f, float_status *s) +static void float32_unpack_canonical(FloatParts64 *p, float32 f, + float_status *s) { - return sf_canonicalize(float32_unpack_raw(f), &float32_params, s); + float32_unpack_raw(p, f); + parts_canonicalize(p, s, &float32_params); } -static float32 float32_round_pack_canonical(FloatParts p, float_status *s) +static float32 float32_round_pack_canonical(FloatParts64 *p, + float_status *s) { - return float32_pack_raw(round_canonical(p, s, &float32_params)); + parts_uncanon(p, s, &float32_params); + return float32_pack_raw(p); } -static FloatParts float64_unpack_canonical(float64 f, float_status *s) +static void float64_unpack_canonical(FloatParts64 *p, float64 f, + float_status *s) { - return sf_canonicalize(float64_unpack_raw(f), &float64_params, s); + float64_unpack_raw(p, f); + parts_canonicalize(p, s, &float64_params); } -static float64 float64_round_pack_canonical(FloatParts p, float_status *s) +static float64 float64_round_pack_canonical(FloatParts64 *p, + float_status *s) { - return float64_pack_raw(round_canonical(p, s, &float64_params)); + parts_uncanon(p, s, &float64_params); + return float64_pack_raw(p); } -static FloatParts return_nan(FloatParts a, float_status *s) +static void float128_unpack_canonical(FloatParts128 *p, float128 f, + float_status *s) { - switch (a.cls) { + float128_unpack_raw(p, f); + parts_canonicalize(p, s, &float128_params); +} + +static float128 float128_round_pack_canonical(FloatParts128 *p, + float_status *s) +{ + parts_uncanon(p, s, &float128_params); + return float128_pack_raw(p); +} + +/* Returns false if the encoding is invalid. */ +static bool floatx80_unpack_canonical(FloatParts128 *p, floatx80 f, + float_status *s) +{ + /* Ensure rounding precision is set before beginning. */ + switch (s->floatx80_rounding_precision) { + case floatx80_precision_x: + case floatx80_precision_d: + case floatx80_precision_s: + break; + default: + g_assert_not_reached(); + } + + if (unlikely(floatx80_invalid_encoding(f))) { + float_raise(float_flag_invalid, s); + return false; + } + + floatx80_unpack_raw(p, f); + + if (likely(p->exp != floatx80_params[floatx80_precision_x].exp_max)) { + parts_canonicalize(p, s, &floatx80_params[floatx80_precision_x]); + } else { + /* The explicit integer bit is ignored, after invalid checks. */ + p->frac_hi &= MAKE_64BIT_MASK(0, 63); + p->cls = (p->frac_hi == 0 ? float_class_inf + : parts_is_snan_frac(p->frac_hi, s) + ? float_class_snan : float_class_qnan); + } + return true; +} + +static floatx80 floatx80_round_pack_canonical(FloatParts128 *p, + float_status *s) +{ + const FloatFmt *fmt = &floatx80_params[s->floatx80_rounding_precision]; + uint64_t frac; + int exp; + + switch (p->cls) { + case float_class_normal: + if (s->floatx80_rounding_precision == floatx80_precision_x) { + parts_uncanon_normal(p, s, fmt); + frac = p->frac_hi; + exp = p->exp; + } else { + FloatParts64 p64; + + p64.sign = p->sign; + p64.exp = p->exp; + frac_truncjam(&p64, p); + parts_uncanon_normal(&p64, s, fmt); + frac = p64.frac; + exp = p64.exp; + } + if (exp != fmt->exp_max) { + break; + } + /* rounded to inf -- fall through to set frac correctly */ + + case float_class_inf: + /* x86 and m68k differ in the setting of the integer bit. */ + frac = floatx80_infinity_low; + exp = fmt->exp_max; + break; + + case float_class_zero: + frac = 0; + exp = 0; + break; + case float_class_snan: - s->float_exception_flags |= float_flag_invalid; - a = parts_silence_nan(a, s); - /* fall through */ case float_class_qnan: - if (s->default_nan_mode) { - return parts_default_nan(s); - } + /* NaNs have the integer bit set. */ + frac = p->frac_hi | (1ull << 63); + exp = fmt->exp_max; break; default: g_assert_not_reached(); } - return a; -} -static FloatParts pick_nan(FloatParts a, FloatParts b, float_status *s) -{ - if (is_snan(a.cls) || is_snan(b.cls)) { - s->float_exception_flags |= float_flag_invalid; - } - - if (s->default_nan_mode) { - return parts_default_nan(s); - } else { - if (pickNaN(a.cls, b.cls, - a.frac > b.frac || - (a.frac == b.frac && a.sign < b.sign), s)) { - a = b; - } - if (is_snan(a.cls)) { - return parts_silence_nan(a, s); - } - } - return a; -} - -static FloatParts pick_nan_muladd(FloatParts a, FloatParts b, FloatParts c, - bool inf_zero, float_status *s) -{ - int which; - - if (is_snan(a.cls) || is_snan(b.cls) || is_snan(c.cls)) { - s->float_exception_flags |= float_flag_invalid; - } - - which = pickNaNMulAdd(a.cls, b.cls, c.cls, inf_zero, s); - - if (s->default_nan_mode) { - /* Note that this check is after pickNaNMulAdd so that function - * has an opportunity to set the Invalid flag. - */ - which = 3; - } - - switch (which) { - case 0: - break; - case 1: - a = b; - break; - case 2: - a = c; - break; - case 3: - return parts_default_nan(s); - default: - g_assert_not_reached(); - } - - if (is_snan(a.cls)) { - return parts_silence_nan(a, s); - } - return a; + return packFloatx80(p->sign, exp, frac); } /* - * Returns the result of adding or subtracting the values of the - * floating-point values `a' and `b'. The operation is performed - * according to the IEC/IEEE Standard for Binary Floating-Point - * Arithmetic. + * Addition and subtraction */ -static FloatParts addsub_floats(FloatParts a, FloatParts b, bool subtract, - float_status *s) +static float16 QEMU_FLATTEN +float16_addsub(float16 a, float16 b, float_status *status, bool subtract) { - bool a_sign = a.sign; - bool b_sign = b.sign ^ subtract; + FloatParts64 pa, pb, *pr; - if (a_sign != b_sign) { - /* Subtraction */ - - if (a.cls == float_class_normal && b.cls == float_class_normal) { - if (a.exp > b.exp || (a.exp == b.exp && a.frac >= b.frac)) { - shift64RightJamming(b.frac, a.exp - b.exp, &b.frac); - a.frac = a.frac - b.frac; - } else { - shift64RightJamming(a.frac, b.exp - a.exp, &a.frac); - a.frac = b.frac - a.frac; - a.exp = b.exp; - a_sign ^= 1; - } - - if (a.frac == 0) { - a.cls = float_class_zero; - a.sign = s->float_rounding_mode == float_round_down; - } else { - int shift = clz64(a.frac) - 1; - a.frac = a.frac << shift; - a.exp = a.exp - shift; - a.sign = a_sign; - } - return a; - } - if (is_nan(a.cls) || is_nan(b.cls)) { - return pick_nan(a, b, s); - } - if (a.cls == float_class_inf) { - if (b.cls == float_class_inf) { - float_raise(float_flag_invalid, s); - return parts_default_nan(s); - } - return a; - } - if (a.cls == float_class_zero && b.cls == float_class_zero) { - a.sign = s->float_rounding_mode == float_round_down; - return a; - } - if (a.cls == float_class_zero || b.cls == float_class_inf) { - b.sign = a_sign ^ 1; - return b; - } - if (b.cls == float_class_zero) { - return a; - } - } else { - /* Addition */ - if (a.cls == float_class_normal && b.cls == float_class_normal) { - if (a.exp > b.exp) { - shift64RightJamming(b.frac, a.exp - b.exp, &b.frac); - } else if (a.exp < b.exp) { - shift64RightJamming(a.frac, b.exp - a.exp, &a.frac); - a.exp = b.exp; - } - a.frac += b.frac; - if (a.frac & DECOMPOSED_OVERFLOW_BIT) { - shift64RightJamming(a.frac, 1, &a.frac); - a.exp += 1; - } - return a; - } - if (is_nan(a.cls) || is_nan(b.cls)) { - return pick_nan(a, b, s); - } - if (a.cls == float_class_inf || b.cls == float_class_zero) { - return a; - } - if (b.cls == float_class_inf || a.cls == float_class_zero) { - b.sign = b_sign; - return b; - } - } - g_assert_not_reached(); -} - -/* - * Returns the result of adding or subtracting the floating-point - * values `a' and `b'. The operation is performed according to the - * IEC/IEEE Standard for Binary Floating-Point Arithmetic. - */ - -float16 QEMU_FLATTEN float16_add(float16 a, float16 b, float_status *status) -{ - FloatParts pa = float16_unpack_canonical(a, status); - FloatParts pb = float16_unpack_canonical(b, status); - FloatParts pr = addsub_floats(pa, pb, false, status); + float16_unpack_canonical(&pa, a, status); + float16_unpack_canonical(&pb, b, status); + pr = parts_addsub(&pa, &pb, status, subtract); return float16_round_pack_canonical(pr, status); } -float16 QEMU_FLATTEN float16_sub(float16 a, float16 b, float_status *status) +float16 float16_add(float16 a, float16 b, float_status *status) { - FloatParts pa = float16_unpack_canonical(a, status); - FloatParts pb = float16_unpack_canonical(b, status); - FloatParts pr = addsub_floats(pa, pb, true, status); + return float16_addsub(a, b, status, false); +} - return float16_round_pack_canonical(pr, status); +float16 float16_sub(float16 a, float16 b, float_status *status) +{ + return float16_addsub(a, b, status, true); } static float32 QEMU_SOFTFLOAT_ATTR -soft_f32_addsub(float32 a, float32 b, bool subtract, float_status *status) +soft_f32_addsub(float32 a, float32 b, float_status *status, bool subtract) { - FloatParts pa = float32_unpack_canonical(a, status); - FloatParts pb = float32_unpack_canonical(b, status); - FloatParts pr = addsub_floats(pa, pb, subtract, status); + FloatParts64 pa, pb, *pr; + + float32_unpack_canonical(&pa, a, status); + float32_unpack_canonical(&pb, b, status); + pr = parts_addsub(&pa, &pb, status, subtract); return float32_round_pack_canonical(pr, status); } -static inline float32 soft_f32_add(float32 a, float32 b, float_status *status) +static float32 soft_f32_add(float32 a, float32 b, float_status *status) { - return soft_f32_addsub(a, b, false, status); + return soft_f32_addsub(a, b, status, false); } -static inline float32 soft_f32_sub(float32 a, float32 b, float_status *status) +static float32 soft_f32_sub(float32 a, float32 b, float_status *status) { - return soft_f32_addsub(a, b, true, status); + return soft_f32_addsub(a, b, status, true); } static float64 QEMU_SOFTFLOAT_ATTR -soft_f64_addsub(float64 a, float64 b, bool subtract, float_status *status) +soft_f64_addsub(float64 a, float64 b, float_status *status, bool subtract) { - FloatParts pa = float64_unpack_canonical(a, status); - FloatParts pb = float64_unpack_canonical(b, status); - FloatParts pr = addsub_floats(pa, pb, subtract, status); + FloatParts64 pa, pb, *pr; + + float64_unpack_canonical(&pa, a, status); + float64_unpack_canonical(&pb, b, status); + pr = parts_addsub(&pa, &pb, status, subtract); return float64_round_pack_canonical(pr, status); } -static inline float64 soft_f64_add(float64 a, float64 b, float_status *status) +static float64 soft_f64_add(float64 a, float64 b, float_status *status) { - return soft_f64_addsub(a, b, false, status); + return soft_f64_addsub(a, b, status, false); } -static inline float64 soft_f64_sub(float64 a, float64 b, float_status *status) +static float64 soft_f64_sub(float64 a, float64 b, float_status *status) { - return soft_f64_addsub(a, b, true, status); + return soft_f64_addsub(a, b, status, true); } static float hard_f32_add(float a, float b) @@ -1182,82 +1933,85 @@ float64_sub(float64 a, float64 b, float_status *s) return float64_addsub(a, b, s, hard_f64_sub, soft_f64_sub); } -/* - * Returns the result of adding or subtracting the bfloat16 - * values `a' and `b'. - */ -bfloat16 QEMU_FLATTEN bfloat16_add(bfloat16 a, bfloat16 b, float_status *status) +static bfloat16 QEMU_FLATTEN +bfloat16_addsub(bfloat16 a, bfloat16 b, float_status *status, bool subtract) { - FloatParts pa = bfloat16_unpack_canonical(a, status); - FloatParts pb = bfloat16_unpack_canonical(b, status); - FloatParts pr = addsub_floats(pa, pb, false, status); + FloatParts64 pa, pb, *pr; + + bfloat16_unpack_canonical(&pa, a, status); + bfloat16_unpack_canonical(&pb, b, status); + pr = parts_addsub(&pa, &pb, status, subtract); return bfloat16_round_pack_canonical(pr, status); } -bfloat16 QEMU_FLATTEN bfloat16_sub(bfloat16 a, bfloat16 b, float_status *status) +bfloat16 bfloat16_add(bfloat16 a, bfloat16 b, float_status *status) { - FloatParts pa = bfloat16_unpack_canonical(a, status); - FloatParts pb = bfloat16_unpack_canonical(b, status); - FloatParts pr = addsub_floats(pa, pb, true, status); + return bfloat16_addsub(a, b, status, false); +} - return bfloat16_round_pack_canonical(pr, status); +bfloat16 bfloat16_sub(bfloat16 a, bfloat16 b, float_status *status) +{ + return bfloat16_addsub(a, b, status, true); +} + +static float128 QEMU_FLATTEN +float128_addsub(float128 a, float128 b, float_status *status, bool subtract) +{ + FloatParts128 pa, pb, *pr; + + float128_unpack_canonical(&pa, a, status); + float128_unpack_canonical(&pb, b, status); + pr = parts_addsub(&pa, &pb, status, subtract); + + return float128_round_pack_canonical(pr, status); +} + +float128 float128_add(float128 a, float128 b, float_status *status) +{ + return float128_addsub(a, b, status, false); +} + +float128 float128_sub(float128 a, float128 b, float_status *status) +{ + return float128_addsub(a, b, status, true); +} + +static floatx80 QEMU_FLATTEN +floatx80_addsub(floatx80 a, floatx80 b, float_status *status, bool subtract) +{ + FloatParts128 pa, pb, *pr; + + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { + return floatx80_default_nan(status); + } + + pr = parts_addsub(&pa, &pb, status, subtract); + return floatx80_round_pack_canonical(pr, status); +} + +floatx80 floatx80_add(floatx80 a, floatx80 b, float_status *status) +{ + return floatx80_addsub(a, b, status, false); +} + +floatx80 floatx80_sub(floatx80 a, floatx80 b, float_status *status) +{ + return floatx80_addsub(a, b, status, true); } /* - * Returns the result of multiplying the floating-point values `a' and - * `b'. The operation is performed according to the IEC/IEEE Standard - * for Binary Floating-Point Arithmetic. + * Multiplication */ -static FloatParts mul_floats(FloatParts a, FloatParts b, float_status *s) -{ - bool sign = a.sign ^ b.sign; - - if (a.cls == float_class_normal && b.cls == float_class_normal) { - uint64_t hi, lo; - int exp = a.exp + b.exp; - - mul64To128(a.frac, b.frac, &hi, &lo); - shift128RightJamming(hi, lo, DECOMPOSED_BINARY_POINT, &hi, &lo); - if (lo & DECOMPOSED_OVERFLOW_BIT) { - shift64RightJamming(lo, 1, &lo); - exp += 1; - } - - /* Re-use a */ - a.exp = exp; - a.sign = sign; - a.frac = lo; - return a; - } - /* handle all the NaN cases */ - if (is_nan(a.cls) || is_nan(b.cls)) { - return pick_nan(a, b, s); - } - /* Inf * Zero == NaN */ - if ((a.cls == float_class_inf && b.cls == float_class_zero) || - (a.cls == float_class_zero && b.cls == float_class_inf)) { - s->float_exception_flags |= float_flag_invalid; - return parts_default_nan(s); - } - /* Multiply by 0 or Inf */ - if (a.cls == float_class_inf || a.cls == float_class_zero) { - a.sign = sign; - return a; - } - if (b.cls == float_class_inf || b.cls == float_class_zero) { - b.sign = sign; - return b; - } - g_assert_not_reached(); -} - float16 QEMU_FLATTEN float16_mul(float16 a, float16 b, float_status *status) { - FloatParts pa = float16_unpack_canonical(a, status); - FloatParts pb = float16_unpack_canonical(b, status); - FloatParts pr = mul_floats(pa, pb, status); + FloatParts64 pa, pb, *pr; + + float16_unpack_canonical(&pa, a, status); + float16_unpack_canonical(&pb, b, status); + pr = parts_mul(&pa, &pb, status); return float16_round_pack_canonical(pr, status); } @@ -1265,9 +2019,11 @@ float16 QEMU_FLATTEN float16_mul(float16 a, float16 b, float_status *status) static float32 QEMU_SOFTFLOAT_ATTR soft_f32_mul(float32 a, float32 b, float_status *status) { - FloatParts pa = float32_unpack_canonical(a, status); - FloatParts pb = float32_unpack_canonical(b, status); - FloatParts pr = mul_floats(pa, pb, status); + FloatParts64 pa, pb, *pr; + + float32_unpack_canonical(&pa, a, status); + float32_unpack_canonical(&pb, b, status); + pr = parts_mul(&pa, &pb, status); return float32_round_pack_canonical(pr, status); } @@ -1275,9 +2031,11 @@ soft_f32_mul(float32 a, float32 b, float_status *status) static float64 QEMU_SOFTFLOAT_ATTR soft_f64_mul(float64 a, float64 b, float_status *status) { - FloatParts pa = float64_unpack_canonical(a, status); - FloatParts pb = float64_unpack_canonical(b, status); - FloatParts pr = mul_floats(pa, pb, status); + FloatParts64 pa, pb, *pr; + + float64_unpack_canonical(&pa, a, status); + float64_unpack_canonical(&pb, b, status); + pr = parts_mul(&pa, &pb, status); return float64_round_pack_canonical(pr, status); } @@ -1306,230 +2064,57 @@ float64_mul(float64 a, float64 b, float_status *s) f64_is_zon2, f64_addsubmul_post); } -/* - * Returns the result of multiplying the bfloat16 - * values `a' and `b'. - */ - -bfloat16 QEMU_FLATTEN bfloat16_mul(bfloat16 a, bfloat16 b, float_status *status) +bfloat16 QEMU_FLATTEN +bfloat16_mul(bfloat16 a, bfloat16 b, float_status *status) { - FloatParts pa = bfloat16_unpack_canonical(a, status); - FloatParts pb = bfloat16_unpack_canonical(b, status); - FloatParts pr = mul_floats(pa, pb, status); + FloatParts64 pa, pb, *pr; + + bfloat16_unpack_canonical(&pa, a, status); + bfloat16_unpack_canonical(&pb, b, status); + pr = parts_mul(&pa, &pb, status); return bfloat16_round_pack_canonical(pr, status); } -/* - * Returns the result of multiplying the floating-point values `a' and - * `b' then adding 'c', with no intermediate rounding step after the - * multiplication. The operation is performed according to the - * IEC/IEEE Standard for Binary Floating-Point Arithmetic 754-2008. - * The flags argument allows the caller to select negation of the - * addend, the intermediate product, or the final result. (The - * difference between this and having the caller do a separate - * negation is that negating externally will flip the sign bit on - * NaNs.) - */ - -static FloatParts muladd_floats(FloatParts a, FloatParts b, FloatParts c, - int flags, float_status *s) +float128 QEMU_FLATTEN +float128_mul(float128 a, float128 b, float_status *status) { - bool inf_zero = ((1 << a.cls) | (1 << b.cls)) == - ((1 << float_class_inf) | (1 << float_class_zero)); - bool p_sign; - bool sign_flip = flags & float_muladd_negate_result; - FloatClass p_class; - uint64_t hi, lo; - int p_exp; + FloatParts128 pa, pb, *pr; - /* It is implementation-defined whether the cases of (0,inf,qnan) - * and (inf,0,qnan) raise InvalidOperation or not (and what QNaN - * they return if they do), so we have to hand this information - * off to the target-specific pick-a-NaN routine. - */ - if (is_nan(a.cls) || is_nan(b.cls) || is_nan(c.cls)) { - return pick_nan_muladd(a, b, c, inf_zero, s); - } + float128_unpack_canonical(&pa, a, status); + float128_unpack_canonical(&pb, b, status); + pr = parts_mul(&pa, &pb, status); - if (inf_zero) { - s->float_exception_flags |= float_flag_invalid; - return parts_default_nan(s); - } - - if (flags & float_muladd_negate_c) { - c.sign ^= 1; - } - - p_sign = a.sign ^ b.sign; - - if (flags & float_muladd_negate_product) { - p_sign ^= 1; - } - - if (a.cls == float_class_inf || b.cls == float_class_inf) { - p_class = float_class_inf; - } else if (a.cls == float_class_zero || b.cls == float_class_zero) { - p_class = float_class_zero; - } else { - p_class = float_class_normal; - } - - if (c.cls == float_class_inf) { - if (p_class == float_class_inf && p_sign != c.sign) { - s->float_exception_flags |= float_flag_invalid; - return parts_default_nan(s); - } else { - a.cls = float_class_inf; - a.sign = c.sign ^ sign_flip; - return a; - } - } - - if (p_class == float_class_inf) { - a.cls = float_class_inf; - a.sign = p_sign ^ sign_flip; - return a; - } - - if (p_class == float_class_zero) { - if (c.cls == float_class_zero) { - if (p_sign != c.sign) { - p_sign = s->float_rounding_mode == float_round_down; - } - c.sign = p_sign; - } else if (flags & float_muladd_halve_result) { - c.exp -= 1; - } - c.sign ^= sign_flip; - return c; - } - - /* a & b should be normals now... */ - assert(a.cls == float_class_normal && - b.cls == float_class_normal); - - p_exp = a.exp + b.exp; - - /* Multiply of 2 62-bit numbers produces a (2*62) == 124-bit - * result. - */ - mul64To128(a.frac, b.frac, &hi, &lo); - /* binary point now at bit 124 */ - - /* check for overflow */ - if (hi & (1ULL << (DECOMPOSED_BINARY_POINT * 2 + 1 - 64))) { - shift128RightJamming(hi, lo, 1, &hi, &lo); - p_exp += 1; - } - - /* + add/sub */ - if (c.cls == float_class_zero) { - /* move binary point back to 62 */ - shift128RightJamming(hi, lo, DECOMPOSED_BINARY_POINT, &hi, &lo); - } else { - int exp_diff = p_exp - c.exp; - if (p_sign == c.sign) { - /* Addition */ - if (exp_diff <= 0) { - shift128RightJamming(hi, lo, - DECOMPOSED_BINARY_POINT - exp_diff, - &hi, &lo); - lo += c.frac; - p_exp = c.exp; - } else { - uint64_t c_hi, c_lo; - /* shift c to the same binary point as the product (124) */ - c_hi = c.frac >> 2; - c_lo = 0; - shift128RightJamming(c_hi, c_lo, - exp_diff, - &c_hi, &c_lo); - add128(hi, lo, c_hi, c_lo, &hi, &lo); - /* move binary point back to 62 */ - shift128RightJamming(hi, lo, DECOMPOSED_BINARY_POINT, &hi, &lo); - } - - if (lo & DECOMPOSED_OVERFLOW_BIT) { - shift64RightJamming(lo, 1, &lo); - p_exp += 1; - } - - } else { - /* Subtraction */ - uint64_t c_hi, c_lo; - /* make C binary point match product at bit 124 */ - c_hi = c.frac >> 2; - c_lo = 0; - - if (exp_diff <= 0) { - shift128RightJamming(hi, lo, -exp_diff, &hi, &lo); - if (exp_diff == 0 - && - (hi > c_hi || (hi == c_hi && lo >= c_lo))) { - sub128(hi, lo, c_hi, c_lo, &hi, &lo); - } else { - sub128(c_hi, c_lo, hi, lo, &hi, &lo); - p_sign ^= 1; - p_exp = c.exp; - } - } else { - shift128RightJamming(c_hi, c_lo, - exp_diff, - &c_hi, &c_lo); - sub128(hi, lo, c_hi, c_lo, &hi, &lo); - } - - if (hi == 0 && lo == 0) { - a.cls = float_class_zero; - a.sign = s->float_rounding_mode == float_round_down; - a.sign ^= sign_flip; - return a; - } else { - int shift; - if (hi != 0) { - shift = clz64(hi); - } else { - shift = clz64(lo) + 64; - } - /* Normalizing to a binary point of 124 is the - correct adjust for the exponent. However since we're - shifting, we might as well put the binary point back - at 62 where we really want it. Therefore shift as - if we're leaving 1 bit at the top of the word, but - adjust the exponent as if we're leaving 3 bits. */ - shift -= 1; - if (shift >= 64) { - lo = lo << (shift - 64); - } else { - hi = (hi << shift) | (lo >> (64 - shift)); - lo = hi | ((lo << shift) != 0); - } - p_exp -= shift - 2; - } - } - } - - if (flags & float_muladd_halve_result) { - p_exp -= 1; - } - - /* finally prepare our result */ - a.cls = float_class_normal; - a.sign = p_sign ^ sign_flip; - a.exp = p_exp; - a.frac = lo; - - return a; + return float128_round_pack_canonical(pr, status); } -float16 QEMU_FLATTEN float16_muladd(float16 a, float16 b, float16 c, - int flags, float_status *status) +floatx80 QEMU_FLATTEN +floatx80_mul(floatx80 a, floatx80 b, float_status *status) { - FloatParts pa = float16_unpack_canonical(a, status); - FloatParts pb = float16_unpack_canonical(b, status); - FloatParts pc = float16_unpack_canonical(c, status); - FloatParts pr = muladd_floats(pa, pb, pc, flags, status); + FloatParts128 pa, pb, *pr; + + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { + return floatx80_default_nan(status); + } + + pr = parts_mul(&pa, &pb, status); + return floatx80_round_pack_canonical(pr, status); +} + +/* + * Fused multiply-add + */ + +float16 QEMU_FLATTEN float16_muladd(float16 a, float16 b, float16 c, + int flags, float_status *status) +{ + FloatParts64 pa, pb, pc, *pr; + + float16_unpack_canonical(&pa, a, status); + float16_unpack_canonical(&pb, b, status); + float16_unpack_canonical(&pc, c, status); + pr = parts_muladd(&pa, &pb, &pc, flags, status); return float16_round_pack_canonical(pr, status); } @@ -1538,10 +2123,12 @@ static float32 QEMU_SOFTFLOAT_ATTR soft_f32_muladd(float32 a, float32 b, float32 c, int flags, float_status *status) { - FloatParts pa = float32_unpack_canonical(a, status); - FloatParts pb = float32_unpack_canonical(b, status); - FloatParts pc = float32_unpack_canonical(c, status); - FloatParts pr = muladd_floats(pa, pb, pc, flags, status); + FloatParts64 pa, pb, pc, *pr; + + float32_unpack_canonical(&pa, a, status); + float32_unpack_canonical(&pb, b, status); + float32_unpack_canonical(&pc, c, status); + pr = parts_muladd(&pa, &pb, &pc, flags, status); return float32_round_pack_canonical(pr, status); } @@ -1550,10 +2137,12 @@ static float64 QEMU_SOFTFLOAT_ATTR soft_f64_muladd(float64 a, float64 b, float64 c, int flags, float_status *status) { - FloatParts pa = float64_unpack_canonical(a, status); - FloatParts pb = float64_unpack_canonical(b, status); - FloatParts pc = float64_unpack_canonical(c, status); - FloatParts pr = muladd_floats(pa, pb, pc, flags, status); + FloatParts64 pa, pb, pc, *pr; + + float64_unpack_canonical(&pa, a, status); + float64_unpack_canonical(&pb, b, status); + float64_unpack_canonical(&pc, c, status); + pr = parts_muladd(&pa, &pb, &pc, flags, status); return float64_round_pack_canonical(pr, status); } @@ -1615,7 +2204,7 @@ float32_muladd(float32 xa, float32 xb, float32 xc, int flags, float_status *s) ur.h = fmaf(ua.h, ub.h, uc.h); if (unlikely(f32_is_inf(ur))) { - s->float_exception_flags |= float_flag_overflow; + float_raise(float_flag_overflow, s); } else if (unlikely(fabsf(ur.h) <= FLT_MIN)) { ua = ua_orig; uc = uc_orig; @@ -1686,7 +2275,7 @@ float64_muladd(float64 xa, float64 xb, float64 xc, int flags, float_status *s) ur.h = fma(ua.h, ub.h, uc.h); if (unlikely(f64_is_inf(ur))) { - s->float_exception_flags |= float_flag_overflow; + float_raise(float_flag_overflow, s); } else if (unlikely(fabs(ur.h) <= FLT_MIN)) { ua = ua_orig; uc = uc_orig; @@ -1702,107 +2291,43 @@ float64_muladd(float64 xa, float64 xb, float64 xc, int flags, float_status *s) return soft_f64_muladd(ua.s, ub.s, uc.s, flags, s); } -/* - * Returns the result of multiplying the bfloat16 values `a' - * and `b' then adding 'c', with no intermediate rounding step after the - * multiplication. - */ - bfloat16 QEMU_FLATTEN bfloat16_muladd(bfloat16 a, bfloat16 b, bfloat16 c, int flags, float_status *status) { - FloatParts pa = bfloat16_unpack_canonical(a, status); - FloatParts pb = bfloat16_unpack_canonical(b, status); - FloatParts pc = bfloat16_unpack_canonical(c, status); - FloatParts pr = muladd_floats(pa, pb, pc, flags, status); + FloatParts64 pa, pb, pc, *pr; + + bfloat16_unpack_canonical(&pa, a, status); + bfloat16_unpack_canonical(&pb, b, status); + bfloat16_unpack_canonical(&pc, c, status); + pr = parts_muladd(&pa, &pb, &pc, flags, status); return bfloat16_round_pack_canonical(pr, status); } -/* - * Returns the result of dividing the floating-point value `a' by the - * corresponding value `b'. The operation is performed according to - * the IEC/IEEE Standard for Binary Floating-Point Arithmetic. - */ - -static FloatParts div_floats(FloatParts a, FloatParts b, float_status *s) +float128 QEMU_FLATTEN float128_muladd(float128 a, float128 b, float128 c, + int flags, float_status *status) { - bool sign = a.sign ^ b.sign; + FloatParts128 pa, pb, pc, *pr; - if (a.cls == float_class_normal && b.cls == float_class_normal) { - uint64_t n0, n1, q, r; - int exp = a.exp - b.exp; + float128_unpack_canonical(&pa, a, status); + float128_unpack_canonical(&pb, b, status); + float128_unpack_canonical(&pc, c, status); + pr = parts_muladd(&pa, &pb, &pc, flags, status); - /* - * We want a 2*N / N-bit division to produce exactly an N-bit - * result, so that we do not lose any precision and so that we - * do not have to renormalize afterward. If A.frac < B.frac, - * then division would produce an (N-1)-bit result; shift A left - * by one to produce the an N-bit result, and decrement the - * exponent to match. - * - * The udiv_qrnnd algorithm that we're using requires normalization, - * i.e. the msb of the denominator must be set. Since we know that - * DECOMPOSED_BINARY_POINT is msb-1, the inputs must be shifted left - * by one (more), and the remainder must be shifted right by one. - */ - if (a.frac < b.frac) { - exp -= 1; - shift128Left(0, a.frac, DECOMPOSED_BINARY_POINT + 2, &n1, &n0); - } else { - shift128Left(0, a.frac, DECOMPOSED_BINARY_POINT + 1, &n1, &n0); - } - q = udiv_qrnnd(&r, n1, n0, b.frac << 1); - - /* - * Set lsb if there is a remainder, to set inexact. - * As mentioned above, to find the actual value of the remainder we - * would need to shift right, but (1) we are only concerned about - * non-zero-ness, and (2) the remainder will always be even because - * both inputs to the division primitive are even. - */ - a.frac = q | (r != 0); - a.sign = sign; - a.exp = exp; - return a; - } - /* handle all the NaN cases */ - if (is_nan(a.cls) || is_nan(b.cls)) { - return pick_nan(a, b, s); - } - /* 0/0 or Inf/Inf */ - if (a.cls == b.cls - && - (a.cls == float_class_inf || a.cls == float_class_zero)) { - s->float_exception_flags |= float_flag_invalid; - return parts_default_nan(s); - } - /* Inf / x or 0 / x */ - if (a.cls == float_class_inf || a.cls == float_class_zero) { - a.sign = sign; - return a; - } - /* Div 0 => Inf */ - if (b.cls == float_class_zero) { - s->float_exception_flags |= float_flag_divbyzero; - a.cls = float_class_inf; - a.sign = sign; - return a; - } - /* Div by Inf */ - if (b.cls == float_class_inf) { - a.cls = float_class_zero; - a.sign = sign; - return a; - } - g_assert_not_reached(); + return float128_round_pack_canonical(pr, status); } +/* + * Division + */ + float16 float16_div(float16 a, float16 b, float_status *status) { - FloatParts pa = float16_unpack_canonical(a, status); - FloatParts pb = float16_unpack_canonical(b, status); - FloatParts pr = div_floats(pa, pb, status); + FloatParts64 pa, pb, *pr; + + float16_unpack_canonical(&pa, a, status); + float16_unpack_canonical(&pb, b, status); + pr = parts_div(&pa, &pb, status); return float16_round_pack_canonical(pr, status); } @@ -1810,9 +2335,11 @@ float16 float16_div(float16 a, float16 b, float_status *status) static float32 QEMU_SOFTFLOAT_ATTR soft_f32_div(float32 a, float32 b, float_status *status) { - FloatParts pa = float32_unpack_canonical(a, status); - FloatParts pb = float32_unpack_canonical(b, status); - FloatParts pr = div_floats(pa, pb, status); + FloatParts64 pa, pb, *pr; + + float32_unpack_canonical(&pa, a, status); + float32_unpack_canonical(&pb, b, status); + pr = parts_div(&pa, &pb, status); return float32_round_pack_canonical(pr, status); } @@ -1820,9 +2347,11 @@ soft_f32_div(float32 a, float32 b, float_status *status) static float64 QEMU_SOFTFLOAT_ATTR soft_f64_div(float64 a, float64 b, float_status *status) { - FloatParts pa = float64_unpack_canonical(a, status); - FloatParts pb = float64_unpack_canonical(b, status); - FloatParts pr = div_floats(pa, pb, status); + FloatParts64 pa, pb, *pr; + + float64_unpack_canonical(&pa, a, status); + float64_unpack_canonical(&pb, b, status); + pr = parts_div(&pa, &pb, status); return float64_round_pack_canonical(pr, status); } @@ -1885,20 +2414,116 @@ float64_div(float64 a, float64 b, float_status *s) f64_div_pre, f64_div_post); } -/* - * Returns the result of dividing the bfloat16 - * value `a' by the corresponding value `b'. - */ - -bfloat16 bfloat16_div(bfloat16 a, bfloat16 b, float_status *status) +bfloat16 QEMU_FLATTEN +bfloat16_div(bfloat16 a, bfloat16 b, float_status *status) { - FloatParts pa = bfloat16_unpack_canonical(a, status); - FloatParts pb = bfloat16_unpack_canonical(b, status); - FloatParts pr = div_floats(pa, pb, status); + FloatParts64 pa, pb, *pr; + + bfloat16_unpack_canonical(&pa, a, status); + bfloat16_unpack_canonical(&pb, b, status); + pr = parts_div(&pa, &pb, status); return bfloat16_round_pack_canonical(pr, status); } +float128 QEMU_FLATTEN +float128_div(float128 a, float128 b, float_status *status) +{ + FloatParts128 pa, pb, *pr; + + float128_unpack_canonical(&pa, a, status); + float128_unpack_canonical(&pb, b, status); + pr = parts_div(&pa, &pb, status); + + return float128_round_pack_canonical(pr, status); +} + +floatx80 floatx80_div(floatx80 a, floatx80 b, float_status *status) +{ + FloatParts128 pa, pb, *pr; + + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { + return floatx80_default_nan(status); + } + + pr = parts_div(&pa, &pb, status); + return floatx80_round_pack_canonical(pr, status); +} + +/* + * Remainder + */ + +float32 float32_rem(float32 a, float32 b, float_status *status) +{ + FloatParts64 pa, pb, *pr; + + float32_unpack_canonical(&pa, a, status); + float32_unpack_canonical(&pb, b, status); + pr = parts_modrem(&pa, &pb, NULL, status); + + return float32_round_pack_canonical(pr, status); +} + +float64 float64_rem(float64 a, float64 b, float_status *status) +{ + FloatParts64 pa, pb, *pr; + + float64_unpack_canonical(&pa, a, status); + float64_unpack_canonical(&pb, b, status); + pr = parts_modrem(&pa, &pb, NULL, status); + + return float64_round_pack_canonical(pr, status); +} + +float128 float128_rem(float128 a, float128 b, float_status *status) +{ + FloatParts128 pa, pb, *pr; + + float128_unpack_canonical(&pa, a, status); + float128_unpack_canonical(&pb, b, status); + pr = parts_modrem(&pa, &pb, NULL, status); + + return float128_round_pack_canonical(pr, status); +} + +/* + * Returns the remainder of the extended double-precision floating-point value + * `a' with respect to the corresponding value `b'. + * If 'mod' is false, the operation is performed according to the IEC/IEEE + * Standard for Binary Floating-Point Arithmetic. If 'mod' is true, return + * the remainder based on truncating the quotient toward zero instead and + * *quotient is set to the low 64 bits of the absolute value of the integer + * quotient. + */ +floatx80 floatx80_modrem(floatx80 a, floatx80 b, bool mod, + uint64_t *quotient, float_status *status) +{ + FloatParts128 pa, pb, *pr; + + *quotient = 0; + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { + return floatx80_default_nan(status); + } + pr = parts_modrem(&pa, &pb, mod ? quotient : NULL, status); + + return floatx80_round_pack_canonical(pr, status); +} + +floatx80 floatx80_rem(floatx80 a, floatx80 b, float_status *status) +{ + uint64_t quotient; + return floatx80_modrem(a, b, false, "ient, status); +} + +floatx80 floatx80_mod(floatx80 a, floatx80 b, float_status *status) +{ + uint64_t quotient; + return floatx80_modrem(a, b, true, "ient, status); +} + /* * Float to Float conversions * @@ -1906,81 +2531,134 @@ bfloat16 bfloat16_div(bfloat16 a, bfloat16 b, float_status *status) * conversion is performed according to the IEC/IEEE Standard for * Binary Floating-Point Arithmetic. * - * The float_to_float helper only needs to take care of raising - * invalid exceptions and handling the conversion on NaNs. + * Usually this only needs to take care of raising invalid exceptions + * and handling the conversion on NaNs. */ -static FloatParts float_to_float(FloatParts a, const FloatFmt *dstf, - float_status *s) +static void parts_float_to_ahp(FloatParts64 *a, float_status *s) { - if (dstf->arm_althp) { - switch (a.cls) { - case float_class_qnan: - case float_class_snan: - /* There is no NaN in the destination format. Raise Invalid - * and return a zero with the sign of the input NaN. - */ - s->float_exception_flags |= float_flag_invalid; - a.cls = float_class_zero; - a.frac = 0; - a.exp = 0; - break; + switch (a->cls) { + case float_class_qnan: + case float_class_snan: + /* + * There is no NaN in the destination format. Raise Invalid + * and return a zero with the sign of the input NaN. + */ + float_raise(float_flag_invalid, s); + a->cls = float_class_zero; + break; - case float_class_inf: - /* There is no Inf in the destination format. Raise Invalid - * and return the maximum normal with the correct sign. - */ - s->float_exception_flags |= float_flag_invalid; - a.cls = float_class_normal; - a.exp = dstf->exp_max; - a.frac = ((1ull << dstf->frac_size) - 1) << dstf->frac_shift; - break; + case float_class_inf: + /* + * There is no Inf in the destination format. Raise Invalid + * and return the maximum normal with the correct sign. + */ + float_raise(float_flag_invalid, s); + a->cls = float_class_normal; + a->exp = float16_params_ahp.exp_max; + a->frac = MAKE_64BIT_MASK(float16_params_ahp.frac_shift, + float16_params_ahp.frac_size + 1); + break; - default: - break; - } - } else if (is_nan(a.cls)) { - if (is_snan(a.cls)) { - s->float_exception_flags |= float_flag_invalid; - a = parts_silence_nan(a, s); - } - if (s->default_nan_mode) { - return parts_default_nan(s); - } + case float_class_normal: + case float_class_zero: + break; + + default: + g_assert_not_reached(); + } +} + +static void parts64_float_to_float(FloatParts64 *a, float_status *s) +{ + if (is_nan(a->cls)) { + parts_return_nan(a, s); + } +} + +static void parts128_float_to_float(FloatParts128 *a, float_status *s) +{ + if (is_nan(a->cls)) { + parts_return_nan(a, s); + } +} + +#define parts_float_to_float(P, S) \ + PARTS_GENERIC_64_128(float_to_float, P)(P, S) + +static void parts_float_to_float_narrow(FloatParts64 *a, FloatParts128 *b, + float_status *s) +{ + a->cls = b->cls; + a->sign = b->sign; + a->exp = b->exp; + + if (a->cls == float_class_normal) { + frac_truncjam(a, b); + } else if (is_nan(a->cls)) { + /* Discard the low bits of the NaN. */ + a->frac = b->frac_hi; + parts_return_nan(a, s); + } +} + +static void parts_float_to_float_widen(FloatParts128 *a, FloatParts64 *b, + float_status *s) +{ + a->cls = b->cls; + a->sign = b->sign; + a->exp = b->exp; + frac_widen(a, b); + + if (is_nan(a->cls)) { + parts_return_nan(a, s); } - return a; } float32 float16_to_float32(float16 a, bool ieee, float_status *s) { const FloatFmt *fmt16 = ieee ? &float16_params : &float16_params_ahp; - FloatParts p = float16a_unpack_canonical(a, s, fmt16); - FloatParts pr = float_to_float(p, &float32_params, s); - return float32_round_pack_canonical(pr, s); + FloatParts64 p; + + float16a_unpack_canonical(&p, a, s, fmt16); + parts_float_to_float(&p, s); + return float32_round_pack_canonical(&p, s); } float64 float16_to_float64(float16 a, bool ieee, float_status *s) { const FloatFmt *fmt16 = ieee ? &float16_params : &float16_params_ahp; - FloatParts p = float16a_unpack_canonical(a, s, fmt16); - FloatParts pr = float_to_float(p, &float64_params, s); - return float64_round_pack_canonical(pr, s); + FloatParts64 p; + + float16a_unpack_canonical(&p, a, s, fmt16); + parts_float_to_float(&p, s); + return float64_round_pack_canonical(&p, s); } float16 float32_to_float16(float32 a, bool ieee, float_status *s) { - const FloatFmt *fmt16 = ieee ? &float16_params : &float16_params_ahp; - FloatParts p = float32_unpack_canonical(a, s); - FloatParts pr = float_to_float(p, fmt16, s); - return float16a_round_pack_canonical(pr, s, fmt16); + FloatParts64 p; + const FloatFmt *fmt; + + float32_unpack_canonical(&p, a, s); + if (ieee) { + parts_float_to_float(&p, s); + fmt = &float16_params; + } else { + parts_float_to_ahp(&p, s); + fmt = &float16_params_ahp; + } + return float16a_round_pack_canonical(&p, s, fmt); } static float64 QEMU_SOFTFLOAT_ATTR soft_float32_to_float64(float32 a, float_status *s) { - FloatParts p = float32_unpack_canonical(a, s); - FloatParts pr = float_to_float(p, &float64_params, s); - return float64_round_pack_canonical(pr, s); + FloatParts64 p; + + float32_unpack_canonical(&p, a, s); + parts_float_to_float(&p, s); + return float64_round_pack_canonical(&p, s); } float64 float32_to_float64(float32 a, float_status *s) @@ -2001,313 +2679,393 @@ float64 float32_to_float64(float32 a, float_status *s) float16 float64_to_float16(float64 a, bool ieee, float_status *s) { - const FloatFmt *fmt16 = ieee ? &float16_params : &float16_params_ahp; - FloatParts p = float64_unpack_canonical(a, s); - FloatParts pr = float_to_float(p, fmt16, s); - return float16a_round_pack_canonical(pr, s, fmt16); + FloatParts64 p; + const FloatFmt *fmt; + + float64_unpack_canonical(&p, a, s); + if (ieee) { + parts_float_to_float(&p, s); + fmt = &float16_params; + } else { + parts_float_to_ahp(&p, s); + fmt = &float16_params_ahp; + } + return float16a_round_pack_canonical(&p, s, fmt); } float32 float64_to_float32(float64 a, float_status *s) { - FloatParts p = float64_unpack_canonical(a, s); - FloatParts pr = float_to_float(p, &float32_params, s); - return float32_round_pack_canonical(pr, s); + FloatParts64 p; + + float64_unpack_canonical(&p, a, s); + parts_float_to_float(&p, s); + return float32_round_pack_canonical(&p, s); } float32 bfloat16_to_float32(bfloat16 a, float_status *s) { - FloatParts p = bfloat16_unpack_canonical(a, s); - FloatParts pr = float_to_float(p, &float32_params, s); - return float32_round_pack_canonical(pr, s); + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + parts_float_to_float(&p, s); + return float32_round_pack_canonical(&p, s); } float64 bfloat16_to_float64(bfloat16 a, float_status *s) { - FloatParts p = bfloat16_unpack_canonical(a, s); - FloatParts pr = float_to_float(p, &float64_params, s); - return float64_round_pack_canonical(pr, s); + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + parts_float_to_float(&p, s); + return float64_round_pack_canonical(&p, s); } bfloat16 float32_to_bfloat16(float32 a, float_status *s) { - FloatParts p = float32_unpack_canonical(a, s); - FloatParts pr = float_to_float(p, &bfloat16_params, s); - return bfloat16_round_pack_canonical(pr, s); + FloatParts64 p; + + float32_unpack_canonical(&p, a, s); + parts_float_to_float(&p, s); + return bfloat16_round_pack_canonical(&p, s); } bfloat16 float64_to_bfloat16(float64 a, float_status *s) { - FloatParts p = float64_unpack_canonical(a, s); - FloatParts pr = float_to_float(p, &bfloat16_params, s); - return bfloat16_round_pack_canonical(pr, s); + FloatParts64 p; + + float64_unpack_canonical(&p, a, s); + parts_float_to_float(&p, s); + return bfloat16_round_pack_canonical(&p, s); +} + +float32 float128_to_float32(float128 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + float128_unpack_canonical(&p128, a, s); + parts_float_to_float_narrow(&p64, &p128, s); + return float32_round_pack_canonical(&p64, s); +} + +float64 float128_to_float64(float128 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + float128_unpack_canonical(&p128, a, s); + parts_float_to_float_narrow(&p64, &p128, s); + return float64_round_pack_canonical(&p64, s); +} + +float128 float32_to_float128(float32 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + float32_unpack_canonical(&p64, a, s); + parts_float_to_float_widen(&p128, &p64, s); + return float128_round_pack_canonical(&p128, s); +} + +float128 float64_to_float128(float64 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + float64_unpack_canonical(&p64, a, s); + parts_float_to_float_widen(&p128, &p64, s); + return float128_round_pack_canonical(&p128, s); +} + +float32 floatx80_to_float32(floatx80 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + if (floatx80_unpack_canonical(&p128, a, s)) { + parts_float_to_float_narrow(&p64, &p128, s); + } else { + parts_default_nan(&p64, s); + } + return float32_round_pack_canonical(&p64, s); +} + +float64 floatx80_to_float64(floatx80 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + if (floatx80_unpack_canonical(&p128, a, s)) { + parts_float_to_float_narrow(&p64, &p128, s); + } else { + parts_default_nan(&p64, s); + } + return float64_round_pack_canonical(&p64, s); +} + +float128 floatx80_to_float128(floatx80 a, float_status *s) +{ + FloatParts128 p; + + if (floatx80_unpack_canonical(&p, a, s)) { + parts_float_to_float(&p, s); + } else { + parts_default_nan(&p, s); + } + return float128_round_pack_canonical(&p, s); +} + +floatx80 float32_to_floatx80(float32 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + float32_unpack_canonical(&p64, a, s); + parts_float_to_float_widen(&p128, &p64, s); + return floatx80_round_pack_canonical(&p128, s); +} + +floatx80 float64_to_floatx80(float64 a, float_status *s) +{ + FloatParts64 p64; + FloatParts128 p128; + + float64_unpack_canonical(&p64, a, s); + parts_float_to_float_widen(&p128, &p64, s); + return floatx80_round_pack_canonical(&p128, s); +} + +floatx80 float128_to_floatx80(float128 a, float_status *s) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, s); + parts_float_to_float(&p, s); + return floatx80_round_pack_canonical(&p, s); } /* - * Rounds the floating-point value `a' to an integer, and returns the - * result as a floating-point value. The operation is performed - * according to the IEC/IEEE Standard for Binary Floating-Point - * Arithmetic. + * Round to integral value */ -static FloatParts round_to_int(FloatParts a, FloatRoundMode rmode, - int scale, float_status *s) -{ - switch (a.cls) { - case float_class_qnan: - case float_class_snan: - return return_nan(a, s); - - case float_class_zero: - case float_class_inf: - /* already "integral" */ - break; - - case float_class_normal: - scale = MIN(MAX(scale, -0x10000), 0x10000); - a.exp += scale; - - if (a.exp >= DECOMPOSED_BINARY_POINT) { - /* already integral */ - break; - } - if (a.exp < 0) { - bool one; - /* all fractional */ - s->float_exception_flags |= float_flag_inexact; - switch (rmode) { - case float_round_nearest_even: - one = a.exp == -1 && a.frac > DECOMPOSED_IMPLICIT_BIT; - break; - case float_round_ties_away: - one = a.exp == -1 && a.frac >= DECOMPOSED_IMPLICIT_BIT; - break; - case float_round_to_zero: - one = false; - break; - case float_round_up: - one = !a.sign; - break; - case float_round_down: - one = a.sign; - break; - case float_round_to_odd: - one = true; - break; - default: - g_assert_not_reached(); - } - - if (one) { - a.frac = DECOMPOSED_IMPLICIT_BIT; - a.exp = 0; - } else { - a.cls = float_class_zero; - } - } else { - uint64_t frac_lsb = DECOMPOSED_IMPLICIT_BIT >> a.exp; - uint64_t frac_lsbm1 = frac_lsb >> 1; - uint64_t rnd_even_mask = (frac_lsb - 1) | frac_lsb; - uint64_t rnd_mask = rnd_even_mask >> 1; - uint64_t inc; - - switch (rmode) { - case float_round_nearest_even: - inc = ((a.frac & rnd_even_mask) != frac_lsbm1 ? frac_lsbm1 : 0); - break; - case float_round_ties_away: - inc = frac_lsbm1; - break; - case float_round_to_zero: - inc = 0; - break; - case float_round_up: - inc = a.sign ? 0 : rnd_mask; - break; - case float_round_down: - inc = a.sign ? rnd_mask : 0; - break; - case float_round_to_odd: - inc = a.frac & frac_lsb ? 0 : rnd_mask; - break; - default: - g_assert_not_reached(); - } - - if (a.frac & rnd_mask) { - s->float_exception_flags |= float_flag_inexact; - a.frac += inc; - a.frac &= ~rnd_mask; - if (a.frac & DECOMPOSED_OVERFLOW_BIT) { - a.frac >>= 1; - a.exp++; - } - } - } - break; - default: - g_assert_not_reached(); - } - return a; -} - float16 float16_round_to_int(float16 a, float_status *s) { - FloatParts pa = float16_unpack_canonical(a, s); - FloatParts pr = round_to_int(pa, s->float_rounding_mode, 0, s); - return float16_round_pack_canonical(pr, s); + FloatParts64 p; + + float16_unpack_canonical(&p, a, s); + parts_round_to_int(&p, s->float_rounding_mode, 0, s, &float16_params); + return float16_round_pack_canonical(&p, s); } float32 float32_round_to_int(float32 a, float_status *s) { - FloatParts pa = float32_unpack_canonical(a, s); - FloatParts pr = round_to_int(pa, s->float_rounding_mode, 0, s); - return float32_round_pack_canonical(pr, s); + FloatParts64 p; + + float32_unpack_canonical(&p, a, s); + parts_round_to_int(&p, s->float_rounding_mode, 0, s, &float32_params); + return float32_round_pack_canonical(&p, s); } float64 float64_round_to_int(float64 a, float_status *s) { - FloatParts pa = float64_unpack_canonical(a, s); - FloatParts pr = round_to_int(pa, s->float_rounding_mode, 0, s); - return float64_round_pack_canonical(pr, s); -} + FloatParts64 p; -/* - * Rounds the bfloat16 value `a' to an integer, and returns the - * result as a bfloat16 value. - */ + float64_unpack_canonical(&p, a, s); + parts_round_to_int(&p, s->float_rounding_mode, 0, s, &float64_params); + return float64_round_pack_canonical(&p, s); +} bfloat16 bfloat16_round_to_int(bfloat16 a, float_status *s) { - FloatParts pa = bfloat16_unpack_canonical(a, s); - FloatParts pr = round_to_int(pa, s->float_rounding_mode, 0, s); - return bfloat16_round_pack_canonical(pr, s); + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + parts_round_to_int(&p, s->float_rounding_mode, 0, s, &bfloat16_params); + return bfloat16_round_pack_canonical(&p, s); +} + +float128 float128_round_to_int(float128 a, float_status *s) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, s); + parts_round_to_int(&p, s->float_rounding_mode, 0, s, &float128_params); + return float128_round_pack_canonical(&p, s); +} + +floatx80 floatx80_round_to_int(floatx80 a, float_status *status) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, status)) { + return floatx80_default_nan(status); + } + + parts_round_to_int(&p, status->float_rounding_mode, 0, status, + &floatx80_params[status->floatx80_rounding_precision]); + return floatx80_round_pack_canonical(&p, status); } /* - * Returns the result of converting the floating-point value `a' to - * the two's complement integer format. The conversion is performed - * according to the IEC/IEEE Standard for Binary Floating-Point - * Arithmetic---which means in particular that the conversion is - * rounded according to the current rounding mode. If `a' is a NaN, - * the largest positive integer is returned. Otherwise, if the - * conversion overflows, the largest integer with the same sign as `a' - * is returned. -*/ - -static int64_t round_to_int_and_pack(FloatParts in, FloatRoundMode rmode, - int scale, int64_t min, int64_t max, - float_status *s) -{ - uint64_t r; - int orig_flags = get_float_exception_flags(s); - FloatParts p = round_to_int(in, rmode, scale, s); - - switch (p.cls) { - case float_class_snan: - case float_class_qnan: - s->float_exception_flags = orig_flags | float_flag_invalid; - return max; - case float_class_inf: - s->float_exception_flags = orig_flags | float_flag_invalid; - return p.sign ? min : max; - case float_class_zero: - return 0; - case float_class_normal: - if (p.exp < DECOMPOSED_BINARY_POINT) { - r = p.frac >> (DECOMPOSED_BINARY_POINT - p.exp); - } else if (p.exp - DECOMPOSED_BINARY_POINT < 2) { - r = p.frac << (p.exp - DECOMPOSED_BINARY_POINT); - } else { - r = UINT64_MAX; - } - if (p.sign) { - if (r <= -(uint64_t) min) { - return -r; - } else { - s->float_exception_flags = orig_flags | float_flag_invalid; - return min; - } - } else { - if (r <= max) { - return r; - } else { - s->float_exception_flags = orig_flags | float_flag_invalid; - return max; - } - } - default: - g_assert_not_reached(); - } -} + * Floating-point to signed integer conversions + */ int8_t float16_to_int8_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_int_and_pack(float16_unpack_canonical(a, s), - rmode, scale, INT8_MIN, INT8_MAX, s); + FloatParts64 p; + + float16_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT8_MIN, INT8_MAX, s); } int16_t float16_to_int16_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_int_and_pack(float16_unpack_canonical(a, s), - rmode, scale, INT16_MIN, INT16_MAX, s); + FloatParts64 p; + + float16_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT16_MIN, INT16_MAX, s); } int32_t float16_to_int32_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_int_and_pack(float16_unpack_canonical(a, s), - rmode, scale, INT32_MIN, INT32_MAX, s); + FloatParts64 p; + + float16_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT32_MIN, INT32_MAX, s); } int64_t float16_to_int64_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_int_and_pack(float16_unpack_canonical(a, s), - rmode, scale, INT64_MIN, INT64_MAX, s); + FloatParts64 p; + + float16_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s); } int16_t float32_to_int16_scalbn(float32 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_int_and_pack(float32_unpack_canonical(a, s), - rmode, scale, INT16_MIN, INT16_MAX, s); + FloatParts64 p; + + float32_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT16_MIN, INT16_MAX, s); } int32_t float32_to_int32_scalbn(float32 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_int_and_pack(float32_unpack_canonical(a, s), - rmode, scale, INT32_MIN, INT32_MAX, s); + FloatParts64 p; + + float32_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT32_MIN, INT32_MAX, s); } int64_t float32_to_int64_scalbn(float32 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_int_and_pack(float32_unpack_canonical(a, s), - rmode, scale, INT64_MIN, INT64_MAX, s); + FloatParts64 p; + + float32_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s); } int16_t float64_to_int16_scalbn(float64 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_int_and_pack(float64_unpack_canonical(a, s), - rmode, scale, INT16_MIN, INT16_MAX, s); + FloatParts64 p; + + float64_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT16_MIN, INT16_MAX, s); } int32_t float64_to_int32_scalbn(float64 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_int_and_pack(float64_unpack_canonical(a, s), - rmode, scale, INT32_MIN, INT32_MAX, s); + FloatParts64 p; + + float64_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT32_MIN, INT32_MAX, s); } int64_t float64_to_int64_scalbn(float64 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_int_and_pack(float64_unpack_canonical(a, s), - rmode, scale, INT64_MIN, INT64_MAX, s); + FloatParts64 p; + + float64_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s); +} + +int16_t bfloat16_to_int16_scalbn(bfloat16 a, FloatRoundMode rmode, int scale, + float_status *s) +{ + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT16_MIN, INT16_MAX, s); +} + +int32_t bfloat16_to_int32_scalbn(bfloat16 a, FloatRoundMode rmode, int scale, + float_status *s) +{ + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT32_MIN, INT32_MAX, s); +} + +int64_t bfloat16_to_int64_scalbn(bfloat16 a, FloatRoundMode rmode, int scale, + float_status *s) +{ + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s); +} + +static int32_t float128_to_int32_scalbn(float128 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT32_MIN, INT32_MAX, s); +} + +static int64_t float128_to_int64_scalbn(float128 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, s); + return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s); +} + +static int32_t floatx80_to_int32_scalbn(floatx80 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, s)) { + parts_default_nan(&p, s); + } + return parts_float_to_sint(&p, rmode, scale, INT32_MIN, INT32_MAX, s); +} + +static int64_t floatx80_to_int64_scalbn(floatx80 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, s)) { + parts_default_nan(&p, s); + } + return parts_float_to_sint(&p, rmode, scale, INT64_MIN, INT64_MAX, s); } int8_t float16_to_int8(float16 a, float_status *s) @@ -2360,6 +3118,26 @@ int64_t float64_to_int64(float64 a, float_status *s) return float64_to_int64_scalbn(a, s->float_rounding_mode, 0, s); } +int32_t float128_to_int32(float128 a, float_status *s) +{ + return float128_to_int32_scalbn(a, s->float_rounding_mode, 0, s); +} + +int64_t float128_to_int64(float128 a, float_status *s) +{ + return float128_to_int64_scalbn(a, s->float_rounding_mode, 0, s); +} + +int32_t floatx80_to_int32(floatx80 a, float_status *s) +{ + return floatx80_to_int32_scalbn(a, s->float_rounding_mode, 0, s); +} + +int64_t floatx80_to_int64(floatx80 a, float_status *s) +{ + return floatx80_to_int64_scalbn(a, s->float_rounding_mode, 0, s); +} + int16_t float16_to_int16_round_to_zero(float16 a, float_status *s) { return float16_to_int16_scalbn(a, float_round_to_zero, 0, s); @@ -2405,30 +3183,24 @@ int64_t float64_to_int64_round_to_zero(float64 a, float_status *s) return float64_to_int64_scalbn(a, float_round_to_zero, 0, s); } -/* - * Returns the result of converting the floating-point value `a' to - * the two's complement integer format. - */ - -int16_t bfloat16_to_int16_scalbn(bfloat16 a, FloatRoundMode rmode, int scale, - float_status *s) +int32_t float128_to_int32_round_to_zero(float128 a, float_status *s) { - return round_to_int_and_pack(bfloat16_unpack_canonical(a, s), - rmode, scale, INT16_MIN, INT16_MAX, s); + return float128_to_int32_scalbn(a, float_round_to_zero, 0, s); } -int32_t bfloat16_to_int32_scalbn(bfloat16 a, FloatRoundMode rmode, int scale, - float_status *s) +int64_t float128_to_int64_round_to_zero(float128 a, float_status *s) { - return round_to_int_and_pack(bfloat16_unpack_canonical(a, s), - rmode, scale, INT32_MIN, INT32_MAX, s); + return float128_to_int64_scalbn(a, float_round_to_zero, 0, s); } -int64_t bfloat16_to_int64_scalbn(bfloat16 a, FloatRoundMode rmode, int scale, - float_status *s) +int32_t floatx80_to_int32_round_to_zero(floatx80 a, float_status *s) { - return round_to_int_and_pack(bfloat16_unpack_canonical(a, s), - rmode, scale, INT64_MIN, INT64_MAX, s); + return floatx80_to_int32_scalbn(a, float_round_to_zero, 0, s); +} + +int64_t floatx80_to_int64_round_to_zero(floatx80 a, float_status *s) +{ + return floatx80_to_int64_scalbn(a, float_round_to_zero, 0, s); } int16_t bfloat16_to_int16(bfloat16 a, float_status *s) @@ -2462,133 +3234,142 @@ int64_t bfloat16_to_int64_round_to_zero(bfloat16 a, float_status *s) } /* - * Returns the result of converting the floating-point value `a' to - * the unsigned integer format. The conversion is performed according - * to the IEC/IEEE Standard for Binary Floating-Point - * Arithmetic---which means in particular that the conversion is - * rounded according to the current rounding mode. If `a' is a NaN, - * the largest unsigned integer is returned. Otherwise, if the - * conversion overflows, the largest unsigned integer is returned. If - * the 'a' is negative, the result is rounded and zero is returned; - * values that do not round to zero will raise the inexact exception - * flag. + * Floating-point to unsigned integer conversions */ -static uint64_t round_to_uint_and_pack(FloatParts in, FloatRoundMode rmode, - int scale, uint64_t max, - float_status *s) -{ - int orig_flags = get_float_exception_flags(s); - FloatParts p = round_to_int(in, rmode, scale, s); - uint64_t r; - - switch (p.cls) { - case float_class_snan: - case float_class_qnan: - s->float_exception_flags = orig_flags | float_flag_invalid; - return max; - case float_class_inf: - s->float_exception_flags = orig_flags | float_flag_invalid; - return p.sign ? 0 : max; - case float_class_zero: - return 0; - case float_class_normal: - if (p.sign) { - s->float_exception_flags = orig_flags | float_flag_invalid; - return 0; - } - - if (p.exp < DECOMPOSED_BINARY_POINT) { - r = p.frac >> (DECOMPOSED_BINARY_POINT - p.exp); - } else if (p.exp - DECOMPOSED_BINARY_POINT < 2) { - r = p.frac << (p.exp - DECOMPOSED_BINARY_POINT); - } else { - s->float_exception_flags = orig_flags | float_flag_invalid; - return max; - } - - /* For uint64 this will never trip, but if p.exp is too large - * to shift a decomposed fraction we shall have exited via the - * 3rd leg above. - */ - if (r > max) { - s->float_exception_flags = orig_flags | float_flag_invalid; - return max; - } - return r; - default: - g_assert_not_reached(); - } -} - uint8_t float16_to_uint8_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_uint_and_pack(float16_unpack_canonical(a, s), - rmode, scale, UINT8_MAX, s); + FloatParts64 p; + + float16_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT8_MAX, s); } uint16_t float16_to_uint16_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_uint_and_pack(float16_unpack_canonical(a, s), - rmode, scale, UINT16_MAX, s); + FloatParts64 p; + + float16_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s); } uint32_t float16_to_uint32_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_uint_and_pack(float16_unpack_canonical(a, s), - rmode, scale, UINT32_MAX, s); + FloatParts64 p; + + float16_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s); } uint64_t float16_to_uint64_scalbn(float16 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_uint_and_pack(float16_unpack_canonical(a, s), - rmode, scale, UINT64_MAX, s); + FloatParts64 p; + + float16_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s); } uint16_t float32_to_uint16_scalbn(float32 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_uint_and_pack(float32_unpack_canonical(a, s), - rmode, scale, UINT16_MAX, s); + FloatParts64 p; + + float32_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s); } uint32_t float32_to_uint32_scalbn(float32 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_uint_and_pack(float32_unpack_canonical(a, s), - rmode, scale, UINT32_MAX, s); + FloatParts64 p; + + float32_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s); } uint64_t float32_to_uint64_scalbn(float32 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_uint_and_pack(float32_unpack_canonical(a, s), - rmode, scale, UINT64_MAX, s); + FloatParts64 p; + + float32_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s); } uint16_t float64_to_uint16_scalbn(float64 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_uint_and_pack(float64_unpack_canonical(a, s), - rmode, scale, UINT16_MAX, s); + FloatParts64 p; + + float64_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s); } uint32_t float64_to_uint32_scalbn(float64 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_uint_and_pack(float64_unpack_canonical(a, s), - rmode, scale, UINT32_MAX, s); + FloatParts64 p; + + float64_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s); } uint64_t float64_to_uint64_scalbn(float64 a, FloatRoundMode rmode, int scale, float_status *s) { - return round_to_uint_and_pack(float64_unpack_canonical(a, s), - rmode, scale, UINT64_MAX, s); + FloatParts64 p; + + float64_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s); +} + +uint16_t bfloat16_to_uint16_scalbn(bfloat16 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT16_MAX, s); +} + +uint32_t bfloat16_to_uint32_scalbn(bfloat16 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s); +} + +uint64_t bfloat16_to_uint64_scalbn(bfloat16 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s); +} + +static uint32_t float128_to_uint32_scalbn(float128 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT32_MAX, s); +} + +static uint64_t float128_to_uint64_scalbn(float128 a, FloatRoundMode rmode, + int scale, float_status *s) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, s); + return parts_float_to_uint(&p, rmode, scale, UINT64_MAX, s); } uint8_t float16_to_uint8(float16 a, float_status *s) @@ -2641,6 +3422,16 @@ uint64_t float64_to_uint64(float64 a, float_status *s) return float64_to_uint64_scalbn(a, s->float_rounding_mode, 0, s); } +uint32_t float128_to_uint32(float128 a, float_status *s) +{ + return float128_to_uint32_scalbn(a, s->float_rounding_mode, 0, s); +} + +uint64_t float128_to_uint64(float128 a, float_status *s) +{ + return float128_to_uint64_scalbn(a, s->float_rounding_mode, 0, s); +} + uint16_t float16_to_uint16_round_to_zero(float16 a, float_status *s) { return float16_to_uint16_scalbn(a, float_round_to_zero, 0, s); @@ -2686,30 +3477,14 @@ uint64_t float64_to_uint64_round_to_zero(float64 a, float_status *s) return float64_to_uint64_scalbn(a, float_round_to_zero, 0, s); } -/* - * Returns the result of converting the bfloat16 value `a' to - * the unsigned integer format. - */ - -uint16_t bfloat16_to_uint16_scalbn(bfloat16 a, FloatRoundMode rmode, - int scale, float_status *s) +uint32_t float128_to_uint32_round_to_zero(float128 a, float_status *s) { - return round_to_uint_and_pack(bfloat16_unpack_canonical(a, s), - rmode, scale, UINT16_MAX, s); + return float128_to_uint32_scalbn(a, float_round_to_zero, 0, s); } -uint32_t bfloat16_to_uint32_scalbn(bfloat16 a, FloatRoundMode rmode, - int scale, float_status *s) +uint64_t float128_to_uint64_round_to_zero(float128 a, float_status *s) { - return round_to_uint_and_pack(bfloat16_unpack_canonical(a, s), - rmode, scale, UINT32_MAX, s); -} - -uint64_t bfloat16_to_uint64_scalbn(bfloat16 a, FloatRoundMode rmode, - int scale, float_status *s) -{ - return round_to_uint_and_pack(bfloat16_unpack_canonical(a, s), - rmode, scale, UINT64_MAX, s); + return float128_to_uint64_scalbn(a, float_round_to_zero, 0, s); } uint16_t bfloat16_to_uint16(bfloat16 a, float_status *s) @@ -2743,42 +3518,15 @@ uint64_t bfloat16_to_uint64_round_to_zero(bfloat16 a, float_status *s) } /* - * Integer to float conversions - * - * Returns the result of converting the two's complement integer `a' - * to the floating-point format. The conversion is performed according - * to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. + * Signed integer to floating-point conversions */ -static FloatParts int_to_float(int64_t a, int scale, float_status *status) -{ - FloatParts r = { .sign = false }; - - if (a == 0) { - r.cls = float_class_zero; - } else { - uint64_t f = a; - int shift; - - r.cls = float_class_normal; - if (a < 0) { - f = -f; - r.sign = true; - } - shift = clz64(f) - 1; - scale = MIN(MAX(scale, -0x10000), 0x10000); - - r.exp = DECOMPOSED_BINARY_POINT - shift + scale; - r.frac = (shift < 0 ? DECOMPOSED_IMPLICIT_BIT : f << shift); - } - - return r; -} - float16 int64_to_float16_scalbn(int64_t a, int scale, float_status *status) { - FloatParts pa = int_to_float(a, scale, status); - return float16_round_pack_canonical(pa, status); + FloatParts64 p; + + parts_sint_to_float(&p, a, scale, status); + return float16_round_pack_canonical(&p, status); } float16 int32_to_float16_scalbn(int32_t a, int scale, float_status *status) @@ -2813,8 +3561,17 @@ float16 int8_to_float16(int8_t a, float_status *status) float32 int64_to_float32_scalbn(int64_t a, int scale, float_status *status) { - FloatParts pa = int_to_float(a, scale, status); - return float32_round_pack_canonical(pa, status); + FloatParts64 p; + + /* Without scaling, there are no overflow concerns. */ + if (likely(scale == 0) && can_use_fpu(status)) { + union_float32 ur; + ur.h = a; + return ur.s; + } + + parts64_sint_to_float(&p, a, scale, status); + return float32_round_pack_canonical(&p, status); } float32 int32_to_float32_scalbn(int32_t a, int scale, float_status *status) @@ -2844,8 +3601,17 @@ float32 int16_to_float32(int16_t a, float_status *status) float64 int64_to_float64_scalbn(int64_t a, int scale, float_status *status) { - FloatParts pa = int_to_float(a, scale, status); - return float64_round_pack_canonical(pa, status); + FloatParts64 p; + + /* Without scaling, there are no overflow concerns. */ + if (likely(scale == 0) && can_use_fpu(status)) { + union_float64 ur; + ur.h = a; + return ur.s; + } + + parts_sint_to_float(&p, a, scale, status); + return float64_round_pack_canonical(&p, status); } float64 int32_to_float64_scalbn(int32_t a, int scale, float_status *status) @@ -2873,15 +3639,12 @@ float64 int16_to_float64(int16_t a, float_status *status) return int64_to_float64_scalbn(a, 0, status); } -/* - * Returns the result of converting the two's complement integer `a' - * to the bfloat16 format. - */ - bfloat16 int64_to_bfloat16_scalbn(int64_t a, int scale, float_status *status) { - FloatParts pa = int_to_float(a, scale, status); - return bfloat16_round_pack_canonical(pa, status); + FloatParts64 p; + + parts_sint_to_float(&p, a, scale, status); + return bfloat16_round_pack_canonical(&p, status); } bfloat16 int32_to_bfloat16_scalbn(int32_t a, int scale, float_status *status) @@ -2909,41 +3672,42 @@ bfloat16 int16_to_bfloat16(int16_t a, float_status *status) return int64_to_bfloat16_scalbn(a, 0, status); } -/* - * Unsigned Integer to float conversions - * - * Returns the result of converting the unsigned integer `a' to the - * floating-point format. The conversion is performed according to the - * IEC/IEEE Standard for Binary Floating-Point Arithmetic. - */ - -static FloatParts uint_to_float(uint64_t a, int scale, float_status *status) +float128 int64_to_float128(int64_t a, float_status *status) { - FloatParts r = { .sign = false }; + FloatParts128 p; - if (a == 0) { - r.cls = float_class_zero; - } else { - scale = MIN(MAX(scale, -0x10000), 0x10000); - r.cls = float_class_normal; - if ((int64_t)a < 0) { - r.exp = DECOMPOSED_BINARY_POINT + 1 + scale; - shift64RightJamming(a, 1, &a); - r.frac = a; - } else { - int shift = clz64(a) - 1; - r.exp = DECOMPOSED_BINARY_POINT - shift + scale; - r.frac = a << shift; - } - } - - return r; + parts_sint_to_float(&p, a, 0, status); + return float128_round_pack_canonical(&p, status); } +float128 int32_to_float128(int32_t a, float_status *status) +{ + return int64_to_float128(a, status); +} + +floatx80 int64_to_floatx80(int64_t a, float_status *status) +{ + FloatParts128 p; + + parts_sint_to_float(&p, a, 0, status); + return floatx80_round_pack_canonical(&p, status); +} + +floatx80 int32_to_floatx80(int32_t a, float_status *status) +{ + return int64_to_floatx80(a, status); +} + +/* + * Unsigned Integer to floating-point conversions + */ + float16 uint64_to_float16_scalbn(uint64_t a, int scale, float_status *status) { - FloatParts pa = uint_to_float(a, scale, status); - return float16_round_pack_canonical(pa, status); + FloatParts64 p; + + parts_uint_to_float(&p, a, scale, status); + return float16_round_pack_canonical(&p, status); } float16 uint32_to_float16_scalbn(uint32_t a, int scale, float_status *status) @@ -2978,8 +3742,17 @@ float16 uint8_to_float16(uint8_t a, float_status *status) float32 uint64_to_float32_scalbn(uint64_t a, int scale, float_status *status) { - FloatParts pa = uint_to_float(a, scale, status); - return float32_round_pack_canonical(pa, status); + FloatParts64 p; + + /* Without scaling, there are no overflow concerns. */ + if (likely(scale == 0) && can_use_fpu(status)) { + union_float32 ur; + ur.h = a; + return ur.s; + } + + parts_uint_to_float(&p, a, scale, status); + return float32_round_pack_canonical(&p, status); } float32 uint32_to_float32_scalbn(uint32_t a, int scale, float_status *status) @@ -3009,8 +3782,17 @@ float32 uint16_to_float32(uint16_t a, float_status *status) float64 uint64_to_float64_scalbn(uint64_t a, int scale, float_status *status) { - FloatParts pa = uint_to_float(a, scale, status); - return float64_round_pack_canonical(pa, status); + FloatParts64 p; + + /* Without scaling, there are no overflow concerns. */ + if (likely(scale == 0) && can_use_fpu(status)) { + union_float64 ur; + ur.h = a; + return ur.s; + } + + parts_uint_to_float(&p, a, scale, status); + return float64_round_pack_canonical(&p, status); } float64 uint32_to_float64_scalbn(uint32_t a, int scale, float_status *status) @@ -3038,15 +3820,12 @@ float64 uint16_to_float64(uint16_t a, float_status *status) return uint64_to_float64_scalbn(a, 0, status); } -/* - * Returns the result of converting the unsigned integer `a' to the - * bfloat16 format. - */ - bfloat16 uint64_to_bfloat16_scalbn(uint64_t a, int scale, float_status *status) { - FloatParts pa = uint_to_float(a, scale, status); - return bfloat16_round_pack_canonical(pa, status); + FloatParts64 p; + + parts_uint_to_float(&p, a, scale, status); + return bfloat16_round_pack_canonical(&p, status); } bfloat16 uint32_to_bfloat16_scalbn(uint32_t a, int scale, float_status *status) @@ -3074,231 +3853,132 @@ bfloat16 uint16_to_bfloat16(uint16_t a, float_status *status) return uint64_to_bfloat16_scalbn(a, 0, status); } -/* Float Min/Max */ -/* min() and max() functions. These can't be implemented as - * 'compare and pick one input' because that would mishandle - * NaNs and +0 vs -0. - * - * minnum() and maxnum() functions. These are similar to the min() - * and max() functions but if one of the arguments is a QNaN and - * the other is numerical then the numerical argument is returned. - * SNaNs will get quietened before being returned. - * minnum() and maxnum correspond to the IEEE 754-2008 minNum() - * and maxNum() operations. min() and max() are the typical min/max - * semantics provided by many CPUs which predate that specification. - * - * minnummag() and maxnummag() functions correspond to minNumMag() - * and minNumMag() from the IEEE-754 2008. +float128 uint64_to_float128(uint64_t a, float_status *status) +{ + FloatParts128 p; + + parts_uint_to_float(&p, a, 0, status); + return float128_round_pack_canonical(&p, status); +} + +/* + * Minimum and maximum */ -static FloatParts minmax_floats(FloatParts a, FloatParts b, bool ismin, - bool ieee, bool ismag, float_status *s) + +static float16 float16_minmax(float16 a, float16 b, float_status *s, int flags) { - if (unlikely(is_nan(a.cls) || is_nan(b.cls))) { - if (ieee) { - /* Takes two floating-point values `a' and `b', one of - * which is a NaN, and returns the appropriate NaN - * result. If either `a' or `b' is a signaling NaN, - * the invalid exception is raised. - */ - if (is_snan(a.cls) || is_snan(b.cls)) { - return pick_nan(a, b, s); - } else if (is_nan(a.cls) && !is_nan(b.cls)) { - return b; - } else if (is_nan(b.cls) && !is_nan(a.cls)) { - return a; - } - } - return pick_nan(a, b, s); - } else { - int a_exp, b_exp; + FloatParts64 pa, pb, *pr; - switch (a.cls) { - case float_class_normal: - a_exp = a.exp; - break; - case float_class_inf: - a_exp = INT_MAX; - break; - case float_class_zero: - a_exp = INT_MIN; - break; - default: - g_assert_not_reached(); - break; - } - switch (b.cls) { - case float_class_normal: - b_exp = b.exp; - break; - case float_class_inf: - b_exp = INT_MAX; - break; - case float_class_zero: - b_exp = INT_MIN; - break; - default: - g_assert_not_reached(); - break; - } + float16_unpack_canonical(&pa, a, s); + float16_unpack_canonical(&pb, b, s); + pr = parts_minmax(&pa, &pb, s, flags); - if (ismag && (a_exp != b_exp || a.frac != b.frac)) { - bool a_less = a_exp < b_exp; - if (a_exp == b_exp) { - a_less = a.frac < b.frac; - } - return a_less ^ ismin ? b : a; - } - - if (a.sign == b.sign) { - bool a_less = a_exp < b_exp; - if (a_exp == b_exp) { - a_less = a.frac < b.frac; - } - return a.sign ^ a_less ^ ismin ? b : a; - } else { - return a.sign ^ ismin ? b : a; - } - } + return float16_round_pack_canonical(pr, s); } -#define MINMAX(sz, name, ismin, isiee, ismag) \ -float ## sz float ## sz ## _ ## name(float ## sz a, float ## sz b, \ - float_status *s) \ -{ \ - FloatParts pa = float ## sz ## _unpack_canonical(a, s); \ - FloatParts pb = float ## sz ## _unpack_canonical(b, s); \ - FloatParts pr = minmax_floats(pa, pb, ismin, isiee, ismag, s); \ - \ - return float ## sz ## _round_pack_canonical(pr, s); \ -} - -MINMAX(16, min, true, false, false) -MINMAX(16, minnum, true, true, false) -MINMAX(16, minnummag, true, true, true) -MINMAX(16, max, false, false, false) -MINMAX(16, maxnum, false, true, false) -MINMAX(16, maxnummag, false, true, true) - -MINMAX(32, min, true, false, false) -MINMAX(32, minnum, true, true, false) -MINMAX(32, minnummag, true, true, true) -MINMAX(32, max, false, false, false) -MINMAX(32, maxnum, false, true, false) -MINMAX(32, maxnummag, false, true, true) - -MINMAX(64, min, true, false, false) -MINMAX(64, minnum, true, true, false) -MINMAX(64, minnummag, true, true, true) -MINMAX(64, max, false, false, false) -MINMAX(64, maxnum, false, true, false) -MINMAX(64, maxnummag, false, true, true) - -#undef MINMAX - -#define BF16_MINMAX(name, ismin, isiee, ismag) \ -bfloat16 bfloat16_ ## name(bfloat16 a, bfloat16 b, float_status *s) \ -{ \ - FloatParts pa = bfloat16_unpack_canonical(a, s); \ - FloatParts pb = bfloat16_unpack_canonical(b, s); \ - FloatParts pr = minmax_floats(pa, pb, ismin, isiee, ismag, s); \ - \ - return bfloat16_round_pack_canonical(pr, s); \ -} - -BF16_MINMAX(min, true, false, false) -BF16_MINMAX(minnum, true, true, false) -BF16_MINMAX(minnummag, true, true, true) -BF16_MINMAX(max, false, false, false) -BF16_MINMAX(maxnum, false, true, false) -BF16_MINMAX(maxnummag, false, true, true) - -#undef BF16_MINMAX - -/* Floating point compare */ -static FloatRelation compare_floats(FloatParts a, FloatParts b, bool is_quiet, - float_status *s) +static bfloat16 bfloat16_minmax(bfloat16 a, bfloat16 b, + float_status *s, int flags) { - if (is_nan(a.cls) || is_nan(b.cls)) { - if (!is_quiet || - a.cls == float_class_snan || - b.cls == float_class_snan) { - s->float_exception_flags |= float_flag_invalid; - } - return float_relation_unordered; - } + FloatParts64 pa, pb, *pr; - if (a.cls == float_class_zero) { - if (b.cls == float_class_zero) { - return float_relation_equal; - } - return b.sign ? float_relation_greater : float_relation_less; - } else if (b.cls == float_class_zero) { - return a.sign ? float_relation_less : float_relation_greater; - } + bfloat16_unpack_canonical(&pa, a, s); + bfloat16_unpack_canonical(&pb, b, s); + pr = parts_minmax(&pa, &pb, s, flags); - /* The only really important thing about infinity is its sign. If - * both are infinities the sign marks the smallest of the two. - */ - if (a.cls == float_class_inf) { - if ((b.cls == float_class_inf) && (a.sign == b.sign)) { - return float_relation_equal; - } - return a.sign ? float_relation_less : float_relation_greater; - } else if (b.cls == float_class_inf) { - return b.sign ? float_relation_greater : float_relation_less; - } - - if (a.sign != b.sign) { - return a.sign ? float_relation_less : float_relation_greater; - } - - if (a.exp == b.exp) { - if (a.frac == b.frac) { - return float_relation_equal; - } - if (a.sign) { - return a.frac > b.frac ? - float_relation_less : float_relation_greater; - } else { - return a.frac > b.frac ? - float_relation_greater : float_relation_less; - } - } else { - if (a.sign) { - return a.exp > b.exp ? float_relation_less : float_relation_greater; - } else { - return a.exp > b.exp ? float_relation_greater : float_relation_less; - } - } + return bfloat16_round_pack_canonical(pr, s); } -#define COMPARE(name, attr, sz) \ -static int attr \ -name(float ## sz a, float ## sz b, bool is_quiet, float_status *s) \ -{ \ - FloatParts pa = float ## sz ## _unpack_canonical(a, s); \ - FloatParts pb = float ## sz ## _unpack_canonical(b, s); \ - return compare_floats(pa, pb, is_quiet, s); \ +static float32 float32_minmax(float32 a, float32 b, float_status *s, int flags) +{ + FloatParts64 pa, pb, *pr; + + float32_unpack_canonical(&pa, a, s); + float32_unpack_canonical(&pb, b, s); + pr = parts_minmax(&pa, &pb, s, flags); + + return float32_round_pack_canonical(pr, s); } -COMPARE(soft_f16_compare, QEMU_FLATTEN, 16) -COMPARE(soft_f32_compare, QEMU_SOFTFLOAT_ATTR, 32) -COMPARE(soft_f64_compare, QEMU_SOFTFLOAT_ATTR, 64) +static float64 float64_minmax(float64 a, float64 b, float_status *s, int flags) +{ + FloatParts64 pa, pb, *pr; -#undef COMPARE + float64_unpack_canonical(&pa, a, s); + float64_unpack_canonical(&pb, b, s); + pr = parts_minmax(&pa, &pb, s, flags); + + return float64_round_pack_canonical(pr, s); +} + +static float128 float128_minmax(float128 a, float128 b, + float_status *s, int flags) +{ + FloatParts128 pa, pb, *pr; + + float128_unpack_canonical(&pa, a, s); + float128_unpack_canonical(&pb, b, s); + pr = parts_minmax(&pa, &pb, s, flags); + + return float128_round_pack_canonical(pr, s); +} + +#define MINMAX_1(type, name, flags) \ + type type##_##name(type a, type b, float_status *s) \ + { return type##_minmax(a, b, s, flags); } + +#define MINMAX_2(type) \ + MINMAX_1(type, max, 0) \ + MINMAX_1(type, maxnum, minmax_isnum) \ + MINMAX_1(type, maxnummag, minmax_isnum | minmax_ismag) \ + MINMAX_1(type, min, minmax_ismin) \ + MINMAX_1(type, minnum, minmax_ismin | minmax_isnum) \ + MINMAX_1(type, minnummag, minmax_ismin | minmax_isnum | minmax_ismag) + +MINMAX_2(float16) +MINMAX_2(bfloat16) +MINMAX_2(float32) +MINMAX_2(float64) +MINMAX_2(float128) + +#undef MINMAX_1 +#undef MINMAX_2 + +/* + * Floating point compare + */ + +static FloatRelation QEMU_FLATTEN +float16_do_compare(float16 a, float16 b, float_status *s, bool is_quiet) +{ + FloatParts64 pa, pb; + + float16_unpack_canonical(&pa, a, s); + float16_unpack_canonical(&pb, b, s); + return parts_compare(&pa, &pb, s, is_quiet); +} FloatRelation float16_compare(float16 a, float16 b, float_status *s) { - return soft_f16_compare(a, b, false, s); + return float16_do_compare(a, b, s, false); } FloatRelation float16_compare_quiet(float16 a, float16 b, float_status *s) { - return soft_f16_compare(a, b, true, s); + return float16_do_compare(a, b, s, true); +} + +static FloatRelation QEMU_SOFTFLOAT_ATTR +float32_do_compare(float32 a, float32 b, float_status *s, bool is_quiet) +{ + FloatParts64 pa, pb; + + float32_unpack_canonical(&pa, a, s); + float32_unpack_canonical(&pb, b, s); + return parts_compare(&pa, &pb, s, is_quiet); } static FloatRelation QEMU_FLATTEN -f32_compare(float32 xa, float32 xb, bool is_quiet, float_status *s) +float32_hs_compare(float32 xa, float32 xb, float_status *s, bool is_quiet) { union_float32 ua, ub; @@ -3319,25 +3999,36 @@ f32_compare(float32 xa, float32 xb, bool is_quiet, float_status *s) if (likely(isless(ua.h, ub.h))) { return float_relation_less; } - /* The only condition remaining is unordered. + /* + * The only condition remaining is unordered. * Fall through to set flags. */ soft: - return soft_f32_compare(ua.s, ub.s, is_quiet, s); + return float32_do_compare(ua.s, ub.s, s, is_quiet); } FloatRelation float32_compare(float32 a, float32 b, float_status *s) { - return f32_compare(a, b, false, s); + return float32_hs_compare(a, b, s, false); } FloatRelation float32_compare_quiet(float32 a, float32 b, float_status *s) { - return f32_compare(a, b, true, s); + return float32_hs_compare(a, b, s, true); +} + +static FloatRelation QEMU_SOFTFLOAT_ATTR +float64_do_compare(float64 a, float64 b, float_status *s, bool is_quiet) +{ + FloatParts64 pa, pb; + + float64_unpack_canonical(&pa, a, s); + float64_unpack_canonical(&pb, b, s); + return parts_compare(&pa, &pb, s, is_quiet); } static FloatRelation QEMU_FLATTEN -f64_compare(float64 xa, float64 xb, bool is_quiet, float_status *s) +float64_hs_compare(float64 xa, float64 xb, float_status *s, bool is_quiet) { union_float64 ua, ub; @@ -3358,181 +4049,177 @@ f64_compare(float64 xa, float64 xb, bool is_quiet, float_status *s) if (likely(isless(ua.h, ub.h))) { return float_relation_less; } - /* The only condition remaining is unordered. + /* + * The only condition remaining is unordered. * Fall through to set flags. */ soft: - return soft_f64_compare(ua.s, ub.s, is_quiet, s); + return float64_do_compare(ua.s, ub.s, s, is_quiet); } FloatRelation float64_compare(float64 a, float64 b, float_status *s) { - return f64_compare(a, b, false, s); + return float64_hs_compare(a, b, s, false); } FloatRelation float64_compare_quiet(float64 a, float64 b, float_status *s) { - return f64_compare(a, b, true, s); + return float64_hs_compare(a, b, s, true); } static FloatRelation QEMU_FLATTEN -soft_bf16_compare(bfloat16 a, bfloat16 b, bool is_quiet, float_status *s) +bfloat16_do_compare(bfloat16 a, bfloat16 b, float_status *s, bool is_quiet) { - FloatParts pa = bfloat16_unpack_canonical(a, s); - FloatParts pb = bfloat16_unpack_canonical(b, s); - return compare_floats(pa, pb, is_quiet, s); + FloatParts64 pa, pb; + + bfloat16_unpack_canonical(&pa, a, s); + bfloat16_unpack_canonical(&pb, b, s); + return parts_compare(&pa, &pb, s, is_quiet); } FloatRelation bfloat16_compare(bfloat16 a, bfloat16 b, float_status *s) { - return soft_bf16_compare(a, b, false, s); + return bfloat16_do_compare(a, b, s, false); } FloatRelation bfloat16_compare_quiet(bfloat16 a, bfloat16 b, float_status *s) { - return soft_bf16_compare(a, b, true, s); + return bfloat16_do_compare(a, b, s, true); } -/* Multiply A by 2 raised to the power N. */ -static FloatParts scalbn_decomposed(FloatParts a, int n, float_status *s) +static FloatRelation QEMU_FLATTEN +float128_do_compare(float128 a, float128 b, float_status *s, bool is_quiet) { - if (unlikely(is_nan(a.cls))) { - return return_nan(a, s); - } - if (a.cls == float_class_normal) { - /* The largest float type (even though not supported by FloatParts) - * is float128, which has a 15 bit exponent. Bounding N to 16 bits - * still allows rounding to infinity, without allowing overflow - * within the int32_t that backs FloatParts.exp. - */ - n = MIN(MAX(n, -0x10000), 0x10000); - a.exp += n; - } - return a; + FloatParts128 pa, pb; + + float128_unpack_canonical(&pa, a, s); + float128_unpack_canonical(&pb, b, s); + return parts_compare(&pa, &pb, s, is_quiet); } +FloatRelation float128_compare(float128 a, float128 b, float_status *s) +{ + return float128_do_compare(a, b, s, false); +} + +FloatRelation float128_compare_quiet(float128 a, float128 b, float_status *s) +{ + return float128_do_compare(a, b, s, true); +} + +static FloatRelation QEMU_FLATTEN +floatx80_do_compare(floatx80 a, floatx80 b, float_status *s, bool is_quiet) +{ + FloatParts128 pa, pb; + + if (!floatx80_unpack_canonical(&pa, a, s) || + !floatx80_unpack_canonical(&pb, b, s)) { + return float_relation_unordered; + } + return parts_compare(&pa, &pb, s, is_quiet); +} + +FloatRelation floatx80_compare(floatx80 a, floatx80 b, float_status *s) +{ + return floatx80_do_compare(a, b, s, false); +} + +FloatRelation floatx80_compare_quiet(floatx80 a, floatx80 b, float_status *s) +{ + return floatx80_do_compare(a, b, s, true); +} + +/* + * Scale by 2**N + */ + float16 float16_scalbn(float16 a, int n, float_status *status) { - FloatParts pa = float16_unpack_canonical(a, status); - FloatParts pr = scalbn_decomposed(pa, n, status); - return float16_round_pack_canonical(pr, status); + FloatParts64 p; + + float16_unpack_canonical(&p, a, status); + parts_scalbn(&p, n, status); + return float16_round_pack_canonical(&p, status); } float32 float32_scalbn(float32 a, int n, float_status *status) { - FloatParts pa = float32_unpack_canonical(a, status); - FloatParts pr = scalbn_decomposed(pa, n, status); - return float32_round_pack_canonical(pr, status); + FloatParts64 p; + + float32_unpack_canonical(&p, a, status); + parts_scalbn(&p, n, status); + return float32_round_pack_canonical(&p, status); } float64 float64_scalbn(float64 a, int n, float_status *status) { - FloatParts pa = float64_unpack_canonical(a, status); - FloatParts pr = scalbn_decomposed(pa, n, status); - return float64_round_pack_canonical(pr, status); + FloatParts64 p; + + float64_unpack_canonical(&p, a, status); + parts_scalbn(&p, n, status); + return float64_round_pack_canonical(&p, status); } bfloat16 bfloat16_scalbn(bfloat16 a, int n, float_status *status) { - FloatParts pa = bfloat16_unpack_canonical(a, status); - FloatParts pr = scalbn_decomposed(pa, n, status); - return bfloat16_round_pack_canonical(pr, status); + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, status); + parts_scalbn(&p, n, status); + return bfloat16_round_pack_canonical(&p, status); +} + +float128 float128_scalbn(float128 a, int n, float_status *status) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, status); + parts_scalbn(&p, n, status); + return float128_round_pack_canonical(&p, status); +} + +floatx80 floatx80_scalbn(floatx80 a, int n, float_status *status) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, status)) { + return floatx80_default_nan(status); + } + parts_scalbn(&p, n, status); + return floatx80_round_pack_canonical(&p, status); } /* * Square Root - * - * The old softfloat code did an approximation step before zeroing in - * on the final result. However for simpleness we just compute the - * square root by iterating down from the implicit bit to enough extra - * bits to ensure we get a correctly rounded result. - * - * This does mean however the calculation is slower than before, - * especially for 64 bit floats. */ -static FloatParts sqrt_float(FloatParts a, float_status *s, const FloatFmt *p) -{ - uint64_t a_frac, r_frac, s_frac; - int bit, last_bit; - - if (is_nan(a.cls)) { - return return_nan(a, s); - } - if (a.cls == float_class_zero) { - return a; /* sqrt(+-0) = +-0 */ - } - if (a.sign) { - s->float_exception_flags |= float_flag_invalid; - return parts_default_nan(s); - } - if (a.cls == float_class_inf) { - return a; /* sqrt(+inf) = +inf */ - } - - assert(a.cls == float_class_normal); - - /* We need two overflow bits at the top. Adding room for that is a - * right shift. If the exponent is odd, we can discard the low bit - * by multiplying the fraction by 2; that's a left shift. Combine - * those and we shift right if the exponent is even. - */ - a_frac = a.frac; - if (!(a.exp & 1)) { - a_frac >>= 1; - } - a.exp >>= 1; - - /* Bit-by-bit computation of sqrt. */ - r_frac = 0; - s_frac = 0; - - /* Iterate from implicit bit down to the 3 extra bits to compute a - * properly rounded result. Remember we've inserted one more bit - * at the top, so these positions are one less. - */ - bit = DECOMPOSED_BINARY_POINT - 1; - last_bit = MAX(p->frac_shift - 4, 0); - do { - uint64_t q = 1ULL << bit; - uint64_t t_frac = s_frac + q; - if (t_frac <= a_frac) { - s_frac = t_frac + q; - a_frac -= t_frac; - r_frac += q; - } - a_frac <<= 1; - } while (--bit >= last_bit); - - /* Undo the right shift done above. If there is any remaining - * fraction, the result is inexact. Set the sticky bit. - */ - a.frac = (r_frac << 1) + (a_frac != 0); - - return a; -} - float16 QEMU_FLATTEN float16_sqrt(float16 a, float_status *status) { - FloatParts pa = float16_unpack_canonical(a, status); - FloatParts pr = sqrt_float(pa, status, &float16_params); - return float16_round_pack_canonical(pr, status); + FloatParts64 p; + + float16_unpack_canonical(&p, a, status); + parts_sqrt(&p, status, &float16_params); + return float16_round_pack_canonical(&p, status); } static float32 QEMU_SOFTFLOAT_ATTR soft_f32_sqrt(float32 a, float_status *status) { - FloatParts pa = float32_unpack_canonical(a, status); - FloatParts pr = sqrt_float(pa, status, &float32_params); - return float32_round_pack_canonical(pr, status); + FloatParts64 p; + + float32_unpack_canonical(&p, a, status); + parts_sqrt(&p, status, &float32_params); + return float32_round_pack_canonical(&p, status); } static float64 QEMU_SOFTFLOAT_ATTR soft_f64_sqrt(float64 a, float_status *status) { - FloatParts pa = float64_unpack_canonical(a, status); - FloatParts pr = sqrt_float(pa, status, &float64_params); - return float64_round_pack_canonical(pr, status); + FloatParts64 p; + + float64_unpack_canonical(&p, a, status); + parts_sqrt(&p, status, &float64_params); + return float64_round_pack_canonical(&p, status); } float32 QEMU_FLATTEN float32_sqrt(float32 xa, float_status *s) @@ -3591,9 +4278,52 @@ float64 QEMU_FLATTEN float64_sqrt(float64 xa, float_status *s) bfloat16 QEMU_FLATTEN bfloat16_sqrt(bfloat16 a, float_status *status) { - FloatParts pa = bfloat16_unpack_canonical(a, status); - FloatParts pr = sqrt_float(pa, status, &bfloat16_params); - return bfloat16_round_pack_canonical(pr, status); + FloatParts64 p; + + bfloat16_unpack_canonical(&p, a, status); + parts_sqrt(&p, status, &bfloat16_params); + return bfloat16_round_pack_canonical(&p, status); +} + +float128 QEMU_FLATTEN float128_sqrt(float128 a, float_status *status) +{ + FloatParts128 p; + + float128_unpack_canonical(&p, a, status); + parts_sqrt(&p, status, &float128_params); + return float128_round_pack_canonical(&p, status); +} + +floatx80 floatx80_sqrt(floatx80 a, float_status *s) +{ + FloatParts128 p; + + if (!floatx80_unpack_canonical(&p, a, s)) { + return floatx80_default_nan(s); + } + parts_sqrt(&p, s, &floatx80_params[s->floatx80_rounding_precision]); + return floatx80_round_pack_canonical(&p, s); +} + +/* + * log2 + */ +float32 float32_log2(float32 a, float_status *status) +{ + FloatParts64 p; + + float32_unpack_canonical(&p, a, status); + parts_log2(&p, status, &float32_params); + return float32_round_pack_canonical(&p, status); +} + +float64 float64_log2(float64 a, float_status *status) +{ + FloatParts64 p; + + float64_unpack_canonical(&p, a, status); + parts_log2(&p, status, &float64_params); + return float64_round_pack_canonical(&p, status); } /*---------------------------------------------------------------------------- @@ -3602,47 +4332,47 @@ bfloat16 QEMU_FLATTEN bfloat16_sqrt(bfloat16 a, float_status *status) float16 float16_default_nan(float_status *status) { - FloatParts p = parts_default_nan(status); + FloatParts64 p; + + parts_default_nan(&p, status); p.frac >>= float16_params.frac_shift; - return float16_pack_raw(p); + return float16_pack_raw(&p); } float32 float32_default_nan(float_status *status) { - FloatParts p = parts_default_nan(status); + FloatParts64 p; + + parts_default_nan(&p, status); p.frac >>= float32_params.frac_shift; - return float32_pack_raw(p); + return float32_pack_raw(&p); } float64 float64_default_nan(float_status *status) { - FloatParts p = parts_default_nan(status); + FloatParts64 p; + + parts_default_nan(&p, status); p.frac >>= float64_params.frac_shift; - return float64_pack_raw(p); + return float64_pack_raw(&p); } float128 float128_default_nan(float_status *status) { - FloatParts p = parts_default_nan(status); - float128 r; + FloatParts128 p; - /* Extrapolate from the choices made by parts_default_nan to fill - * in the quad-floating format. If the low bit is set, assume we - * want to set all non-snan bits. - */ - r.low = -(p.frac & 1); - r.high = p.frac >> (DECOMPOSED_BINARY_POINT - 48); - r.high |= UINT64_C(0x7FFF000000000000); - r.high |= (uint64_t)p.sign << 63; - - return r; + parts_default_nan(&p, status); + frac_shr(&p, float128_params.frac_shift); + return float128_pack_raw(&p); } bfloat16 bfloat16_default_nan(float_status *status) { - FloatParts p = parts_default_nan(status); + FloatParts64 p; + + parts_default_nan(&p, status); p.frac >>= bfloat16_params.frac_shift; - return bfloat16_pack_raw(p); + return bfloat16_pack_raw(&p); } /*---------------------------------------------------------------------------- @@ -3651,38 +4381,57 @@ bfloat16 bfloat16_default_nan(float_status *status) float16 float16_silence_nan(float16 a, float_status *status) { - FloatParts p = float16_unpack_raw(a); + FloatParts64 p; + + float16_unpack_raw(&p, a); p.frac <<= float16_params.frac_shift; - p = parts_silence_nan(p, status); + parts_silence_nan(&p, status); p.frac >>= float16_params.frac_shift; - return float16_pack_raw(p); + return float16_pack_raw(&p); } float32 float32_silence_nan(float32 a, float_status *status) { - FloatParts p = float32_unpack_raw(a); + FloatParts64 p; + + float32_unpack_raw(&p, a); p.frac <<= float32_params.frac_shift; - p = parts_silence_nan(p, status); + parts_silence_nan(&p, status); p.frac >>= float32_params.frac_shift; - return float32_pack_raw(p); + return float32_pack_raw(&p); } float64 float64_silence_nan(float64 a, float_status *status) { - FloatParts p = float64_unpack_raw(a); + FloatParts64 p; + + float64_unpack_raw(&p, a); p.frac <<= float64_params.frac_shift; - p = parts_silence_nan(p, status); + parts_silence_nan(&p, status); p.frac >>= float64_params.frac_shift; - return float64_pack_raw(p); + return float64_pack_raw(&p); } bfloat16 bfloat16_silence_nan(bfloat16 a, float_status *status) { - FloatParts p = bfloat16_unpack_raw(a); + FloatParts64 p; + + bfloat16_unpack_raw(&p, a); p.frac <<= bfloat16_params.frac_shift; - p = parts_silence_nan(p, status); + parts_silence_nan(&p, status); p.frac >>= bfloat16_params.frac_shift; - return bfloat16_pack_raw(p); + return bfloat16_pack_raw(&p); +} + +float128 float128_silence_nan(float128 a, float_status *status) +{ + FloatParts128 p; + + float128_unpack_raw(&p, a); + frac_shl(&p, float128_params.frac_shift); + parts_silence_nan(&p, status); + frac_shr(&p, float128_params.frac_shift); + return float128_pack_raw(&p); } /*---------------------------------------------------------------------------- @@ -3690,7 +4439,7 @@ bfloat16 bfloat16_silence_nan(bfloat16 a, float_status *status) | input-denormal exception and return zero. Otherwise just return the value. *----------------------------------------------------------------------------*/ -static bool parts_squash_denormal(FloatParts p, float_status *status) +static bool parts_squash_denormal(FloatParts64 p, float_status *status) { if (p.exp == 0 && p.frac != 0) { float_raise(float_flag_input_denormal, status); @@ -3703,7 +4452,9 @@ static bool parts_squash_denormal(FloatParts p, float_status *status) float16 float16_squash_input_denormal(float16 a, float_status *status) { if (status->flush_inputs_to_zero) { - FloatParts p = float16_unpack_raw(a); + FloatParts64 p; + + float16_unpack_raw(&p, a); if (parts_squash_denormal(p, status)) { return float16_set_sign(float16_zero, p.sign); } @@ -3714,7 +4465,9 @@ float16 float16_squash_input_denormal(float16 a, float_status *status) float32 float32_squash_input_denormal(float32 a, float_status *status) { if (status->flush_inputs_to_zero) { - FloatParts p = float32_unpack_raw(a); + FloatParts64 p; + + float32_unpack_raw(&p, a); if (parts_squash_denormal(p, status)) { return float32_set_sign(float32_zero, p.sign); } @@ -3725,7 +4478,9 @@ float32 float32_squash_input_denormal(float32 a, float_status *status) float64 float64_squash_input_denormal(float64 a, float_status *status) { if (status->flush_inputs_to_zero) { - FloatParts p = float64_unpack_raw(a); + FloatParts64 p; + + float64_unpack_raw(&p, a); if (parts_squash_denormal(p, status)) { return float64_set_sign(float64_zero, p.sign); } @@ -3736,7 +4491,9 @@ float64 float64_squash_input_denormal(float64 a, float_status *status) bfloat16 bfloat16_squash_input_denormal(bfloat16 a, float_status *status) { if (status->flush_inputs_to_zero) { - FloatParts p = bfloat16_unpack_raw(a); + FloatParts64 p; + + bfloat16_unpack_raw(&p, a); if (parts_squash_denormal(p, status)) { return bfloat16_set_sign(bfloat16_zero, p.sign); } @@ -3744,481 +4501,6 @@ bfloat16 bfloat16_squash_input_denormal(bfloat16 a, float_status *status) return a; } -/*---------------------------------------------------------------------------- -| Takes a 64-bit fixed-point value `absZ' with binary point between bits 6 -| and 7, and returns the properly rounded 32-bit integer corresponding to the -| input. If `zSign' is 1, the input is negated before being converted to an -| integer. Bit 63 of `absZ' must be zero. Ordinarily, the fixed-point input -| is simply rounded to an integer, with the inexact exception raised if the -| input cannot be represented exactly as an integer. However, if the fixed- -| point input is too large, the invalid exception is raised and the largest -| positive or negative integer is returned. -*----------------------------------------------------------------------------*/ - -static int32_t roundAndPackInt32(bool zSign, uint64_t absZ, - float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven; - int8_t roundIncrement, roundBits; - int32_t z; - - roundingMode = status->float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - roundIncrement = 0x40; - break; - case float_round_to_zero: - roundIncrement = 0; - break; - case float_round_up: - roundIncrement = zSign ? 0 : 0x7f; - break; - case float_round_down: - roundIncrement = zSign ? 0x7f : 0; - break; - case float_round_to_odd: - roundIncrement = absZ & 0x80 ? 0 : 0x7f; - break; - default: - abort(); - } - roundBits = absZ & 0x7F; - absZ = ( absZ + roundIncrement )>>7; - if (!(roundBits ^ 0x40) && roundNearestEven) { - absZ &= ~1; - } - z = absZ; - if ( zSign ) z = - z; - if ( ( absZ>>32 ) || ( z && ( ( z < 0 ) ^ zSign ) ) ) { - float_raise(float_flag_invalid, status); - return zSign ? INT32_MIN : INT32_MAX; - } - if (roundBits) { - status->float_exception_flags |= float_flag_inexact; - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Takes the 128-bit fixed-point value formed by concatenating `absZ0' and -| `absZ1', with binary point between bits 63 and 64 (between the input words), -| and returns the properly rounded 64-bit integer corresponding to the input. -| If `zSign' is 1, the input is negated before being converted to an integer. -| Ordinarily, the fixed-point input is simply rounded to an integer, with -| the inexact exception raised if the input cannot be represented exactly as -| an integer. However, if the fixed-point input is too large, the invalid -| exception is raised and the largest positive or negative integer is -| returned. -*----------------------------------------------------------------------------*/ - -static int64_t roundAndPackInt64(bool zSign, uint64_t absZ0, uint64_t absZ1, - float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven, increment; - int64_t z; - - roundingMode = status->float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - increment = ((int64_t) absZ1 < 0); - break; - case float_round_to_zero: - increment = 0; - break; - case float_round_up: - increment = !zSign && absZ1; - break; - case float_round_down: - increment = zSign && absZ1; - break; - case float_round_to_odd: - increment = !(absZ0 & 1) && absZ1; - break; - default: - abort(); - } - if ( increment ) { - ++absZ0; - if ( absZ0 == 0 ) goto overflow; - if (!(absZ1 << 1) && roundNearestEven) { - absZ0 &= ~1; - } - } - z = absZ0; - if ( zSign ) z = - z; - if ( z && ( ( z < 0 ) ^ zSign ) ) { - overflow: - float_raise(float_flag_invalid, status); - return zSign ? INT64_MIN : INT64_MAX; - } - if (absZ1) { - status->float_exception_flags |= float_flag_inexact; - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Takes the 128-bit fixed-point value formed by concatenating `absZ0' and -| `absZ1', with binary point between bits 63 and 64 (between the input words), -| and returns the properly rounded 64-bit unsigned integer corresponding to the -| input. Ordinarily, the fixed-point input is simply rounded to an integer, -| with the inexact exception raised if the input cannot be represented exactly -| as an integer. However, if the fixed-point input is too large, the invalid -| exception is raised and the largest unsigned integer is returned. -*----------------------------------------------------------------------------*/ - -static int64_t roundAndPackUint64(bool zSign, uint64_t absZ0, - uint64_t absZ1, float_status *status) -{ - int8_t roundingMode; - bool roundNearestEven, increment; - - roundingMode = status->float_rounding_mode; - roundNearestEven = (roundingMode == float_round_nearest_even); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - increment = ((int64_t)absZ1 < 0); - break; - case float_round_to_zero: - increment = 0; - break; - case float_round_up: - increment = !zSign && absZ1; - break; - case float_round_down: - increment = zSign && absZ1; - break; - case float_round_to_odd: - increment = !(absZ0 & 1) && absZ1; - break; - default: - abort(); - } - if (increment) { - ++absZ0; - if (absZ0 == 0) { - float_raise(float_flag_invalid, status); - return UINT64_MAX; - } - if (!(absZ1 << 1) && roundNearestEven) { - absZ0 &= ~1; - } - } - - if (zSign && absZ0) { - float_raise(float_flag_invalid, status); - return 0; - } - - if (absZ1) { - status->float_exception_flags |= float_flag_inexact; - } - return absZ0; -} - -/*---------------------------------------------------------------------------- -| Normalizes the subnormal single-precision floating-point value represented -| by the denormalized significand `aSig'. The normalized exponent and -| significand are stored at the locations pointed to by `zExpPtr' and -| `zSigPtr', respectively. -*----------------------------------------------------------------------------*/ - -static void - normalizeFloat32Subnormal(uint32_t aSig, int *zExpPtr, uint32_t *zSigPtr) -{ - int8_t shiftCount; - - shiftCount = clz32(aSig) - 8; - *zSigPtr = aSig<float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - roundIncrement = 0x40; - break; - case float_round_to_zero: - roundIncrement = 0; - break; - case float_round_up: - roundIncrement = zSign ? 0 : 0x7f; - break; - case float_round_down: - roundIncrement = zSign ? 0x7f : 0; - break; - case float_round_to_odd: - roundIncrement = zSig & 0x80 ? 0 : 0x7f; - break; - default: - abort(); - break; - } - roundBits = zSig & 0x7F; - if ( 0xFD <= (uint16_t) zExp ) { - if ( ( 0xFD < zExp ) - || ( ( zExp == 0xFD ) - && ( (int32_t) ( zSig + roundIncrement ) < 0 ) ) - ) { - bool overflow_to_inf = roundingMode != float_round_to_odd && - roundIncrement != 0; - float_raise(float_flag_overflow | float_flag_inexact, status); - return packFloat32(zSign, 0xFF, -!overflow_to_inf); - } - if ( zExp < 0 ) { - if (status->flush_to_zero) { - float_raise(float_flag_output_denormal, status); - return packFloat32(zSign, 0, 0); - } - isTiny = status->tininess_before_rounding - || (zExp < -1) - || (zSig + roundIncrement < 0x80000000); - shift32RightJamming( zSig, - zExp, &zSig ); - zExp = 0; - roundBits = zSig & 0x7F; - if (isTiny && roundBits) { - float_raise(float_flag_underflow, status); - } - if (roundingMode == float_round_to_odd) { - /* - * For round-to-odd case, the roundIncrement depends on - * zSig which just changed. - */ - roundIncrement = zSig & 0x80 ? 0 : 0x7f; - } - } - } - if (roundBits) { - status->float_exception_flags |= float_flag_inexact; - } - zSig = ( zSig + roundIncrement )>>7; - if (!(roundBits ^ 0x40) && roundNearestEven) { - zSig &= ~1; - } - if ( zSig == 0 ) zExp = 0; - return packFloat32( zSign, zExp, zSig ); - -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and significand `zSig', and returns the proper single-precision floating- -| point value corresponding to the abstract input. This routine is just like -| `roundAndPackFloat32' except that `zSig' does not have to be normalized. -| Bit 31 of `zSig' must be zero, and `zExp' must be 1 less than the ``true'' -| floating-point exponent. -*----------------------------------------------------------------------------*/ - -static float32 - normalizeRoundAndPackFloat32(bool zSign, int zExp, uint32_t zSig, - float_status *status) -{ - int8_t shiftCount; - - shiftCount = clz32(zSig) - 1; - return roundAndPackFloat32(zSign, zExp - shiftCount, zSig<float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - roundIncrement = 0x200; - break; - case float_round_to_zero: - roundIncrement = 0; - break; - case float_round_up: - roundIncrement = zSign ? 0 : 0x3ff; - break; - case float_round_down: - roundIncrement = zSign ? 0x3ff : 0; - break; - case float_round_to_odd: - roundIncrement = (zSig & 0x400) ? 0 : 0x3ff; - break; - default: - abort(); - } - roundBits = zSig & 0x3FF; - if ( 0x7FD <= (uint16_t) zExp ) { - if ( ( 0x7FD < zExp ) - || ( ( zExp == 0x7FD ) - && ( (int64_t) ( zSig + roundIncrement ) < 0 ) ) - ) { - bool overflow_to_inf = roundingMode != float_round_to_odd && - roundIncrement != 0; - float_raise(float_flag_overflow | float_flag_inexact, status); - return packFloat64(zSign, 0x7FF, -(!overflow_to_inf)); - } - if ( zExp < 0 ) { - if (status->flush_to_zero) { - float_raise(float_flag_output_denormal, status); - return packFloat64(zSign, 0, 0); - } - isTiny = status->tininess_before_rounding - || (zExp < -1) - || (zSig + roundIncrement < UINT64_C(0x8000000000000000)); - shift64RightJamming( zSig, - zExp, &zSig ); - zExp = 0; - roundBits = zSig & 0x3FF; - if (isTiny && roundBits) { - float_raise(float_flag_underflow, status); - } - if (roundingMode == float_round_to_odd) { - /* - * For round-to-odd case, the roundIncrement depends on - * zSig which just changed. - */ - roundIncrement = (zSig & 0x400) ? 0 : 0x3ff; - } - } - } - if (roundBits) { - status->float_exception_flags |= float_flag_inexact; - } - zSig = ( zSig + roundIncrement )>>10; - if (!(roundBits ^ 0x200) && roundNearestEven) { - zSig &= ~1; - } - if ( zSig == 0 ) zExp = 0; - return packFloat64( zSign, zExp, zSig ); - -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and significand `zSig', and returns the proper double-precision floating- -| point value corresponding to the abstract input. This routine is just like -| `roundAndPackFloat64' except that `zSig' does not have to be normalized. -| Bit 63 of `zSig' must be zero, and `zExp' must be 1 less than the ``true'' -| floating-point exponent. -*----------------------------------------------------------------------------*/ - -static float64 - normalizeRoundAndPackFloat64(bool zSign, int zExp, uint64_t zSig, - float_status *status) -{ - int8_t shiftCount; - - shiftCount = clz64(zSig) - 1; - return roundAndPackFloat64(zSign, zExp - shiftCount, zSig<float_rounding_mode; roundNearestEven = ( roundingMode == float_round_nearest_even ); - if ( roundingPrecision == 80 ) goto precision80; - if ( roundingPrecision == 64 ) { + switch (roundingPrecision) { + case floatx80_precision_x: + goto precision80; + case floatx80_precision_d: roundIncrement = UINT64_C(0x0000000000000400); roundMask = UINT64_C(0x00000000000007FF); - } - else if ( roundingPrecision == 32 ) { + break; + case floatx80_precision_s: roundIncrement = UINT64_C(0x0000008000000000); roundMask = UINT64_C(0x000000FFFFFFFFFF); - } - else { - goto precision80; + break; + default: + g_assert_not_reached(); } zSig0 |= ( zSig1 != 0 ); switch (roundingMode) { @@ -4321,7 +4605,7 @@ floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, float_raise(float_flag_underflow, status); } if (roundBits) { - status->float_exception_flags |= float_flag_inexact; + float_raise(float_flag_inexact, status); } zSig0 += roundIncrement; if ( (int64_t) zSig0 < 0 ) zExp = 1; @@ -4334,7 +4618,7 @@ floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, } } if (roundBits) { - status->float_exception_flags |= float_flag_inexact; + float_raise(float_flag_inexact, status); } zSig0 += roundIncrement; if ( zSig0 < roundIncrement ) { @@ -4397,7 +4681,7 @@ floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, float_raise(float_flag_underflow, status); } if (zSig1) { - status->float_exception_flags |= float_flag_inexact; + float_raise(float_flag_inexact, status); } switch (roundingMode) { case float_round_nearest_even: @@ -4427,7 +4711,7 @@ floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, } } if (zSig1) { - status->float_exception_flags |= float_flag_inexact; + float_raise(float_flag_inexact, status); } if ( increment ) { ++zSig0; @@ -4457,7 +4741,7 @@ floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, | normalized. *----------------------------------------------------------------------------*/ -floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision, +floatx80 normalizeRoundAndPackFloatx80(FloatX80RoundPrec roundingPrecision, bool zSign, int32_t zExp, uint64_t zSig0, uint64_t zSig1, float_status *status) @@ -4477,570 +4761,6 @@ floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision, } -/*---------------------------------------------------------------------------- -| Returns the least-significant 64 fraction bits of the quadruple-precision -| floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline uint64_t extractFloat128Frac1( float128 a ) -{ - - return a.low; - -} - -/*---------------------------------------------------------------------------- -| Returns the most-significant 48 fraction bits of the quadruple-precision -| floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline uint64_t extractFloat128Frac0( float128 a ) -{ - - return a.high & UINT64_C(0x0000FFFFFFFFFFFF); - -} - -/*---------------------------------------------------------------------------- -| Returns the exponent bits of the quadruple-precision floating-point value -| `a'. -*----------------------------------------------------------------------------*/ - -static inline int32_t extractFloat128Exp( float128 a ) -{ - - return ( a.high>>48 ) & 0x7FFF; - -} - -/*---------------------------------------------------------------------------- -| Returns the sign bit of the quadruple-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline bool extractFloat128Sign(float128 a) -{ - return a.high >> 63; -} - -/*---------------------------------------------------------------------------- -| Normalizes the subnormal quadruple-precision floating-point value -| represented by the denormalized significand formed by the concatenation of -| `aSig0' and `aSig1'. The normalized exponent is stored at the location -| pointed to by `zExpPtr'. The most significant 49 bits of the normalized -| significand are stored at the location pointed to by `zSig0Ptr', and the -| least significant 64 bits of the normalized significand are stored at the -| location pointed to by `zSig1Ptr'. -*----------------------------------------------------------------------------*/ - -static void - normalizeFloat128Subnormal( - uint64_t aSig0, - uint64_t aSig1, - int32_t *zExpPtr, - uint64_t *zSig0Ptr, - uint64_t *zSig1Ptr - ) -{ - int8_t shiftCount; - - if ( aSig0 == 0 ) { - shiftCount = clz64(aSig1) - 15; - if ( shiftCount < 0 ) { - *zSig0Ptr = aSig1>>( - shiftCount ); - *zSig1Ptr = aSig1<<( shiftCount & 63 ); - } - else { - *zSig0Ptr = aSig1<float_rounding_mode; - roundNearestEven = ( roundingMode == float_round_nearest_even ); - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - increment = ((int64_t)zSig2 < 0); - break; - case float_round_to_zero: - increment = 0; - break; - case float_round_up: - increment = !zSign && zSig2; - break; - case float_round_down: - increment = zSign && zSig2; - break; - case float_round_to_odd: - increment = !(zSig1 & 0x1) && zSig2; - break; - default: - abort(); - } - if ( 0x7FFD <= (uint32_t) zExp ) { - if ( ( 0x7FFD < zExp ) - || ( ( zExp == 0x7FFD ) - && eq128( - UINT64_C(0x0001FFFFFFFFFFFF), - UINT64_C(0xFFFFFFFFFFFFFFFF), - zSig0, - zSig1 - ) - && increment - ) - ) { - float_raise(float_flag_overflow | float_flag_inexact, status); - if ( ( roundingMode == float_round_to_zero ) - || ( zSign && ( roundingMode == float_round_up ) ) - || ( ! zSign && ( roundingMode == float_round_down ) ) - || (roundingMode == float_round_to_odd) - ) { - return - packFloat128( - zSign, - 0x7FFE, - UINT64_C(0x0000FFFFFFFFFFFF), - UINT64_C(0xFFFFFFFFFFFFFFFF) - ); - } - return packFloat128( zSign, 0x7FFF, 0, 0 ); - } - if ( zExp < 0 ) { - if (status->flush_to_zero) { - float_raise(float_flag_output_denormal, status); - return packFloat128(zSign, 0, 0, 0); - } - isTiny = status->tininess_before_rounding - || (zExp < -1) - || !increment - || lt128(zSig0, zSig1, - UINT64_C(0x0001FFFFFFFFFFFF), - UINT64_C(0xFFFFFFFFFFFFFFFF)); - shift128ExtraRightJamming( - zSig0, zSig1, zSig2, - zExp, &zSig0, &zSig1, &zSig2 ); - zExp = 0; - if (isTiny && zSig2) { - float_raise(float_flag_underflow, status); - } - switch (roundingMode) { - case float_round_nearest_even: - case float_round_ties_away: - increment = ((int64_t)zSig2 < 0); - break; - case float_round_to_zero: - increment = 0; - break; - case float_round_up: - increment = !zSign && zSig2; - break; - case float_round_down: - increment = zSign && zSig2; - break; - case float_round_to_odd: - increment = !(zSig1 & 0x1) && zSig2; - break; - default: - abort(); - } - } - } - if (zSig2) { - status->float_exception_flags |= float_flag_inexact; - } - if ( increment ) { - add128( zSig0, zSig1, 0, 1, &zSig0, &zSig1 ); - if ((zSig2 + zSig2 == 0) && roundNearestEven) { - zSig1 &= ~1; - } - } - else { - if ( ( zSig0 | zSig1 ) == 0 ) zExp = 0; - } - return packFloat128( zSign, zExp, zSig0, zSig1 ); - -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and significand formed by the concatenation of `zSig0' and `zSig1', and -| returns the proper quadruple-precision floating-point value corresponding -| to the abstract input. This routine is just like `roundAndPackFloat128' -| except that the input significand has fewer bits and does not have to be -| normalized. In all cases, `zExp' must be 1 less than the ``true'' floating- -| point exponent. -*----------------------------------------------------------------------------*/ - -static float128 normalizeRoundAndPackFloat128(bool zSign, int32_t zExp, - uint64_t zSig0, uint64_t zSig1, - float_status *status) -{ - int8_t shiftCount; - uint64_t zSig2; - - if ( zSig0 == 0 ) { - zSig0 = zSig1; - zSig1 = 0; - zExp -= 64; - } - shiftCount = clz64(zSig0) - 15; - if ( 0 <= shiftCount ) { - zSig2 = 0; - shortShift128Left( zSig0, zSig1, shiftCount, &zSig0, &zSig1 ); - } - else { - shift128ExtraRightJamming( - zSig0, zSig1, 0, - shiftCount, &zSig0, &zSig1, &zSig2 ); - } - zExp -= shiftCount; - return roundAndPackFloat128(zSign, zExp, zSig0, zSig1, zSig2, status); - -} - - -/*---------------------------------------------------------------------------- -| Returns the result of converting the 32-bit two's complement integer `a' -| to the extended double-precision floating-point format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 int32_to_floatx80(int32_t a, float_status *status) -{ - bool zSign; - uint32_t absA; - int8_t shiftCount; - uint64_t zSig; - - if ( a == 0 ) return packFloatx80( 0, 0, 0 ); - zSign = ( a < 0 ); - absA = zSign ? - a : a; - shiftCount = clz32(absA) + 32; - zSig = absA; - return packFloatx80( zSign, 0x403E - shiftCount, zSig<>= 1; - } - q = ( bSig <= aSig ); - if ( q ) aSig -= bSig; - if ( 0 < expDiff ) { - q = ( ( (uint64_t) aSig )<<32 ) / bSig; - q >>= 32 - expDiff; - bSig >>= 2; - aSig = ( ( aSig>>1 )<<( expDiff - 1 ) ) - bSig * q; - } - else { - aSig >>= 2; - bSig >>= 2; - } - } - else { - if ( bSig <= aSig ) aSig -= bSig; - aSig64 = ( (uint64_t) aSig )<<40; - bSig64 = ( (uint64_t) bSig )<<40; - expDiff -= 64; - while ( 0 < expDiff ) { - q64 = estimateDiv128To64( aSig64, 0, bSig64 ); - q64 = ( 2 < q64 ) ? q64 - 2 : 0; - aSig64 = - ( ( bSig * q64 )<<38 ); - expDiff -= 62; - } - expDiff += 64; - q64 = estimateDiv128To64( aSig64, 0, bSig64 ); - q64 = ( 2 < q64 ) ? q64 - 2 : 0; - q = q64>>( 64 - expDiff ); - bSig <<= 6; - aSig = ( ( aSig64>>33 )<<( expDiff - 1 ) ) - bSig * q; - } - do { - alternateASig = aSig; - ++q; - aSig -= bSig; - } while ( 0 <= (int32_t) aSig ); - sigMean = aSig + alternateASig; - if ( ( sigMean < 0 ) || ( ( sigMean == 0 ) && ( q & 1 ) ) ) { - aSig = alternateASig; - } - zSign = ( (int32_t) aSig < 0 ); - if ( zSign ) aSig = - aSig; - return normalizeRoundAndPackFloat32(aSign ^ zSign, bExp, aSig, status); -} - - - /*---------------------------------------------------------------------------- | Returns the binary exponential of the single-precision floating-point value | `a'. The operation is performed according to the IEC/IEEE Standard for @@ -5080,576 +4800,40 @@ static const float64 float32_exp2_coefficients[15] = float32 float32_exp2(float32 a, float_status *status) { - bool aSign; - int aExp; - uint32_t aSig; - float64 r, x, xn; + FloatParts64 xp, xnp, tp, rp; int i; - a = float32_squash_input_denormal(a, status); - aSig = extractFloat32Frac( a ); - aExp = extractFloat32Exp( a ); - aSign = extractFloat32Sign( a ); - - if ( aExp == 0xFF) { - if (aSig) { - return propagateFloat32NaN(a, float32_zero, status); + float32_unpack_canonical(&xp, a, status); + if (unlikely(xp.cls != float_class_normal)) { + switch (xp.cls) { + case float_class_snan: + case float_class_qnan: + parts_return_nan(&xp, status); + return float32_round_pack_canonical(&xp, status); + case float_class_inf: + return xp.sign ? float32_zero : a; + case float_class_zero: + return float32_one; + default: + break; } - return (aSign) ? float32_zero : a; - } - if (aExp == 0) { - if (aSig == 0) return float32_one; + g_assert_not_reached(); } float_raise(float_flag_inexact, status); - /* ******************************* */ - /* using float64 for approximation */ - /* ******************************* */ - x = float32_to_float64(a, status); - x = float64_mul(x, float64_ln2, status); + float64_unpack_canonical(&tp, float64_ln2, status); + xp = *parts_mul(&xp, &tp, status); + xnp = xp; - xn = x; - r = float64_one; + float64_unpack_canonical(&rp, float64_one, status); for (i = 0 ; i < 15 ; i++) { - float64 f; - - f = float64_mul(xn, float32_exp2_coefficients[i], status); - r = float64_add(r, f, status); - - xn = float64_mul(xn, x, status); + float64_unpack_canonical(&tp, float32_exp2_coefficients[i], status); + rp = *parts_muladd(&tp, &xp, &rp, 0, status); + xnp = *parts_mul(&xnp, &xp, status); } - return float64_to_float32(r, status); -} - -/*---------------------------------------------------------------------------- -| Returns the binary log of the single-precision floating-point value `a'. -| The operation is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ -float32 float32_log2(float32 a, float_status *status) -{ - bool aSign, zSign; - int aExp; - uint32_t aSig, zSig, i; - - a = float32_squash_input_denormal(a, status); - aSig = extractFloat32Frac( a ); - aExp = extractFloat32Exp( a ); - aSign = extractFloat32Sign( a ); - - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloat32( 1, 0xFF, 0 ); - normalizeFloat32Subnormal( aSig, &aExp, &aSig ); - } - if ( aSign ) { - float_raise(float_flag_invalid, status); - return float32_default_nan(status); - } - if ( aExp == 0xFF ) { - if (aSig) { - return propagateFloat32NaN(a, float32_zero, status); - } - return a; - } - - aExp -= 0x7F; - aSig |= 0x00800000; - zSign = aExp < 0; - zSig = aExp << 23; - - for (i = 1 << 22; i > 0; i >>= 1) { - aSig = ( (uint64_t)aSig * aSig ) >> 23; - if ( aSig & 0x01000000 ) { - aSig >>= 1; - zSig |= i; - } - } - - if ( zSign ) - zSig = -zSig; - - return normalizeRoundAndPackFloat32(zSign, 0x85, zSig, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the double-precision floating-point value -| `a' to the extended double-precision floating-point format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 float64_to_floatx80(float64 a, float_status *status) -{ - bool aSign; - int aExp; - uint64_t aSig; - - a = float64_squash_input_denormal(a, status); - aSig = extractFloat64Frac( a ); - aExp = extractFloat64Exp( a ); - aSign = extractFloat64Sign( a ); - if ( aExp == 0x7FF ) { - if (aSig) { - floatx80 res = commonNaNToFloatx80(float64ToCommonNaN(a, status), - status); - return floatx80_silence_nan(res, status); - } - return packFloatx80(aSign, - floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloatx80( aSign, 0, 0 ); - normalizeFloat64Subnormal( aSig, &aExp, &aSig ); - } - return - packFloatx80( - aSign, aExp + 0x3C00, (aSig | UINT64_C(0x0010000000000000)) << 11); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the double-precision floating-point value -| `a' to the quadruple-precision floating-point format. The conversion is -| performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 float64_to_float128(float64 a, float_status *status) -{ - bool aSign; - int aExp; - uint64_t aSig, zSig0, zSig1; - - a = float64_squash_input_denormal(a, status); - aSig = extractFloat64Frac( a ); - aExp = extractFloat64Exp( a ); - aSign = extractFloat64Sign( a ); - if ( aExp == 0x7FF ) { - if (aSig) { - return commonNaNToFloat128(float64ToCommonNaN(a, status), status); - } - return packFloat128( aSign, 0x7FFF, 0, 0 ); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloat128( aSign, 0, 0, 0 ); - normalizeFloat64Subnormal( aSig, &aExp, &aSig ); - --aExp; - } - shift128Right( aSig, 0, 4, &zSig0, &zSig1 ); - return packFloat128( aSign, aExp + 0x3C00, zSig0, zSig1 ); - -} - - -/*---------------------------------------------------------------------------- -| Returns the remainder of the double-precision floating-point value `a' -| with respect to the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float64 float64_rem(float64 a, float64 b, float_status *status) -{ - bool aSign, zSign; - int aExp, bExp, expDiff; - uint64_t aSig, bSig; - uint64_t q, alternateASig; - int64_t sigMean; - - a = float64_squash_input_denormal(a, status); - b = float64_squash_input_denormal(b, status); - aSig = extractFloat64Frac( a ); - aExp = extractFloat64Exp( a ); - aSign = extractFloat64Sign( a ); - bSig = extractFloat64Frac( b ); - bExp = extractFloat64Exp( b ); - if ( aExp == 0x7FF ) { - if ( aSig || ( ( bExp == 0x7FF ) && bSig ) ) { - return propagateFloat64NaN(a, b, status); - } - float_raise(float_flag_invalid, status); - return float64_default_nan(status); - } - if ( bExp == 0x7FF ) { - if (bSig) { - return propagateFloat64NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) { - if ( bSig == 0 ) { - float_raise(float_flag_invalid, status); - return float64_default_nan(status); - } - normalizeFloat64Subnormal( bSig, &bExp, &bSig ); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return a; - normalizeFloat64Subnormal( aSig, &aExp, &aSig ); - } - expDiff = aExp - bExp; - aSig = (aSig | UINT64_C(0x0010000000000000)) << 11; - bSig = (bSig | UINT64_C(0x0010000000000000)) << 11; - if ( expDiff < 0 ) { - if ( expDiff < -1 ) return a; - aSig >>= 1; - } - q = ( bSig <= aSig ); - if ( q ) aSig -= bSig; - expDiff -= 64; - while ( 0 < expDiff ) { - q = estimateDiv128To64( aSig, 0, bSig ); - q = ( 2 < q ) ? q - 2 : 0; - aSig = - ( ( bSig>>2 ) * q ); - expDiff -= 62; - } - expDiff += 64; - if ( 0 < expDiff ) { - q = estimateDiv128To64( aSig, 0, bSig ); - q = ( 2 < q ) ? q - 2 : 0; - q >>= 64 - expDiff; - bSig >>= 2; - aSig = ( ( aSig>>1 )<<( expDiff - 1 ) ) - bSig * q; - } - else { - aSig >>= 2; - bSig >>= 2; - } - do { - alternateASig = aSig; - ++q; - aSig -= bSig; - } while ( 0 <= (int64_t) aSig ); - sigMean = aSig + alternateASig; - if ( ( sigMean < 0 ) || ( ( sigMean == 0 ) && ( q & 1 ) ) ) { - aSig = alternateASig; - } - zSign = ( (int64_t) aSig < 0 ); - if ( zSign ) aSig = - aSig; - return normalizeRoundAndPackFloat64(aSign ^ zSign, bExp, aSig, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the binary log of the double-precision floating-point value `a'. -| The operation is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ -float64 float64_log2(float64 a, float_status *status) -{ - bool aSign, zSign; - int aExp; - uint64_t aSig, aSig0, aSig1, zSig, i; - a = float64_squash_input_denormal(a, status); - - aSig = extractFloat64Frac( a ); - aExp = extractFloat64Exp( a ); - aSign = extractFloat64Sign( a ); - - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloat64( 1, 0x7FF, 0 ); - normalizeFloat64Subnormal( aSig, &aExp, &aSig ); - } - if ( aSign ) { - float_raise(float_flag_invalid, status); - return float64_default_nan(status); - } - if ( aExp == 0x7FF ) { - if (aSig) { - return propagateFloat64NaN(a, float64_zero, status); - } - return a; - } - - aExp -= 0x3FF; - aSig |= UINT64_C(0x0010000000000000); - zSign = aExp < 0; - zSig = (uint64_t)aExp << 52; - for (i = 1LL << 51; i > 0; i >>= 1) { - mul64To128( aSig, aSig, &aSig0, &aSig1 ); - aSig = ( aSig0 << 12 ) | ( aSig1 >> 52 ); - if ( aSig & UINT64_C(0x0020000000000000) ) { - aSig >>= 1; - zSig |= i; - } - } - - if ( zSign ) - zSig = -zSig; - return normalizeRoundAndPackFloat64(zSign, 0x408, zSig, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the 32-bit two's complement integer format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic---which means in particular that the conversion -| is rounded according to the current rounding mode. If `a' is a NaN, the -| largest positive integer is returned. Otherwise, if the conversion -| overflows, the largest integer with the same sign as `a' is returned. -*----------------------------------------------------------------------------*/ - -int32_t floatx80_to_int32(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1 << 31; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( ( aExp == 0x7FFF ) && (uint64_t) ( aSig<<1 ) ) aSign = 0; - shiftCount = 0x4037 - aExp; - if ( shiftCount <= 0 ) shiftCount = 1; - shift64RightJamming( aSig, shiftCount, &aSig ); - return roundAndPackInt32(aSign, aSig, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the 32-bit two's complement integer format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic, except that the conversion is always rounded -| toward zero. If `a' is a NaN, the largest positive integer is returned. -| Otherwise, if the conversion overflows, the largest integer with the same -| sign as `a' is returned. -*----------------------------------------------------------------------------*/ - -int32_t floatx80_to_int32_round_to_zero(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig, savedASig; - int32_t z; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1 << 31; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( 0x401E < aExp ) { - if ( ( aExp == 0x7FFF ) && (uint64_t) ( aSig<<1 ) ) aSign = 0; - goto invalid; - } - else if ( aExp < 0x3FFF ) { - if (aExp || aSig) { - status->float_exception_flags |= float_flag_inexact; - } - return 0; - } - shiftCount = 0x403E - aExp; - savedASig = aSig; - aSig >>= shiftCount; - z = aSig; - if ( aSign ) z = - z; - if ( ( z < 0 ) ^ aSign ) { - invalid: - float_raise(float_flag_invalid, status); - return aSign ? (int32_t) 0x80000000 : 0x7FFFFFFF; - } - if ( ( aSig<float_exception_flags |= float_flag_inexact; - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the 64-bit two's complement integer format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic---which means in particular that the conversion -| is rounded according to the current rounding mode. If `a' is a NaN, -| the largest positive integer is returned. Otherwise, if the conversion -| overflows, the largest integer with the same sign as `a' is returned. -*----------------------------------------------------------------------------*/ - -int64_t floatx80_to_int64(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig, aSigExtra; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1ULL << 63; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - shiftCount = 0x403E - aExp; - if ( shiftCount <= 0 ) { - if ( shiftCount ) { - float_raise(float_flag_invalid, status); - if (!aSign || floatx80_is_any_nan(a)) { - return INT64_MAX; - } - return INT64_MIN; - } - aSigExtra = 0; - } - else { - shift64ExtraRightJamming( aSig, 0, shiftCount, &aSig, &aSigExtra ); - } - return roundAndPackInt64(aSign, aSig, aSigExtra, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the 64-bit two's complement integer format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic, except that the conversion is always rounded -| toward zero. If `a' is a NaN, the largest positive integer is returned. -| Otherwise, if the conversion overflows, the largest integer with the same -| sign as `a' is returned. -*----------------------------------------------------------------------------*/ - -int64_t floatx80_to_int64_round_to_zero(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig; - int64_t z; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return 1ULL << 63; - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - shiftCount = aExp - 0x403E; - if ( 0 <= shiftCount ) { - aSig &= UINT64_C(0x7FFFFFFFFFFFFFFF); - if ( ( a.high != 0xC03E ) || aSig ) { - float_raise(float_flag_invalid, status); - if ( ! aSign || ( ( aExp == 0x7FFF ) && aSig ) ) { - return INT64_MAX; - } - } - return INT64_MIN; - } - else if ( aExp < 0x3FFF ) { - if (aExp | aSig) { - status->float_exception_flags |= float_flag_inexact; - } - return 0; - } - z = aSig>>( - shiftCount ); - if ( (uint64_t) ( aSig<<( shiftCount & 63 ) ) ) { - status->float_exception_flags |= float_flag_inexact; - } - if ( aSign ) z = - z; - return z; - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the single-precision floating-point format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float32 floatx80_to_float32(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return float32_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( aSig<<1 ) ) { - float32 res = commonNaNToFloat32(floatx80ToCommonNaN(a, status), - status); - return float32_silence_nan(res, status); - } - return packFloat32( aSign, 0xFF, 0 ); - } - shift64RightJamming( aSig, 33, &aSig ); - if ( aExp || aSig ) aExp -= 0x3F81; - return roundAndPackFloat32(aSign, aExp, aSig, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the double-precision floating-point format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float64 floatx80_to_float64(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig, zSig; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return float64_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( aSig<<1 ) ) { - float64 res = commonNaNToFloat64(floatx80ToCommonNaN(a, status), - status); - return float64_silence_nan(res, status); - } - return packFloat64( aSign, 0x7FF, 0 ); - } - shift64RightJamming( aSig, 1, &zSig ); - if ( aExp || aSig ) aExp -= 0x3C01; - return roundAndPackFloat64(aSign, aExp, zSig, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the extended double-precision floating- -| point value `a' to the quadruple-precision floating-point format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 floatx80_to_float128(floatx80 a, float_status *status) -{ - bool aSign; - int aExp; - uint64_t aSig, zSig0, zSig1; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return float128_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( ( aExp == 0x7FFF ) && (uint64_t) ( aSig<<1 ) ) { - float128 res = commonNaNToFloat128(floatx80ToCommonNaN(a, status), - status); - return float128_silence_nan(res, status); - } - shift128Right( aSig<<1, 0, 16, &zSig0, &zSig1 ); - return packFloat128( aSign, aExp, zSig0, zSig1 ); - + return float32_round_pack_canonical(&rp, status); } /*---------------------------------------------------------------------------- @@ -5662,1978 +4846,12 @@ float128 floatx80_to_float128(floatx80 a, float_status *status) floatx80 floatx80_round(floatx80 a, float_status *status) { - return roundAndPackFloatx80(status->floatx80_rounding_precision, - extractFloatx80Sign(a), - extractFloatx80Exp(a), - extractFloatx80Frac(a), 0, status); -} + FloatParts128 p; -/*---------------------------------------------------------------------------- -| Rounds the extended double-precision floating-point value `a' to an integer, -| and returns the result as an extended quadruple-precision floating-point -| value. The operation is performed according to the IEC/IEEE Standard for -| Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_round_to_int(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t lastBitMask, roundBitsMask; - floatx80 z; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); + if (!floatx80_unpack_canonical(&p, a, status)) { return floatx80_default_nan(status); } - aExp = extractFloatx80Exp( a ); - if ( 0x403E <= aExp ) { - if ( ( aExp == 0x7FFF ) && (uint64_t) ( extractFloatx80Frac( a )<<1 ) ) { - return propagateFloatx80NaN(a, a, status); - } - return a; - } - if ( aExp < 0x3FFF ) { - if ( ( aExp == 0 ) - && ( (uint64_t) ( extractFloatx80Frac( a ) ) == 0 ) ) { - return a; - } - status->float_exception_flags |= float_flag_inexact; - aSign = extractFloatx80Sign( a ); - switch (status->float_rounding_mode) { - case float_round_nearest_even: - if ( ( aExp == 0x3FFE ) && (uint64_t) ( extractFloatx80Frac( a )<<1 ) - ) { - return - packFloatx80( aSign, 0x3FFF, UINT64_C(0x8000000000000000)); - } - break; - case float_round_ties_away: - if (aExp == 0x3FFE) { - return packFloatx80(aSign, 0x3FFF, UINT64_C(0x8000000000000000)); - } - break; - case float_round_down: - return - aSign ? - packFloatx80( 1, 0x3FFF, UINT64_C(0x8000000000000000)) - : packFloatx80( 0, 0, 0 ); - case float_round_up: - return - aSign ? packFloatx80( 1, 0, 0 ) - : packFloatx80( 0, 0x3FFF, UINT64_C(0x8000000000000000)); - - case float_round_to_zero: - break; - default: - g_assert_not_reached(); - } - return packFloatx80( aSign, 0, 0 ); - } - lastBitMask = 1; - lastBitMask <<= 0x403E - aExp; - roundBitsMask = lastBitMask - 1; - z = a; - switch (status->float_rounding_mode) { - case float_round_nearest_even: - z.low += lastBitMask>>1; - if ((z.low & roundBitsMask) == 0) { - z.low &= ~lastBitMask; - } - break; - case float_round_ties_away: - z.low += lastBitMask >> 1; - break; - case float_round_to_zero: - break; - case float_round_up: - if (!extractFloatx80Sign(z)) { - z.low += roundBitsMask; - } - break; - case float_round_down: - if (extractFloatx80Sign(z)) { - z.low += roundBitsMask; - } - break; - default: - abort(); - } - z.low &= ~ roundBitsMask; - if ( z.low == 0 ) { - ++z.high; - z.low = UINT64_C(0x8000000000000000); - } - if (z.low != a.low) { - status->float_exception_flags |= float_flag_inexact; - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Returns the result of adding the absolute values of the extended double- -| precision floating-point values `a' and `b'. If `zSign' is 1, the sum is -| negated before being returned. `zSign' is ignored if the result is a NaN. -| The addition is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static floatx80 addFloatx80Sigs(floatx80 a, floatx80 b, bool zSign, - float_status *status) -{ - int32_t aExp, bExp, zExp; - uint64_t aSig, bSig, zSig0, zSig1; - int32_t expDiff; - - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - expDiff = aExp - bExp; - if ( 0 < expDiff ) { - if ( aExp == 0x7FFF ) { - if ((uint64_t)(aSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) --expDiff; - shift64ExtraRightJamming( bSig, 0, expDiff, &bSig, &zSig1 ); - zExp = aExp; - } - else if ( expDiff < 0 ) { - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return packFloatx80(zSign, - floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) ++expDiff; - shift64ExtraRightJamming( aSig, 0, - expDiff, &aSig, &zSig1 ); - zExp = bExp; - } - else { - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( ( aSig | bSig )<<1 ) ) { - return propagateFloatx80NaN(a, b, status); - } - return a; - } - zSig1 = 0; - zSig0 = aSig + bSig; - if ( aExp == 0 ) { - if ((aSig | bSig) & UINT64_C(0x8000000000000000) && zSig0 < aSig) { - /* At least one of the values is a pseudo-denormal, - * and there is a carry out of the result. */ - zExp = 1; - goto shiftRight1; - } - if (zSig0 == 0) { - return packFloatx80(zSign, 0, 0); - } - normalizeFloatx80Subnormal( zSig0, &zExp, &zSig0 ); - goto roundAndPack; - } - zExp = aExp; - goto shiftRight1; - } - zSig0 = aSig + bSig; - if ( (int64_t) zSig0 < 0 ) goto roundAndPack; - shiftRight1: - shift64ExtraRightJamming( zSig0, zSig1, 1, &zSig0, &zSig1 ); - zSig0 |= UINT64_C(0x8000000000000000); - ++zExp; - roundAndPack: - return roundAndPackFloatx80(status->floatx80_rounding_precision, - zSign, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of subtracting the absolute values of the extended -| double-precision floating-point values `a' and `b'. If `zSign' is 1, the -| difference is negated before being returned. `zSign' is ignored if the -| result is a NaN. The subtraction is performed according to the IEC/IEEE -| Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static floatx80 subFloatx80Sigs(floatx80 a, floatx80 b, bool zSign, - float_status *status) -{ - int32_t aExp, bExp, zExp; - uint64_t aSig, bSig, zSig0, zSig1; - int32_t expDiff; - - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - expDiff = aExp - bExp; - if ( 0 < expDiff ) goto aExpBigger; - if ( expDiff < 0 ) goto bExpBigger; - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( ( aSig | bSig )<<1 ) ) { - return propagateFloatx80NaN(a, b, status); - } - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - if ( aExp == 0 ) { - aExp = 1; - bExp = 1; - } - zSig1 = 0; - if ( bSig < aSig ) goto aBigger; - if ( aSig < bSig ) goto bBigger; - return packFloatx80(status->float_rounding_mode == float_round_down, 0, 0); - bExpBigger: - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return packFloatx80(zSign ^ 1, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) ++expDiff; - shift128RightJamming( aSig, 0, - expDiff, &aSig, &zSig1 ); - bBigger: - sub128( bSig, 0, aSig, zSig1, &zSig0, &zSig1 ); - zExp = bExp; - zSign ^= 1; - goto normalizeRoundAndPack; - aExpBigger: - if ( aExp == 0x7FFF ) { - if ((uint64_t)(aSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) --expDiff; - shift128RightJamming( bSig, 0, expDiff, &bSig, &zSig1 ); - aBigger: - sub128( aSig, 0, bSig, zSig1, &zSig0, &zSig1 ); - zExp = aExp; - normalizeRoundAndPack: - return normalizeRoundAndPackFloatx80(status->floatx80_rounding_precision, - zSign, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of adding the extended double-precision floating-point -| values `a' and `b'. The operation is performed according to the IEC/IEEE -| Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_add(floatx80 a, floatx80 b, float_status *status) -{ - bool aSign, bSign; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSign = extractFloatx80Sign( a ); - bSign = extractFloatx80Sign( b ); - if ( aSign == bSign ) { - return addFloatx80Sigs(a, b, aSign, status); - } - else { - return subFloatx80Sigs(a, b, aSign, status); - } - -} - -/*---------------------------------------------------------------------------- -| Returns the result of subtracting the extended double-precision floating- -| point values `a' and `b'. The operation is performed according to the -| IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_sub(floatx80 a, floatx80 b, float_status *status) -{ - bool aSign, bSign; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSign = extractFloatx80Sign( a ); - bSign = extractFloatx80Sign( b ); - if ( aSign == bSign ) { - return subFloatx80Sigs(a, b, aSign, status); - } - else { - return addFloatx80Sigs(a, b, aSign, status); - } - -} - -/*---------------------------------------------------------------------------- -| Returns the result of multiplying the extended double-precision floating- -| point values `a' and `b'. The operation is performed according to the -| IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_mul(floatx80 a, floatx80 b, float_status *status) -{ - bool aSign, bSign, zSign; - int32_t aExp, bExp, zExp; - uint64_t aSig, bSig, zSig0, zSig1; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - bSign = extractFloatx80Sign( b ); - zSign = aSign ^ bSign; - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( aSig<<1 ) - || ( ( bExp == 0x7FFF ) && (uint64_t) ( bSig<<1 ) ) ) { - return propagateFloatx80NaN(a, b, status); - } - if ( ( bExp | bSig ) == 0 ) goto invalid; - return packFloatx80(zSign, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - if ( ( aExp | aSig ) == 0 ) { - invalid: - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - return packFloatx80(zSign, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloatx80( zSign, 0, 0 ); - normalizeFloatx80Subnormal( aSig, &aExp, &aSig ); - } - if ( bExp == 0 ) { - if ( bSig == 0 ) return packFloatx80( zSign, 0, 0 ); - normalizeFloatx80Subnormal( bSig, &bExp, &bSig ); - } - zExp = aExp + bExp - 0x3FFE; - mul64To128( aSig, bSig, &zSig0, &zSig1 ); - if ( 0 < (int64_t) zSig0 ) { - shortShift128Left( zSig0, zSig1, 1, &zSig0, &zSig1 ); - --zExp; - } - return roundAndPackFloatx80(status->floatx80_rounding_precision, - zSign, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of dividing the extended double-precision floating-point -| value `a' by the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_div(floatx80 a, floatx80 b, float_status *status) -{ - bool aSign, bSign, zSign; - int32_t aExp, bExp, zExp; - uint64_t aSig, bSig, zSig0, zSig1; - uint64_t rem0, rem1, rem2, term0, term1, term2; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - bSign = extractFloatx80Sign( b ); - zSign = aSign ^ bSign; - if ( aExp == 0x7FFF ) { - if ((uint64_t)(aSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - goto invalid; - } - return packFloatx80(zSign, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - return packFloatx80( zSign, 0, 0 ); - } - if ( bExp == 0 ) { - if ( bSig == 0 ) { - if ( ( aExp | aSig ) == 0 ) { - invalid: - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - float_raise(float_flag_divbyzero, status); - return packFloatx80(zSign, floatx80_infinity_high, - floatx80_infinity_low); - } - normalizeFloatx80Subnormal( bSig, &bExp, &bSig ); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloatx80( zSign, 0, 0 ); - normalizeFloatx80Subnormal( aSig, &aExp, &aSig ); - } - zExp = aExp - bExp + 0x3FFE; - rem1 = 0; - if ( bSig <= aSig ) { - shift128Right( aSig, 0, 1, &aSig, &rem1 ); - ++zExp; - } - zSig0 = estimateDiv128To64( aSig, rem1, bSig ); - mul64To128( bSig, zSig0, &term0, &term1 ); - sub128( aSig, rem1, term0, term1, &rem0, &rem1 ); - while ( (int64_t) rem0 < 0 ) { - --zSig0; - add128( rem0, rem1, 0, bSig, &rem0, &rem1 ); - } - zSig1 = estimateDiv128To64( rem1, 0, bSig ); - if ( (uint64_t) ( zSig1<<1 ) <= 8 ) { - mul64To128( bSig, zSig1, &term1, &term2 ); - sub128( rem1, 0, term1, term2, &rem1, &rem2 ); - while ( (int64_t) rem1 < 0 ) { - --zSig1; - add128( rem1, rem2, 0, bSig, &rem1, &rem2 ); - } - zSig1 |= ( ( rem1 | rem2 ) != 0 ); - } - return roundAndPackFloatx80(status->floatx80_rounding_precision, - zSign, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the remainder of the extended double-precision floating-point value -| `a' with respect to the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic, -| if 'mod' is false; if 'mod' is true, return the remainder based on truncating -| the quotient toward zero instead. '*quotient' is set to the low 64 bits of -| the absolute value of the integer quotient. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_modrem(floatx80 a, floatx80 b, bool mod, uint64_t *quotient, - float_status *status) -{ - bool aSign, zSign; - int32_t aExp, bExp, expDiff, aExpOrig; - uint64_t aSig0, aSig1, bSig; - uint64_t q, term0, term1, alternateASig0, alternateASig1; - - *quotient = 0; - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSig0 = extractFloatx80Frac( a ); - aExpOrig = aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - bSig = extractFloatx80Frac( b ); - bExp = extractFloatx80Exp( b ); - if ( aExp == 0x7FFF ) { - if ( (uint64_t) ( aSig0<<1 ) - || ( ( bExp == 0x7FFF ) && (uint64_t) ( bSig<<1 ) ) ) { - return propagateFloatx80NaN(a, b, status); - } - goto invalid; - } - if ( bExp == 0x7FFF ) { - if ((uint64_t)(bSig << 1)) { - return propagateFloatx80NaN(a, b, status); - } - if (aExp == 0 && aSig0 >> 63) { - /* - * Pseudo-denormal argument must be returned in normalized - * form. - */ - return packFloatx80(aSign, 1, aSig0); - } - return a; - } - if ( bExp == 0 ) { - if ( bSig == 0 ) { - invalid: - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - normalizeFloatx80Subnormal( bSig, &bExp, &bSig ); - } - if ( aExp == 0 ) { - if ( aSig0 == 0 ) return a; - normalizeFloatx80Subnormal( aSig0, &aExp, &aSig0 ); - } - zSign = aSign; - expDiff = aExp - bExp; - aSig1 = 0; - if ( expDiff < 0 ) { - if ( mod || expDiff < -1 ) { - if (aExp == 1 && aExpOrig == 0) { - /* - * Pseudo-denormal argument must be returned in - * normalized form. - */ - return packFloatx80(aSign, aExp, aSig0); - } - return a; - } - shift128Right( aSig0, 0, 1, &aSig0, &aSig1 ); - expDiff = 0; - } - *quotient = q = ( bSig <= aSig0 ); - if ( q ) aSig0 -= bSig; - expDiff -= 64; - while ( 0 < expDiff ) { - q = estimateDiv128To64( aSig0, aSig1, bSig ); - q = ( 2 < q ) ? q - 2 : 0; - mul64To128( bSig, q, &term0, &term1 ); - sub128( aSig0, aSig1, term0, term1, &aSig0, &aSig1 ); - shortShift128Left( aSig0, aSig1, 62, &aSig0, &aSig1 ); - expDiff -= 62; - *quotient <<= 62; - *quotient += q; - } - expDiff += 64; - if ( 0 < expDiff ) { - q = estimateDiv128To64( aSig0, aSig1, bSig ); - q = ( 2 < q ) ? q - 2 : 0; - q >>= 64 - expDiff; - mul64To128( bSig, q<<( 64 - expDiff ), &term0, &term1 ); - sub128( aSig0, aSig1, term0, term1, &aSig0, &aSig1 ); - shortShift128Left( 0, bSig, 64 - expDiff, &term0, &term1 ); - while ( le128( term0, term1, aSig0, aSig1 ) ) { - ++q; - sub128( aSig0, aSig1, term0, term1, &aSig0, &aSig1 ); - } - if (expDiff < 64) { - *quotient <<= expDiff; - } else { - *quotient = 0; - } - *quotient += q; - } - else { - term1 = 0; - term0 = bSig; - } - if (!mod) { - sub128( term0, term1, aSig0, aSig1, &alternateASig0, &alternateASig1 ); - if ( lt128( alternateASig0, alternateASig1, aSig0, aSig1 ) - || ( eq128( alternateASig0, alternateASig1, aSig0, aSig1 ) - && ( q & 1 ) ) - ) { - aSig0 = alternateASig0; - aSig1 = alternateASig1; - zSign = ! zSign; - ++*quotient; - } - } - return - normalizeRoundAndPackFloatx80( - 80, zSign, bExp + expDiff, aSig0, aSig1, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the remainder of the extended double-precision floating-point value -| `a' with respect to the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_rem(floatx80 a, floatx80 b, float_status *status) -{ - uint64_t quotient; - return floatx80_modrem(a, b, false, "ient, status); -} - -/*---------------------------------------------------------------------------- -| Returns the remainder of the extended double-precision floating-point value -| `a' with respect to the corresponding value `b', with the quotient truncated -| toward zero. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_mod(floatx80 a, floatx80 b, float_status *status) -{ - uint64_t quotient; - return floatx80_modrem(a, b, true, "ient, status); -} - -/*---------------------------------------------------------------------------- -| Returns the square root of the extended double-precision floating-point -| value `a'. The operation is performed according to the IEC/IEEE Standard -| for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 floatx80_sqrt(floatx80 a, float_status *status) -{ - bool aSign; - int32_t aExp, zExp; - uint64_t aSig0, aSig1, zSig0, zSig1, doubleZSig0; - uint64_t rem0, rem1, rem2, rem3, term0, term1, term2, term3; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSig0 = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - if ( aExp == 0x7FFF ) { - if ((uint64_t)(aSig0 << 1)) { - return propagateFloatx80NaN(a, a, status); - } - if ( ! aSign ) return a; - goto invalid; - } - if ( aSign ) { - if ( ( aExp | aSig0 ) == 0 ) return a; - invalid: - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - if ( aExp == 0 ) { - if ( aSig0 == 0 ) return packFloatx80( 0, 0, 0 ); - normalizeFloatx80Subnormal( aSig0, &aExp, &aSig0 ); - } - zExp = ( ( aExp - 0x3FFF )>>1 ) + 0x3FFF; - zSig0 = estimateSqrt32( aExp, aSig0>>32 ); - shift128Right( aSig0, 0, 2 + ( aExp & 1 ), &aSig0, &aSig1 ); - zSig0 = estimateDiv128To64( aSig0, aSig1, zSig0<<32 ) + ( zSig0<<30 ); - doubleZSig0 = zSig0<<1; - mul64To128( zSig0, zSig0, &term0, &term1 ); - sub128( aSig0, aSig1, term0, term1, &rem0, &rem1 ); - while ( (int64_t) rem0 < 0 ) { - --zSig0; - doubleZSig0 -= 2; - add128( rem0, rem1, zSig0>>63, doubleZSig0 | 1, &rem0, &rem1 ); - } - zSig1 = estimateDiv128To64( rem1, 0, doubleZSig0 ); - if ( ( zSig1 & UINT64_C(0x3FFFFFFFFFFFFFFF) ) <= 5 ) { - if ( zSig1 == 0 ) zSig1 = 1; - mul64To128( doubleZSig0, zSig1, &term1, &term2 ); - sub128( rem1, 0, term1, term2, &rem1, &rem2 ); - mul64To128( zSig1, zSig1, &term2, &term3 ); - sub192( rem1, rem2, 0, 0, term2, term3, &rem1, &rem2, &rem3 ); - while ( (int64_t) rem1 < 0 ) { - --zSig1; - shortShift128Left( 0, zSig1, 1, &term2, &term3 ); - term3 |= 1; - term2 |= doubleZSig0; - add192( rem1, rem2, rem3, 0, term2, term3, &rem1, &rem2, &rem3 ); - } - zSig1 |= ( ( rem1 | rem2 | rem3 ) != 0 ); - } - shortShift128Left( 0, zSig1, 1, &zSig0, &zSig1 ); - zSig0 |= doubleZSig0; - return roundAndPackFloatx80(status->floatx80_rounding_precision, - 0, zExp, zSig0, zSig1, status); -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point -| value `a' to the 32-bit two's complement integer format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic---which means in particular that the conversion is rounded -| according to the current rounding mode. If `a' is a NaN, the largest -| positive integer is returned. Otherwise, if the conversion overflows, the -| largest integer with the same sign as `a' is returned. -*----------------------------------------------------------------------------*/ - -int32_t float128_to_int32(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig0, aSig1; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( ( aExp == 0x7FFF ) && ( aSig0 | aSig1 ) ) aSign = 0; - if ( aExp ) aSig0 |= UINT64_C(0x0001000000000000); - aSig0 |= ( aSig1 != 0 ); - shiftCount = 0x4028 - aExp; - if ( 0 < shiftCount ) shift64RightJamming( aSig0, shiftCount, &aSig0 ); - return roundAndPackInt32(aSign, aSig0, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point -| value `a' to the 32-bit two's complement integer format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic, except that the conversion is always rounded toward zero. If -| `a' is a NaN, the largest positive integer is returned. Otherwise, if the -| conversion overflows, the largest integer with the same sign as `a' is -| returned. -*----------------------------------------------------------------------------*/ - -int32_t float128_to_int32_round_to_zero(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig0, aSig1, savedASig; - int32_t z; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - aSig0 |= ( aSig1 != 0 ); - if ( 0x401E < aExp ) { - if ( ( aExp == 0x7FFF ) && aSig0 ) aSign = 0; - goto invalid; - } - else if ( aExp < 0x3FFF ) { - if (aExp || aSig0) { - status->float_exception_flags |= float_flag_inexact; - } - return 0; - } - aSig0 |= UINT64_C(0x0001000000000000); - shiftCount = 0x402F - aExp; - savedASig = aSig0; - aSig0 >>= shiftCount; - z = aSig0; - if ( aSign ) z = - z; - if ( ( z < 0 ) ^ aSign ) { - invalid: - float_raise(float_flag_invalid, status); - return aSign ? INT32_MIN : INT32_MAX; - } - if ( ( aSig0<float_exception_flags |= float_flag_inexact; - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point -| value `a' to the 64-bit two's complement integer format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic---which means in particular that the conversion is rounded -| according to the current rounding mode. If `a' is a NaN, the largest -| positive integer is returned. Otherwise, if the conversion overflows, the -| largest integer with the same sign as `a' is returned. -*----------------------------------------------------------------------------*/ - -int64_t float128_to_int64(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig0, aSig1; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( aExp ) aSig0 |= UINT64_C(0x0001000000000000); - shiftCount = 0x402F - aExp; - if ( shiftCount <= 0 ) { - if ( 0x403E < aExp ) { - float_raise(float_flag_invalid, status); - if ( ! aSign - || ( ( aExp == 0x7FFF ) - && ( aSig1 || ( aSig0 != UINT64_C(0x0001000000000000) ) ) - ) - ) { - return INT64_MAX; - } - return INT64_MIN; - } - shortShift128Left( aSig0, aSig1, - shiftCount, &aSig0, &aSig1 ); - } - else { - shift64ExtraRightJamming( aSig0, aSig1, shiftCount, &aSig0, &aSig1 ); - } - return roundAndPackInt64(aSign, aSig0, aSig1, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point -| value `a' to the 64-bit two's complement integer format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic, except that the conversion is always rounded toward zero. -| If `a' is a NaN, the largest positive integer is returned. Otherwise, if -| the conversion overflows, the largest integer with the same sign as `a' is -| returned. -*----------------------------------------------------------------------------*/ - -int64_t float128_to_int64_round_to_zero(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp, shiftCount; - uint64_t aSig0, aSig1; - int64_t z; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( aExp ) aSig0 |= UINT64_C(0x0001000000000000); - shiftCount = aExp - 0x402F; - if ( 0 < shiftCount ) { - if ( 0x403E <= aExp ) { - aSig0 &= UINT64_C(0x0000FFFFFFFFFFFF); - if ( ( a.high == UINT64_C(0xC03E000000000000) ) - && ( aSig1 < UINT64_C(0x0002000000000000) ) ) { - if (aSig1) { - status->float_exception_flags |= float_flag_inexact; - } - } - else { - float_raise(float_flag_invalid, status); - if ( ! aSign || ( ( aExp == 0x7FFF ) && ( aSig0 | aSig1 ) ) ) { - return INT64_MAX; - } - } - return INT64_MIN; - } - z = ( aSig0<>( ( - shiftCount ) & 63 ) ); - if ( (uint64_t) ( aSig1<float_exception_flags |= float_flag_inexact; - } - } - else { - if ( aExp < 0x3FFF ) { - if ( aExp | aSig0 | aSig1 ) { - status->float_exception_flags |= float_flag_inexact; - } - return 0; - } - z = aSig0>>( - shiftCount ); - if ( aSig1 - || ( shiftCount && (uint64_t) ( aSig0<<( shiftCount & 63 ) ) ) ) { - status->float_exception_flags |= float_flag_inexact; - } - } - if ( aSign ) z = - z; - return z; - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point value -| `a' to the 64-bit unsigned integer format. The conversion is -| performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic---which means in particular that the conversion is rounded -| according to the current rounding mode. If `a' is a NaN, the largest -| positive integer is returned. If the conversion overflows, the -| largest unsigned integer is returned. If 'a' is negative, the value is -| rounded and zero is returned; negative values that do not round to zero -| will raise the inexact exception. -*----------------------------------------------------------------------------*/ - -uint64_t float128_to_uint64(float128 a, float_status *status) -{ - bool aSign; - int aExp; - int shiftCount; - uint64_t aSig0, aSig1; - - aSig0 = extractFloat128Frac0(a); - aSig1 = extractFloat128Frac1(a); - aExp = extractFloat128Exp(a); - aSign = extractFloat128Sign(a); - if (aSign && (aExp > 0x3FFE)) { - float_raise(float_flag_invalid, status); - if (float128_is_any_nan(a)) { - return UINT64_MAX; - } else { - return 0; - } - } - if (aExp) { - aSig0 |= UINT64_C(0x0001000000000000); - } - shiftCount = 0x402F - aExp; - if (shiftCount <= 0) { - if (0x403E < aExp) { - float_raise(float_flag_invalid, status); - return UINT64_MAX; - } - shortShift128Left(aSig0, aSig1, -shiftCount, &aSig0, &aSig1); - } else { - shift64ExtraRightJamming(aSig0, aSig1, shiftCount, &aSig0, &aSig1); - } - return roundAndPackUint64(aSign, aSig0, aSig1, status); -} - -uint64_t float128_to_uint64_round_to_zero(float128 a, float_status *status) -{ - uint64_t v; - signed char current_rounding_mode = status->float_rounding_mode; - - set_float_rounding_mode(float_round_to_zero, status); - v = float128_to_uint64(a, status); - set_float_rounding_mode(current_rounding_mode, status); - - return v; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point -| value `a' to the 32-bit unsigned integer format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic except that the conversion is always rounded toward zero. -| If `a' is a NaN, the largest positive integer is returned. Otherwise, -| if the conversion overflows, the largest unsigned integer is returned. -| If 'a' is negative, the value is rounded and zero is returned; negative -| values that do not round to zero will raise the inexact exception. -*----------------------------------------------------------------------------*/ - -uint32_t float128_to_uint32_round_to_zero(float128 a, float_status *status) -{ - uint64_t v; - uint32_t res; - int old_exc_flags = get_float_exception_flags(status); - - v = float128_to_uint64_round_to_zero(a, status); - if (v > 0xffffffff) { - res = 0xffffffff; - } else { - return v; - } - set_float_exception_flags(old_exc_flags, status); - float_raise(float_flag_invalid, status); - return res; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point value -| `a' to the 32-bit unsigned integer format. The conversion is -| performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic---which means in particular that the conversion is rounded -| according to the current rounding mode. If `a' is a NaN, the largest -| positive integer is returned. If the conversion overflows, the -| largest unsigned integer is returned. If 'a' is negative, the value is -| rounded and zero is returned; negative values that do not round to zero -| will raise the inexact exception. -*----------------------------------------------------------------------------*/ - -uint32_t float128_to_uint32(float128 a, float_status *status) -{ - uint64_t v; - uint32_t res; - int old_exc_flags = get_float_exception_flags(status); - - v = float128_to_uint64(a, status); - if (v > 0xffffffff) { - res = 0xffffffff; - } else { - return v; - } - set_float_exception_flags(old_exc_flags, status); - float_raise(float_flag_invalid, status); - return res; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point -| value `a' to the single-precision floating-point format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -float32 float128_to_float32(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig0, aSig1; - uint32_t zSig; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( aExp == 0x7FFF ) { - if ( aSig0 | aSig1 ) { - return commonNaNToFloat32(float128ToCommonNaN(a, status), status); - } - return packFloat32( aSign, 0xFF, 0 ); - } - aSig0 |= ( aSig1 != 0 ); - shift64RightJamming( aSig0, 18, &aSig0 ); - zSig = aSig0; - if ( aExp || zSig ) { - zSig |= 0x40000000; - aExp -= 0x3F81; - } - return roundAndPackFloat32(aSign, aExp, zSig, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point -| value `a' to the double-precision floating-point format. The conversion -| is performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -float64 float128_to_float64(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig0, aSig1; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( aExp == 0x7FFF ) { - if ( aSig0 | aSig1 ) { - return commonNaNToFloat64(float128ToCommonNaN(a, status), status); - } - return packFloat64( aSign, 0x7FF, 0 ); - } - shortShift128Left( aSig0, aSig1, 14, &aSig0, &aSig1 ); - aSig0 |= ( aSig1 != 0 ); - if ( aExp || aSig0 ) { - aSig0 |= UINT64_C(0x4000000000000000); - aExp -= 0x3C01; - } - return roundAndPackFloat64(aSign, aExp, aSig0, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the quadruple-precision floating-point -| value `a' to the extended double-precision floating-point format. The -| conversion is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -floatx80 float128_to_floatx80(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig0, aSig1; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( aExp == 0x7FFF ) { - if ( aSig0 | aSig1 ) { - floatx80 res = commonNaNToFloatx80(float128ToCommonNaN(a, status), - status); - return floatx80_silence_nan(res, status); - } - return packFloatx80(aSign, floatx80_infinity_high, - floatx80_infinity_low); - } - if ( aExp == 0 ) { - if ( ( aSig0 | aSig1 ) == 0 ) return packFloatx80( aSign, 0, 0 ); - normalizeFloat128Subnormal( aSig0, aSig1, &aExp, &aSig0, &aSig1 ); - } - else { - aSig0 |= UINT64_C(0x0001000000000000); - } - shortShift128Left( aSig0, aSig1, 15, &aSig0, &aSig1 ); - return roundAndPackFloatx80(80, aSign, aExp, aSig0, aSig1, status); - -} - -/*---------------------------------------------------------------------------- -| Rounds the quadruple-precision floating-point value `a' to an integer, and -| returns the result as a quadruple-precision floating-point value. The -| operation is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 float128_round_to_int(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t lastBitMask, roundBitsMask; - float128 z; - - aExp = extractFloat128Exp( a ); - if ( 0x402F <= aExp ) { - if ( 0x406F <= aExp ) { - if ( ( aExp == 0x7FFF ) - && ( extractFloat128Frac0( a ) | extractFloat128Frac1( a ) ) - ) { - return propagateFloat128NaN(a, a, status); - } - return a; - } - lastBitMask = 1; - lastBitMask = ( lastBitMask<<( 0x406E - aExp ) )<<1; - roundBitsMask = lastBitMask - 1; - z = a; - switch (status->float_rounding_mode) { - case float_round_nearest_even: - if ( lastBitMask ) { - add128( z.high, z.low, 0, lastBitMask>>1, &z.high, &z.low ); - if ( ( z.low & roundBitsMask ) == 0 ) z.low &= ~ lastBitMask; - } - else { - if ( (int64_t) z.low < 0 ) { - ++z.high; - if ( (uint64_t) ( z.low<<1 ) == 0 ) z.high &= ~1; - } - } - break; - case float_round_ties_away: - if (lastBitMask) { - add128(z.high, z.low, 0, lastBitMask >> 1, &z.high, &z.low); - } else { - if ((int64_t) z.low < 0) { - ++z.high; - } - } - break; - case float_round_to_zero: - break; - case float_round_up: - if (!extractFloat128Sign(z)) { - add128(z.high, z.low, 0, roundBitsMask, &z.high, &z.low); - } - break; - case float_round_down: - if (extractFloat128Sign(z)) { - add128(z.high, z.low, 0, roundBitsMask, &z.high, &z.low); - } - break; - case float_round_to_odd: - /* - * Note that if lastBitMask == 0, the last bit is the lsb - * of high, and roundBitsMask == -1. - */ - if ((lastBitMask ? z.low & lastBitMask : z.high & 1) == 0) { - add128(z.high, z.low, 0, roundBitsMask, &z.high, &z.low); - } - break; - default: - abort(); - } - z.low &= ~ roundBitsMask; - } - else { - if ( aExp < 0x3FFF ) { - if ( ( ( (uint64_t) ( a.high<<1 ) ) | a.low ) == 0 ) return a; - status->float_exception_flags |= float_flag_inexact; - aSign = extractFloat128Sign( a ); - switch (status->float_rounding_mode) { - case float_round_nearest_even: - if ( ( aExp == 0x3FFE ) - && ( extractFloat128Frac0( a ) - | extractFloat128Frac1( a ) ) - ) { - return packFloat128( aSign, 0x3FFF, 0, 0 ); - } - break; - case float_round_ties_away: - if (aExp == 0x3FFE) { - return packFloat128(aSign, 0x3FFF, 0, 0); - } - break; - case float_round_down: - return - aSign ? packFloat128( 1, 0x3FFF, 0, 0 ) - : packFloat128( 0, 0, 0, 0 ); - case float_round_up: - return - aSign ? packFloat128( 1, 0, 0, 0 ) - : packFloat128( 0, 0x3FFF, 0, 0 ); - - case float_round_to_odd: - return packFloat128(aSign, 0x3FFF, 0, 0); - - case float_round_to_zero: - break; - } - return packFloat128( aSign, 0, 0, 0 ); - } - lastBitMask = 1; - lastBitMask <<= 0x402F - aExp; - roundBitsMask = lastBitMask - 1; - z.low = 0; - z.high = a.high; - switch (status->float_rounding_mode) { - case float_round_nearest_even: - z.high += lastBitMask>>1; - if ( ( ( z.high & roundBitsMask ) | a.low ) == 0 ) { - z.high &= ~ lastBitMask; - } - break; - case float_round_ties_away: - z.high += lastBitMask>>1; - break; - case float_round_to_zero: - break; - case float_round_up: - if (!extractFloat128Sign(z)) { - z.high |= ( a.low != 0 ); - z.high += roundBitsMask; - } - break; - case float_round_down: - if (extractFloat128Sign(z)) { - z.high |= (a.low != 0); - z.high += roundBitsMask; - } - break; - case float_round_to_odd: - if ((z.high & lastBitMask) == 0) { - z.high |= (a.low != 0); - z.high += roundBitsMask; - } - break; - default: - abort(); - } - z.high &= ~ roundBitsMask; - } - if ( ( z.low != a.low ) || ( z.high != a.high ) ) { - status->float_exception_flags |= float_flag_inexact; - } - return z; - -} - -/*---------------------------------------------------------------------------- -| Returns the result of adding the absolute values of the quadruple-precision -| floating-point values `a' and `b'. If `zSign' is 1, the sum is negated -| before being returned. `zSign' is ignored if the result is a NaN. -| The addition is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static float128 addFloat128Sigs(float128 a, float128 b, bool zSign, - float_status *status) -{ - int32_t aExp, bExp, zExp; - uint64_t aSig0, aSig1, bSig0, bSig1, zSig0, zSig1, zSig2; - int32_t expDiff; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - bSig1 = extractFloat128Frac1( b ); - bSig0 = extractFloat128Frac0( b ); - bExp = extractFloat128Exp( b ); - expDiff = aExp - bExp; - if ( 0 < expDiff ) { - if ( aExp == 0x7FFF ) { - if (aSig0 | aSig1) { - return propagateFloat128NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) { - --expDiff; - } - else { - bSig0 |= UINT64_C(0x0001000000000000); - } - shift128ExtraRightJamming( - bSig0, bSig1, 0, expDiff, &bSig0, &bSig1, &zSig2 ); - zExp = aExp; - } - else if ( expDiff < 0 ) { - if ( bExp == 0x7FFF ) { - if (bSig0 | bSig1) { - return propagateFloat128NaN(a, b, status); - } - return packFloat128( zSign, 0x7FFF, 0, 0 ); - } - if ( aExp == 0 ) { - ++expDiff; - } - else { - aSig0 |= UINT64_C(0x0001000000000000); - } - shift128ExtraRightJamming( - aSig0, aSig1, 0, - expDiff, &aSig0, &aSig1, &zSig2 ); - zExp = bExp; - } - else { - if ( aExp == 0x7FFF ) { - if ( aSig0 | aSig1 | bSig0 | bSig1 ) { - return propagateFloat128NaN(a, b, status); - } - return a; - } - add128( aSig0, aSig1, bSig0, bSig1, &zSig0, &zSig1 ); - if ( aExp == 0 ) { - if (status->flush_to_zero) { - if (zSig0 | zSig1) { - float_raise(float_flag_output_denormal, status); - } - return packFloat128(zSign, 0, 0, 0); - } - return packFloat128( zSign, 0, zSig0, zSig1 ); - } - zSig2 = 0; - zSig0 |= UINT64_C(0x0002000000000000); - zExp = aExp; - goto shiftRight1; - } - aSig0 |= UINT64_C(0x0001000000000000); - add128( aSig0, aSig1, bSig0, bSig1, &zSig0, &zSig1 ); - --zExp; - if ( zSig0 < UINT64_C(0x0002000000000000) ) goto roundAndPack; - ++zExp; - shiftRight1: - shift128ExtraRightJamming( - zSig0, zSig1, zSig2, 1, &zSig0, &zSig1, &zSig2 ); - roundAndPack: - return roundAndPackFloat128(zSign, zExp, zSig0, zSig1, zSig2, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of subtracting the absolute values of the quadruple- -| precision floating-point values `a' and `b'. If `zSign' is 1, the -| difference is negated before being returned. `zSign' is ignored if the -| result is a NaN. The subtraction is performed according to the IEC/IEEE -| Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static float128 subFloat128Sigs(float128 a, float128 b, bool zSign, - float_status *status) -{ - int32_t aExp, bExp, zExp; - uint64_t aSig0, aSig1, bSig0, bSig1, zSig0, zSig1; - int32_t expDiff; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - bSig1 = extractFloat128Frac1( b ); - bSig0 = extractFloat128Frac0( b ); - bExp = extractFloat128Exp( b ); - expDiff = aExp - bExp; - shortShift128Left( aSig0, aSig1, 14, &aSig0, &aSig1 ); - shortShift128Left( bSig0, bSig1, 14, &bSig0, &bSig1 ); - if ( 0 < expDiff ) goto aExpBigger; - if ( expDiff < 0 ) goto bExpBigger; - if ( aExp == 0x7FFF ) { - if ( aSig0 | aSig1 | bSig0 | bSig1 ) { - return propagateFloat128NaN(a, b, status); - } - float_raise(float_flag_invalid, status); - return float128_default_nan(status); - } - if ( aExp == 0 ) { - aExp = 1; - bExp = 1; - } - if ( bSig0 < aSig0 ) goto aBigger; - if ( aSig0 < bSig0 ) goto bBigger; - if ( bSig1 < aSig1 ) goto aBigger; - if ( aSig1 < bSig1 ) goto bBigger; - return packFloat128(status->float_rounding_mode == float_round_down, - 0, 0, 0); - bExpBigger: - if ( bExp == 0x7FFF ) { - if (bSig0 | bSig1) { - return propagateFloat128NaN(a, b, status); - } - return packFloat128( zSign ^ 1, 0x7FFF, 0, 0 ); - } - if ( aExp == 0 ) { - ++expDiff; - } - else { - aSig0 |= UINT64_C(0x4000000000000000); - } - shift128RightJamming( aSig0, aSig1, - expDiff, &aSig0, &aSig1 ); - bSig0 |= UINT64_C(0x4000000000000000); - bBigger: - sub128( bSig0, bSig1, aSig0, aSig1, &zSig0, &zSig1 ); - zExp = bExp; - zSign ^= 1; - goto normalizeRoundAndPack; - aExpBigger: - if ( aExp == 0x7FFF ) { - if (aSig0 | aSig1) { - return propagateFloat128NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) { - --expDiff; - } - else { - bSig0 |= UINT64_C(0x4000000000000000); - } - shift128RightJamming( bSig0, bSig1, expDiff, &bSig0, &bSig1 ); - aSig0 |= UINT64_C(0x4000000000000000); - aBigger: - sub128( aSig0, aSig1, bSig0, bSig1, &zSig0, &zSig1 ); - zExp = aExp; - normalizeRoundAndPack: - --zExp; - return normalizeRoundAndPackFloat128(zSign, zExp - 14, zSig0, zSig1, - status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of adding the quadruple-precision floating-point values -| `a' and `b'. The operation is performed according to the IEC/IEEE Standard -| for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 float128_add(float128 a, float128 b, float_status *status) -{ - bool aSign, bSign; - - aSign = extractFloat128Sign( a ); - bSign = extractFloat128Sign( b ); - if ( aSign == bSign ) { - return addFloat128Sigs(a, b, aSign, status); - } - else { - return subFloat128Sigs(a, b, aSign, status); - } - -} - -/*---------------------------------------------------------------------------- -| Returns the result of subtracting the quadruple-precision floating-point -| values `a' and `b'. The operation is performed according to the IEC/IEEE -| Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 float128_sub(float128 a, float128 b, float_status *status) -{ - bool aSign, bSign; - - aSign = extractFloat128Sign( a ); - bSign = extractFloat128Sign( b ); - if ( aSign == bSign ) { - return subFloat128Sigs(a, b, aSign, status); - } - else { - return addFloat128Sigs(a, b, aSign, status); - } - -} - -/*---------------------------------------------------------------------------- -| Returns the result of multiplying the quadruple-precision floating-point -| values `a' and `b'. The operation is performed according to the IEC/IEEE -| Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 float128_mul(float128 a, float128 b, float_status *status) -{ - bool aSign, bSign, zSign; - int32_t aExp, bExp, zExp; - uint64_t aSig0, aSig1, bSig0, bSig1, zSig0, zSig1, zSig2, zSig3; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - bSig1 = extractFloat128Frac1( b ); - bSig0 = extractFloat128Frac0( b ); - bExp = extractFloat128Exp( b ); - bSign = extractFloat128Sign( b ); - zSign = aSign ^ bSign; - if ( aExp == 0x7FFF ) { - if ( ( aSig0 | aSig1 ) - || ( ( bExp == 0x7FFF ) && ( bSig0 | bSig1 ) ) ) { - return propagateFloat128NaN(a, b, status); - } - if ( ( bExp | bSig0 | bSig1 ) == 0 ) goto invalid; - return packFloat128( zSign, 0x7FFF, 0, 0 ); - } - if ( bExp == 0x7FFF ) { - if (bSig0 | bSig1) { - return propagateFloat128NaN(a, b, status); - } - if ( ( aExp | aSig0 | aSig1 ) == 0 ) { - invalid: - float_raise(float_flag_invalid, status); - return float128_default_nan(status); - } - return packFloat128( zSign, 0x7FFF, 0, 0 ); - } - if ( aExp == 0 ) { - if ( ( aSig0 | aSig1 ) == 0 ) return packFloat128( zSign, 0, 0, 0 ); - normalizeFloat128Subnormal( aSig0, aSig1, &aExp, &aSig0, &aSig1 ); - } - if ( bExp == 0 ) { - if ( ( bSig0 | bSig1 ) == 0 ) return packFloat128( zSign, 0, 0, 0 ); - normalizeFloat128Subnormal( bSig0, bSig1, &bExp, &bSig0, &bSig1 ); - } - zExp = aExp + bExp - 0x4000; - aSig0 |= UINT64_C(0x0001000000000000); - shortShift128Left( bSig0, bSig1, 16, &bSig0, &bSig1 ); - mul128To256( aSig0, aSig1, bSig0, bSig1, &zSig0, &zSig1, &zSig2, &zSig3 ); - add128( zSig0, zSig1, aSig0, aSig1, &zSig0, &zSig1 ); - zSig2 |= ( zSig3 != 0 ); - if (UINT64_C( 0x0002000000000000) <= zSig0 ) { - shift128ExtraRightJamming( - zSig0, zSig1, zSig2, 1, &zSig0, &zSig1, &zSig2 ); - ++zExp; - } - return roundAndPackFloat128(zSign, zExp, zSig0, zSig1, zSig2, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the result of dividing the quadruple-precision floating-point value -| `a' by the corresponding value `b'. The operation is performed according to -| the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 float128_div(float128 a, float128 b, float_status *status) -{ - bool aSign, bSign, zSign; - int32_t aExp, bExp, zExp; - uint64_t aSig0, aSig1, bSig0, bSig1, zSig0, zSig1, zSig2; - uint64_t rem0, rem1, rem2, rem3, term0, term1, term2, term3; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - bSig1 = extractFloat128Frac1( b ); - bSig0 = extractFloat128Frac0( b ); - bExp = extractFloat128Exp( b ); - bSign = extractFloat128Sign( b ); - zSign = aSign ^ bSign; - if ( aExp == 0x7FFF ) { - if (aSig0 | aSig1) { - return propagateFloat128NaN(a, b, status); - } - if ( bExp == 0x7FFF ) { - if (bSig0 | bSig1) { - return propagateFloat128NaN(a, b, status); - } - goto invalid; - } - return packFloat128( zSign, 0x7FFF, 0, 0 ); - } - if ( bExp == 0x7FFF ) { - if (bSig0 | bSig1) { - return propagateFloat128NaN(a, b, status); - } - return packFloat128( zSign, 0, 0, 0 ); - } - if ( bExp == 0 ) { - if ( ( bSig0 | bSig1 ) == 0 ) { - if ( ( aExp | aSig0 | aSig1 ) == 0 ) { - invalid: - float_raise(float_flag_invalid, status); - return float128_default_nan(status); - } - float_raise(float_flag_divbyzero, status); - return packFloat128( zSign, 0x7FFF, 0, 0 ); - } - normalizeFloat128Subnormal( bSig0, bSig1, &bExp, &bSig0, &bSig1 ); - } - if ( aExp == 0 ) { - if ( ( aSig0 | aSig1 ) == 0 ) return packFloat128( zSign, 0, 0, 0 ); - normalizeFloat128Subnormal( aSig0, aSig1, &aExp, &aSig0, &aSig1 ); - } - zExp = aExp - bExp + 0x3FFD; - shortShift128Left( - aSig0 | UINT64_C(0x0001000000000000), aSig1, 15, &aSig0, &aSig1 ); - shortShift128Left( - bSig0 | UINT64_C(0x0001000000000000), bSig1, 15, &bSig0, &bSig1 ); - if ( le128( bSig0, bSig1, aSig0, aSig1 ) ) { - shift128Right( aSig0, aSig1, 1, &aSig0, &aSig1 ); - ++zExp; - } - zSig0 = estimateDiv128To64( aSig0, aSig1, bSig0 ); - mul128By64To192( bSig0, bSig1, zSig0, &term0, &term1, &term2 ); - sub192( aSig0, aSig1, 0, term0, term1, term2, &rem0, &rem1, &rem2 ); - while ( (int64_t) rem0 < 0 ) { - --zSig0; - add192( rem0, rem1, rem2, 0, bSig0, bSig1, &rem0, &rem1, &rem2 ); - } - zSig1 = estimateDiv128To64( rem1, rem2, bSig0 ); - if ( ( zSig1 & 0x3FFF ) <= 4 ) { - mul128By64To192( bSig0, bSig1, zSig1, &term1, &term2, &term3 ); - sub192( rem1, rem2, 0, term1, term2, term3, &rem1, &rem2, &rem3 ); - while ( (int64_t) rem1 < 0 ) { - --zSig1; - add192( rem1, rem2, rem3, 0, bSig0, bSig1, &rem1, &rem2, &rem3 ); - } - zSig1 |= ( ( rem1 | rem2 | rem3 ) != 0 ); - } - shift128ExtraRightJamming( zSig0, zSig1, 0, 15, &zSig0, &zSig1, &zSig2 ); - return roundAndPackFloat128(zSign, zExp, zSig0, zSig1, zSig2, status); - -} - -/*---------------------------------------------------------------------------- -| Returns the remainder of the quadruple-precision floating-point value `a' -| with respect to the corresponding value `b'. The operation is performed -| according to the IEC/IEEE Standard for Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 float128_rem(float128 a, float128 b, float_status *status) -{ - bool aSign, zSign; - int32_t aExp, bExp, expDiff; - uint64_t aSig0, aSig1, bSig0, bSig1, q, term0, term1, term2; - uint64_t allZero, alternateASig0, alternateASig1, sigMean1; - int64_t sigMean0; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - bSig1 = extractFloat128Frac1( b ); - bSig0 = extractFloat128Frac0( b ); - bExp = extractFloat128Exp( b ); - if ( aExp == 0x7FFF ) { - if ( ( aSig0 | aSig1 ) - || ( ( bExp == 0x7FFF ) && ( bSig0 | bSig1 ) ) ) { - return propagateFloat128NaN(a, b, status); - } - goto invalid; - } - if ( bExp == 0x7FFF ) { - if (bSig0 | bSig1) { - return propagateFloat128NaN(a, b, status); - } - return a; - } - if ( bExp == 0 ) { - if ( ( bSig0 | bSig1 ) == 0 ) { - invalid: - float_raise(float_flag_invalid, status); - return float128_default_nan(status); - } - normalizeFloat128Subnormal( bSig0, bSig1, &bExp, &bSig0, &bSig1 ); - } - if ( aExp == 0 ) { - if ( ( aSig0 | aSig1 ) == 0 ) return a; - normalizeFloat128Subnormal( aSig0, aSig1, &aExp, &aSig0, &aSig1 ); - } - expDiff = aExp - bExp; - if ( expDiff < -1 ) return a; - shortShift128Left( - aSig0 | UINT64_C(0x0001000000000000), - aSig1, - 15 - ( expDiff < 0 ), - &aSig0, - &aSig1 - ); - shortShift128Left( - bSig0 | UINT64_C(0x0001000000000000), bSig1, 15, &bSig0, &bSig1 ); - q = le128( bSig0, bSig1, aSig0, aSig1 ); - if ( q ) sub128( aSig0, aSig1, bSig0, bSig1, &aSig0, &aSig1 ); - expDiff -= 64; - while ( 0 < expDiff ) { - q = estimateDiv128To64( aSig0, aSig1, bSig0 ); - q = ( 4 < q ) ? q - 4 : 0; - mul128By64To192( bSig0, bSig1, q, &term0, &term1, &term2 ); - shortShift192Left( term0, term1, term2, 61, &term1, &term2, &allZero ); - shortShift128Left( aSig0, aSig1, 61, &aSig0, &allZero ); - sub128( aSig0, 0, term1, term2, &aSig0, &aSig1 ); - expDiff -= 61; - } - if ( -64 < expDiff ) { - q = estimateDiv128To64( aSig0, aSig1, bSig0 ); - q = ( 4 < q ) ? q - 4 : 0; - q >>= - expDiff; - shift128Right( bSig0, bSig1, 12, &bSig0, &bSig1 ); - expDiff += 52; - if ( expDiff < 0 ) { - shift128Right( aSig0, aSig1, - expDiff, &aSig0, &aSig1 ); - } - else { - shortShift128Left( aSig0, aSig1, expDiff, &aSig0, &aSig1 ); - } - mul128By64To192( bSig0, bSig1, q, &term0, &term1, &term2 ); - sub128( aSig0, aSig1, term1, term2, &aSig0, &aSig1 ); - } - else { - shift128Right( aSig0, aSig1, 12, &aSig0, &aSig1 ); - shift128Right( bSig0, bSig1, 12, &bSig0, &bSig1 ); - } - do { - alternateASig0 = aSig0; - alternateASig1 = aSig1; - ++q; - sub128( aSig0, aSig1, bSig0, bSig1, &aSig0, &aSig1 ); - } while ( 0 <= (int64_t) aSig0 ); - add128( - aSig0, aSig1, alternateASig0, alternateASig1, (uint64_t *)&sigMean0, &sigMean1 ); - if ( ( sigMean0 < 0 ) - || ( ( ( sigMean0 | sigMean1 ) == 0 ) && ( q & 1 ) ) ) { - aSig0 = alternateASig0; - aSig1 = alternateASig1; - } - zSign = ( (int64_t) aSig0 < 0 ); - if ( zSign ) sub128( 0, 0, aSig0, aSig1, &aSig0, &aSig1 ); - return normalizeRoundAndPackFloat128(aSign ^ zSign, bExp - 4, aSig0, aSig1, - status); -} - -/*---------------------------------------------------------------------------- -| Returns the square root of the quadruple-precision floating-point value `a'. -| The operation is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float128 float128_sqrt(float128 a, float_status *status) -{ - bool aSign; - int32_t aExp, zExp; - uint64_t aSig0, aSig1, zSig0, zSig1, zSig2, doubleZSig0; - uint64_t rem0, rem1, rem2, rem3, term0, term1, term2, term3; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( aExp == 0x7FFF ) { - if (aSig0 | aSig1) { - return propagateFloat128NaN(a, a, status); - } - if ( ! aSign ) return a; - goto invalid; - } - if ( aSign ) { - if ( ( aExp | aSig0 | aSig1 ) == 0 ) return a; - invalid: - float_raise(float_flag_invalid, status); - return float128_default_nan(status); - } - if ( aExp == 0 ) { - if ( ( aSig0 | aSig1 ) == 0 ) return packFloat128( 0, 0, 0, 0 ); - normalizeFloat128Subnormal( aSig0, aSig1, &aExp, &aSig0, &aSig1 ); - } - zExp = ( ( aExp - 0x3FFF )>>1 ) + 0x3FFE; - aSig0 |= UINT64_C(0x0001000000000000); - zSig0 = estimateSqrt32( aExp, aSig0>>17 ); - shortShift128Left( aSig0, aSig1, 13 - ( aExp & 1 ), &aSig0, &aSig1 ); - zSig0 = estimateDiv128To64( aSig0, aSig1, zSig0<<32 ) + ( zSig0<<30 ); - doubleZSig0 = zSig0<<1; - mul64To128( zSig0, zSig0, &term0, &term1 ); - sub128( aSig0, aSig1, term0, term1, &rem0, &rem1 ); - while ( (int64_t) rem0 < 0 ) { - --zSig0; - doubleZSig0 -= 2; - add128( rem0, rem1, zSig0>>63, doubleZSig0 | 1, &rem0, &rem1 ); - } - zSig1 = estimateDiv128To64( rem1, 0, doubleZSig0 ); - if ( ( zSig1 & 0x1FFF ) <= 5 ) { - if ( zSig1 == 0 ) zSig1 = 1; - mul64To128( doubleZSig0, zSig1, &term1, &term2 ); - sub128( rem1, 0, term1, term2, &rem1, &rem2 ); - mul64To128( zSig1, zSig1, &term2, &term3 ); - sub192( rem1, rem2, 0, 0, term2, term3, &rem1, &rem2, &rem3 ); - while ( (int64_t) rem1 < 0 ) { - --zSig1; - shortShift128Left( 0, zSig1, 1, &term2, &term3 ); - term3 |= 1; - term2 |= doubleZSig0; - add192( rem1, rem2, rem3, 0, term2, term3, &rem1, &rem2, &rem3 ); - } - zSig1 |= ( ( rem1 | rem2 | rem3 ) != 0 ); - } - shift128ExtraRightJamming( zSig0, zSig1, 0, 14, &zSig0, &zSig1, &zSig2 ); - return roundAndPackFloat128(0, zExp, zSig0, zSig1, zSig2, status); - -} - -static inline FloatRelation -floatx80_compare_internal(floatx80 a, floatx80 b, bool is_quiet, - float_status *status) -{ - bool aSign, bSign; - - if (floatx80_invalid_encoding(a) || floatx80_invalid_encoding(b)) { - float_raise(float_flag_invalid, status); - return float_relation_unordered; - } - if (( ( extractFloatx80Exp( a ) == 0x7fff ) && - ( extractFloatx80Frac( a )<<1 ) ) || - ( ( extractFloatx80Exp( b ) == 0x7fff ) && - ( extractFloatx80Frac( b )<<1 ) )) { - if (!is_quiet || - floatx80_is_signaling_nan(a, status) || - floatx80_is_signaling_nan(b, status)) { - float_raise(float_flag_invalid, status); - } - return float_relation_unordered; - } - aSign = extractFloatx80Sign( a ); - bSign = extractFloatx80Sign( b ); - if ( aSign != bSign ) { - - if ( ( ( (uint16_t) ( ( a.high | b.high ) << 1 ) ) == 0) && - ( ( a.low | b.low ) == 0 ) ) { - /* zero case */ - return float_relation_equal; - } else { - return 1 - (2 * aSign); - } - } else { - /* Normalize pseudo-denormals before comparison. */ - if ((a.high & 0x7fff) == 0 && a.low & UINT64_C(0x8000000000000000)) { - ++a.high; - } - if ((b.high & 0x7fff) == 0 && b.low & UINT64_C(0x8000000000000000)) { - ++b.high; - } - if (a.low == b.low && a.high == b.high) { - return float_relation_equal; - } else { - return 1 - 2 * (aSign ^ ( lt128( a.high, a.low, b.high, b.low ) )); - } - } -} - -FloatRelation floatx80_compare(floatx80 a, floatx80 b, float_status *status) -{ - return floatx80_compare_internal(a, b, 0, status); -} - -FloatRelation floatx80_compare_quiet(floatx80 a, floatx80 b, - float_status *status) -{ - return floatx80_compare_internal(a, b, 1, status); -} - -static inline FloatRelation -float128_compare_internal(float128 a, float128 b, bool is_quiet, - float_status *status) -{ - bool aSign, bSign; - - if (( ( extractFloat128Exp( a ) == 0x7fff ) && - ( extractFloat128Frac0( a ) | extractFloat128Frac1( a ) ) ) || - ( ( extractFloat128Exp( b ) == 0x7fff ) && - ( extractFloat128Frac0( b ) | extractFloat128Frac1( b ) ) )) { - if (!is_quiet || - float128_is_signaling_nan(a, status) || - float128_is_signaling_nan(b, status)) { - float_raise(float_flag_invalid, status); - } - return float_relation_unordered; - } - aSign = extractFloat128Sign( a ); - bSign = extractFloat128Sign( b ); - if ( aSign != bSign ) { - if ( ( ( ( a.high | b.high )<<1 ) | a.low | b.low ) == 0 ) { - /* zero case */ - return float_relation_equal; - } else { - return 1 - (2 * aSign); - } - } else { - if (a.low == b.low && a.high == b.high) { - return float_relation_equal; - } else { - return 1 - 2 * (aSign ^ ( lt128( a.high, a.low, b.high, b.low ) )); - } - } -} - -FloatRelation float128_compare(float128 a, float128 b, float_status *status) -{ - return float128_compare_internal(a, b, 0, status); -} - -FloatRelation float128_compare_quiet(float128 a, float128 b, - float_status *status) -{ - return float128_compare_internal(a, b, 1, status); -} - -floatx80 floatx80_scalbn(floatx80 a, int n, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig; - - if (floatx80_invalid_encoding(a)) { - float_raise(float_flag_invalid, status); - return floatx80_default_nan(status); - } - aSig = extractFloatx80Frac( a ); - aExp = extractFloatx80Exp( a ); - aSign = extractFloatx80Sign( a ); - - if ( aExp == 0x7FFF ) { - if ( aSig<<1 ) { - return propagateFloatx80NaN(a, a, status); - } - return a; - } - - if (aExp == 0) { - if (aSig == 0) { - return a; - } - aExp++; - } - - if (n > 0x10000) { - n = 0x10000; - } else if (n < -0x10000) { - n = -0x10000; - } - - aExp += n; - return normalizeRoundAndPackFloatx80(status->floatx80_rounding_precision, - aSign, aExp, aSig, 0, status); -} - -float128 float128_scalbn(float128 a, int n, float_status *status) -{ - bool aSign; - int32_t aExp; - uint64_t aSig0, aSig1; - - aSig1 = extractFloat128Frac1( a ); - aSig0 = extractFloat128Frac0( a ); - aExp = extractFloat128Exp( a ); - aSign = extractFloat128Sign( a ); - if ( aExp == 0x7FFF ) { - if ( aSig0 | aSig1 ) { - return propagateFloat128NaN(a, a, status); - } - return a; - } - if (aExp != 0) { - aSig0 |= UINT64_C(0x0001000000000000); - } else if (aSig0 == 0 && aSig1 == 0) { - return a; - } else { - aExp++; - } - - if (n > 0x10000) { - n = 0x10000; - } else if (n < -0x10000) { - n = -0x10000; - } - - aExp += n - 1; - return normalizeRoundAndPackFloat128( aSign, aExp, aSig0, aSig1 - , status); - + return floatx80_round_pack_canonical(&p, status); } static void __attribute__((constructor)) softfloat_init(void) diff --git a/gdbstub.c b/gdbstub.c index 054665e93e..52bde5bdc9 100644 --- a/gdbstub.c +++ b/gdbstub.c @@ -37,7 +37,6 @@ #include "monitor/monitor.h" #include "chardev/char.h" #include "chardev/char-fe.h" -#include "sysemu/sysemu.h" #include "exec/gdbstub.h" #include "hw/cpu/cluster.h" #include "hw/boards.h" @@ -466,6 +465,15 @@ int use_gdb_syscalls(void) return gdb_syscall_mode == GDB_SYS_ENABLED; } +static bool stub_can_reverse(void) +{ +#ifdef CONFIG_USER_ONLY + return false; +#else + return replay_mode == REPLAY_MODE_PLAY; +#endif +} + /* Resume execution. */ static inline void gdb_continue(void) { @@ -1339,6 +1347,8 @@ typedef union GdbCmdVariant { } thread_id; } GdbCmdVariant; +#define get_param(p, i) (&g_array_index(p, GdbCmdVariant, i)) + static const char *cmd_next_param(const char *param, const char delimiter) { static const char all_delimiters[] = ",;:="; @@ -1364,55 +1374,52 @@ static const char *cmd_next_param(const char *param, const char delimiter) } static int cmd_parse_params(const char *data, const char *schema, - GdbCmdVariant *params, int *num_params) + GArray *params) { - int curr_param; const char *curr_schema, *curr_data; - *num_params = 0; - - if (!schema) { - return 0; - } + g_assert(schema); + g_assert(params->len == 0); curr_schema = schema; - curr_param = 0; curr_data = data; while (curr_schema[0] && curr_schema[1] && *curr_data) { + GdbCmdVariant this_param; + switch (curr_schema[0]) { case 'l': if (qemu_strtoul(curr_data, &curr_data, 16, - ¶ms[curr_param].val_ul)) { + &this_param.val_ul)) { return -EINVAL; } - curr_param++; curr_data = cmd_next_param(curr_data, curr_schema[1]); + g_array_append_val(params, this_param); break; case 'L': if (qemu_strtou64(curr_data, &curr_data, 16, - (uint64_t *)¶ms[curr_param].val_ull)) { + (uint64_t *)&this_param.val_ull)) { return -EINVAL; } - curr_param++; curr_data = cmd_next_param(curr_data, curr_schema[1]); + g_array_append_val(params, this_param); break; case 's': - params[curr_param].data = curr_data; - curr_param++; + this_param.data = curr_data; curr_data = cmd_next_param(curr_data, curr_schema[1]); + g_array_append_val(params, this_param); break; case 'o': - params[curr_param].opcode = *(uint8_t *)curr_data; - curr_param++; + this_param.opcode = *(uint8_t *)curr_data; curr_data = cmd_next_param(curr_data, curr_schema[1]); + g_array_append_val(params, this_param); break; case 't': - params[curr_param].thread_id.kind = + this_param.thread_id.kind = read_thread_id(curr_data, &curr_data, - ¶ms[curr_param].thread_id.pid, - ¶ms[curr_param].thread_id.tid); - curr_param++; + &this_param.thread_id.pid, + &this_param.thread_id.tid); curr_data = cmd_next_param(curr_data, curr_schema[1]); + g_array_append_val(params, this_param); break; case '?': curr_data = cmd_next_param(curr_data, curr_schema[1]); @@ -1423,16 +1430,10 @@ static int cmd_parse_params(const char *data, const char *schema, curr_schema += 2; } - *num_params = curr_param; return 0; } -typedef struct GdbCmdContext { - GdbCmdVariant *params; - int num_params; -} GdbCmdContext; - -typedef void (*GdbCmdHandler)(GdbCmdContext *gdb_ctx, void *user_ctx); +typedef void (*GdbCmdHandler)(GArray *params, void *user_ctx); /* * cmd_startswith -> cmd is compared using startswith @@ -1472,8 +1473,8 @@ static inline int startswith(const char *string, const char *pattern) static int process_string_cmd(void *user_ctx, const char *data, const GdbCmdParseEntry *cmds, int num_cmds) { - int i, schema_len, max_num_params = 0; - GdbCmdContext gdb_ctx; + int i; + g_autoptr(GArray) params = g_array_new(false, true, sizeof(GdbCmdVariant)); if (!cmds) { return -1; @@ -1489,24 +1490,13 @@ static int process_string_cmd(void *user_ctx, const char *data, } if (cmd->schema) { - schema_len = strlen(cmd->schema); - if (schema_len % 2) { - return -2; + if (cmd_parse_params(&data[strlen(cmd->cmd)], + cmd->schema, params)) { + return -1; } - - max_num_params = schema_len / 2; } - gdb_ctx.params = - (GdbCmdVariant *)alloca(sizeof(*gdb_ctx.params) * max_num_params); - memset(gdb_ctx.params, 0, sizeof(*gdb_ctx.params) * max_num_params); - - if (cmd_parse_params(&data[strlen(cmd->cmd)], cmd->schema, - gdb_ctx.params, &gdb_ctx.num_params)) { - return -1; - } - - cmd->handler(&gdb_ctx, user_ctx); + cmd->handler(params, user_ctx); return 0; } @@ -1529,18 +1519,18 @@ static void run_cmd_parser(const char *data, const GdbCmdParseEntry *cmd) } } -static void handle_detach(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_detach(GArray *params, void *user_ctx) { GDBProcess *process; uint32_t pid = 1; if (gdbserver_state.multiprocess) { - if (!gdb_ctx->num_params) { + if (!params->len) { put_packet("E22"); return; } - pid = gdb_ctx->params[0].val_ul; + pid = get_param(params, 0)->val_ul; } process = gdb_get_process(pid); @@ -1563,22 +1553,22 @@ static void handle_detach(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet("OK"); } -static void handle_thread_alive(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_thread_alive(GArray *params, void *user_ctx) { CPUState *cpu; - if (!gdb_ctx->num_params) { + if (!params->len) { put_packet("E22"); return; } - if (gdb_ctx->params[0].thread_id.kind == GDB_READ_THREAD_ERR) { + if (get_param(params, 0)->thread_id.kind == GDB_READ_THREAD_ERR) { put_packet("E22"); return; } - cpu = gdb_get_cpu(gdb_ctx->params[0].thread_id.pid, - gdb_ctx->params[0].thread_id.tid); + cpu = gdb_get_cpu(get_param(params, 0)->thread_id.pid, + get_param(params, 0)->thread_id.tid); if (!cpu) { put_packet("E22"); return; @@ -1587,17 +1577,17 @@ static void handle_thread_alive(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet("OK"); } -static void handle_continue(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_continue(GArray *params, void *user_ctx) { - if (gdb_ctx->num_params) { - gdb_set_cpu_pc(gdb_ctx->params[0].val_ull); + if (params->len) { + gdb_set_cpu_pc(get_param(params, 0)->val_ull); } gdbserver_state.signal = 0; gdb_continue(); } -static void handle_cont_with_sig(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_cont_with_sig(GArray *params, void *user_ctx) { unsigned long signal = 0; @@ -1605,8 +1595,8 @@ static void handle_cont_with_sig(GdbCmdContext *gdb_ctx, void *user_ctx) * Note: C sig;[addr] is currently unsupported and we simply * omit the addr parameter */ - if (gdb_ctx->num_params) { - signal = gdb_ctx->params[0].val_ul; + if (params->len) { + signal = get_param(params, 0)->val_ul; } gdbserver_state.signal = gdb_signal_to_target(signal); @@ -1616,27 +1606,27 @@ static void handle_cont_with_sig(GdbCmdContext *gdb_ctx, void *user_ctx) gdb_continue(); } -static void handle_set_thread(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_set_thread(GArray *params, void *user_ctx) { CPUState *cpu; - if (gdb_ctx->num_params != 2) { + if (params->len != 2) { put_packet("E22"); return; } - if (gdb_ctx->params[1].thread_id.kind == GDB_READ_THREAD_ERR) { + if (get_param(params, 1)->thread_id.kind == GDB_READ_THREAD_ERR) { put_packet("E22"); return; } - if (gdb_ctx->params[1].thread_id.kind != GDB_ONE_THREAD) { + if (get_param(params, 1)->thread_id.kind != GDB_ONE_THREAD) { put_packet("OK"); return; } - cpu = gdb_get_cpu(gdb_ctx->params[1].thread_id.pid, - gdb_ctx->params[1].thread_id.tid); + cpu = gdb_get_cpu(get_param(params, 1)->thread_id.pid, + get_param(params, 1)->thread_id.tid); if (!cpu) { put_packet("E22"); return; @@ -1646,7 +1636,7 @@ static void handle_set_thread(GdbCmdContext *gdb_ctx, void *user_ctx) * Note: This command is deprecated and modern gdb's will be using the * vCont command instead. */ - switch (gdb_ctx->params[0].opcode) { + switch (get_param(params, 0)->opcode) { case 'c': gdbserver_state.c_cpu = cpu; put_packet("OK"); @@ -1661,18 +1651,18 @@ static void handle_set_thread(GdbCmdContext *gdb_ctx, void *user_ctx) } } -static void handle_insert_bp(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_insert_bp(GArray *params, void *user_ctx) { int res; - if (gdb_ctx->num_params != 3) { + if (params->len != 3) { put_packet("E22"); return; } - res = gdb_breakpoint_insert(gdb_ctx->params[0].val_ul, - gdb_ctx->params[1].val_ull, - gdb_ctx->params[2].val_ull); + res = gdb_breakpoint_insert(get_param(params, 0)->val_ul, + get_param(params, 1)->val_ull, + get_param(params, 2)->val_ull); if (res >= 0) { put_packet("OK"); return; @@ -1684,18 +1674,18 @@ static void handle_insert_bp(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet("E22"); } -static void handle_remove_bp(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_remove_bp(GArray *params, void *user_ctx) { int res; - if (gdb_ctx->num_params != 3) { + if (params->len != 3) { put_packet("E22"); return; } - res = gdb_breakpoint_remove(gdb_ctx->params[0].val_ul, - gdb_ctx->params[1].val_ull, - gdb_ctx->params[2].val_ull); + res = gdb_breakpoint_remove(get_param(params, 0)->val_ul, + get_param(params, 1)->val_ull, + get_param(params, 2)->val_ull); if (res >= 0) { put_packet("OK"); return; @@ -1718,7 +1708,7 @@ static void handle_remove_bp(GdbCmdContext *gdb_ctx, void *user_ctx) * the remote gdb to fallback to older methods. */ -static void handle_set_reg(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_set_reg(GArray *params, void *user_ctx) { int reg_size; @@ -1727,19 +1717,19 @@ static void handle_set_reg(GdbCmdContext *gdb_ctx, void *user_ctx) return; } - if (gdb_ctx->num_params != 2) { + if (params->len != 2) { put_packet("E22"); return; } - reg_size = strlen(gdb_ctx->params[1].data) / 2; - hextomem(gdbserver_state.mem_buf, gdb_ctx->params[1].data, reg_size); + reg_size = strlen(get_param(params, 1)->data) / 2; + hextomem(gdbserver_state.mem_buf, get_param(params, 1)->data, reg_size); gdb_write_register(gdbserver_state.g_cpu, gdbserver_state.mem_buf->data, - gdb_ctx->params[0].val_ull); + get_param(params, 0)->val_ull); put_packet("OK"); } -static void handle_get_reg(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_get_reg(GArray *params, void *user_ctx) { int reg_size; @@ -1748,14 +1738,14 @@ static void handle_get_reg(GdbCmdContext *gdb_ctx, void *user_ctx) return; } - if (!gdb_ctx->num_params) { + if (!params->len) { put_packet("E14"); return; } reg_size = gdb_read_register(gdbserver_state.g_cpu, gdbserver_state.mem_buf, - gdb_ctx->params[0].val_ull); + get_param(params, 0)->val_ull); if (!reg_size) { put_packet("E14"); return; @@ -1767,22 +1757,24 @@ static void handle_get_reg(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } -static void handle_write_mem(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_write_mem(GArray *params, void *user_ctx) { - if (gdb_ctx->num_params != 3) { + if (params->len != 3) { put_packet("E22"); return; } /* hextomem() reads 2*len bytes */ - if (gdb_ctx->params[1].val_ull > strlen(gdb_ctx->params[2].data) / 2) { + if (get_param(params, 1)->val_ull > + strlen(get_param(params, 2)->data) / 2) { put_packet("E22"); return; } - hextomem(gdbserver_state.mem_buf, gdb_ctx->params[2].data, - gdb_ctx->params[1].val_ull); - if (target_memory_rw_debug(gdbserver_state.g_cpu, gdb_ctx->params[0].val_ull, + hextomem(gdbserver_state.mem_buf, get_param(params, 2)->data, + get_param(params, 1)->val_ull); + if (target_memory_rw_debug(gdbserver_state.g_cpu, + get_param(params, 0)->val_ull, gdbserver_state.mem_buf->data, gdbserver_state.mem_buf->len, true)) { put_packet("E14"); @@ -1792,22 +1784,24 @@ static void handle_write_mem(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet("OK"); } -static void handle_read_mem(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_read_mem(GArray *params, void *user_ctx) { - if (gdb_ctx->num_params != 2) { + if (params->len != 2) { put_packet("E22"); return; } /* memtohex() doubles the required space */ - if (gdb_ctx->params[1].val_ull > MAX_PACKET_LENGTH / 2) { + if (get_param(params, 1)->val_ull > MAX_PACKET_LENGTH / 2) { put_packet("E22"); return; } - g_byte_array_set_size(gdbserver_state.mem_buf, gdb_ctx->params[1].val_ull); + g_byte_array_set_size(gdbserver_state.mem_buf, + get_param(params, 1)->val_ull); - if (target_memory_rw_debug(gdbserver_state.g_cpu, gdb_ctx->params[0].val_ull, + if (target_memory_rw_debug(gdbserver_state.g_cpu, + get_param(params, 0)->val_ull, gdbserver_state.mem_buf->data, gdbserver_state.mem_buf->len, false)) { put_packet("E14"); @@ -1819,19 +1813,19 @@ static void handle_read_mem(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } -static void handle_write_all_regs(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_write_all_regs(GArray *params, void *user_ctx) { target_ulong addr, len; uint8_t *registers; int reg_size; - if (!gdb_ctx->num_params) { + if (!params->len) { return; } cpu_synchronize_state(gdbserver_state.g_cpu); - len = strlen(gdb_ctx->params[0].data) / 2; - hextomem(gdbserver_state.mem_buf, gdb_ctx->params[0].data, len); + len = strlen(get_param(params, 0)->data) / 2; + hextomem(gdbserver_state.mem_buf, get_param(params, 0)->data, len); registers = gdbserver_state.mem_buf->data; for (addr = 0; addr < gdbserver_state.g_cpu->gdb_num_g_regs && len > 0; addr++) { @@ -1842,7 +1836,7 @@ static void handle_write_all_regs(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet("OK"); } -static void handle_read_all_regs(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_read_all_regs(GArray *params, void *user_ctx) { target_ulong addr, len; @@ -1860,14 +1854,14 @@ static void handle_read_all_regs(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } -static void handle_file_io(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_file_io(GArray *params, void *user_ctx) { - if (gdb_ctx->num_params >= 1 && gdbserver_state.current_syscall_cb) { + if (params->len >= 1 && gdbserver_state.current_syscall_cb) { target_ulong ret, err; - ret = (target_ulong)gdb_ctx->params[0].val_ull; - if (gdb_ctx->num_params >= 2) { - err = (target_ulong)gdb_ctx->params[1].val_ull; + ret = (target_ulong)get_param(params, 0)->val_ull; + if (params->len >= 2) { + err = (target_ulong)get_param(params, 1)->val_ull; } else { err = 0; } @@ -1875,7 +1869,7 @@ static void handle_file_io(GdbCmdContext *gdb_ctx, void *user_ctx) gdbserver_state.current_syscall_cb = NULL; } - if (gdb_ctx->num_params >= 3 && gdb_ctx->params[2].opcode == (uint8_t)'C') { + if (params->len >= 3 && get_param(params, 2)->opcode == (uint8_t)'C') { put_packet("T02"); return; } @@ -1883,23 +1877,23 @@ static void handle_file_io(GdbCmdContext *gdb_ctx, void *user_ctx) gdb_continue(); } -static void handle_step(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_step(GArray *params, void *user_ctx) { - if (gdb_ctx->num_params) { - gdb_set_cpu_pc((target_ulong)gdb_ctx->params[0].val_ull); + if (params->len) { + gdb_set_cpu_pc((target_ulong)get_param(params, 0)->val_ull); } cpu_single_step(gdbserver_state.c_cpu, get_sstep_flags()); gdb_continue(); } -static void handle_backward(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_backward(GArray *params, void *user_ctx) { - if (replay_mode != REPLAY_MODE_PLAY) { + if (!stub_can_reverse()) { put_packet("E22"); } - if (gdb_ctx->num_params == 1) { - switch (gdb_ctx->params[0].opcode) { + if (params->len == 1) { + switch (get_param(params, 0)->opcode) { case 's': if (replay_reverse_step()) { gdb_continue(); @@ -1921,20 +1915,20 @@ static void handle_backward(GdbCmdContext *gdb_ctx, void *user_ctx) put_packet(""); } -static void handle_v_cont_query(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_v_cont_query(GArray *params, void *user_ctx) { put_packet("vCont;c;C;s;S"); } -static void handle_v_cont(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_v_cont(GArray *params, void *user_ctx) { int res; - if (!gdb_ctx->num_params) { + if (!params->len) { return; } - res = gdb_handle_vcont(gdb_ctx->params[0].data); + res = gdb_handle_vcont(get_param(params, 0)->data); if ((res == -EINVAL) || (res == -ERANGE)) { put_packet("E22"); } else if (res) { @@ -1942,17 +1936,17 @@ static void handle_v_cont(GdbCmdContext *gdb_ctx, void *user_ctx) } } -static void handle_v_attach(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_v_attach(GArray *params, void *user_ctx) { GDBProcess *process; CPUState *cpu; g_string_assign(gdbserver_state.str_buf, "E22"); - if (!gdb_ctx->num_params) { + if (!params->len) { goto cleanup; } - process = gdb_get_process(gdb_ctx->params[0].val_ul); + process = gdb_get_process(get_param(params, 0)->val_ul); if (!process) { goto cleanup; } @@ -1973,7 +1967,7 @@ cleanup: put_strbuf(); } -static void handle_v_kill(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_v_kill(GArray *params, void *user_ctx) { /* Kill the target */ put_packet("OK"); @@ -1982,7 +1976,7 @@ static void handle_v_kill(GdbCmdContext *gdb_ctx, void *user_ctx) exit(0); } -static GdbCmdParseEntry gdb_v_commands_table[] = { +static const GdbCmdParseEntry gdb_v_commands_table[] = { /* Order is important if has same prefix */ { .handler = handle_v_cont_query, @@ -2008,43 +2002,43 @@ static GdbCmdParseEntry gdb_v_commands_table[] = { }, }; -static void handle_v_commands(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_v_commands(GArray *params, void *user_ctx) { - if (!gdb_ctx->num_params) { + if (!params->len) { return; } - if (process_string_cmd(NULL, gdb_ctx->params[0].data, + if (process_string_cmd(NULL, get_param(params, 0)->data, gdb_v_commands_table, ARRAY_SIZE(gdb_v_commands_table))) { put_packet(""); } } -static void handle_query_qemu_sstepbits(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_qemu_sstepbits(GArray *params, void *user_ctx) { g_string_printf(gdbserver_state.str_buf, "ENABLE=%x,NOIRQ=%x,NOTIMER=%x", SSTEP_ENABLE, SSTEP_NOIRQ, SSTEP_NOTIMER); put_strbuf(); } -static void handle_set_qemu_sstep(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_set_qemu_sstep(GArray *params, void *user_ctx) { - if (!gdb_ctx->num_params) { + if (!params->len) { return; } - sstep_flags = gdb_ctx->params[0].val_ul; + sstep_flags = get_param(params, 0)->val_ul; put_packet("OK"); } -static void handle_query_qemu_sstep(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_qemu_sstep(GArray *params, void *user_ctx) { g_string_printf(gdbserver_state.str_buf, "0x%x", sstep_flags); put_strbuf(); } -static void handle_query_curr_tid(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_curr_tid(GArray *params, void *user_ctx) { CPUState *cpu; GDBProcess *process; @@ -2061,7 +2055,7 @@ static void handle_query_curr_tid(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } -static void handle_query_threads(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_threads(GArray *params, void *user_ctx) { if (!gdbserver_state.query_cpu) { put_packet("l"); @@ -2074,25 +2068,25 @@ static void handle_query_threads(GdbCmdContext *gdb_ctx, void *user_ctx) gdbserver_state.query_cpu = gdb_next_attached_cpu(gdbserver_state.query_cpu); } -static void handle_query_first_threads(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_first_threads(GArray *params, void *user_ctx) { gdbserver_state.query_cpu = gdb_first_attached_cpu(); - handle_query_threads(gdb_ctx, user_ctx); + handle_query_threads(params, user_ctx); } -static void handle_query_thread_extra(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_thread_extra(GArray *params, void *user_ctx) { g_autoptr(GString) rs = g_string_new(NULL); CPUState *cpu; - if (!gdb_ctx->num_params || - gdb_ctx->params[0].thread_id.kind == GDB_READ_THREAD_ERR) { + if (!params->len || + get_param(params, 0)->thread_id.kind == GDB_READ_THREAD_ERR) { put_packet("E22"); return; } - cpu = gdb_get_cpu(gdb_ctx->params[0].thread_id.pid, - gdb_ctx->params[0].thread_id.tid); + cpu = gdb_get_cpu(get_param(params, 0)->thread_id.pid, + get_param(params, 0)->thread_id.tid); if (!cpu) { return; } @@ -2117,7 +2111,7 @@ static void handle_query_thread_extra(GdbCmdContext *gdb_ctx, void *user_ctx) } #ifdef CONFIG_USER_ONLY -static void handle_query_offsets(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_offsets(GArray *params, void *user_ctx) { TaskState *ts; @@ -2132,17 +2126,17 @@ static void handle_query_offsets(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } #else -static void handle_query_rcmd(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_rcmd(GArray *params, void *user_ctx) { const guint8 zero = 0; int len; - if (!gdb_ctx->num_params) { + if (!params->len) { put_packet("E22"); return; } - len = strlen(gdb_ctx->params[0].data); + len = strlen(get_param(params, 0)->data); if (len % 2) { put_packet("E01"); return; @@ -2150,7 +2144,7 @@ static void handle_query_rcmd(GdbCmdContext *gdb_ctx, void *user_ctx) g_assert(gdbserver_state.mem_buf->len == 0); len = len / 2; - hextomem(gdbserver_state.mem_buf, gdb_ctx->params[0].data, len); + hextomem(gdbserver_state.mem_buf, get_param(params, 0)->data, len); g_byte_array_append(gdbserver_state.mem_buf, &zero, 1); qemu_chr_be_write(gdbserver_state.mon_chr, gdbserver_state.mem_buf->data, gdbserver_state.mem_buf->len); @@ -2158,7 +2152,7 @@ static void handle_query_rcmd(GdbCmdContext *gdb_ctx, void *user_ctx) } #endif -static void handle_query_supported(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_supported(GArray *params, void *user_ctx) { CPUClass *cc; @@ -2168,7 +2162,7 @@ static void handle_query_supported(GdbCmdContext *gdb_ctx, void *user_ctx) g_string_append(gdbserver_state.str_buf, ";qXfer:features:read+"); } - if (replay_mode == REPLAY_MODE_PLAY) { + if (stub_can_reverse()) { g_string_append(gdbserver_state.str_buf, ";ReverseStep+;ReverseContinue+"); } @@ -2179,8 +2173,8 @@ static void handle_query_supported(GdbCmdContext *gdb_ctx, void *user_ctx) } #endif - if (gdb_ctx->num_params && - strstr(gdb_ctx->params[0].data, "multiprocess+")) { + if (params->len && + strstr(get_param(params, 0)->data, "multiprocess+")) { gdbserver_state.multiprocess = true; } @@ -2188,7 +2182,7 @@ static void handle_query_supported(GdbCmdContext *gdb_ctx, void *user_ctx) put_strbuf(); } -static void handle_query_xfer_features(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_xfer_features(GArray *params, void *user_ctx) { GDBProcess *process; CPUClass *cc; @@ -2196,7 +2190,7 @@ static void handle_query_xfer_features(GdbCmdContext *gdb_ctx, void *user_ctx) const char *xml; const char *p; - if (gdb_ctx->num_params < 3) { + if (params->len < 3) { put_packet("E22"); return; } @@ -2209,15 +2203,15 @@ static void handle_query_xfer_features(GdbCmdContext *gdb_ctx, void *user_ctx) } gdb_has_xml = true; - p = gdb_ctx->params[0].data; + p = get_param(params, 0)->data; xml = get_feature_xml(p, &p, process); if (!xml) { put_packet("E00"); return; } - addr = gdb_ctx->params[1].val_ul; - len = gdb_ctx->params[2].val_ul; + addr = get_param(params, 1)->val_ul; + len = get_param(params, 2)->val_ul; total_len = strlen(xml); if (addr > total_len) { put_packet("E00"); @@ -2241,18 +2235,18 @@ static void handle_query_xfer_features(GdbCmdContext *gdb_ctx, void *user_ctx) } #if defined(CONFIG_USER_ONLY) && defined(CONFIG_LINUX_USER) -static void handle_query_xfer_auxv(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_xfer_auxv(GArray *params, void *user_ctx) { TaskState *ts; unsigned long offset, len, saved_auxv, auxv_len; - if (gdb_ctx->num_params < 2) { + if (params->len < 2) { put_packet("E22"); return; } - offset = gdb_ctx->params[0].val_ul; - len = gdb_ctx->params[1].val_ul; + offset = get_param(params, 0)->val_ul; + len = get_param(params, 1)->val_ul; ts = gdbserver_state.c_cpu->opaque; saved_auxv = ts->info->saved_auxv; auxv_len = ts->info->auxv_len; @@ -2287,12 +2281,12 @@ static void handle_query_xfer_auxv(GdbCmdContext *gdb_ctx, void *user_ctx) } #endif -static void handle_query_attached(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_attached(GArray *params, void *user_ctx) { put_packet(GDB_ATTACHED); } -static void handle_query_qemu_supported(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_query_qemu_supported(GArray *params, void *user_ctx) { g_string_printf(gdbserver_state.str_buf, "sstepbits;sstep"); #ifndef CONFIG_USER_ONLY @@ -2302,21 +2296,21 @@ static void handle_query_qemu_supported(GdbCmdContext *gdb_ctx, void *user_ctx) } #ifndef CONFIG_USER_ONLY -static void handle_query_qemu_phy_mem_mode(GdbCmdContext *gdb_ctx, +static void handle_query_qemu_phy_mem_mode(GArray *params, void *user_ctx) { g_string_printf(gdbserver_state.str_buf, "%d", phy_memory_mode); put_strbuf(); } -static void handle_set_qemu_phy_mem_mode(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_set_qemu_phy_mem_mode(GArray *params, void *user_ctx) { - if (!gdb_ctx->num_params) { + if (!params->len) { put_packet("E22"); return; } - if (!gdb_ctx->params[0].val_ul) { + if (!get_param(params, 0)->val_ul) { phy_memory_mode = 0; } else { phy_memory_mode = 1; @@ -2325,7 +2319,7 @@ static void handle_set_qemu_phy_mem_mode(GdbCmdContext *gdb_ctx, void *user_ctx) } #endif -static GdbCmdParseEntry gdb_gen_query_set_common_table[] = { +static const GdbCmdParseEntry gdb_gen_query_set_common_table[] = { /* Order is important if has same prefix */ { .handler = handle_query_qemu_sstepbits, @@ -2343,7 +2337,7 @@ static GdbCmdParseEntry gdb_gen_query_set_common_table[] = { }, }; -static GdbCmdParseEntry gdb_gen_query_table[] = { +static const GdbCmdParseEntry gdb_gen_query_table[] = { { .handler = handle_query_curr_tid, .cmd = "C", @@ -2421,7 +2415,7 @@ static GdbCmdParseEntry gdb_gen_query_table[] = { #endif }; -static GdbCmdParseEntry gdb_gen_set_table[] = { +static const GdbCmdParseEntry gdb_gen_set_table[] = { /* Order is important if has same prefix */ { .handler = handle_set_qemu_sstep, @@ -2439,45 +2433,45 @@ static GdbCmdParseEntry gdb_gen_set_table[] = { #endif }; -static void handle_gen_query(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_gen_query(GArray *params, void *user_ctx) { - if (!gdb_ctx->num_params) { + if (!params->len) { return; } - if (!process_string_cmd(NULL, gdb_ctx->params[0].data, + if (!process_string_cmd(NULL, get_param(params, 0)->data, gdb_gen_query_set_common_table, ARRAY_SIZE(gdb_gen_query_set_common_table))) { return; } - if (process_string_cmd(NULL, gdb_ctx->params[0].data, + if (process_string_cmd(NULL, get_param(params, 0)->data, gdb_gen_query_table, ARRAY_SIZE(gdb_gen_query_table))) { put_packet(""); } } -static void handle_gen_set(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_gen_set(GArray *params, void *user_ctx) { - if (!gdb_ctx->num_params) { + if (!params->len) { return; } - if (!process_string_cmd(NULL, gdb_ctx->params[0].data, + if (!process_string_cmd(NULL, get_param(params, 0)->data, gdb_gen_query_set_common_table, ARRAY_SIZE(gdb_gen_query_set_common_table))) { return; } - if (process_string_cmd(NULL, gdb_ctx->params[0].data, + if (process_string_cmd(NULL, get_param(params, 0)->data, gdb_gen_set_table, ARRAY_SIZE(gdb_gen_set_table))) { put_packet(""); } } -static void handle_target_halt(GdbCmdContext *gdb_ctx, void *user_ctx) +static void handle_target_halt(GArray *params, void *user_ctx) { g_string_printf(gdbserver_state.str_buf, "T%02xthread:", GDB_SIGNAL_TRAP); gdb_append_thread_id(gdbserver_state.c_cpu, gdbserver_state.str_buf); diff --git a/gitdm.config b/gitdm.config index c01c219078..288b100d89 100644 --- a/gitdm.config +++ b/gitdm.config @@ -28,20 +28,25 @@ EmailMap contrib/gitdm/domain-map # # Use GroupMap to map a file full of addresses to the # same employer. This is used for people that don't post from easily -# identifiable corporate emails. +# identifiable corporate emails. Please keep this list sorted. # -GroupMap contrib/gitdm/group-map-redhat Red Hat -GroupMap contrib/gitdm/group-map-wavecomp Wave Computing GroupMap contrib/gitdm/group-map-cadence Cadence Design Systems GroupMap contrib/gitdm/group-map-codeweavers CodeWeavers GroupMap contrib/gitdm/group-map-ibm IBM GroupMap contrib/gitdm/group-map-janustech Janus Technologies +GroupMap contrib/gitdm/group-map-netflix Netflix +GroupMap contrib/gitdm/group-map-redhat Red Hat +GroupMap contrib/gitdm/group-map-wavecomp Wave Computing # Also group together our prolific individual contributors -# and those working under academic auspices +# and those working under academic or intern auspices GroupMap contrib/gitdm/group-map-individuals (None) GroupMap contrib/gitdm/group-map-academics Academics (various) +GroupMap contrib/gitdm/group-map-interns GSoC/Outreachy Interns + +# Group together robots and other auto-reporters +GroupMap contrib/gitdm/group-map-robots Robots (various) # # diff --git a/hmp-commands-info.hx b/hmp-commands-info.hx index ab0c7aa5ee..27206ac049 100644 --- a/hmp-commands-info.hx +++ b/hmp-commands-info.hx @@ -274,7 +274,6 @@ ERST .args_type = "", .params = "", .help = "show dynamic compiler info", - .cmd = hmp_info_jit, }, #endif @@ -289,7 +288,6 @@ ERST .args_type = "", .params = "", .help = "show dynamic compiler opcode counters", - .cmd = hmp_info_opcount, }, #endif @@ -368,7 +366,6 @@ ERST .args_type = "", .params = "", .help = "show host USB devices", - .cmd = hmp_info_usbhost, }, SRST @@ -500,19 +497,6 @@ SRST Show the current VM UUID. ERST - { - .name = "cpustats", - .args_type = "", - .params = "", - .help = "show CPU statistics", - .cmd = hmp_info_cpustats, - }, - -SRST - ``info cpustats`` - Show CPU statistics. -ERST - #if defined(CONFIG_SLIRP) { .name = "usernet", @@ -880,3 +864,16 @@ SRST ``info replay`` Display the record/replay information: mode and the current icount. ERST + + { + .name = "dirty_rate", + .args_type = "", + .params = "", + .help = "show dirty rate information", + .cmd = hmp_info_dirty_rate, + }, + +SRST + ``info dirty_rate`` + Display the vcpu dirty rate information. +ERST diff --git a/hmp-commands.hx b/hmp-commands.hx index 435c591a1c..8e45bce2cd 100644 --- a/hmp-commands.hx +++ b/hmp-commands.hx @@ -1269,6 +1269,7 @@ ERST .help = "add host network device", .cmd = hmp_netdev_add, .command_completion = netdev_add_completion, + .flags = "p", }, SRST @@ -1283,6 +1284,7 @@ ERST .help = "remove host network device", .cmd = hmp_netdev_del, .command_completion = netdev_del_completion, + .flags = "p", }, SRST @@ -1297,6 +1299,7 @@ ERST .help = "create QOM object", .cmd = hmp_object_add, .command_completion = object_add_completion, + .flags = "p", }, SRST @@ -1311,6 +1314,7 @@ ERST .help = "destroy QOM object", .cmd = hmp_object_del, .command_completion = object_del_completion, + .flags = "p", }, SRST @@ -1667,7 +1671,7 @@ ERST { .name = "replay_break", - .args_type = "icount:i", + .args_type = "icount:l", .params = "icount", .help = "set breakpoint at the specified instruction count", .cmd = hmp_replay_break, @@ -1699,7 +1703,7 @@ ERST { .name = "replay_seek", - .args_type = "icount:i", + .args_type = "icount:l", .params = "icount", .help = "replay execution to the specified instruction count", .cmd = hmp_replay_seek, @@ -1725,3 +1729,17 @@ ERST .flags = "p", }, +SRST +``calc_dirty_rate`` *second* + Start a round of dirty rate measurement with the period specified in *second*. + The result of the dirty rate measurement may be observed with ``info + dirty_rate`` command. +ERST + + { + .name = "calc_dirty_rate", + .args_type = "second:l,sample_pages_per_GB:l?", + .params = "second [sample_pages_per_GB]", + .help = "start a round of guest dirty rate measurement", + .cmd = hmp_calc_dirty_rate, + }, diff --git a/hw/9pfs/9p-local.c b/hw/9pfs/9p-local.c index af52c1daac..210d9e7705 100644 --- a/hw/9pfs/9p-local.c +++ b/hw/9pfs/9p-local.c @@ -10,6 +10,11 @@ * the COPYING file in the top-level directory. */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "9p.h" #include "9p-local.h" diff --git a/hw/9pfs/9p-posix-acl.c b/hw/9pfs/9p-posix-acl.c index bbf89064f7..eadae270dd 100644 --- a/hw/9pfs/9p-posix-acl.c +++ b/hw/9pfs/9p-posix-acl.c @@ -11,6 +11,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "qemu/xattr.h" #include "9p.h" diff --git a/hw/9pfs/9p-proxy.c b/hw/9pfs/9p-proxy.c index 4aa4e0a3ba..09bd9f1464 100644 --- a/hw/9pfs/9p-proxy.c +++ b/hw/9pfs/9p-proxy.c @@ -10,6 +10,11 @@ * the COPYING file in the top-level directory. */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include #include diff --git a/hw/9pfs/9p-synth.c b/hw/9pfs/9p-synth.c index 473ef914b0..b38088e066 100644 --- a/hw/9pfs/9p-synth.c +++ b/hw/9pfs/9p-synth.c @@ -12,6 +12,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "9p.h" #include "fsdev/qemu-fsdev.h" diff --git a/hw/9pfs/9p-util.c b/hw/9pfs/9p-util.c index 614b7fc34d..3221d9b498 100644 --- a/hw/9pfs/9p-util.c +++ b/hw/9pfs/9p-util.c @@ -10,6 +10,11 @@ * See the COPYING file in the top-level directory. */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "qemu/xattr.h" #include "9p-util.h" diff --git a/hw/9pfs/9p-xattr-user.c b/hw/9pfs/9p-xattr-user.c index 2c90817b75..f2ae9582e6 100644 --- a/hw/9pfs/9p-xattr-user.c +++ b/hw/9pfs/9p-xattr-user.c @@ -11,6 +11,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "9p.h" #include "fsdev/file-op-9p.h" diff --git a/hw/9pfs/9p-xattr.c b/hw/9pfs/9p-xattr.c index c696d8f846..9ae69dd8db 100644 --- a/hw/9pfs/9p-xattr.c +++ b/hw/9pfs/9p-xattr.c @@ -11,6 +11,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "9p.h" #include "fsdev/file-op-9p.h" diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c index 134806db52..2815257f42 100644 --- a/hw/9pfs/9p.c +++ b/hw/9pfs/9p.c @@ -11,6 +11,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include #include "hw/virtio/virtio.h" @@ -966,23 +971,6 @@ static int stat_to_qid(V9fsPDU *pdu, const struct stat *stbuf, V9fsQID *qidp) return 0; } -static int coroutine_fn fid_to_qid(V9fsPDU *pdu, V9fsFidState *fidp, - V9fsQID *qidp) -{ - struct stat stbuf; - int err; - - err = v9fs_co_lstat(pdu, &fidp->path, &stbuf); - if (err < 0) { - return err; - } - err = stat_to_qid(pdu, &stbuf, qidp); - if (err < 0) { - return err; - } - return 0; -} - V9fsPDU *pdu_alloc(V9fsState *s) { V9fsPDU *pdu = NULL; @@ -1395,6 +1383,7 @@ static void coroutine_fn v9fs_attach(void *opaque) size_t offset = 7; V9fsQID qid; ssize_t err; + struct stat stbuf; v9fs_string_init(&uname); v9fs_string_init(&aname); @@ -1417,7 +1406,13 @@ static void coroutine_fn v9fs_attach(void *opaque) clunk_fid(s, fid); goto out; } - err = fid_to_qid(pdu, fidp, &qid); + err = v9fs_co_lstat(pdu, &fidp->path, &stbuf); + if (err < 0) { + err = -EINVAL; + clunk_fid(s, fid); + goto out; + } + err = stat_to_qid(pdu, &stbuf, &qid); if (err < 0) { err = -EINVAL; clunk_fid(s, fid); @@ -1449,7 +1444,7 @@ static void coroutine_fn v9fs_attach(void *opaque) } err += offset; - memcpy(&s->root_qid, &qid, sizeof(qid)); + memcpy(&s->root_st, &stbuf, sizeof(stbuf)); trace_v9fs_attach_return(pdu->tag, pdu->id, qid.type, qid.version, qid.path); out: @@ -1700,12 +1695,9 @@ static bool name_is_illegal(const char *name) return !*name || strchr(name, '/') != NULL; } -static bool not_same_qid(const V9fsQID *qid1, const V9fsQID *qid2) +static bool same_stat_id(const struct stat *a, const struct stat *b) { - return - qid1->type != qid2->type || - qid1->version != qid2->version || - qid1->path != qid2->path; + return a->st_dev == b->st_dev && a->st_ino == b->st_ino; } static void coroutine_fn v9fs_walk(void *opaque) @@ -1713,9 +1705,9 @@ static void coroutine_fn v9fs_walk(void *opaque) int name_idx; V9fsQID *qids = NULL; int i, err = 0; - V9fsPath dpath, path; + V9fsPath dpath, path, *pathes = NULL; uint16_t nwnames; - struct stat stbuf; + struct stat stbuf, fidst, *stbufs = NULL; size_t offset = 7; int32_t fid, newfid; V9fsString *wnames = NULL; @@ -1734,9 +1726,15 @@ static void coroutine_fn v9fs_walk(void *opaque) trace_v9fs_walk(pdu->tag, pdu->id, fid, newfid, nwnames); - if (nwnames && nwnames <= P9_MAXWELEM) { + if (nwnames > P9_MAXWELEM) { + err = -EINVAL; + goto out_nofid; + } + if (nwnames) { wnames = g_new0(V9fsString, nwnames); qids = g_new0(V9fsQID, nwnames); + stbufs = g_new0(struct stat, nwnames); + pathes = g_new0(V9fsPath, nwnames); for (i = 0; i < nwnames; i++) { err = pdu_unmarshal(pdu, offset, "s", &wnames[i]); if (err < 0) { @@ -1748,9 +1746,6 @@ static void coroutine_fn v9fs_walk(void *opaque) } offset += err; } - } else if (nwnames > P9_MAXWELEM) { - err = -EINVAL; - goto out_nofid; } fidp = get_fid(pdu, fid); if (fidp == NULL) { @@ -1760,35 +1755,85 @@ static void coroutine_fn v9fs_walk(void *opaque) v9fs_path_init(&dpath); v9fs_path_init(&path); - - err = fid_to_qid(pdu, fidp, &qid); - if (err < 0) { - goto out; - } - /* - * Both dpath and path initially poin to fidp. + * Both dpath and path initially point to fidp. * Needed to handle request with nwnames == 0 */ v9fs_path_copy(&dpath, &fidp->path); v9fs_path_copy(&path, &fidp->path); - for (name_idx = 0; name_idx < nwnames; name_idx++) { - if (not_same_qid(&pdu->s->root_qid, &qid) || - strcmp("..", wnames[name_idx].data)) { - err = v9fs_co_name_to_path(pdu, &dpath, wnames[name_idx].data, - &path); - if (err < 0) { - goto out; - } - err = v9fs_co_lstat(pdu, &path, &stbuf); - if (err < 0) { - goto out; + /* + * To keep latency (i.e. overall execution time for processing this + * Twalk client request) as small as possible, run all the required fs + * driver code altogether inside the following block. + */ + v9fs_co_run_in_worker({ + if (v9fs_request_cancelled(pdu)) { + err = -EINTR; + break; + } + err = s->ops->lstat(&s->ctx, &dpath, &fidst); + if (err < 0) { + err = -errno; + break; + } + stbuf = fidst; + for (name_idx = 0; name_idx < nwnames; name_idx++) { + if (v9fs_request_cancelled(pdu)) { + err = -EINTR; + break; } + if (!same_stat_id(&pdu->s->root_st, &stbuf) || + strcmp("..", wnames[name_idx].data)) + { + err = s->ops->name_to_path(&s->ctx, &dpath, + wnames[name_idx].data, &path); + if (err < 0) { + err = -errno; + break; + } + if (v9fs_request_cancelled(pdu)) { + err = -EINTR; + break; + } + err = s->ops->lstat(&s->ctx, &path, &stbuf); + if (err < 0) { + err = -errno; + break; + } + stbufs[name_idx] = stbuf; + v9fs_path_copy(&dpath, &path); + v9fs_path_copy(&pathes[name_idx], &path); + } + } + }); + /* + * Handle all the rest of this Twalk request on main thread ... + */ + if (err < 0) { + goto out; + } + + err = stat_to_qid(pdu, &fidst, &qid); + if (err < 0) { + goto out; + } + stbuf = fidst; + + /* reset dpath and path */ + v9fs_path_copy(&dpath, &fidp->path); + v9fs_path_copy(&path, &fidp->path); + + for (name_idx = 0; name_idx < nwnames; name_idx++) { + if (!same_stat_id(&pdu->s->root_st, &stbuf) || + strcmp("..", wnames[name_idx].data)) + { + stbuf = stbufs[name_idx]; err = stat_to_qid(pdu, &stbuf, &qid); if (err < 0) { goto out; } + v9fs_path_copy(&path, &pathes[name_idx]); v9fs_path_copy(&dpath, &path); } memcpy(&qids[name_idx], &qid, sizeof(qid)); @@ -1824,9 +1869,12 @@ out_nofid: if (nwnames && nwnames <= P9_MAXWELEM) { for (name_idx = 0; name_idx < nwnames; name_idx++) { v9fs_string_free(&wnames[name_idx]); + v9fs_path_free(&pathes[name_idx]); } g_free(wnames); g_free(qids); + g_free(stbufs); + g_free(pathes); } } diff --git a/hw/9pfs/9p.h b/hw/9pfs/9p.h index 00381591ff..1567b67841 100644 --- a/hw/9pfs/9p.h +++ b/hw/9pfs/9p.h @@ -355,7 +355,7 @@ struct V9fsState { int32_t root_fid; Error *migration_blocker; V9fsConf fsconf; - V9fsQID root_qid; + struct stat root_st; dev_t dev_id; struct qht qpd_table; struct qht qpp_table; diff --git a/hw/9pfs/codir.c b/hw/9pfs/codir.c index 1f70a58df5..032cce04c4 100644 --- a/hw/9pfs/codir.c +++ b/hw/9pfs/codir.c @@ -11,6 +11,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "fsdev/qemu-fsdev.h" #include "qemu/thread.h" diff --git a/hw/9pfs/cofile.c b/hw/9pfs/cofile.c index 83bb6c14e0..20f93a90e7 100644 --- a/hw/9pfs/cofile.c +++ b/hw/9pfs/cofile.c @@ -11,6 +11,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "fsdev/qemu-fsdev.h" #include "qemu/thread.h" diff --git a/hw/9pfs/cofs.c b/hw/9pfs/cofs.c index 0b321b456e..9d0adc2e78 100644 --- a/hw/9pfs/cofs.c +++ b/hw/9pfs/cofs.c @@ -11,6 +11,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "fsdev/qemu-fsdev.h" #include "qemu/thread.h" diff --git a/hw/9pfs/coth.c b/hw/9pfs/coth.c index 9778f24b00..2802d41cce 100644 --- a/hw/9pfs/coth.c +++ b/hw/9pfs/coth.c @@ -12,6 +12,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "block/thread-pool.h" #include "qemu/coroutine.h" diff --git a/hw/9pfs/coxattr.c b/hw/9pfs/coxattr.c index 0e00ffaa0d..dbcd09e0fd 100644 --- a/hw/9pfs/coxattr.c +++ b/hw/9pfs/coxattr.c @@ -11,6 +11,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "fsdev/qemu-fsdev.h" #include "qemu/thread.h" diff --git a/hw/9pfs/trace-events b/hw/9pfs/trace-events index 10188daf7f..6c77966c0b 100644 --- a/hw/9pfs/trace-events +++ b/hw/9pfs/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # 9p.c v9fs_rcancel(uint16_t tag, uint8_t id) "tag %d id %d" diff --git a/hw/9pfs/virtio-9p-device.c b/hw/9pfs/virtio-9p-device.c index 14371a78ef..54ee93b71f 100644 --- a/hw/9pfs/virtio-9p-device.c +++ b/hw/9pfs/virtio-9p-device.c @@ -11,6 +11,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "hw/virtio/virtio.h" #include "qemu/sockets.h" diff --git a/hw/9pfs/xen-9p-backend.c b/hw/9pfs/xen-9p-backend.c index a969fcc54c..65c4979c3c 100644 --- a/hw/9pfs/xen-9p-backend.c +++ b/hw/9pfs/xen-9p-backend.c @@ -8,6 +8,11 @@ * */ +/* + * Not so fast! You might want to read the 9p developer docs first: + * https://wiki.qemu.org/Documentation/9p + */ + #include "qemu/osdep.h" #include "hw/9pfs/9p.h" diff --git a/hw/Kconfig b/hw/Kconfig index ff40bd3f7b..8cb7664d70 100644 --- a/hw/Kconfig +++ b/hw/Kconfig @@ -21,6 +21,7 @@ source mem/Kconfig source misc/Kconfig source net/Kconfig source nubus/Kconfig +source nvme/Kconfig source nvram/Kconfig source pci-bridge/Kconfig source pci-host/Kconfig @@ -31,6 +32,7 @@ source remote/Kconfig source rtc/Kconfig source scsi/Kconfig source sd/Kconfig +source sensor/Kconfig source smbios/Kconfig source ssi/Kconfig source timer/Kconfig @@ -47,11 +49,9 @@ source avr/Kconfig source cris/Kconfig source hppa/Kconfig source i386/Kconfig -source lm32/Kconfig source m68k/Kconfig source microblaze/Kconfig source mips/Kconfig -source moxie/Kconfig source nios2/Kconfig source openrisc/Kconfig source ppc/Kconfig @@ -62,7 +62,6 @@ source sh4/Kconfig source sparc/Kconfig source sparc64/Kconfig source tricore/Kconfig -source unicore32/Kconfig source xtensa/Kconfig # Symbols used by multiple targets diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig index 1932f66af8..cfc4ede8d9 100644 --- a/hw/acpi/Kconfig +++ b/hw/acpi/Kconfig @@ -42,3 +42,7 @@ config ACPI_VMGENID depends on PC config ACPI_HW_REDUCED + bool + select ACPI + select ACPI_MEMORY_HOTPLUG + select ACPI_NVDIMM diff --git a/hw/acpi/acpi-x86-stub.c b/hw/acpi/acpi-x86-stub.c index f88d6a090b..e9e46c5c5f 100644 --- a/hw/acpi/acpi-x86-stub.c +++ b/hw/acpi/acpi-x86-stub.c @@ -1,7 +1,13 @@ #include "qemu/osdep.h" #include "hw/i386/pc.h" +#include "hw/i386/acpi-build.h" void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid, const CPUArchIdList *apic_ids, GArray *entry) { } + +Object *acpi_get_i386_pci_host(void) +{ + return NULL; +} diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index d33ce8954a..d5103e6d7b 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -1830,6 +1830,7 @@ build_rsdt(GArray *table_data, BIOSLinker *linker, GArray *table_offsets, int i; unsigned rsdt_entries_offset; AcpiRsdtDescriptorRev1 *rsdt; + int rsdt_start = table_data->len; const unsigned table_data_len = (sizeof(uint32_t) * table_offsets->len); const unsigned rsdt_entry_size = sizeof(rsdt->table_offset_entry[0]); const size_t rsdt_len = sizeof(*rsdt) + table_data_len; @@ -1846,7 +1847,8 @@ build_rsdt(GArray *table_data, BIOSLinker *linker, GArray *table_offsets, ACPI_BUILD_TABLE_FILE, ref_tbl_offset); } build_header(linker, table_data, - (void *)rsdt, "RSDT", rsdt_len, 1, oem_id, oem_table_id); + (void *)(table_data->data + rsdt_start), + "RSDT", rsdt_len, 1, oem_id, oem_table_id); } /* Build xsdt table */ @@ -1857,6 +1859,7 @@ build_xsdt(GArray *table_data, BIOSLinker *linker, GArray *table_offsets, int i; unsigned xsdt_entries_offset; AcpiXsdtDescriptorRev2 *xsdt; + int xsdt_start = table_data->len; const unsigned table_data_len = (sizeof(uint64_t) * table_offsets->len); const unsigned xsdt_entry_size = sizeof(xsdt->table_offset_entry[0]); const size_t xsdt_len = sizeof(*xsdt) + table_data_len; @@ -1873,7 +1876,8 @@ build_xsdt(GArray *table_data, BIOSLinker *linker, GArray *table_offsets, ACPI_BUILD_TABLE_FILE, ref_tbl_offset); } build_header(linker, table_data, - (void *)xsdt, "XSDT", xsdt_len, 1, oem_id, oem_table_id); + (void *)(table_data->data + xsdt_start), + "XSDT", xsdt_len, 1, oem_id, oem_table_id); } void build_srat_memory(AcpiSratMemoryAffinity *numamem, uint64_t base, @@ -2040,6 +2044,7 @@ build_hdr: "FACP", tbl->len - fadt_start, f->rev, oem_id, oem_table_id); } +#ifdef CONFIG_TPM /* * build_tpm2 - Build the TPM2 table as specified in * table 7: TCG Hardware Interface Description Table Format for TPM 2.0 @@ -2053,10 +2058,9 @@ void build_tpm2(GArray *table_data, BIOSLinker *linker, GArray *tcpalog, uint64_t control_area_start_address; TPMIf *tpmif = tpm_find(); uint32_t start_method; - void *tpm2_ptr; tpm2_start = table_data->len; - tpm2_ptr = acpi_data_push(table_data, sizeof(AcpiTableHeader)); + acpi_data_push(table_data, sizeof(AcpiTableHeader)); /* Platform Class */ build_append_int_noprefix(table_data, TPM2_ACPI_CLASS_CLIENT, 2); @@ -2095,9 +2099,10 @@ void build_tpm2(GArray *table_data, BIOSLinker *linker, GArray *tcpalog, log_addr_offset, 8, ACPI_BUILD_TPMLOG_FILE, 0); build_header(linker, table_data, - tpm2_ptr, "TPM2", table_data->len - tpm2_start, 4, oem_id, - oem_table_id); + (void *)(table_data->data + tpm2_start), + "TPM2", table_data->len - tpm2_start, 4, oem_id, oem_table_id); } +#endif Aml *build_crs(PCIHostState *host, CrsRangeSet *range_set, uint32_t io_offset, uint32_t mmio32_offset, uint64_t mmio64_offset, diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c index e2317be546..f82e9512fd 100644 --- a/hw/acpi/cpu.c +++ b/hw/acpi/cpu.c @@ -1,5 +1,4 @@ #include "qemu/osdep.h" -#include "hw/boards.h" #include "migration/vmstate.h" #include "hw/acpi/cpu.h" #include "qapi/error.h" diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c index 5454be67d5..e28457a7d1 100644 --- a/hw/acpi/generic_event_device.c +++ b/hw/acpi/generic_event_device.c @@ -11,7 +11,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "exec/address-spaces.h" #include "hw/acpi/acpi.h" #include "hw/acpi/generic_event_device.h" #include "hw/irq.h" @@ -208,7 +207,7 @@ static void ged_regs_write(void *opaque, hwaddr addr, uint64_t data, return; case ACPI_GED_REG_RESET: if (data == ACPI_GED_RESET_VALUE) { - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); } return; } diff --git a/hw/acpi/ghes-stub.c b/hw/acpi/ghes-stub.c new file mode 100644 index 0000000000..c315de1802 --- /dev/null +++ b/hw/acpi/ghes-stub.c @@ -0,0 +1,22 @@ +/* + * Support for generating APEI tables and recording CPER for Guests: + * stub functions. + * + * Copyright (c) 2021 Linaro, Ltd + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/acpi/ghes.h" + +int acpi_ghes_record_errors(uint8_t source_id, uint64_t physical_address) +{ + return -1; +} + +bool acpi_ghes_present(void) +{ + return false; +} diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c index a4dac6bf15..a749b84d62 100644 --- a/hw/acpi/ghes.c +++ b/hw/acpi/ghes.c @@ -386,6 +386,8 @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s, /* Create a read-write fw_cfg file for Address */ fw_cfg_add_file_callback(s, ACPI_GHES_DATA_ADDR_FW_CFG_FILE, NULL, NULL, NULL, &(ags->ghes_addr_le), sizeof(ags->ghes_addr_le), false); + + ags->present = true; } int acpi_ghes_record_errors(uint8_t source_id, uint64_t physical_address) @@ -443,3 +445,18 @@ int acpi_ghes_record_errors(uint8_t source_id, uint64_t physical_address) return ret; } + +bool acpi_ghes_present(void) +{ + AcpiGedState *acpi_ged_state; + AcpiGhesState *ags; + + acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED, + NULL)); + + if (!acpi_ged_state) { + return false; + } + ags = &acpi_ged_state->ghes_state; + return ags->present; +} diff --git a/hw/acpi/ich9.c b/hw/acpi/ich9.c index 853447cf9d..778e27b659 100644 --- a/hw/acpi/ich9.c +++ b/hw/acpi/ich9.c @@ -35,7 +35,6 @@ #include "sysemu/runstate.h" #include "hw/acpi/acpi.h" #include "hw/acpi/tco.h" -#include "exec/address-spaces.h" #include "hw/i386/ich9.h" #include "hw/mem/pc-dimm.h" @@ -218,6 +217,26 @@ static const VMStateDescription vmstate_cpuhp_state = { } }; +static bool vmstate_test_use_pcihp(void *opaque) +{ + ICH9LPCPMRegs *s = opaque; + + return s->use_acpi_hotplug_bridge; +} + +static const VMStateDescription vmstate_pcihp_state = { + .name = "ich9_pm/pcihp", + .version_id = 1, + .minimum_version_id = 1, + .needed = vmstate_test_use_pcihp, + .fields = (VMStateField[]) { + VMSTATE_PCI_HOTPLUG(acpi_pci_hotplug, + ICH9LPCPMRegs, + NULL, NULL), + VMSTATE_END_OF_LIST() + } +}; + const VMStateDescription vmstate_ich9_pm = { .name = "ich9_pm", .version_id = 1, @@ -239,6 +258,7 @@ const VMStateDescription vmstate_ich9_pm = { &vmstate_memhp_state, &vmstate_tco_io_state, &vmstate_cpuhp_state, + &vmstate_pcihp_state, NULL } }; @@ -260,6 +280,10 @@ static void pm_reset(void *opaque) } pm->smi_en_wmask = ~0; + if (pm->use_acpi_hotplug_bridge) { + acpi_pcihp_reset(&pm->acpi_pci_hotplug, true); + } + acpi_update_sci(&pm->acpi_regs, pm->irq); } @@ -298,6 +322,18 @@ void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm, pm->enable_tco = true; acpi_pm_tco_init(&pm->tco_regs, &pm->io); + if (pm->use_acpi_hotplug_bridge) { + acpi_pcihp_init(OBJECT(lpc_pci), + &pm->acpi_pci_hotplug, + pci_get_bus(lpc_pci), + pci_address_space_io(lpc_pci), + true, + ACPI_PCIHP_ADDR_ICH9); + + qbus_set_hotplug_handler(BUS(pci_get_bus(lpc_pci)), + OBJECT(lpc_pci)); + } + pm->irq = sci_irq; qemu_register_reset(pm_reset, pm); pm->powerdown_notifier.notify = pm_powerdown_req; @@ -369,6 +405,20 @@ static void ich9_pm_set_enable_tco(Object *obj, bool value, Error **errp) s->pm.enable_tco = value; } +static bool ich9_pm_get_acpi_pci_hotplug(Object *obj, Error **errp) +{ + ICH9LPCState *s = ICH9_LPC_DEVICE(obj); + + return s->pm.use_acpi_hotplug_bridge; +} + +static void ich9_pm_set_acpi_pci_hotplug(Object *obj, bool value, Error **errp) +{ + ICH9LPCState *s = ICH9_LPC_DEVICE(obj); + + s->pm.use_acpi_hotplug_bridge = value; +} + void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm) { static const uint32_t gpe0_len = ICH9_PMIO_GPE0_LEN; @@ -377,6 +427,7 @@ void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm) pm->disable_s3 = 0; pm->disable_s4 = 0; pm->s4_val = 2; + pm->use_acpi_hotplug_bridge = true; object_property_add_uint32_ptr(obj, ACPI_PM_PROP_PM_IO_BASE, &pm->pm_io_base, OBJ_PROP_FLAG_READ); @@ -400,6 +451,9 @@ void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm) object_property_add_bool(obj, ACPI_PM_PROP_TCO_ENABLED, ich9_pm_get_enable_tco, ich9_pm_set_enable_tco); + object_property_add_bool(obj, "acpi-pci-hotplug-with-bridge-support", + ich9_pm_get_acpi_pci_hotplug, + ich9_pm_set_acpi_pci_hotplug); } void ich9_pm_device_pre_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, @@ -407,6 +461,11 @@ void ich9_pm_device_pre_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, { ICH9LPCState *lpc = ICH9_LPC_DEVICE(hotplug_dev); + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + acpi_pcihp_device_pre_plug_cb(hotplug_dev, dev, errp); + return; + } + if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) && !lpc->pm.acpi_memory_hotplug.is_enabled) { error_setg(errp, @@ -442,6 +501,9 @@ void ich9_pm_device_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, } else { acpi_cpu_plug_cb(hotplug_dev, &lpc->pm.cpuhp_state, dev, errp); } + } else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + acpi_pcihp_device_plug_cb(hotplug_dev, &lpc->pm.acpi_pci_hotplug, + dev, errp); } else { error_setg(errp, "acpi: device plug request for not supported device" " type: %s", object_get_typename(OBJECT(dev))); @@ -474,6 +536,10 @@ void ich9_pm_device_unplug_request_cb(HotplugHandler *hotplug_dev, acpi_cpu_unplug_request_cb(hotplug_dev, &lpc->pm.cpuhp_state, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + acpi_pcihp_device_unplug_request_cb(hotplug_dev, + &lpc->pm.acpi_pci_hotplug, + dev, errp); } else { error_setg(errp, "acpi: device unplug request for not supported device" " type: %s", object_get_typename(OBJECT(dev))); @@ -491,6 +557,9 @@ void ich9_pm_device_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU) && !lpc->pm.cpu_hotplug_legacy) { acpi_cpu_unplug_cb(&lpc->pm.cpuhp_state, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + acpi_pcihp_device_unplug_cb(hotplug_dev, &lpc->pm.acpi_pci_hotplug, + dev, errp); } else { error_setg(errp, "acpi: device unplug for not supported device" " type: %s", object_get_typename(OBJECT(dev))); diff --git a/hw/acpi/memory_hotplug.c b/hw/acpi/memory_hotplug.c index 0bdcf15528..af37889423 100644 --- a/hw/acpi/memory_hotplug.c +++ b/hw/acpi/memory_hotplug.c @@ -2,7 +2,6 @@ #include "hw/acpi/memory_hotplug.h" #include "hw/acpi/pc-hotplug.h" #include "hw/mem/pc-dimm.h" -#include "hw/boards.h" #include "hw/qdev-core.h" #include "migration/vmstate.h" #include "trace.h" diff --git a/hw/acpi/meson.build b/hw/acpi/meson.build index dd69577212..29f804d13e 100644 --- a/hw/acpi/meson.build +++ b/hw/acpi/meson.build @@ -3,6 +3,7 @@ acpi_ss.add(files( 'acpi_interface.c', 'aml-build.c', 'bios-linker-loader.c', + 'core.c', 'utils.c', )) acpi_ss.add(when: 'CONFIG_ACPI_CPU_HOTPLUG', if_true: files('cpu.c')) @@ -13,13 +14,13 @@ acpi_ss.add(when: 'CONFIG_ACPI_PCI', if_true: files('pci.c')) acpi_ss.add(when: 'CONFIG_ACPI_VMGENID', if_true: files('vmgenid.c')) acpi_ss.add(when: 'CONFIG_ACPI_HW_REDUCED', if_true: files('generic_event_device.c')) acpi_ss.add(when: 'CONFIG_ACPI_HMAT', if_true: files('hmat.c')) -acpi_ss.add(when: 'CONFIG_ACPI_APEI', if_true: files('ghes.c')) -acpi_ss.add(when: 'CONFIG_ACPI_X86', if_true: files('core.c', 'piix4.c', 'pcihp.c'), if_false: files('acpi-stub.c')) +acpi_ss.add(when: 'CONFIG_ACPI_APEI', if_true: files('ghes.c'), if_false: files('ghes-stub.c')) +acpi_ss.add(when: 'CONFIG_ACPI_X86', if_true: files('piix4.c', 'pcihp.c')) acpi_ss.add(when: 'CONFIG_ACPI_X86_ICH', if_true: files('ich9.c', 'tco.c')) acpi_ss.add(when: 'CONFIG_IPMI', if_true: files('ipmi.c'), if_false: files('ipmi-stub.c')) acpi_ss.add(when: 'CONFIG_PC', if_false: files('acpi-x86-stub.c')) acpi_ss.add(when: 'CONFIG_TPM', if_true: files('tpm.c')) -softmmu_ss.add(when: 'CONFIG_ACPI', if_false: files('acpi-stub.c', 'aml-build-stub.c')) +softmmu_ss.add(when: 'CONFIG_ACPI', if_false: files('acpi-stub.c', 'aml-build-stub.c', 'ghes-stub.c')) softmmu_ss.add_all(when: 'CONFIG_ACPI', if_true: acpi_ss) softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('acpi-stub.c', 'aml-build-stub.c', - 'acpi-x86-stub.c', 'ipmi-stub.c')) + 'acpi-x86-stub.c', 'ipmi-stub.c', 'ghes-stub.c')) diff --git a/hw/acpi/pcihp.c b/hw/acpi/pcihp.c index f4cb3c979d..f4d706e47d 100644 --- a/hw/acpi/pcihp.c +++ b/hw/acpi/pcihp.c @@ -30,15 +30,16 @@ #include "hw/pci-host/i440fx.h" #include "hw/pci/pci.h" #include "hw/pci/pci_bridge.h" +#include "hw/pci/pci_host.h" +#include "hw/pci/pcie_port.h" +#include "hw/i386/acpi-build.h" #include "hw/acpi/acpi.h" -#include "exec/address-spaces.h" #include "hw/pci/pci_bus.h" #include "migration/vmstate.h" #include "qapi/error.h" #include "qom/qom-qobject.h" #include "trace.h" -#define ACPI_PCIHP_ADDR 0xae00 #define ACPI_PCIHP_SIZE 0x0018 #define PCI_UP_BASE 0x0000 #define PCI_DOWN_BASE 0x0004 @@ -105,6 +106,7 @@ static void *acpi_set_bsel(PCIBus *bus, void *opaque) static void acpi_set_pci_info(void) { static bool bsel_is_set; + Object *host = acpi_get_i386_pci_host(); PCIBus *bus; unsigned bsel_alloc = ACPI_PCIHP_BSEL_DEFAULT; @@ -113,7 +115,11 @@ static void acpi_set_pci_info(void) } bsel_is_set = true; - bus = find_i440fx(); /* TODO: Q35 support */ + if (!host) { + return; + } + + bus = PCI_HOST_BRIDGE(host)->bus; if (bus) { /* Scan all PCI buses. Set property to enable acpi based hotplug. */ pci_for_each_bus_depth_first(bus, acpi_set_bsel, NULL, &bsel_alloc); @@ -123,13 +129,14 @@ static void acpi_set_pci_info(void) static void acpi_pcihp_disable_root_bus(void) { static bool root_hp_disabled; + Object *host = acpi_get_i386_pci_host(); PCIBus *bus; if (root_hp_disabled) { return; } - bus = find_i440fx(); + bus = PCI_HOST_BRIDGE(host)->bus; if (bus) { /* setting the hotplug handler to NULL makes the bus non-hotpluggable */ qbus_set_hotplug_handler(BUS(bus), NULL); @@ -330,6 +337,13 @@ void acpi_pcihp_device_plug_cb(HotplugHandler *hotplug_dev, AcpiPciHpState *s, object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) { PCIBus *sec = pci_bridge_get_sec_bus(PCI_BRIDGE(pdev)); + /* Remove all hot-plug handlers if hot-plug is disabled on slot */ + if (object_dynamic_cast(OBJECT(dev), TYPE_PCIE_SLOT) && + !PCIE_SLOT(pdev)->hotplug) { + qbus_set_hotplug_handler(BUS(sec), NULL); + return; + } + qbus_set_hotplug_handler(BUS(sec), OBJECT(hotplug_dev)); /* We don't have to overwrite any other hotplug handler yet */ assert(QLIST_EMPTY(&sec->child)); @@ -489,10 +503,11 @@ static const MemoryRegionOps acpi_pcihp_io_ops = { }; void acpi_pcihp_init(Object *owner, AcpiPciHpState *s, PCIBus *root_bus, - MemoryRegion *address_space_io, bool bridges_enabled) + MemoryRegion *address_space_io, bool bridges_enabled, + uint16_t io_base) { s->io_len = ACPI_PCIHP_SIZE; - s->io_base = ACPI_PCIHP_ADDR; + s->io_base = io_base; s->root = root_bus; s->legacy_piix = !bridges_enabled; diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c index 8f8b0e95e5..48f7a1edbc 100644 --- a/hw/acpi/piix4.c +++ b/hw/acpi/piix4.c @@ -33,7 +33,6 @@ #include "sysemu/xen.h" #include "qapi/error.h" #include "qemu/range.h" -#include "exec/address-spaces.h" #include "hw/acpi/pcihp.h" #include "hw/acpi/cpu_hotplug.h" #include "hw/acpi/cpu.h" @@ -50,6 +49,8 @@ #define GPE_BASE 0xafe0 #define GPE_LEN 4 +#define ACPI_PCIHP_ADDR_PIIX4 0xae00 + struct pci_status { uint32_t up; /* deprecated, maintained for migration compatibility */ uint32_t down; @@ -608,7 +609,7 @@ static void piix4_acpi_system_hot_add_init(MemoryRegion *parent, if (s->use_acpi_hotplug_bridge || s->use_acpi_root_pci_hotplug) { acpi_pcihp_init(OBJECT(s), &s->acpi_pci_hotplug, bus, parent, - s->use_acpi_hotplug_bridge); + s->use_acpi_hotplug_bridge, ACPI_PCIHP_ADDR_PIIX4); } s->cpu_hotplug_legacy = true; diff --git a/hw/acpi/tpm.c b/hw/acpi/tpm.c index b96459e45b..cdc0227536 100644 --- a/hw/acpi/tpm.c +++ b/hw/acpi/tpm.c @@ -57,7 +57,7 @@ void tpm_build_ppi_acpi(TPMIf *tpm, Aml *dev) aml_operation_region( "TPP3", AML_SYSTEM_MEMORY, aml_int(TPM_PPI_ADDR_BASE + - 0x15a /* movv, docs/specs/tpm.txt */), + 0x15a /* movv, docs/specs/tpm.rst */), 0x1)); field = aml_field("TPP3", AML_BYTE_ACC, AML_NOLOCK, AML_PRESERVE); aml_append(field, aml_named_field("MOVV", 8)); diff --git a/hw/acpi/trace-events b/hw/acpi/trace-events index dcc1438f3a..974d770e8b 100644 --- a/hw/acpi/trace-events +++ b/hw/acpi/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # memory_hotplug.c mhp_acpi_invalid_slot_selected(uint32_t slot) "0x%"PRIx32 diff --git a/hw/adc/Kconfig b/hw/adc/Kconfig index 25d2229fb8..a825bd3d34 100644 --- a/hw/adc/Kconfig +++ b/hw/adc/Kconfig @@ -1,2 +1,5 @@ config STM32F2XX_ADC bool + +config MAX111X + bool diff --git a/hw/misc/max111x.c b/hw/adc/max111x.c similarity index 99% rename from hw/misc/max111x.c rename to hw/adc/max111x.c index 1b3234a519..e8bf4cccd4 100644 --- a/hw/misc/max111x.c +++ b/hw/adc/max111x.c @@ -11,7 +11,7 @@ */ #include "qemu/osdep.h" -#include "hw/misc/max111x.h" +#include "hw/adc/max111x.h" #include "hw/irq.h" #include "migration/vmstate.h" #include "qemu/module.h" diff --git a/hw/adc/meson.build b/hw/adc/meson.build index 6ddee23813..ac4f093fea 100644 --- a/hw/adc/meson.build +++ b/hw/adc/meson.build @@ -1,2 +1,4 @@ softmmu_ss.add(when: 'CONFIG_STM32F2XX_ADC', if_true: files('stm32f2xx_adc.c')) softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_adc.c')) +softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq-xadc.c')) +softmmu_ss.add(when: 'CONFIG_MAX111X', if_true: files('max111x.c')) diff --git a/hw/adc/trace-events b/hw/adc/trace-events index 4c3279ece2..456f21c8f4 100644 --- a/hw/adc/trace-events +++ b/hw/adc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # npcm7xx_adc.c npcm7xx_adc_read(const char *id, uint64_t offset, uint32_t value) " %s offset: 0x%04" PRIx64 " value 0x%04" PRIx32 diff --git a/hw/misc/zynq-xadc.c b/hw/adc/zynq-xadc.c similarity index 99% rename from hw/misc/zynq-xadc.c rename to hw/adc/zynq-xadc.c index 7b1972ce06..cfc7bab065 100644 --- a/hw/misc/zynq-xadc.c +++ b/hw/adc/zynq-xadc.c @@ -15,7 +15,7 @@ #include "qemu/osdep.h" #include "hw/irq.h" -#include "hw/misc/zynq-xadc.h" +#include "hw/adc/zynq-xadc.h" #include "migration/vmstate.h" #include "qemu/timer.h" #include "qemu/log.h" diff --git a/hw/alpha/Kconfig b/hw/alpha/Kconfig index 15c59ff264..9af650c94e 100644 --- a/hw/alpha/Kconfig +++ b/hw/alpha/Kconfig @@ -3,9 +3,7 @@ config DP264 imply PCI_DEVICES imply TEST_DEVICES imply E1000_PCI - select I82374 - select I8254 - select I8259 + select I82378 select IDE_CMD646 select MC146818RTC select PCI diff --git a/hw/alpha/alpha_sys.h b/hw/alpha/alpha_sys.h index e2c02e2bbe..2263e821da 100644 --- a/hw/alpha/alpha_sys.h +++ b/hw/alpha/alpha_sys.h @@ -10,8 +10,8 @@ #include "hw/intc/i8259.h" -PCIBus *typhoon_init(MemoryRegion *, ISABus **, qemu_irq *, AlphaCPU *[4], - pci_map_irq_fn); +PCIBus *typhoon_init(MemoryRegion *, qemu_irq *, qemu_irq *, AlphaCPU *[4], + pci_map_irq_fn, uint8_t devfn_min); /* alpha_pci.c. */ extern const MemoryRegionOps alpha_pci_ignore_ops; diff --git a/hw/alpha/dp264.c b/hw/alpha/dp264.c index c8e300d93f..c78ed96d0e 100644 --- a/hw/alpha/dp264.c +++ b/hw/alpha/dp264.c @@ -13,12 +13,9 @@ #include "hw/loader.h" #include "alpha_sys.h" #include "qemu/error-report.h" -#include "sysemu/sysemu.h" #include "hw/rtc/mc146818rtc.h" #include "hw/ide/pci.h" -#include "hw/timer/i8254.h" #include "hw/isa/superio.h" -#include "hw/dma/i8257.h" #include "net/net.h" #include "qemu/cutils.h" #include "qemu/datadir.h" @@ -59,8 +56,10 @@ static void clipper_init(MachineState *machine) AlphaCPU *cpus[4]; PCIBus *pci_bus; PCIDevice *pci_dev; + DeviceState *i82378_dev; ISABus *isa_bus; qemu_irq rtc_irq; + qemu_irq isa_irq; long size, i; char *palcode_filename; uint64_t palcode_entry; @@ -73,19 +72,57 @@ static void clipper_init(MachineState *machine) cpus[i] = ALPHA_CPU(cpu_create(machine->cpu_type)); } + /* + * arg0 -> memory size + * arg1 -> kernel entry point + * arg2 -> config word + * + * Config word: bits 0-5 -> ncpus + * bit 6 -> nographics option (for HWRPB CTB) + * + * See init_hwrpb() in the PALcode. + */ cpus[0]->env.trap_arg0 = ram_size; cpus[0]->env.trap_arg1 = 0; - cpus[0]->env.trap_arg2 = smp_cpus; + cpus[0]->env.trap_arg2 = smp_cpus | (!machine->enable_graphics << 6); - /* Init the chipset. */ - pci_bus = typhoon_init(machine->ram, &isa_bus, &rtc_irq, cpus, - clipper_pci_map_irq); + /* + * Init the chipset. Because we're using CLIPPER IRQ mappings, + * the minimum PCI device IdSel is 1. + */ + pci_bus = typhoon_init(machine->ram, &isa_irq, &rtc_irq, cpus, + clipper_pci_map_irq, PCI_DEVFN(1, 0)); + + /* + * Init the PCI -> ISA bridge. + * + * Technically, PCI-based Alphas shipped with one of three different + * PCI-ISA bridges: + * + * - Intel i82378 SIO + * - Cypress CY82c693UB + * - ALI M1533 + * + * (An Intel i82375 PCI-EISA bridge was also used on some models.) + * + * For simplicity, we model an i82378 here, even though it wouldn't + * have been on any Tsunami/Typhoon systems; it's close enough, and + * we don't want to deal with modelling the CY82c693UB (which has + * incompatible edge/level control registers, plus other peripherals + * like IDE and USB) or the M1533 (which also has IDE and USB). + * + * Importantly, we need to provide a PCI device node for it, otherwise + * some operating systems won't notice there's an ISA bus to configure. + */ + i82378_dev = DEVICE(pci_create_simple(pci_bus, PCI_DEVFN(7, 0), "i82378")); + isa_bus = ISA_BUS(qdev_get_child_bus(i82378_dev, "isa.0")); + + /* Connect the ISA PIC to the Typhoon IRQ used for ISA interrupts. */ + qdev_connect_gpio_out(i82378_dev, 0, isa_irq); /* Since we have an SRM-compatible PALcode, use the SRM epoch. */ mc146818_rtc_init(isa_bus, 1900, rtc_irq); - i8254_pit_init(isa_bus, 0x40, 0, NULL); - /* VGA setup. Don't bother loading the bios. */ pci_vga_init(pci_bus); @@ -94,9 +131,6 @@ static void clipper_init(MachineState *machine) pci_nic_init_nofail(&nd_table[i], pci_bus, "e1000", NULL); } - /* 2 82C37 (dma) */ - isa_create_simple(isa_bus, "i82374"); - /* Super I/O */ isa_create_simple(isa_bus, TYPE_SMC37C669_SUPERIO); diff --git a/hw/alpha/trace-events b/hw/alpha/trace-events index 5b8315f27f..952a816407 100644 --- a/hw/alpha/trace-events +++ b/hw/alpha/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pci.c alpha_pci_iack_write(void) "" diff --git a/hw/alpha/typhoon.c b/hw/alpha/typhoon.c index a42b319812..bd39c8ca86 100644 --- a/hw/alpha/typhoon.c +++ b/hw/alpha/typhoon.c @@ -11,10 +11,8 @@ #include "qemu/units.h" #include "qapi/error.h" #include "cpu.h" -#include "hw/boards.h" #include "hw/irq.h" #include "alpha_sys.h" -#include "exec/address-spaces.h" #include "qom/object.h" @@ -816,8 +814,9 @@ static void typhoon_alarm_timer(void *opaque) cpu_interrupt(CPU(s->cchip.cpu[cpu]), CPU_INTERRUPT_TIMER); } -PCIBus *typhoon_init(MemoryRegion *ram, ISABus **isa_bus, qemu_irq *p_rtc_irq, - AlphaCPU *cpus[4], pci_map_irq_fn sys_map_irq) +PCIBus *typhoon_init(MemoryRegion *ram, qemu_irq *p_isa_irq, + qemu_irq *p_rtc_irq, AlphaCPU *cpus[4], + pci_map_irq_fn sys_map_irq, uint8_t devfn_min) { MemoryRegion *addr_space = get_system_memory(); DeviceState *dev; @@ -845,6 +844,7 @@ PCIBus *typhoon_init(MemoryRegion *ram, ISABus **isa_bus, qemu_irq *p_rtc_irq, } } + *p_isa_irq = qemu_allocate_irq(typhoon_set_isa_irq, s, 0); *p_rtc_irq = qemu_allocate_irq(typhoon_set_timer_irq, s, 0); /* Main memory region, 0x00.0000.0000. Real hardware supports 32GB, @@ -887,7 +887,7 @@ PCIBus *typhoon_init(MemoryRegion *ram, ISABus **isa_bus, qemu_irq *p_rtc_irq, b = pci_register_root_bus(dev, "pci", typhoon_set_irq, sys_map_irq, s, &s->pchip.reg_mem, &s->pchip.reg_io, - 0, 64, TYPE_PCI_BUS); + devfn_min, 64, TYPE_PCI_BUS); phb->bus = b; sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); @@ -920,18 +920,6 @@ PCIBus *typhoon_init(MemoryRegion *ram, ISABus **isa_bus, qemu_irq *p_rtc_irq, /* Pchip1 PCI I/O, 0x802.FC00.0000, 32MB. */ /* Pchip1 PCI configuration, 0x802.FE00.0000, 16MB. */ - /* Init the ISA bus. */ - /* ??? Technically there should be a cy82c693ub pci-isa bridge. */ - { - qemu_irq *isa_irqs; - - *isa_bus = isa_bus_new(NULL, get_system_memory(), &s->pchip.reg_io, - &error_abort); - isa_irqs = i8259_init(*isa_bus, - qemu_allocate_irq(typhoon_set_isa_irq, s, 0)); - isa_bus_irqs(*isa_bus, isa_irqs); - } - return b; } diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index 8c37cf00da..4ba0aca067 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -6,6 +6,7 @@ config ARM_VIRT imply VFIO_PLATFORM imply VFIO_XGMAC imply TPM_TIS_SYSBUS + imply NVDIMM select ARM_GIC select ACPI select ARM_SMMUV3 @@ -142,6 +143,7 @@ config PXA2XX select SD select SSI select USB_OHCI + select PCMCIA config GUMSTIX bool @@ -237,6 +239,10 @@ config STELLARIS select STELLARIS_ENET # ethernet select UNIMP +config STM32VLDISCOVERY + bool + select STM32F100_SOC + config STRONGARM bool select PXA2XX @@ -294,7 +300,10 @@ config ZYNQ config ARM_V7M bool + # currently v7M must be included in a TCG build due to translate.c + default y if TCG && (ARM || AARCH64) select PTIMER + select ARM_COMPATIBLE_SEMIHOSTING config ALLWINNER_A10 bool @@ -324,6 +333,12 @@ config RASPI select SDHCI select USB_DWC2 +config STM32F100_SOC + bool + select ARM_V7M + select STM32F2XX_USART + select STM32F2XX_SPI + config STM32F205_SOC bool select ARM_V7M @@ -366,16 +381,22 @@ config XLNX_VERSAL select UNIMP select XLNX_ZDMA select XLNX_ZYNQMP + select OR_IRQ config NPCM7XX bool select A9MPCORE + select ADM1272 select ARM_GIC + select SMBUS select AT24C # EEPROM + select MAX34451 select PL310 # cache controller + select PMBUS select SERIAL select SSI select UNIMP + select PCA954X config FSL_IMX25 bool @@ -383,7 +404,7 @@ config FSL_IMX25 select IMX_FEC select IMX_I2C select WDT_IMX2 - select DS1338 + select SDHCI config FSL_IMX31 bool @@ -411,6 +432,7 @@ config ASPEED_SOC select PCA9552 select SERIAL select SMBUS_EEPROM + select PCA954X select SSI select SSI_M25P80 select TMP105 diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index d404f31e02..05e84728cb 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -16,10 +16,8 @@ */ #include "qemu/osdep.h" -#include "exec/address-spaces.h" #include "qapi/error.h" #include "qemu/module.h" -#include "cpu.h" #include "hw/sysbus.h" #include "hw/arm/allwinner-a10.h" #include "hw/misc/unimp.h" diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index 88259a9c0d..27f1070145 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -18,13 +18,11 @@ */ #include "qemu/osdep.h" -#include "exec/address-spaces.h" #include "qapi/error.h" #include "qemu/error-report.h" #include "qemu/module.h" #include "qemu/units.h" #include "hw/qdev-core.h" -#include "cpu.h" #include "hw/sysbus.h" #include "hw/char/serial.h" #include "hw/misc/unimp.h" diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index 2e5d0679e7..a1456cb0f4 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -13,6 +13,7 @@ #include "qemu/log.h" #include "qemu/module.h" #include "qemu/bitops.h" +#include "qemu/units.h" #include "qapi/error.h" #include "trace.h" #include "hw/sysbus.h" @@ -59,6 +60,7 @@ struct ARMSSEInfo { const char *cpu_type; uint32_t sse_version; int sram_banks; + uint32_t sram_bank_base; int num_cpus; uint32_t sys_version; uint32_t iidr; @@ -69,6 +71,7 @@ struct ARMSSEInfo { bool has_cpuid; bool has_cpu_pwrctrl; bool has_sse_counter; + bool has_tcms; Property *props; const ARMSSEDeviceInfo *devinfo; const bool *irq_is_common; @@ -102,7 +105,7 @@ static Property sse300_properties[] = { DEFINE_PROP_LINK("memory", ARMSSE, board_memory, TYPE_MEMORY_REGION, MemoryRegion *), DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64), - DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 15), + DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 18), DEFINE_PROP_UINT32("init-svtor", ARMSSE, init_svtor, 0x10000000), DEFINE_PROP_BOOL("CPU0_FPU", ARMSSE, cpu_fpu[0], true), DEFINE_PROP_BOOL("CPU0_DSP", ARMSSE, cpu_dsp[0], true), @@ -504,6 +507,7 @@ static const ARMSSEInfo armsse_variants[] = { .sse_version = ARMSSE_IOTKIT, .cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"), .sram_banks = 1, + .sram_bank_base = 0x20000000, .num_cpus = 1, .sys_version = 0x41743, .iidr = 0, @@ -514,6 +518,7 @@ static const ARMSSEInfo armsse_variants[] = { .has_cpuid = false, .has_cpu_pwrctrl = false, .has_sse_counter = false, + .has_tcms = false, .props = iotkit_properties, .devinfo = iotkit_devices, .irq_is_common = sse200_irq_is_common, @@ -523,6 +528,7 @@ static const ARMSSEInfo armsse_variants[] = { .sse_version = ARMSSE_SSE200, .cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"), .sram_banks = 4, + .sram_bank_base = 0x20000000, .num_cpus = 2, .sys_version = 0x22041743, .iidr = 0, @@ -533,6 +539,7 @@ static const ARMSSEInfo armsse_variants[] = { .has_cpuid = true, .has_cpu_pwrctrl = false, .has_sse_counter = false, + .has_tcms = false, .props = sse200_properties, .devinfo = sse200_devices, .irq_is_common = sse200_irq_is_common, @@ -542,6 +549,7 @@ static const ARMSSEInfo armsse_variants[] = { .sse_version = ARMSSE_SSE300, .cpu_type = ARM_CPU_TYPE_NAME("cortex-m55"), .sram_banks = 2, + .sram_bank_base = 0x21000000, .num_cpus = 1, .sys_version = 0x7e00043b, .iidr = 0x74a0043b, @@ -552,6 +560,7 @@ static const ARMSSEInfo armsse_variants[] = { .has_cpuid = true, .has_cpu_pwrctrl = true, .has_sse_counter = true, + .has_tcms = true, .props = sse300_properties, .devinfo = sse300_devices, .irq_is_common = sse300_irq_is_common, @@ -909,7 +918,6 @@ static void armsse_realize(DeviceState *dev, Error **errp) const ARMSSEDeviceInfo *devinfo; int i; MemoryRegion *mr; - Error *err = NULL; SysBusDevice *sbd_apb_ppc0; SysBusDevice *sbd_secctl; DeviceState *dev_apb_ppc0; @@ -918,6 +926,8 @@ static void armsse_realize(DeviceState *dev, Error **errp) DeviceState *dev_splitter; uint32_t addr_width_max; + ERRP_GUARD(); + if (!s->board_memory) { error_setg(errp, "memory property was not set"); return; @@ -1147,10 +1157,9 @@ static void armsse_realize(DeviceState *dev, Error **errp) uint32_t sram_bank_size = 1 << s->sram_addr_width; memory_region_init_ram(&s->sram[i], NULL, ramname, - sram_bank_size, &err); + sram_bank_size, errp); g_free(ramname); - if (err) { - error_propagate(errp, err); + if (*errp) { return; } object_property_set_link(OBJECT(&s->mpc[i]), "downstream", @@ -1161,7 +1170,7 @@ static void armsse_realize(DeviceState *dev, Error **errp) /* Map the upstream end of the MPC into the right place... */ sbd_mpc = SYS_BUS_DEVICE(&s->mpc[i]); memory_region_add_subregion(&s->container, - 0x20000000 + i * sram_bank_size, + info->sram_bank_base + i * sram_bank_size, sysbus_mmio_get_region(sbd_mpc, 1)); /* ...and its register interface */ memory_region_add_subregion(&s->container, 0x50083000 + i * 0x1000, @@ -1210,6 +1219,20 @@ static void armsse_realize(DeviceState *dev, Error **errp) sysbus_mmio_get_region(sbd, 1)); } + if (info->has_tcms) { + /* The SSE-300 has an ITCM at 0x0000_0000 and a DTCM at 0x2000_0000 */ + memory_region_init_ram(&s->itcm, NULL, "sse300-itcm", 512 * KiB, errp); + if (*errp) { + return; + } + memory_region_init_ram(&s->dtcm, NULL, "sse300-dtcm", 512 * KiB, errp); + if (*errp) { + return; + } + memory_region_add_subregion(&s->container, 0x00000000, &s->itcm); + memory_region_add_subregion(&s->container, 0x20000000, &s->dtcm); + } + /* Devices behind APB PPC0: * 0x40000000: timer0 * 0x40001000: timer1 diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index 6dd10d8470..9ce5c30cd5 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -10,7 +10,6 @@ #include "qemu/osdep.h" #include "hw/arm/armv7m.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/sysbus.h" #include "hw/arm/boot.h" #include "hw/loader.h" @@ -19,7 +18,6 @@ #include "sysemu/reset.h" #include "qemu/error-report.h" #include "qemu/module.h" -#include "exec/address-spaces.h" #include "target/arm/idau.h" /* Bitbanded IO. Each word corresponds to a single bit. */ @@ -178,6 +176,12 @@ static void armv7m_realize(DeviceState *dev, Error **errp) return; } } + if (object_property_find(OBJECT(s->cpu), "init-nsvtor")) { + if (!object_property_set_uint(OBJECT(s->cpu), "init-nsvtor", + s->init_nsvtor, errp)) { + return; + } + } if (object_property_find(OBJECT(s->cpu), "start-powered-off")) { if (!object_property_set_bool(OBJECT(s->cpu), "start-powered-off", s->start_powered_off, errp)) { @@ -256,6 +260,7 @@ static Property armv7m_properties[] = { MemoryRegion *), DEFINE_PROP_LINK("idau", ARMv7MState, idau, TYPE_IDAU_INTERFACE, Object *), DEFINE_PROP_UINT32("init-svtor", ARMv7MState, init_svtor, 0), + DEFINE_PROP_UINT32("init-nsvtor", ARMv7MState, init_nsvtor, 0), DEFINE_PROP_BOOL("enable-bitband", ARMv7MState, enable_bitband, false), DEFINE_PROP_BOOL("start-powered-off", ARMv7MState, start_powered_off, false), diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index a17b75f494..9d43e26c51 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -11,20 +11,16 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" -#include "exec/address-spaces.h" #include "hw/arm/boot.h" #include "hw/arm/aspeed.h" #include "hw/arm/aspeed_soc.h" -#include "hw/boards.h" +#include "hw/i2c/i2c_mux_pca954x.h" #include "hw/i2c/smbus_eeprom.h" #include "hw/misc/pca9552.h" -#include "hw/misc/tmp105.h" +#include "hw/sensor/tmp105.h" #include "hw/misc/led.h" #include "hw/qdev-properties.h" -#include "qemu/log.h" #include "sysemu/block-backend.h" -#include "sysemu/sysemu.h" #include "hw/loader.h" #include "qemu/error-report.h" #include "qemu/units.h" @@ -138,6 +134,19 @@ struct AspeedMachineState { /* Witherspoon hardware value: 0xF10AD216 (but use romulus definition) */ #define WITHERSPOON_BMC_HW_STRAP1 ROMULUS_BMC_HW_STRAP1 +/* Quanta-Q71l hardware value */ +#define QUANTA_Q71L_BMC_HW_STRAP1 ( \ + SCU_AST2400_HW_STRAP_DRAM_SIZE(DRAM_SIZE_128MB) | \ + SCU_AST2400_HW_STRAP_DRAM_CONFIG(2/* DDR3 with CL=6, CWL=5 */) | \ + SCU_AST2400_HW_STRAP_ACPI_DIS | \ + SCU_AST2400_HW_STRAP_SET_CLK_SOURCE(AST2400_CLK_24M_IN) | \ + SCU_HW_STRAP_VGA_CLASS_CODE | \ + SCU_HW_STRAP_SPI_MODE(SCU_HW_STRAP_SPI_PASS_THROUGH) | \ + SCU_AST2400_HW_STRAP_SET_CPU_AHB_RATIO(AST2400_CPU_AHB_RATIO_2_1) | \ + SCU_HW_STRAP_SPI_WIDTH | \ + SCU_HW_STRAP_VGA_SIZE_SET(VGA_8M_DRAM) | \ + SCU_AST2400_HW_STRAP_BOOT_MODE(AST2400_SPI_BOOT)) + /* AST2600 evb hardware value */ #define AST2600_EVB_HW_STRAP1 0x000000C0 #define AST2600_EVB_HW_STRAP2 0x00000003 @@ -146,6 +155,10 @@ struct AspeedMachineState { #define TACOMA_BMC_HW_STRAP1 0x00000000 #define TACOMA_BMC_HW_STRAP2 0x00000040 +/* Rainier hardware value: (QEMU prototype) */ +#define RAINIER_BMC_HW_STRAP1 0x00000000 +#define RAINIER_BMC_HW_STRAP2 0x00000000 + /* * The max ram region is for firmwares that scan the address space * with load/store to guess how much RAM the SoC has. @@ -327,7 +340,7 @@ static void aspeed_machine_init(MachineState *machine) object_property_set_int(OBJECT(&bmc->soc), "num-cs", amc->num_cs, &error_abort); object_property_set_link(OBJECT(&bmc->soc), "dram", - OBJECT(&bmc->ram_container), &error_abort); + OBJECT(machine->ram), &error_abort); if (machine->kernel_filename) { /* * When booting with a -kernel command line there is no u-boot @@ -433,6 +446,38 @@ static void palmetto_bmc_i2c_init(AspeedMachineState *bmc) object_property_set_int(OBJECT(dev), "temperature3", 110000, &error_abort); } +static void quanta_q71l_bmc_i2c_init(AspeedMachineState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + /* + * The quanta-q71l platform expects tmp75s which are compatible with + * tmp105s. + */ + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 1), "tmp105", 0x4c); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 1), "tmp105", 0x4e); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 1), "tmp105", 0x4f); + + /* TODO: i2c-1: Add baseboard FRU eeprom@54 24c64 */ + /* TODO: i2c-1: Add Frontpanel FRU eeprom@57 24c64 */ + /* TODO: Add Memory Riser i2c mux and eeproms. */ + + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 2), "pca9546", 0x74); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 2), "pca9548", 0x77); + + /* TODO: i2c-3: Add BIOS FRU eeprom@56 24c64 */ + + /* i2c-7 */ + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 7), "pca9546", 0x70); + /* - i2c@0: pmbus@59 */ + /* - i2c@1: pmbus@58 */ + /* - i2c@2: pmbus@58 */ + /* - i2c@3: pmbus@59 */ + + /* TODO: i2c-7: Add PDB FRU eeprom@52 */ + /* TODO: i2c-8: Add BMC FRU eeprom@50 */ +} + static void ast2500_evb_i2c_init(AspeedMachineState *bmc) { AspeedSoCState *soc = &bmc->soc; @@ -629,6 +674,58 @@ static void g220a_bmc_i2c_init(AspeedMachineState *bmc) eeprom_buf); } +static void rainier_bmc_i2c_init(AspeedMachineState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + /* The rainier expects a TMP275 but a TMP105 is compatible */ + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 4), TYPE_TMP105, + 0x48); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 4), TYPE_TMP105, + 0x49); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 4), TYPE_TMP105, + 0x4a); + + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 5), TYPE_TMP105, + 0x48); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 5), TYPE_TMP105, + 0x49); + + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 6), TYPE_TMP105, + 0x48); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 6), TYPE_TMP105, + 0x4a); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 6), TYPE_TMP105, + 0x4b); + + /* Bus 7: TODO dps310@76 */ + /* Bus 7: TODO max31785@52 */ + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 7), "pca9552", 0x61); + /* Bus 7: TODO si7021-a20@20 */ + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 7), TYPE_TMP105, + 0x48); + + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 8), TYPE_TMP105, + 0x48); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 8), TYPE_TMP105, + 0x4a); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 8), "pca9552", 0x61); + /* Bus 8: ucd90320@11 */ + /* Bus 8: ucd90320@b */ + /* Bus 8: ucd90320@c */ + + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 9), "tmp423", 0x4c); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 9), "tmp423", 0x4d); + + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 10), "tmp423", 0x4c); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 10), "tmp423", 0x4d); + + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 11), TYPE_TMP105, + 0x48); + i2c_slave_create_simple(aspeed_i2c_get_bus(&soc->i2c, 11), TYPE_TMP105, + 0x49); +} + static bool aspeed_get_mmio_exec(Object *obj, Error **errp) { return ASPEED_MACHINE(obj)->mmio_exec; @@ -728,6 +825,23 @@ static void aspeed_machine_palmetto_class_init(ObjectClass *oc, void *data) aspeed_soc_num_cpus(amc->soc_name); }; +static void aspeed_machine_quanta_q71l_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc); + + mc->desc = "Quanta-Q71l BMC (ARM926EJ-S)"; + amc->soc_name = "ast2400-a1"; + amc->hw_strap1 = QUANTA_Q71L_BMC_HW_STRAP1; + amc->fmc_model = "n25q256a"; + amc->spi_model = "mx25l25635e"; + amc->num_cs = 1; + amc->i2c_init = quanta_q71l_bmc_i2c_init; + mc->default_ram_size = 128 * MiB; + mc->default_cpus = mc->min_cpus = mc->max_cpus = + aspeed_soc_num_cpus(amc->soc_name); +} + static void aspeed_machine_supermicrox11_bmc_class_init(ObjectClass *oc, void *data) { @@ -811,6 +925,9 @@ static void aspeed_machine_swift_class_init(ObjectClass *oc, void *data) mc->default_ram_size = 512 * MiB; mc->default_cpus = mc->min_cpus = mc->max_cpus = aspeed_soc_num_cpus(amc->soc_name); + + mc->deprecation_reason = "redundant system. Please use a similar " + "OpenPOWER BMC, Witherspoon or Romulus."; }; static void aspeed_machine_witherspoon_class_init(ObjectClass *oc, void *data) @@ -835,7 +952,7 @@ static void aspeed_machine_ast2600_evb_class_init(ObjectClass *oc, void *data) MachineClass *mc = MACHINE_CLASS(oc); AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc); - mc->desc = "Aspeed AST2600 EVB (Cortex A7)"; + mc->desc = "Aspeed AST2600 EVB (Cortex-A7)"; amc->soc_name = "ast2600-a1"; amc->hw_strap1 = AST2600_EVB_HW_STRAP1; amc->hw_strap2 = AST2600_EVB_HW_STRAP2; @@ -854,7 +971,7 @@ static void aspeed_machine_tacoma_class_init(ObjectClass *oc, void *data) MachineClass *mc = MACHINE_CLASS(oc); AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc); - mc->desc = "OpenPOWER Tacoma BMC (Cortex A7)"; + mc->desc = "OpenPOWER Tacoma BMC (Cortex-A7)"; amc->soc_name = "ast2600-a1"; amc->hw_strap1 = TACOMA_BMC_HW_STRAP1; amc->hw_strap2 = TACOMA_BMC_HW_STRAP2; @@ -886,6 +1003,25 @@ static void aspeed_machine_g220a_class_init(ObjectClass *oc, void *data) aspeed_soc_num_cpus(amc->soc_name); }; +static void aspeed_machine_rainier_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc); + + mc->desc = "IBM Rainier BMC (Cortex-A7)"; + amc->soc_name = "ast2600-a1"; + amc->hw_strap1 = RAINIER_BMC_HW_STRAP1; + amc->hw_strap2 = RAINIER_BMC_HW_STRAP2; + amc->fmc_model = "mx66l1g45g"; + amc->spi_model = "mx66l1g45g"; + amc->num_cs = 2; + amc->macs_mask = ASPEED_MAC2_ON | ASPEED_MAC3_ON; + amc->i2c_init = rainier_bmc_i2c_init; + mc->default_ram_size = 1 * GiB; + mc->default_cpus = mc->min_cpus = mc->max_cpus = + aspeed_soc_num_cpus(amc->soc_name); +}; + static const TypeInfo aspeed_machine_types[] = { { .name = MACHINE_TYPE_NAME("palmetto-bmc"), @@ -927,6 +1063,14 @@ static const TypeInfo aspeed_machine_types[] = { .name = MACHINE_TYPE_NAME("g220a-bmc"), .parent = TYPE_ASPEED_MACHINE, .class_init = aspeed_machine_g220a_class_init, + }, { + .name = MACHINE_TYPE_NAME("quanta-q71l-bmc"), + .parent = TYPE_ASPEED_MACHINE, + .class_init = aspeed_machine_quanta_q71l_class_init, + }, { + .name = MACHINE_TYPE_NAME("rainier-bmc"), + .parent = TYPE_ASPEED_MACHINE, + .class_init = aspeed_machine_rainier_class_init, }, { .name = TYPE_ASPEED_MACHINE, .parent = TYPE_MACHINE, diff --git a/hw/arm/aspeed_ast2600.c b/hw/arm/aspeed_ast2600.c index bc87e754a3..e3013128c6 100644 --- a/hw/arm/aspeed_ast2600.c +++ b/hw/arm/aspeed_ast2600.c @@ -9,12 +9,9 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" -#include "exec/address-spaces.h" #include "hw/misc/unimp.h" #include "hw/arm/aspeed_soc.h" #include "hw/char/serial.h" -#include "qemu/log.h" #include "qemu/module.h" #include "qemu/error-report.h" #include "hw/i2c/aspeed_i2c.h" @@ -42,6 +39,7 @@ static const hwaddr aspeed_soc_ast2600_memmap[] = { [ASPEED_DEV_ETH2] = 0x1E680000, [ASPEED_DEV_ETH4] = 0x1E690000, [ASPEED_DEV_VIC] = 0x1E6C0000, + [ASPEED_DEV_HACE] = 0x1E6D0000, [ASPEED_DEV_SDMC] = 0x1E6E0000, [ASPEED_DEV_SCU] = 0x1E6E2000, [ASPEED_DEV_XDMA] = 0x1E6E7000, @@ -102,6 +100,7 @@ static const int aspeed_soc_ast2600_irqmap[] = { [ASPEED_DEV_I2C] = 110, /* 110 -> 125 */ [ASPEED_DEV_ETH1] = 2, [ASPEED_DEV_ETH2] = 3, + [ASPEED_DEV_HACE] = 4, [ASPEED_DEV_ETH3] = 32, [ASPEED_DEV_ETH4] = 33, [ASPEED_DEV_KCS] = 138, /* 138 -> 142 */ @@ -185,7 +184,8 @@ static void aspeed_soc_ast2600_init(Object *obj) object_initialize_child(obj, "mii[*]", &s->mii[i], TYPE_ASPEED_MII); } - object_initialize_child(obj, "xdma", &s->xdma, TYPE_ASPEED_XDMA); + snprintf(typename, sizeof(typename), TYPE_ASPEED_XDMA "-%s", socname); + object_initialize_child(obj, "xdma", &s->xdma, typename); snprintf(typename, sizeof(typename), "aspeed.gpio-%s", socname); object_initialize_child(obj, "gpio", &s->gpio, typename); @@ -213,6 +213,9 @@ static void aspeed_soc_ast2600_init(Object *obj) TYPE_SYSBUS_SDHCI); object_initialize_child(obj, "lpc", &s->lpc, TYPE_ASPEED_LPC); + + snprintf(typename, sizeof(typename), "aspeed.hace-%s", socname); + object_initialize_child(obj, "hace", &s->hace, typename); } /* @@ -344,10 +347,6 @@ static void aspeed_soc_ast2600_realize(DeviceState *dev, Error **errp) /* FMC, The number of CS is set at the board level */ object_property_set_link(OBJECT(&s->fmc), "dram", OBJECT(s->dram_mr), &error_abort); - if (!object_property_set_int(OBJECT(&s->fmc), "sdram-base", - sc->memmap[ASPEED_DEV_SDRAM], errp)) { - return; - } if (!sysbus_realize(SYS_BUS_DEVICE(&s->fmc), errp)) { return; } @@ -498,6 +497,16 @@ static void aspeed_soc_ast2600_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->lpc), 1 + aspeed_lpc_kcs_4, qdev_get_gpio_in(DEVICE(&s->a7mpcore), sc->irqmap[ASPEED_DEV_KCS] + aspeed_lpc_kcs_4)); + + /* HACE */ + object_property_set_link(OBJECT(&s->hace), "dram", OBJECT(s->dram_mr), + &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->hace), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->hace), 0, sc->memmap[ASPEED_DEV_HACE]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->hace), 0, + aspeed_soc_get_irq(s, ASPEED_DEV_HACE)); } static void aspeed_soc_ast2600_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index 057d053c84..3ad6c56fa9 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -12,12 +12,9 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" -#include "exec/address-spaces.h" #include "hw/misc/unimp.h" #include "hw/arm/aspeed_soc.h" #include "hw/char/serial.h" -#include "qemu/log.h" #include "qemu/module.h" #include "qemu/error-report.h" #include "hw/i2c/aspeed_i2c.h" @@ -34,6 +31,7 @@ static const hwaddr aspeed_soc_ast2400_memmap[] = { [ASPEED_DEV_VIC] = 0x1E6C0000, [ASPEED_DEV_SDMC] = 0x1E6E0000, [ASPEED_DEV_SCU] = 0x1E6E2000, + [ASPEED_DEV_HACE] = 0x1E6E3000, [ASPEED_DEV_XDMA] = 0x1E6E7000, [ASPEED_DEV_VIDEO] = 0x1E700000, [ASPEED_DEV_ADC] = 0x1E6E9000, @@ -65,6 +63,7 @@ static const hwaddr aspeed_soc_ast2500_memmap[] = { [ASPEED_DEV_VIC] = 0x1E6C0000, [ASPEED_DEV_SDMC] = 0x1E6E0000, [ASPEED_DEV_SCU] = 0x1E6E2000, + [ASPEED_DEV_HACE] = 0x1E6E3000, [ASPEED_DEV_XDMA] = 0x1E6E7000, [ASPEED_DEV_ADC] = 0x1E6E9000, [ASPEED_DEV_VIDEO] = 0x1E700000, @@ -117,6 +116,7 @@ static const int aspeed_soc_ast2400_irqmap[] = { [ASPEED_DEV_ETH2] = 3, [ASPEED_DEV_XDMA] = 6, [ASPEED_DEV_SDHCI] = 26, + [ASPEED_DEV_HACE] = 4, }; #define aspeed_soc_ast2500_irqmap aspeed_soc_ast2400_irqmap @@ -196,7 +196,8 @@ static void aspeed_soc_init(Object *obj) TYPE_FTGMAC100); } - object_initialize_child(obj, "xdma", &s->xdma, TYPE_ASPEED_XDMA); + snprintf(typename, sizeof(typename), TYPE_ASPEED_XDMA "-%s", socname); + object_initialize_child(obj, "xdma", &s->xdma, typename); snprintf(typename, sizeof(typename), "aspeed.gpio-%s", socname); object_initialize_child(obj, "gpio", &s->gpio, typename); @@ -212,6 +213,9 @@ static void aspeed_soc_init(Object *obj) } object_initialize_child(obj, "lpc", &s->lpc, TYPE_ASPEED_LPC); + + snprintf(typename, sizeof(typename), "aspeed.hace-%s", socname); + object_initialize_child(obj, "hace", &s->hace, typename); } static void aspeed_soc_realize(DeviceState *dev, Error **errp) @@ -301,10 +305,6 @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) /* FMC, The number of CS is set at the board level */ object_property_set_link(OBJECT(&s->fmc), "dram", OBJECT(s->dram_mr), &error_abort); - if (!object_property_set_int(OBJECT(&s->fmc), "sdram-base", - sc->memmap[ASPEED_DEV_SDRAM], errp)) { - return; - } if (!sysbus_realize(SYS_BUS_DEVICE(&s->fmc), errp)) { return; } @@ -425,6 +425,16 @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->lpc), 1 + aspeed_lpc_kcs_4, qdev_get_gpio_in(DEVICE(&s->lpc), aspeed_lpc_kcs_4)); + + /* HACE */ + object_property_set_link(OBJECT(&s->hace), "dram", OBJECT(s->dram_mr), + &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->hace), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->hace), 0, sc->memmap[ASPEED_DEV_HACE]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->hace), 0, + aspeed_soc_get_irq(s, ASPEED_DEV_HACE)); } static Property aspeed_soc_properties[] = { DEFINE_PROP_LINK("dram", AspeedSoCState, dram_mr, TYPE_MEMORY_REGION, diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index dcff13433e..48538c9360 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -126,6 +126,10 @@ static void bcm2835_peripherals_init(Object *obj) object_property_add_const_link(OBJECT(&s->dwc2), "dma-mr", OBJECT(&s->gpu_bus_mr)); + + /* Power Management */ + object_initialize_child(obj, "powermgt", &s->powermgt, + TYPE_BCM2835_POWERMGT); } static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) @@ -364,9 +368,16 @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, INTERRUPT_USB)); + /* Power Management */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->powermgt), errp)) { + return; + } + + memory_region_add_subregion(&s->peri_mr, PM_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->powermgt), 0)); + create_unimp(s, &s->txp, "bcm2835-txp", TXP_OFFSET, 0x1000); create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); - create_unimp(s, &s->powermgt, "bcm2835-powermgt", PM_OFFSET, 0x114); create_unimp(s, &s->i2s, "bcm2835-i2s", I2S_OFFSET, 0x100); create_unimp(s, &s->smi, "bcm2835-smi", SMI_OFFSET, 0x100); create_unimp(s, &s->spi[0], "bcm2835-spi0", SPI0_OFFSET, 0x20); diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c index de7ade2878..24354338ca 100644 --- a/hw/arm/bcm2836.c +++ b/hw/arm/bcm2836.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu/module.h" -#include "cpu.h" #include "hw/arm/bcm2836.h" #include "hw/arm/raspi_platform.h" #include "hw/sysbus.h" diff --git a/hw/arm/boot.c b/hw/arm/boot.c index e56c42ac22..57efb61ee4 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -25,7 +25,6 @@ #include "sysemu/device_tree.h" #include "qemu/config-file.h" #include "qemu/option.h" -#include "exec/address-spaces.h" #include "qemu/units.h" /* Kernel boot protocol is specified in the kernel docs @@ -1244,6 +1243,15 @@ static void arm_setup_firmware_boot(ARMCPU *cpu, struct arm_boot_info *info) bool try_decompressing_kernel; fw_cfg = fw_cfg_find(); + + if (!fw_cfg) { + error_report("This machine type does not support loading both " + "a guest firmware/BIOS image and a guest kernel at " + "the same time. You should change your QEMU command " + "line to specify one or the other, but not both."); + exit(1); + } + try_decompressing_kernel = arm_feature(&cpu->env, ARM_FEATURE_AARCH64); diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index 9d0d728180..294ba5de6e 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -16,11 +16,7 @@ */ #include "qemu/osdep.h" -#include "exec/address-spaces.h" #include "qapi/error.h" -#include "cpu.h" -#include "sysemu/sysemu.h" -#include "hw/sysbus.h" #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-a10.h" diff --git a/hw/arm/digic_boards.c b/hw/arm/digic_boards.c index 6cdc1d83fc..b771a3d8b7 100644 --- a/hw/arm/digic_boards.c +++ b/hw/arm/digic_boards.c @@ -27,14 +27,11 @@ #include "qapi/error.h" #include "qemu-common.h" #include "qemu/datadir.h" -#include "cpu.h" #include "hw/boards.h" -#include "exec/address-spaces.h" #include "qemu/error-report.h" #include "hw/arm/digic.h" #include "hw/block/flash.h" #include "hw/loader.h" -#include "sysemu/sysemu.h" #include "sysemu/qtest.h" #include "qemu/units.h" #include "qemu/cutils.h" diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index ced2769b10..5c7a51bbad 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -23,7 +23,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "qemu/log.h" #include "cpu.h" #include "hw/cpu/a9mpcore.h" #include "hw/irq.h" diff --git a/hw/arm/exynos4_boards.c b/hw/arm/exynos4_boards.c index 56b729141b..35dd9875da 100644 --- a/hw/arm/exynos4_boards.c +++ b/hw/arm/exynos4_boards.c @@ -25,8 +25,6 @@ #include "qemu/units.h" #include "qapi/error.h" #include "qemu/error-report.h" -#include "cpu.h" -#include "sysemu/sysemu.h" #include "hw/sysbus.h" #include "net/net.h" #include "hw/arm/boot.h" diff --git a/hw/arm/fsl-imx25.c b/hw/arm/fsl-imx25.c index 08a98f828f..24c4374590 100644 --- a/hw/arm/fsl-imx25.c +++ b/hw/arm/fsl-imx25.c @@ -24,10 +24,8 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/arm/fsl-imx25.h" #include "sysemu/sysemu.h" -#include "exec/address-spaces.h" #include "hw/qdev-properties.h" #include "chardev/char.h" diff --git a/hw/arm/fsl-imx31.c b/hw/arm/fsl-imx31.c index 0983998bb4..def27bb913 100644 --- a/hw/arm/fsl-imx31.c +++ b/hw/arm/fsl-imx31.c @@ -21,7 +21,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/arm/fsl-imx31.h" #include "sysemu/sysemu.h" #include "exec/address-spaces.h" diff --git a/hw/arm/highbank.c b/hw/arm/highbank.c index bf886268c5..c3cb315dbc 100644 --- a/hw/arm/highbank.c +++ b/hw/arm/highbank.c @@ -29,7 +29,6 @@ #include "sysemu/runstate.h" #include "sysemu/sysemu.h" #include "hw/boards.h" -#include "exec/address-spaces.h" #include "qemu/error-report.h" #include "hw/char/pl011.h" #include "hw/ide/ahci.h" @@ -170,7 +169,7 @@ struct HighbankRegsState { uint32_t regs[NUM_REGS]; }; -static VMStateDescription vmstate_highbank_regs = { +static const VMStateDescription vmstate_highbank_regs = { .name = "highbank-regs", .version_id = 0, .minimum_version_id = 0, diff --git a/hw/arm/imx25_pdk.c b/hw/arm/imx25_pdk.c index 1c201d0d8e..bd16acd4d9 100644 --- a/hw/arm/imx25_pdk.c +++ b/hw/arm/imx25_pdk.c @@ -25,12 +25,10 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/qdev-properties.h" #include "hw/arm/fsl-imx25.h" #include "hw/boards.h" #include "qemu/error-report.h" -#include "exec/address-spaces.h" #include "sysemu/qtest.h" #include "hw/i2c/i2c.h" #include "qemu/cutils.h" @@ -67,7 +65,6 @@ static struct arm_boot_info imx25_pdk_binfo; static void imx25_pdk_init(MachineState *machine) { - MachineClass *mc = MACHINE_GET_CLASS(machine); IMX25PDK *s = g_new0(IMX25PDK, 1); unsigned int ram_size; unsigned int alias_offset; @@ -79,8 +76,8 @@ static void imx25_pdk_init(MachineState *machine) /* We need to initialize our memory */ if (machine->ram_size > (FSL_IMX25_SDRAM0_SIZE + FSL_IMX25_SDRAM1_SIZE)) { - char *sz = size_to_str(mc->default_ram_size); - error_report("Invalid RAM size, should be %s", sz); + char *sz = size_to_str(FSL_IMX25_SDRAM0_SIZE + FSL_IMX25_SDRAM1_SIZE); + error_report("RAM size more than %s is not supported", sz); g_free(sz); exit(EXIT_FAILURE); } diff --git a/hw/arm/kzm.c b/hw/arm/kzm.c index e3f7d4ead2..39559c44c2 100644 --- a/hw/arm/kzm.c +++ b/hw/arm/kzm.c @@ -15,7 +15,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/arm/fsl-imx31.h" #include "hw/boards.h" #include "qemu/error-report.h" diff --git a/hw/arm/mcimx6ul-evk.c b/hw/arm/mcimx6ul-evk.c index ed69a7b037..77fae874b1 100644 --- a/hw/arm/mcimx6ul-evk.c +++ b/hw/arm/mcimx6ul-evk.c @@ -15,7 +15,6 @@ #include "hw/arm/fsl-imx6ul.h" #include "hw/boards.h" #include "hw/qdev-properties.h" -#include "sysemu/sysemu.h" #include "qemu/error-report.h" #include "sysemu/qtest.h" @@ -68,7 +67,7 @@ static void mcimx6ul_evk_init(MachineState *machine) static void mcimx6ul_evk_machine_init(MachineClass *mc) { - mc->desc = "Freescale i.MX6UL Evaluation Kit (Cortex A7)"; + mc->desc = "Freescale i.MX6UL Evaluation Kit (Cortex-A7)"; mc->init = mcimx6ul_evk_init; mc->max_cpus = FSL_IMX6UL_NUM_CPUS; mc->default_ram_id = "mcimx6ul-evk.ram"; diff --git a/hw/arm/mcimx7d-sabre.c b/hw/arm/mcimx7d-sabre.c index e57d52b344..935d4b0f1c 100644 --- a/hw/arm/mcimx7d-sabre.c +++ b/hw/arm/mcimx7d-sabre.c @@ -17,7 +17,6 @@ #include "hw/arm/fsl-imx7.h" #include "hw/boards.h" #include "hw/qdev-properties.h" -#include "sysemu/sysemu.h" #include "qemu/error-report.h" #include "sysemu/qtest.h" @@ -68,7 +67,7 @@ static void mcimx7d_sabre_init(MachineState *machine) static void mcimx7d_sabre_machine_init(MachineClass *mc) { - mc->desc = "Freescale i.MX7 DUAL SABRE (Cortex A7)"; + mc->desc = "Freescale i.MX7 DUAL SABRE (Cortex-A7)"; mc->init = mcimx7d_sabre_init; mc->max_cpus = FSL_IMX7_NUM_CPUS; mc->default_ram_id = "mcimx7d-sabre.ram"; diff --git a/hw/arm/meson.build b/hw/arm/meson.build index be39117b9b..721a8eb8be 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -24,6 +24,7 @@ arm_ss.add(when: 'CONFIG_Z2', if_true: files('z2.c')) arm_ss.add(when: 'CONFIG_REALVIEW', if_true: files('realview.c')) arm_ss.add(when: 'CONFIG_SBSA_REF', if_true: files('sbsa-ref.c')) arm_ss.add(when: 'CONFIG_STELLARIS', if_true: files('stellaris.c')) +arm_ss.add(when: 'CONFIG_STM32VLDISCOVERY', if_true: files('stm32vldiscovery.c')) arm_ss.add(when: 'CONFIG_COLLIE', if_true: files('collie.c')) arm_ss.add(when: 'CONFIG_VERSATILE', if_true: files('versatilepb.c')) arm_ss.add(when: 'CONFIG_VEXPRESS', if_true: files('vexpress.c')) @@ -39,6 +40,7 @@ arm_ss.add(when: 'CONFIG_STRONGARM', if_true: files('strongarm.c')) arm_ss.add(when: 'CONFIG_ALLWINNER_A10', if_true: files('allwinner-a10.c', 'cubieboard.c')) arm_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3.c', 'orangepi.c')) arm_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_peripherals.c', 'bcm2836.c', 'raspi.c')) +arm_ss.add(when: 'CONFIG_STM32F100_SOC', if_true: files('stm32f100_soc.c')) arm_ss.add(when: 'CONFIG_STM32F205_SOC', if_true: files('stm32f205_soc.c')) arm_ss.add(when: 'CONFIG_STM32F405_SOC', if_true: files('stm32f405_soc.c')) arm_ss.add(when: 'CONFIG_XLNX_ZYNQMP_ARM', if_true: files('xlnx-zynqmp.c', 'xlnx-zcu102.c')) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index 25016e464d..e23830f4b7 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -55,6 +55,7 @@ #include "hw/boards.h" #include "exec/address-spaces.h" #include "sysemu/sysemu.h" +#include "sysemu/reset.h" #include "hw/misc/unimp.h" #include "hw/char/cmsdk-apb-uart.h" #include "hw/timer/cmsdk-apb-timer.h" @@ -72,6 +73,7 @@ #include "hw/core/split-irq.h" #include "hw/qdev-clock.h" #include "qom/object.h" +#include "hw/irq.h" #define MPS2TZ_NUMIRQ_MAX 96 #define MPS2TZ_RAM_MAX 5 @@ -121,8 +123,10 @@ struct MPS2TZMachineClass { int numirq; /* Number of external interrupts */ int uart_overflow_irq; /* number of the combined UART overflow IRQ */ uint32_t init_svtor; /* init-svtor setting for SSE */ + uint32_t sram_addr_width; /* SRAM_ADDR_WIDTH setting for SSE */ const RAMInfo *raminfo; const char *armsse_type; + uint32_t boot_ram_size; /* size of ram at address 0; 0 == find in raminfo */ }; struct MPS2TZMachineState { @@ -153,6 +157,9 @@ struct MPS2TZMachineState { SplitIRQ cpu_irq_splitter[MPS2TZ_NUMIRQ_MAX]; Clock *sysclk; Clock *s32kclk; + + bool remap; + qemu_irq remap_irq; }; #define TYPE_MPS2TZ_MACHINE "mps2tz" @@ -228,25 +235,23 @@ static const RAMInfo an505_raminfo[] = { { }, }; +/* + * Note that the addresses and MPC numbering here should match up + * with those used in remap_memory(), which can swap the BRAM and QSPI. + */ static const RAMInfo an524_raminfo[] = { { .name = "bram", .base = 0x00000000, .size = 512 * KiB, .mpc = 0, .mrindex = 0, - }, { - .name = "sram", - .base = 0x20000000, - .size = 32 * 4 * KiB, - .mpc = -1, - .mrindex = 1, }, { /* We don't model QSPI flash yet; for now expose it as simple ROM */ .name = "QSPI", .base = 0x28000000, .size = 8 * MiB, .mpc = 1, - .mrindex = 2, + .mrindex = 1, .flags = IS_ROM, }, { .name = "DDR", @@ -260,23 +265,11 @@ static const RAMInfo an524_raminfo[] = { { }; static const RAMInfo an547_raminfo[] = { { - .name = "itcm", - .base = 0x00000000, - .size = 512 * KiB, - .mpc = -1, - .mrindex = 0, - }, { .name = "sram", .base = 0x01000000, .size = 2 * MiB, .mpc = 0, .mrindex = 1, - }, { - .name = "dtcm", - .base = 0x20000000, - .size = 4 * 128 * KiB, - .mpc = -1, - .mrindex = 2, }, { .name = "sram 2", .base = 0x21000000, @@ -457,6 +450,7 @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, object_initialize_child(OBJECT(mms), "scc", scc, TYPE_MPS2_SCC); sccdev = DEVICE(scc); + qdev_prop_set_uint32(sccdev, "scc-cfg0", mms->remap ? 1 : 0); qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); qdev_prop_set_uint32(sccdev, "scc-aid", 0x00200008); qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); @@ -573,6 +567,52 @@ static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 0); } +static hwaddr boot_mem_base(MPS2TZMachineState *mms) +{ + /* + * Return the canonical address of the block which will be mapped + * at address 0x0 (i.e. where the vector table is). + * This is usually 0, but if the AN524 alternate memory map is + * enabled it will be the base address of the QSPI block. + */ + return mms->remap ? 0x28000000 : 0; +} + +static void remap_memory(MPS2TZMachineState *mms, int map) +{ + /* + * Remap the memory for the AN524. 'map' is the value of + * SCC CFG_REG0 bit 0, i.e. 0 for the default map and 1 + * for the "option 1" mapping where QSPI is at address 0. + * + * Effectively we need to swap around the "upstream" ends of + * MPC 0 and MPC 1. + */ + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + int i; + + if (mmc->fpga_type != FPGA_AN524) { + return; + } + + memory_region_transaction_begin(); + for (i = 0; i < 2; i++) { + TZMPC *mpc = &mms->mpc[i]; + MemoryRegion *upstream = sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 1); + hwaddr addr = (i ^ map) ? 0x28000000 : 0; + + memory_region_set_address(upstream, addr); + } + memory_region_transaction_commit(); +} + +static void remap_irq_fn(void *opaque, int n, int level) +{ + MPS2TZMachineState *mms = opaque; + + remap_memory(mms, level); +} + static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, const int *irqs) @@ -710,8 +750,16 @@ static uint32_t boot_ram_size(MPS2TZMachineState *mms) const RAMInfo *p; MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + /* + * Use a per-board specification (for when the boot RAM is in + * the SSE and so doesn't have a RAMInfo list entry) + */ + if (mmc->boot_ram_size) { + return mmc->boot_ram_size; + } + for (p = mmc->raminfo; p->name; p++) { - if (p->base == 0) { + if (p->base == boot_mem_base(mms)) { return p->size; } } @@ -756,6 +804,7 @@ static void mps2tz_common_init(MachineState *machine) OBJECT(system_memory), &error_abort); qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", mmc->numirq); qdev_prop_set_uint32(iotkitdev, "init-svtor", mmc->init_svtor); + qdev_prop_set_uint32(iotkitdev, "SRAM_ADDR_WIDTH", mmc->sram_addr_width); qdev_connect_clock_in(iotkitdev, "MAINCLK", mms->sysclk); qdev_connect_clock_in(iotkitdev, "S32KCLK", mms->s32kclk); sysbus_realize(SYS_BUS_DEVICE(&mms->iotkit), &error_fatal); @@ -1095,6 +1144,16 @@ static void mps2tz_common_init(MachineState *machine) create_non_mpc_ram(mms); + if (mmc->fpga_type == FPGA_AN524) { + /* + * Connect the line from the SCC so that we can remap when the + * guest updates that register. + */ + mms->remap_irq = qemu_allocate_irq(remap_irq_fn, mms, 0); + qdev_connect_gpio_out_named(DEVICE(&mms->scc), "remap", 0, + mms->remap_irq); + } + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, boot_ram_size(mms)); } @@ -1117,12 +1176,47 @@ static void mps2_tz_idau_check(IDAUInterface *ii, uint32_t address, *iregion = region; } +static char *mps2_get_remap(Object *obj, Error **errp) +{ + MPS2TZMachineState *mms = MPS2TZ_MACHINE(obj); + const char *val = mms->remap ? "QSPI" : "BRAM"; + return g_strdup(val); +} + +static void mps2_set_remap(Object *obj, const char *value, Error **errp) +{ + MPS2TZMachineState *mms = MPS2TZ_MACHINE(obj); + + if (!strcmp(value, "BRAM")) { + mms->remap = false; + } else if (!strcmp(value, "QSPI")) { + mms->remap = true; + } else { + error_setg(errp, "Invalid remap value"); + error_append_hint(errp, "Valid values are BRAM and QSPI.\n"); + } +} + +static void mps2_machine_reset(MachineState *machine) +{ + MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); + + /* + * Set the initial memory mapping before triggering the reset of + * the rest of the system, so that the guest image loader and CPU + * reset see the correct mapping. + */ + remap_memory(mms, mms->remap); + qemu_devices_reset(); +} + static void mps2tz_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); IDAUInterfaceClass *iic = IDAU_INTERFACE_CLASS(oc); mc->init = mps2tz_common_init; + mc->reset = mps2_machine_reset; iic->check = mps2_tz_idau_check; } @@ -1168,8 +1262,10 @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->numirq = 92; mmc->uart_overflow_irq = 47; mmc->init_svtor = 0x10000000; + mmc->sram_addr_width = 15; mmc->raminfo = an505_raminfo; mmc->armsse_type = TYPE_IOTKIT; + mmc->boot_ram_size = 0; mps2tz_set_default_ram_info(mmc); } @@ -1195,8 +1291,10 @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->numirq = 92; mmc->uart_overflow_irq = 47; mmc->init_svtor = 0x10000000; + mmc->sram_addr_width = 15; mmc->raminfo = an505_raminfo; /* AN521 is the same as AN505 here */ mmc->armsse_type = TYPE_SSE200; + mmc->boot_ram_size = 0; mps2tz_set_default_ram_info(mmc); } @@ -1222,9 +1320,16 @@ static void mps3tz_an524_class_init(ObjectClass *oc, void *data) mmc->numirq = 95; mmc->uart_overflow_irq = 47; mmc->init_svtor = 0x10000000; + mmc->sram_addr_width = 15; mmc->raminfo = an524_raminfo; mmc->armsse_type = TYPE_SSE200; + mmc->boot_ram_size = 0; mps2tz_set_default_ram_info(mmc); + + object_class_property_add_str(oc, "remap", mps2_get_remap, mps2_set_remap); + object_class_property_set_description(oc, "remap", + "Set memory mapping. Valid values " + "are BRAM (default) and QSPI."); } static void mps3tz_an547_class_init(ObjectClass *oc, void *data) @@ -1249,8 +1354,10 @@ static void mps3tz_an547_class_init(ObjectClass *oc, void *data) mmc->numirq = 96; mmc->uart_overflow_irq = 48; mmc->init_svtor = 0x00000000; + mmc->sram_addr_width = 21; mmc->raminfo = an547_raminfo; mmc->armsse_type = TYPE_SSE300; + mmc->boot_ram_size = 512 * KiB; mps2tz_set_default_ram_info(mmc); } diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c index d2c29e82d1..5cfe7caf83 100644 --- a/hw/arm/msf2-soc.c +++ b/hw/arm/msf2-soc.c @@ -27,7 +27,6 @@ #include "qapi/error.h" #include "exec/address-spaces.h" #include "hw/char/serial.h" -#include "hw/irq.h" #include "hw/arm/msf2-soc.h" #include "hw/misc/unimp.h" #include "sysemu/sysemu.h" diff --git a/hw/arm/msf2-som.c b/hw/arm/msf2-som.c index f9b61c36dd..343ec977c0 100644 --- a/hw/arm/msf2-som.c +++ b/hw/arm/msf2-som.c @@ -31,7 +31,6 @@ #include "hw/arm/boot.h" #include "exec/address-spaces.h" #include "hw/arm/msf2-soc.h" -#include "cpu.h" #define DDR_BASE_ADDRESS 0xA0000000 #define DDR_SIZE (64 * MiB) diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c index 9cebece2de..2d612cc0c9 100644 --- a/hw/arm/musicpal.c +++ b/hw/arm/musicpal.c @@ -19,7 +19,6 @@ #include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/char/serial.h" -#include "hw/hw.h" #include "qemu/timer.h" #include "hw/ptimer.h" #include "hw/qdev-properties.h" @@ -32,7 +31,6 @@ #include "sysemu/block-backend.h" #include "sysemu/runstate.h" #include "sysemu/dma.h" -#include "exec/address-spaces.h" #include "ui/pixel_ops.h" #include "qemu/cutils.h" #include "qom/object.h" diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index 495b0f8e91..2ab0080e0b 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -16,7 +16,6 @@ #include "qemu/osdep.h" -#include "exec/address-spaces.h" #include "hw/arm/boot.h" #include "hw/arm/npcm7xx.h" #include "hw/char/serial.h" diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index e22fe4bf8f..e5a3243995 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -16,9 +16,9 @@ #include "qemu/osdep.h" -#include "exec/address-spaces.h" #include "hw/arm/npcm7xx.h" #include "hw/core/cpu.h" +#include "hw/i2c/i2c_mux_pca954x.h" #include "hw/i2c/smbus_eeprom.h" #include "hw/loader.h" #include "hw/qdev-core.h" @@ -27,10 +27,10 @@ #include "qemu-common.h" #include "qemu/datadir.h" #include "qemu/units.h" -#include "sysemu/sysemu.h" #define NPCM750_EVB_POWER_ON_STRAPS 0x00001ff7 #define QUANTA_GSJ_POWER_ON_STRAPS 0x00001fff +#define QUANTA_GBS_POWER_ON_STRAPS 0x000017ff static const char npcm7xx_default_bootrom[] = "npcm7xx_bootrom.bin"; @@ -222,7 +222,18 @@ static void quanta_gsj_i2c_init(NPCM7xxState *soc) at24c_eeprom_init(soc, 9, 0x55, 8192); at24c_eeprom_init(soc, 10, 0x55, 8192); - /* TODO: Add additional i2c devices. */ + /* + * i2c-11: + * - power-brick@36: delta,dps800 + * - hotswap@15: ti,lm5066i + */ + + /* + * i2c-12: + * - ucd90160@6b + */ + + i2c_slave_create_simple(npcm7xx_i2c_get_bus(soc, 15), "pca9548", 0x75); } static void quanta_gsj_fan_init(NPCM7xxMachine *machine, NPCM7xxState *soc) @@ -239,6 +250,65 @@ static void quanta_gsj_fan_init(NPCM7xxMachine *machine, NPCM7xxState *soc) npcm7xx_connect_pwm_fan(soc, &splitter[2], 0x05, 1); } +static void quanta_gbs_i2c_init(NPCM7xxState *soc) +{ + /* + * i2c-0: + * pca9546@71 + * + * i2c-1: + * pca9535@24 + * pca9535@20 + * pca9535@21 + * pca9535@22 + * pca9535@23 + * pca9535@25 + * pca9535@26 + * + * i2c-2: + * sbtsi@4c + * + * i2c-5: + * atmel,24c64@50 mb_fru + * pca9546@71 + * - channel 0: max31725@54 + * - channel 1: max31725@55 + * - channel 2: max31725@5d + * atmel,24c64@51 fan_fru + * - channel 3: atmel,24c64@52 hsbp_fru + * + * i2c-6: + * pca9545@73 + * + * i2c-7: + * pca9545@72 + * + * i2c-8: + * adi,adm1272@10 + * + * i2c-9: + * pca9546@71 + * - channel 0: isil,isl68137@60 + * - channel 1: isil,isl68137@61 + * - channel 2: isil,isl68137@63 + * - channel 3: isil,isl68137@45 + * + * i2c-10: + * pca9545@71 + * + * i2c-11: + * pca9545@76 + * + * i2c-12: + * maxim,max34451@4e + * isil,isl68137@5d + * isil,isl68137@5e + * + * i2c-14: + * pca9545@70 + */ +} + static void npcm750_evb_init(MachineState *machine) { NPCM7xxState *soc; @@ -270,6 +340,23 @@ static void quanta_gsj_init(MachineState *machine) npcm7xx_load_kernel(machine, soc); } +static void quanta_gbs_init(MachineState *machine) +{ + NPCM7xxState *soc; + + soc = npcm7xx_create_soc(machine, QUANTA_GBS_POWER_ON_STRAPS); + npcm7xx_connect_dram(soc, machine->ram); + qdev_realize(DEVICE(soc), NULL, &error_fatal); + + npcm7xx_load_bootrom(machine, soc); + + npcm7xx_connect_flash(&soc->fiu[0], 0, "mx66u51235f", + drive_get(IF_MTD, 0, 0)); + + quanta_gbs_i2c_init(soc); + npcm7xx_load_kernel(machine, soc); +} + static void npcm7xx_set_soc_type(NPCM7xxMachineClass *nmc, const char *type) { NPCM7xxClass *sc = NPCM7XX_CLASS(object_class_by_name(type)); @@ -301,7 +388,7 @@ static void npcm750_evb_machine_class_init(ObjectClass *oc, void *data) npcm7xx_set_soc_type(nmc, TYPE_NPCM750); - mc->desc = "Nuvoton NPCM750 Evaluation Board (Cortex A9)"; + mc->desc = "Nuvoton NPCM750 Evaluation Board (Cortex-A9)"; mc->init = npcm750_evb_init; mc->default_ram_size = 512 * MiB; }; @@ -313,11 +400,23 @@ static void gsj_machine_class_init(ObjectClass *oc, void *data) npcm7xx_set_soc_type(nmc, TYPE_NPCM730); - mc->desc = "Quanta GSJ (Cortex A9)"; + mc->desc = "Quanta GSJ (Cortex-A9)"; mc->init = quanta_gsj_init; mc->default_ram_size = 512 * MiB; }; +static void gbs_bmc_machine_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_CLASS(oc); + MachineClass *mc = MACHINE_CLASS(oc); + + npcm7xx_set_soc_type(nmc, TYPE_NPCM730); + + mc->desc = "Quanta GBS (Cortex-A9)"; + mc->init = quanta_gbs_init; + mc->default_ram_size = 1 * GiB; +} + static const TypeInfo npcm7xx_machine_types[] = { { .name = TYPE_NPCM7XX_MACHINE, @@ -334,6 +433,10 @@ static const TypeInfo npcm7xx_machine_types[] = { .name = MACHINE_TYPE_NAME("quanta-gsj"), .parent = TYPE_NPCM7XX_MACHINE, .class_init = gsj_machine_class_init, + }, { + .name = MACHINE_TYPE_NAME("quanta-gbs-bmc"), + .parent = TYPE_NPCM7XX_MACHINE, + .class_init = gbs_bmc_machine_class_init, }, }; diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c index e15981e019..9407c2f268 100644 --- a/hw/arm/nrf51_soc.c +++ b/hw/arm/nrf51_soc.c @@ -13,9 +13,7 @@ #include "hw/arm/boot.h" #include "hw/sysbus.h" #include "hw/misc/unimp.h" -#include "exec/address-spaces.h" #include "qemu/log.h" -#include "cpu.h" #include "hw/arm/nrf51.h" #include "hw/arm/nrf51_soc.h" diff --git a/hw/arm/nseries.c b/hw/arm/nseries.c index 387eea4d44..af3164c551 100644 --- a/hw/arm/nseries.c +++ b/hw/arm/nseries.c @@ -34,16 +34,16 @@ #include "hw/boards.h" #include "hw/i2c/i2c.h" #include "hw/display/blizzard.h" +#include "hw/input/lm832x.h" #include "hw/input/tsc2xxx.h" #include "hw/misc/cbus.h" -#include "hw/misc/tmp105.h" +#include "hw/sensor/tmp105.h" #include "hw/qdev-properties.h" #include "hw/block/flash.h" #include "hw/hw.h" #include "hw/loader.h" #include "hw/sysbus.h" #include "qemu/log.h" -#include "exec/address-spaces.h" /* Nokia N8x0 support */ struct n800_s { @@ -417,7 +417,7 @@ static void n810_kbd_setup(struct n800_s *s) /* Attach the LM8322 keyboard to the I2C bus, * should happen in n8x0_i2c_setup and s->kbd be initialised here. */ s->kbd = DEVICE(i2c_slave_create_simple(omap_i2c_bus(s->mpu->i2c[0]), - "lm8323", N810_LM8323_ADDR)); + TYPE_LM8323, N810_LM8323_ADDR)); qdev_connect_gpio_out(s->kbd, 0, kbd_irq); } @@ -692,7 +692,7 @@ static uint32_t mipid_txrx(void *opaque, uint32_t cmd, int len) default: bad_cmd: qemu_log_mask(LOG_GUEST_ERROR, - "%s: unknown command %02x\n", __func__, s->cmd); + "%s: unknown command 0x%02x\n", __func__, s->cmd); break; } diff --git a/hw/arm/omap1.c b/hw/arm/omap1.c index 02c0f66431..180d3788f8 100644 --- a/hw/arm/omap1.c +++ b/hw/arm/omap1.c @@ -24,7 +24,6 @@ #include "qemu-common.h" #include "cpu.h" #include "exec/address-spaces.h" -#include "hw/boards.h" #include "hw/hw.h" #include "hw/irq.h" #include "hw/qdev-properties.h" diff --git a/hw/arm/omap2.c b/hw/arm/omap2.c index 16d388fc79..02b1aa8c97 100644 --- a/hw/arm/omap2.c +++ b/hw/arm/omap2.c @@ -27,7 +27,6 @@ #include "sysemu/qtest.h" #include "sysemu/reset.h" #include "sysemu/runstate.h" -#include "hw/boards.h" #include "hw/irq.h" #include "hw/qdev-properties.h" #include "hw/arm/boot.h" diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index 40cdb5c6d2..0cf9895ce7 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -21,12 +21,9 @@ #include "qemu/units.h" #include "exec/address-spaces.h" #include "qapi/error.h" -#include "cpu.h" -#include "hw/sysbus.h" #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-h3.h" -#include "sysemu/sysemu.h" static struct arm_boot_info orangepi_binfo = { .nb_cpus = AW_H3_NUM_CPUS, diff --git a/hw/arm/palm.c b/hw/arm/palm.c index 4e3dc5fbbf..68e11dd1ec 100644 --- a/hw/arm/palm.c +++ b/hw/arm/palm.c @@ -29,7 +29,6 @@ #include "hw/input/tsc2xxx.h" #include "hw/irq.h" #include "hw/loader.h" -#include "exec/address-spaces.h" #include "cpu.h" #include "qemu/cutils.h" #include "qom/object.h" diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index fdc4955e95..15a247efae 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -1437,7 +1437,7 @@ static void pxa2xx_i2c_write(void *opaque, hwaddr addr, break; case ISAR: - i2c_set_slave_address(I2C_SLAVE(s->slave), value & 0x7f); + i2c_slave_set_address(I2C_SLAVE(s->slave), value & 0x7f); break; case IDBR: diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c index cf6cb2a373..ed032fed54 100644 --- a/hw/arm/pxa2xx_pic.c +++ b/hw/arm/pxa2xx_pic.c @@ -301,7 +301,7 @@ DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) return dev; } -static VMStateDescription vmstate_pxa2xx_pic_regs = { +static const VMStateDescription vmstate_pxa2xx_pic_regs = { .name = "pxa2xx_pic", .version_id = 0, .minimum_version_id = 0, diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c index 990509d385..b30a17871f 100644 --- a/hw/arm/raspi.c +++ b/hw/arm/raspi.c @@ -16,14 +16,12 @@ #include "qemu/units.h" #include "qemu/cutils.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/arm/bcm2836.h" #include "hw/registerfields.h" #include "qemu/error-report.h" #include "hw/boards.h" #include "hw/loader.h" #include "hw/arm/boot.h" -#include "sysemu/sysemu.h" #include "qom/object.h" #define SMPBOOT_ADDR 0x300 /* this should leave enough space for ATAGS */ diff --git a/hw/arm/realview.c b/hw/arm/realview.c index 0831159d15..1c54316ba3 100644 --- a/hw/arm/realview.c +++ b/hw/arm/realview.c @@ -20,7 +20,6 @@ #include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/i2c/i2c.h" -#include "exec/address-spaces.h" #include "qemu/error-report.h" #include "hw/char/pl011.h" #include "hw/cpu/a9mpcore.h" diff --git a/hw/arm/sabrelite.c b/hw/arm/sabrelite.c index a3dbf85e0e..29fc777b61 100644 --- a/hw/arm/sabrelite.c +++ b/hw/arm/sabrelite.c @@ -15,7 +15,6 @@ #include "hw/arm/fsl-imx6.h" #include "hw/boards.h" #include "hw/qdev-properties.h" -#include "sysemu/sysemu.h" #include "qemu/error-report.h" #include "sysemu/qtest.h" @@ -106,7 +105,7 @@ static void sabrelite_init(MachineState *machine) static void sabrelite_machine_init(MachineClass *mc) { - mc->desc = "Freescale i.MX6 Quad SABRE Lite Board (Cortex A9)"; + mc->desc = "Freescale i.MX6 Quad SABRE Lite Board (Cortex-A9)"; mc->init = sabrelite_init; mc->max_cpus = FSL_IMX6_NUM_CPUS; mc->ignore_memory_transaction_failures = true; diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index 88dfb2284c..c1629df603 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -27,7 +27,6 @@ #include "sysemu/numa.h" #include "sysemu/runstate.h" #include "sysemu/sysemu.h" -#include "exec/address-spaces.h" #include "exec/hwaddr.h" #include "kvm_arm.h" #include "hw/arm/boot.h" @@ -692,13 +691,6 @@ static void sbsa_ref_init(MachineState *machine) firmware_loaded = sbsa_firmware_init(sms, sysmem, secure_sysmem); - if (machine->kernel_filename && firmware_loaded) { - error_report("sbsa-ref: No fw_cfg device on this machine, " - "so -kernel option is not supported when firmware loaded, " - "please load OS from hard disk instead"); - exit(1); - } - /* * This machine has EL3 enabled, external firmware should supply PSCI * implementation, so the QEMU's internal PSCI is disabled. diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c index 84d2c62c26..0459850a93 100644 --- a/hw/arm/smmu-common.c +++ b/hw/arm/smmu-common.c @@ -17,7 +17,6 @@ */ #include "qemu/osdep.h" -#include "exec/address-spaces.h" #include "trace.h" #include "exec/target_page.h" #include "hw/core/cpu.h" diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h index 3dac5766ca..d1885ae3f2 100644 --- a/hw/arm/smmuv3-internal.h +++ b/hw/arm/smmuv3-internal.h @@ -570,7 +570,7 @@ static inline int pa_range(STE *ste) /* CD fields */ -#define CD_VALID(x) extract32((x)->word[0], 30, 1) +#define CD_VALID(x) extract32((x)->word[0], 31, 1) #define CD_ASID(x) extract32((x)->word[1], 16, 16) #define CD_TTB(x, sel) \ ({ \ diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index 8705612535..01b60bee49 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -23,7 +23,6 @@ #include "migration/vmstate.h" #include "hw/qdev-core.h" #include "hw/pci/pci.h" -#include "exec/address-spaces.h" #include "cpu.h" #include "trace.h" #include "qemu/log.h" @@ -259,8 +258,9 @@ static void smmuv3_init_regs(SMMUv3State *s) s->idr[3] = FIELD_DP32(s->idr[3], IDR3, RIL, 1); s->idr[3] = FIELD_DP32(s->idr[3], IDR3, HAD, 1); - /* 4K and 64K granule support */ + /* 4K, 16K and 64K granule support */ s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN4K, 1); + s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN16K, 1); s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN64K, 1); s->idr[5] = FIELD_DP32(s->idr[5], IDR5, OAS, SMMU_IDR5_OAS); /* 44 bits */ @@ -503,7 +503,8 @@ static int decode_cd(SMMUTransCfg *cfg, CD *cd, SMMUEventInfo *event) tg = CD_TG(cd, i); tt->granule_sz = tg2granule(tg, i); - if ((tt->granule_sz != 12 && tt->granule_sz != 16) || CD_ENDI(cd)) { + if ((tt->granule_sz != 12 && tt->granule_sz != 14 && + tt->granule_sz != 16) || CD_ENDI(cd)) { goto bad_cd; } @@ -856,43 +857,45 @@ static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, dma_addr_t iova, static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd) { - uint8_t scale = 0, num = 0, ttl = 0; - dma_addr_t addr = CMD_ADDR(cmd); + dma_addr_t end, addr = CMD_ADDR(cmd); uint8_t type = CMD_TYPE(cmd); uint16_t vmid = CMD_VMID(cmd); + uint8_t scale = CMD_SCALE(cmd); + uint8_t num = CMD_NUM(cmd); + uint8_t ttl = CMD_TTL(cmd); bool leaf = CMD_LEAF(cmd); uint8_t tg = CMD_TG(cmd); - uint64_t first_page = 0, last_page; - uint64_t num_pages = 1; + uint64_t num_pages; + uint8_t granule; int asid = -1; - if (tg) { - scale = CMD_SCALE(cmd); - num = CMD_NUM(cmd); - ttl = CMD_TTL(cmd); - num_pages = (num + 1) * BIT_ULL(scale); - } - if (type == SMMU_CMD_TLBI_NH_VA) { asid = CMD_ASID(cmd); } + if (!tg) { + trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, 1, ttl, leaf); + smmuv3_inv_notifiers_iova(s, asid, addr, tg, 1); + smmu_iotlb_inv_iova(s, asid, addr, tg, 1, ttl); + return; + } + + /* RIL in use */ + + num_pages = (num + 1) * BIT_ULL(scale); + granule = tg * 2 + 10; + /* Split invalidations into ^2 range invalidations */ - last_page = num_pages - 1; - while (num_pages) { - uint8_t granule = tg * 2 + 10; - uint64_t mask, count; + end = addr + (num_pages << granule) - 1; - mask = dma_aligned_pow2_mask(first_page, last_page, 64 - granule); - count = mask + 1; + while (addr != end + 1) { + uint64_t mask = dma_aligned_pow2_mask(addr, end, 64); - trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, count, ttl, leaf); - smmuv3_inv_notifiers_iova(s, asid, addr, tg, count); - smmu_iotlb_inv_iova(s, asid, addr, tg, count, ttl); - - num_pages -= count; - first_page += count; - addr += count * BIT_ULL(granule); + num_pages = (mask + 1) >> granule; + trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf); + smmuv3_inv_notifiers_iova(s, asid, addr, tg, num_pages); + smmu_iotlb_inv_iova(s, asid, addr, tg, num_pages, ttl); + addr += mask + 1; } } diff --git a/hw/arm/spitz.c b/hw/arm/spitz.c index 6b3bf9828b..5aab0b8565 100644 --- a/hw/arm/spitz.c +++ b/hw/arm/spitz.c @@ -30,7 +30,7 @@ #include "audio/audio.h" #include "hw/boards.h" #include "hw/sysbus.h" -#include "hw/misc/max111x.h" +#include "hw/adc/max111x.h" #include "migration/vmstate.h" #include "exec/address-spaces.h" #include "cpu.h" @@ -769,9 +769,9 @@ static void spitz_wm8750_addr(void *opaque, int line, int level) { I2CSlave *wm = (I2CSlave *) opaque; if (level) - i2c_set_slave_address(wm, SPITZ_WM_ADDRH); + i2c_slave_set_address(wm, SPITZ_WM_ADDRH); else - i2c_set_slave_address(wm, SPITZ_WM_ADDRL); + i2c_slave_set_address(wm, SPITZ_WM_ADDRL); } static void spitz_i2c_setup(PXA2xxState *cpu) @@ -1134,7 +1134,7 @@ static bool is_version_0(void *opaque, int version_id) return version_id == 0; } -static VMStateDescription vmstate_sl_nand_info = { +static const VMStateDescription vmstate_sl_nand_info = { .name = "sl-nand", .version_id = 0, .minimum_version_id = 0, @@ -1170,7 +1170,7 @@ static const TypeInfo sl_nand_info = { .class_init = sl_nand_class_init, }; -static VMStateDescription vmstate_spitz_kbd = { +static const VMStateDescription vmstate_spitz_kbd = { .name = "spitz-keyboard", .version_id = 1, .minimum_version_id = 0, diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index 27292ec411..ad48cf2605 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -27,7 +27,6 @@ #include "migration/vmstate.h" #include "hw/misc/unimp.h" #include "hw/qdev-clock.h" -#include "cpu.h" #include "qom/object.h" #define GPIO_A 0 @@ -1454,13 +1453,67 @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) DeviceState *sddev; DeviceState *ssddev; - /* Some boards have both an OLED controller and SD card connected to + /* + * Some boards have both an OLED controller and SD card connected to * the same SSI port, with the SD card chip select connected to a * GPIO pin. Technically the OLED chip select is connected to the * SSI Fss pin. We do not bother emulating that as both devices * should never be selected simultaneously, and our OLED controller * ignores stray 0xff commands that occur when deselecting the SD * card. + * + * The h/w wiring is: + * - GPIO pin D0 is wired to the active-low SD card chip select + * - GPIO pin A3 is wired to the active-low OLED chip select + * - The SoC wiring of the PL061 "auxiliary function" for A3 is + * SSI0Fss ("frame signal"), which is an output from the SoC's + * SSI controller. The SSI controller takes SSI0Fss low when it + * transmits a frame, so it can work as a chip-select signal. + * - GPIO A4 is aux-function SSI0Rx, and wired to the SD card Tx + * (the OLED never sends data to the CPU, so no wiring needed) + * - GPIO A5 is aux-function SSI0Tx, and wired to the SD card Rx + * and the OLED display-data-in + * - GPIO A2 is aux-function SSI0Clk, wired to SD card and OLED + * serial-clock input + * So a guest that wants to use the OLED can configure the PL061 + * to make pins A2, A3, A5 aux-function, so they are connected + * directly to the SSI controller. When the SSI controller sends + * data it asserts SSI0Fss which selects the OLED. + * A guest that wants to use the SD card configures A2, A4 and A5 + * as aux-function, but leaves A3 as a software-controlled GPIO + * line. It asserts the SD card chip-select by using the PL061 + * to control pin D0, and lets the SSI controller handle Clk, Tx + * and Rx. (The SSI controller asserts Fss during tx cycles as + * usual, but because A3 is not set to aux-function this is not + * forwarded to the OLED, and so the OLED stays unselected.) + * + * The QEMU implementation instead is: + * - GPIO pin D0 is wired to the active-low SD card chip select, + * and also to the OLED chip-select which is implemented + * as *active-high* + * - SSI controller signals go to the devices regardless of + * whether the guest programs A2, A4, A5 as aux-function or not + * + * The problem with this implementation is if the guest doesn't + * care about the SD card and only uses the OLED. In that case it + * may choose never to do anything with D0 (leaving it in its + * default floating state, which reliably leaves the card disabled + * because an SD card has a pullup on CS within the card itself), + * and only set up A2, A3, A5. This for us would mean the OLED + * never gets the chip-select assert it needs. We work around + * this with a manual raise of D0 here (despite board creation + * code being the wrong place to raise IRQ lines) to put the OLED + * into an initially selected state. + * + * In theory the right way to model this would be: + * - Implement aux-function support in the PL061, with an + * extra set of AFIN and AFOUT GPIO lines (set up so that + * if a GPIO line is in auxfn mode the main GPIO in and out + * track the AFIN and AFOUT lines) + * - Wire the AFOUT for D0 up to either a line from the + * SSI controller that's pulled low around every transmit, + * or at least to an always-0 line here on the board + * - Make the ssd0323 OLED controller chipselect active-low */ bus = qdev_get_child_bus(dev, "ssi"); diff --git a/hw/arm/stm32f100_soc.c b/hw/arm/stm32f100_soc.c new file mode 100644 index 0000000000..0c4a5c6645 --- /dev/null +++ b/hw/arm/stm32f100_soc.c @@ -0,0 +1,182 @@ +/* + * STM32F100 SoC + * + * Copyright (c) 2021 Alexandre Iooss + * Copyright (c) 2014 Alistair Francis + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/module.h" +#include "hw/arm/boot.h" +#include "exec/address-spaces.h" +#include "hw/arm/stm32f100_soc.h" +#include "hw/qdev-properties.h" +#include "hw/misc/unimp.h" +#include "sysemu/sysemu.h" + +/* stm32f100_soc implementation is derived from stm32f205_soc */ + +static const uint32_t usart_addr[STM_NUM_USARTS] = { 0x40013800, 0x40004400, + 0x40004800 }; +static const uint32_t spi_addr[STM_NUM_SPIS] = { 0x40013000, 0x40003800 }; + +static const int usart_irq[STM_NUM_USARTS] = {37, 38, 39}; +static const int spi_irq[STM_NUM_SPIS] = {35, 36}; + +static void stm32f100_soc_initfn(Object *obj) +{ + STM32F100State *s = STM32F100_SOC(obj); + int i; + + object_initialize_child(obj, "armv7m", &s->armv7m, TYPE_ARMV7M); + + for (i = 0; i < STM_NUM_USARTS; i++) { + object_initialize_child(obj, "usart[*]", &s->usart[i], + TYPE_STM32F2XX_USART); + } + + for (i = 0; i < STM_NUM_SPIS; i++) { + object_initialize_child(obj, "spi[*]", &s->spi[i], TYPE_STM32F2XX_SPI); + } +} + +static void stm32f100_soc_realize(DeviceState *dev_soc, Error **errp) +{ + STM32F100State *s = STM32F100_SOC(dev_soc); + DeviceState *dev, *armv7m; + SysBusDevice *busdev; + int i; + + MemoryRegion *system_memory = get_system_memory(); + MemoryRegion *sram = g_new(MemoryRegion, 1); + MemoryRegion *flash = g_new(MemoryRegion, 1); + MemoryRegion *flash_alias = g_new(MemoryRegion, 1); + + /* + * Init flash region + * Flash starts at 0x08000000 and then is aliased to boot memory at 0x0 + */ + memory_region_init_rom(flash, OBJECT(dev_soc), "STM32F100.flash", + FLASH_SIZE, &error_fatal); + memory_region_init_alias(flash_alias, OBJECT(dev_soc), + "STM32F100.flash.alias", flash, 0, FLASH_SIZE); + memory_region_add_subregion(system_memory, FLASH_BASE_ADDRESS, flash); + memory_region_add_subregion(system_memory, 0, flash_alias); + + /* Init SRAM region */ + memory_region_init_ram(sram, NULL, "STM32F100.sram", SRAM_SIZE, + &error_fatal); + memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram); + + /* Init ARMv7m */ + armv7m = DEVICE(&s->armv7m); + qdev_prop_set_uint32(armv7m, "num-irq", 61); + qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); + qdev_prop_set_bit(armv7m, "enable-bitband", true); + object_property_set_link(OBJECT(&s->armv7m), "memory", + OBJECT(get_system_memory()), &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { + return; + } + + /* Attach UART (uses USART registers) and USART controllers */ + for (i = 0; i < STM_NUM_USARTS; i++) { + dev = DEVICE(&(s->usart[i])); + qdev_prop_set_chr(dev, "chardev", serial_hd(i)); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->usart[i]), errp)) { + return; + } + busdev = SYS_BUS_DEVICE(dev); + sysbus_mmio_map(busdev, 0, usart_addr[i]); + sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, usart_irq[i])); + } + + /* SPI 1 and 2 */ + for (i = 0; i < STM_NUM_SPIS; i++) { + dev = DEVICE(&(s->spi[i])); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->spi[i]), errp)) { + return; + } + busdev = SYS_BUS_DEVICE(dev); + sysbus_mmio_map(busdev, 0, spi_addr[i]); + sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, spi_irq[i])); + } + + create_unimplemented_device("timer[2]", 0x40000000, 0x400); + create_unimplemented_device("timer[3]", 0x40000400, 0x400); + create_unimplemented_device("timer[4]", 0x40000800, 0x400); + create_unimplemented_device("timer[6]", 0x40001000, 0x400); + create_unimplemented_device("timer[7]", 0x40001400, 0x400); + create_unimplemented_device("RTC", 0x40002800, 0x400); + create_unimplemented_device("WWDG", 0x40002C00, 0x400); + create_unimplemented_device("IWDG", 0x40003000, 0x400); + create_unimplemented_device("I2C1", 0x40005400, 0x400); + create_unimplemented_device("I2C2", 0x40005800, 0x400); + create_unimplemented_device("BKP", 0x40006C00, 0x400); + create_unimplemented_device("PWR", 0x40007000, 0x400); + create_unimplemented_device("DAC", 0x40007400, 0x400); + create_unimplemented_device("CEC", 0x40007800, 0x400); + create_unimplemented_device("AFIO", 0x40010000, 0x400); + create_unimplemented_device("EXTI", 0x40010400, 0x400); + create_unimplemented_device("GPIOA", 0x40010800, 0x400); + create_unimplemented_device("GPIOB", 0x40010C00, 0x400); + create_unimplemented_device("GPIOC", 0x40011000, 0x400); + create_unimplemented_device("GPIOD", 0x40011400, 0x400); + create_unimplemented_device("GPIOE", 0x40011800, 0x400); + create_unimplemented_device("ADC1", 0x40012400, 0x400); + create_unimplemented_device("timer[1]", 0x40012C00, 0x400); + create_unimplemented_device("timer[15]", 0x40014000, 0x400); + create_unimplemented_device("timer[16]", 0x40014400, 0x400); + create_unimplemented_device("timer[17]", 0x40014800, 0x400); + create_unimplemented_device("DMA", 0x40020000, 0x400); + create_unimplemented_device("RCC", 0x40021000, 0x400); + create_unimplemented_device("Flash Int", 0x40022000, 0x400); + create_unimplemented_device("CRC", 0x40023000, 0x400); +} + +static Property stm32f100_soc_properties[] = { + DEFINE_PROP_STRING("cpu-type", STM32F100State, cpu_type), + DEFINE_PROP_END_OF_LIST(), +}; + +static void stm32f100_soc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = stm32f100_soc_realize; + device_class_set_props(dc, stm32f100_soc_properties); +} + +static const TypeInfo stm32f100_soc_info = { + .name = TYPE_STM32F100_SOC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(STM32F100State), + .instance_init = stm32f100_soc_initfn, + .class_init = stm32f100_soc_class_init, +}; + +static void stm32f100_soc_types(void) +{ + type_register_static(&stm32f100_soc_info); +} + +type_init(stm32f100_soc_types) diff --git a/hw/arm/stm32vldiscovery.c b/hw/arm/stm32vldiscovery.c new file mode 100644 index 0000000000..7e8191ebf5 --- /dev/null +++ b/hw/arm/stm32vldiscovery.c @@ -0,0 +1,66 @@ +/* + * ST STM32VLDISCOVERY machine + * + * Copyright (c) 2021 Alexandre Iooss + * Copyright (c) 2014 Alistair Francis + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "qemu/error-report.h" +#include "hw/arm/stm32f100_soc.h" +#include "hw/arm/boot.h" + +/* stm32vldiscovery implementation is derived from netduinoplus2 */ + +/* Main SYSCLK frequency in Hz (24MHz) */ +#define SYSCLK_FRQ 24000000ULL + +static void stm32vldiscovery_init(MachineState *machine) +{ + DeviceState *dev; + + /* + * TODO: ideally we would model the SoC RCC and let it handle + * system_clock_scale, including its ability to define different + * possible SYSCLK sources. + */ + system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; + + dev = qdev_new(TYPE_STM32F100_SOC); + qdev_prop_set_string(dev, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m3")); + sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + + armv7m_load_kernel(ARM_CPU(first_cpu), + machine->kernel_filename, + FLASH_SIZE); +} + +static void stm32vldiscovery_machine_init(MachineClass *mc) +{ + mc->desc = "ST STM32VLDISCOVERY (Cortex-M3)"; + mc->init = stm32vldiscovery_init; +} + +DEFINE_MACHINE("stm32vldiscovery", stm32vldiscovery_machine_init) + diff --git a/hw/arm/strongarm.c b/hw/arm/strongarm.c index c7ca54bcea..939a57dda5 100644 --- a/hw/arm/strongarm.c +++ b/hw/arm/strongarm.c @@ -30,7 +30,6 @@ #include "qemu/osdep.h" #include "qemu-common.h" #include "cpu.h" -#include "hw/boards.h" #include "hw/irq.h" #include "hw/qdev-properties.h" #include "hw/qdev-properties-system.h" @@ -207,7 +206,7 @@ static int strongarm_pic_post_load(void *opaque, int version_id) return 0; } -static VMStateDescription vmstate_strongarm_pic_regs = { +static const VMStateDescription vmstate_strongarm_pic_regs = { .name = "strongarm_pic", .version_id = 0, .minimum_version_id = 0, diff --git a/hw/arm/sysbus-fdt.c b/hw/arm/sysbus-fdt.c index 6b6906f4cf..48c5fe9bf1 100644 --- a/hw/arm/sysbus-fdt.c +++ b/hw/arm/sysbus-fdt.c @@ -437,6 +437,7 @@ static bool vfio_platform_match(SysBusDevice *sbdev, #endif /* CONFIG_LINUX */ +#ifdef CONFIG_TPM /* * add_tpm_tis_fdt_node: Create a DT node for TPM TIS * @@ -467,6 +468,7 @@ static int add_tpm_tis_fdt_node(SysBusDevice *sbdev, void *opaque) g_free(nodename); return 0; } +#endif static int no_fdt_node(SysBusDevice *sbdev, void *opaque) { @@ -488,7 +490,9 @@ static const BindingEntry bindings[] = { TYPE_BINDING(TYPE_VFIO_AMD_XGBE, add_amd_xgbe_fdt_node), VFIO_PLATFORM_BINDING("amd,xgbe-seattle-v1a", add_amd_xgbe_fdt_node), #endif +#ifdef CONFIG_TPM TYPE_BINDING(TYPE_TPM_TIS_SYSBUS, add_tpm_tis_fdt_node), +#endif TYPE_BINDING(TYPE_RAMFB_DEVICE, no_fdt_node), TYPE_BINDING("", NULL), /* last element */ }; diff --git a/hw/arm/trace-events b/hw/arm/trace-events index b79a91af5f..2dee296c8f 100644 --- a/hw/arm/trace-events +++ b/hw/arm/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # virt-acpi-build.c virt_acpi_setup(void) "No fw cfg or ACPI disabled. Bailing out." diff --git a/hw/arm/versatilepb.c b/hw/arm/versatilepb.c index 1ea5534626..575399c4fc 100644 --- a/hw/arm/versatilepb.c +++ b/hw/arm/versatilepb.c @@ -21,7 +21,6 @@ #include "hw/i2c/arm_sbcon_i2c.h" #include "hw/irq.h" #include "hw/boards.h" -#include "exec/address-spaces.h" #include "hw/block/flash.h" #include "qemu/error-report.h" #include "hw/char/pl011.h" diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c index 326a1a6db5..58481c0762 100644 --- a/hw/arm/vexpress.c +++ b/hw/arm/vexpress.c @@ -35,7 +35,6 @@ #include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/loader.h" -#include "exec/address-spaces.h" #include "hw/block/flash.h" #include "sysemu/device_tree.h" #include "qemu/error-report.h" diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 60fe2e65a7..037cc1fd82 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -44,6 +44,7 @@ #include "hw/acpi/tpm.h" #include "hw/pci/pcie_host.h" #include "hw/pci/pci.h" +#include "hw/pci/pci_bus.h" #include "hw/pci-host/gpex.h" #include "hw/arm/virt.h" #include "hw/mem/nvdimm.h" @@ -205,6 +206,7 @@ static void acpi_dsdt_add_gpio(Aml *scope, const MemMapEntry *gpio_memmap, aml_append(scope, dev); } +#ifdef CONFIG_TPM static void acpi_dsdt_add_tpm(Aml *scope, VirtMachineState *vms) { PlatformBusDevice *pbus = PLATFORM_BUS_DEVICE(vms->platform_bus_dev); @@ -236,24 +238,91 @@ static void acpi_dsdt_add_tpm(Aml *scope, VirtMachineState *vms) aml_append(dev, aml_name_decl("_CRS", crs)); aml_append(scope, dev); } +#endif + +/* Build the iort ID mapping to SMMUv3 for a given PCI host bridge */ +static int +iort_host_bridges(Object *obj, void *opaque) +{ + GArray *idmap_blob = opaque; + + if (object_dynamic_cast(obj, TYPE_PCI_HOST_BRIDGE)) { + PCIBus *bus = PCI_HOST_BRIDGE(obj)->bus; + + if (bus && !pci_bus_bypass_iommu(bus)) { + int min_bus, max_bus; + + pci_bus_range(bus, &min_bus, &max_bus); + + AcpiIortIdMapping idmap = { + .input_base = min_bus << 8, + .id_count = (max_bus - min_bus + 1) << 8, + }; + g_array_append_val(idmap_blob, idmap); + } + } + + return 0; +} + +static int iort_idmap_compare(gconstpointer a, gconstpointer b) +{ + AcpiIortIdMapping *idmap_a = (AcpiIortIdMapping *)a; + AcpiIortIdMapping *idmap_b = (AcpiIortIdMapping *)b; + + return idmap_a->input_base - idmap_b->input_base; +} static void build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) { - int nb_nodes, iort_start = table_data->len; + int i, nb_nodes, rc_mapping_count, iort_start = table_data->len; AcpiIortIdMapping *idmap; AcpiIortItsGroup *its; AcpiIortTable *iort; AcpiIortSmmu3 *smmu; size_t node_size, iort_node_offset, iort_length, smmu_offset = 0; AcpiIortRC *rc; + GArray *smmu_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping)); + GArray *its_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping)); iort = acpi_data_push(table_data, sizeof(*iort)); if (vms->iommu == VIRT_IOMMU_SMMUV3) { + AcpiIortIdMapping next_range = {0}; + + object_child_foreach_recursive(object_get_root(), + iort_host_bridges, smmu_idmaps); + + /* Sort the smmu idmap by input_base */ + g_array_sort(smmu_idmaps, iort_idmap_compare); + + /* + * Split the whole RIDs by mapping from RC to SMMU, + * build the ID mapping from RC to ITS directly. + */ + for (i = 0; i < smmu_idmaps->len; i++) { + idmap = &g_array_index(smmu_idmaps, AcpiIortIdMapping, i); + + if (next_range.input_base < idmap->input_base) { + next_range.id_count = idmap->input_base - next_range.input_base; + g_array_append_val(its_idmaps, next_range); + } + + next_range.input_base = idmap->input_base + idmap->id_count; + } + + /* Append the last RC -> ITS ID mapping */ + if (next_range.input_base < 0xFFFF) { + next_range.id_count = 0xFFFF - next_range.input_base; + g_array_append_val(its_idmaps, next_range); + } + nb_nodes = 3; /* RC, ITS, SMMUv3 */ + rc_mapping_count = smmu_idmaps->len + its_idmaps->len; } else { nb_nodes = 2; /* RC, ITS */ + rc_mapping_count = 1; } iort_length = sizeof(*iort); @@ -305,13 +374,13 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) } /* Root Complex Node */ - node_size = sizeof(*rc) + sizeof(*idmap); + node_size = sizeof(*rc) + sizeof(*idmap) * rc_mapping_count; iort_length += node_size; rc = acpi_data_push(table_data, node_size); rc->type = ACPI_IORT_NODE_PCI_ROOT_COMPLEX; rc->length = cpu_to_le16(node_size); - rc->mapping_count = cpu_to_le32(1); + rc->mapping_count = cpu_to_le32(rc_mapping_count); rc->mapping_offset = cpu_to_le32(sizeof(*rc)); /* fully coherent device */ @@ -319,20 +388,45 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) rc->memory_properties.memory_flags = 0x3; /* CCA = CPM = DCAS = 1 */ rc->pci_segment_number = 0; /* MCFG pci_segment */ - /* Identity RID mapping covering the whole input RID range */ - idmap = &rc->id_mapping_array[0]; - idmap->input_base = 0; - idmap->id_count = cpu_to_le32(0xFFFF); - idmap->output_base = 0; - if (vms->iommu == VIRT_IOMMU_SMMUV3) { - /* output IORT node is the smmuv3 node */ - idmap->output_reference = cpu_to_le32(smmu_offset); + AcpiIortIdMapping *range; + + /* translated RIDs connect to SMMUv3 node: RC -> SMMUv3 -> ITS */ + for (i = 0; i < smmu_idmaps->len; i++) { + idmap = &rc->id_mapping_array[i]; + range = &g_array_index(smmu_idmaps, AcpiIortIdMapping, i); + + idmap->input_base = cpu_to_le32(range->input_base); + idmap->id_count = cpu_to_le32(range->id_count); + idmap->output_base = cpu_to_le32(range->input_base); + /* output IORT node is the smmuv3 node */ + idmap->output_reference = cpu_to_le32(smmu_offset); + } + + /* bypassed RIDs connect to ITS group node directly: RC -> ITS */ + for (i = 0; i < its_idmaps->len; i++) { + idmap = &rc->id_mapping_array[smmu_idmaps->len + i]; + range = &g_array_index(its_idmaps, AcpiIortIdMapping, i); + + idmap->input_base = cpu_to_le32(range->input_base); + idmap->id_count = cpu_to_le32(range->id_count); + idmap->output_base = cpu_to_le32(range->input_base); + /* output IORT node is the ITS group node (the first node) */ + idmap->output_reference = cpu_to_le32(iort_node_offset); + } } else { + /* Identity RID mapping covering the whole input RID range */ + idmap = &rc->id_mapping_array[0]; + idmap->input_base = cpu_to_le32(0); + idmap->id_count = cpu_to_le32(0xFFFF); + idmap->output_base = cpu_to_le32(0); /* output IORT node is the ITS group node (the first node) */ idmap->output_reference = cpu_to_le32(iort_node_offset); } + g_array_free(smmu_idmaps, true); + g_array_free(its_idmaps, true); + /* * Update the pointer address in case table_data->data moves during above * acpi_data_push operations. @@ -642,7 +736,9 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) } acpi_dsdt_add_power_button(scope); +#ifdef CONFIG_TPM acpi_dsdt_add_tpm(scope, vms); +#endif aml_append(dsdt, scope); @@ -745,11 +841,13 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) build_iort(tables_blob, tables->linker, vms); } +#ifdef CONFIG_TPM if (tpm_get_version(tpm_find()) == TPM_VERSION_2_0) { acpi_add_table(table_offsets, tables_blob); build_tpm2(tables_blob, tables->linker, tables->tcpalog, vms->oem_id, vms->oem_table_id); } +#endif /* XSDT is pointed to by RSDP */ xsdt = tables_blob->len; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 9f01d9041b..81eda46b0b 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -36,7 +36,6 @@ #include "monitor/qdev.h" #include "qapi/error.h" #include "hw/sysbus.h" -#include "hw/boards.h" #include "hw/arm/boot.h" #include "hw/arm/primecell.h" #include "hw/arm/virt.h" @@ -48,11 +47,10 @@ #include "sysemu/device_tree.h" #include "sysemu/numa.h" #include "sysemu/runstate.h" -#include "sysemu/sysemu.h" #include "sysemu/tpm.h" #include "sysemu/kvm.h" #include "hw/loader.h" -#include "exec/address-spaces.h" +#include "qapi/error.h" #include "qemu/bitops.h" #include "qemu/error-report.h" #include "qemu/module.h" @@ -897,6 +895,9 @@ static void create_gpio_devices(const VirtMachineState *vms, int gpio, MachineState *ms = MACHINE(vms); pl061_dev = qdev_new("pl061"); + /* Pull lines down to 0 if not driven by the PL061 */ + qdev_prop_set_uint32(pl061_dev, "pullups", 0); + qdev_prop_set_uint32(pl061_dev, "pulldowns", 0xff); s = SYS_BUS_DEVICE(pl061_dev); sysbus_realize_and_unref(s, &error_fatal); memory_region_add_subregion(mem, base, sysbus_mmio_get_region(s, 0)); @@ -1366,6 +1367,7 @@ static void create_pcie(VirtMachineState *vms) } pci = PCI_HOST_BRIDGE(dev); + pci->bypass_iommu = vms->default_bus_bypass_iommu; vms->bus = pci->bus; if (vms->bus) { for (i = 0; i < nb_nics; i++) { @@ -1524,8 +1526,10 @@ static void virt_build_smbios(VirtMachineState *vms) vmc->smbios_old_sys_ver ? "1.0" : mc->name, false, true, SMBIOS_ENTRY_POINT_30); - smbios_get_tables(MACHINE(vms), NULL, 0, &smbios_tables, &smbios_tables_len, - &smbios_anchor, &smbios_anchor_len); + smbios_get_tables(MACHINE(vms), NULL, 0, + &smbios_tables, &smbios_tables_len, + &smbios_anchor, &smbios_anchor_len, + &error_fatal); if (smbios_anchor) { fw_cfg_add_file(vms->fw_cfg, "etc/smbios/smbios-tables", @@ -2319,6 +2323,21 @@ static void virt_set_iommu(Object *obj, const char *value, Error **errp) } } +static bool virt_get_default_bus_bypass_iommu(Object *obj, Error **errp) +{ + VirtMachineState *vms = VIRT_MACHINE(obj); + + return vms->default_bus_bypass_iommu; +} + +static void virt_set_default_bus_bypass_iommu(Object *obj, bool value, + Error **errp) +{ + VirtMachineState *vms = VIRT_MACHINE(obj); + + vms->default_bus_bypass_iommu = value; +} + static CpuInstanceProperties virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index) { @@ -2599,7 +2618,9 @@ static void virt_machine_class_init(ObjectClass *oc, void *data) machine_class_allow_dynamic_sysbus_dev(mc, TYPE_VFIO_AMD_XGBE); machine_class_allow_dynamic_sysbus_dev(mc, TYPE_RAMFB_DEVICE); machine_class_allow_dynamic_sysbus_dev(mc, TYPE_VFIO_PLATFORM); +#ifdef CONFIG_TPM machine_class_allow_dynamic_sysbus_dev(mc, TYPE_TPM_TIS_SYSBUS); +#endif mc->block_default_type = IF_VIRTIO; mc->no_cdrom = 1; mc->pci_allow_0_address = true; @@ -2656,6 +2677,13 @@ static void virt_machine_class_init(ObjectClass *oc, void *data) "Set the IOMMU type. " "Valid values are none and smmuv3"); + object_class_property_add_bool(oc, "default_bus_bypass_iommu", + virt_get_default_bus_bypass_iommu, + virt_set_default_bus_bypass_iommu); + object_class_property_set_description(oc, "default_bus_bypass_iommu", + "Set on/off to enable/disable " + "bypass_iommu for default root bus"); + object_class_property_add_bool(oc, "ras", virt_get_ras, virt_set_ras); object_class_property_set_description(oc, "ras", @@ -2723,6 +2751,9 @@ static void virt_instance_init(Object *obj) /* Default disallows iommu instantiation */ vms->iommu = VIRT_IOMMU_NONE; + /* The default root bus is attached to iommu by default */ + vms->default_bus_bypass_iommu = false; + /* Default disallows RAS instantiation */ vms->ras = false; @@ -2757,10 +2788,17 @@ static void machvirt_machine_init(void) } type_init(machvirt_machine_init); -static void virt_machine_6_0_options(MachineClass *mc) +static void virt_machine_6_1_options(MachineClass *mc) { } -DEFINE_VIRT_MACHINE_AS_LATEST(6, 0) +DEFINE_VIRT_MACHINE_AS_LATEST(6, 1) + +static void virt_machine_6_0_options(MachineClass *mc) +{ + virt_machine_6_1_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_0, hw_compat_6_0_len); +} +DEFINE_VIRT_MACHINE(6, 0) static void virt_machine_5_2_options(MachineClass *mc) { diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index 8db6cfd47f..245af81bbb 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -22,12 +22,11 @@ #include "hw/sysbus.h" #include "hw/arm/boot.h" #include "net/net.h" -#include "exec/address-spaces.h" #include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/block/flash.h" #include "hw/loader.h" -#include "hw/misc/zynq-xadc.h" +#include "hw/adc/zynq-xadc.h" #include "hw/ssi/ssi.h" #include "hw/usb/chipidea.h" #include "qemu/error-report.h" @@ -119,7 +118,7 @@ static void gem_init(NICInfo *nd, uint32_t base, qemu_irq irq) qemu_check_nic_model(nd, TYPE_CADENCE_GEM); qdev_set_nic_properties(dev, nd); } - object_property_set_int(OBJECT(dev), "phy-addr", 23, &error_abort); + object_property_set_int(OBJECT(dev), "phy-addr", 7, &error_abort); s = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(s, &error_fatal); sysbus_mmio_map(s, 0, base); diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index 8482cd6196..5bca360dce 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -10,11 +10,9 @@ */ #include "qemu/osdep.h" -#include "qemu/log.h" #include "qemu/error-report.h" #include "qapi/error.h" #include "sysemu/device_tree.h" -#include "exec/address-spaces.h" #include "hw/boards.h" #include "hw/sysbus.h" #include "hw/arm/sysbus-fdt.h" diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index 79609692e4..fb776834f7 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" #include "qemu/units.h" #include "qapi/error.h" -#include "qemu/log.h" #include "qemu/module.h" #include "hw/sysbus.h" #include "net/net.h" diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index a9db25eb99..6c6cb02e86 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -17,7 +17,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/arm/xlnx-zynqmp.h" #include "hw/boards.h" #include "qemu/error-report.h" diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c index 7f01284a5c..3597e8db4d 100644 --- a/hw/arm/xlnx-zynqmp.c +++ b/hw/arm/xlnx-zynqmp.c @@ -18,11 +18,9 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu/module.h" -#include "cpu.h" #include "hw/arm/xlnx-zynqmp.h" #include "hw/intc/arm_gic_common.h" #include "hw/boards.h" -#include "exec/address-spaces.h" #include "sysemu/kvm.h" #include "sysemu/sysemu.h" #include "kvm_arm.h" diff --git a/hw/arm/z2.c b/hw/arm/z2.c index 5099bd8380..9c1e876207 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -162,7 +162,7 @@ static void zipit_lcd_realize(SSIPeripheral *dev, Error **errp) z->pos = 0; } -static VMStateDescription vmstate_zipit_lcd_state = { +static const VMStateDescription vmstate_zipit_lcd_state = { .name = "zipit-lcd", .version_id = 2, .minimum_version_id = 2, @@ -268,7 +268,7 @@ static uint8_t aer915_recv(I2CSlave *slave) return retval; } -static VMStateDescription vmstate_aer915_state = { +static const VMStateDescription vmstate_aer915_state = { .name = "aer915", .version_id = 1, .minimum_version_id = 1, diff --git a/hw/audio/adlib.c b/hw/audio/adlib.c index 42d50d2fdc..5f979b1487 100644 --- a/hw/audio/adlib.c +++ b/hw/audio/adlib.c @@ -186,7 +186,7 @@ static int write_audio (AdlibState *s, int samples) static void adlib_callback (void *opaque, int free) { AdlibState *s = opaque; - int samples, net = 0, to_play, written; + int samples, to_play, written; samples = free >> SHIFT; if (!(s->active && s->enabled) || !samples) { @@ -219,7 +219,6 @@ static void adlib_callback (void *opaque, int free) written = write_audio (s, samples); if (written) { - net += written; samples -= written; s->pos = (s->pos + written) % s->samples; } diff --git a/hw/audio/meson.build b/hw/audio/meson.build index 32c42bdebe..e48a9fc73d 100644 --- a/hw/audio/meson.build +++ b/hw/audio/meson.build @@ -7,7 +7,6 @@ softmmu_ss.add(when: 'CONFIG_ES1370', if_true: files('es1370.c')) softmmu_ss.add(when: 'CONFIG_GUS', if_true: files('gus.c', 'gusemu_hal.c', 'gusemu_mixer.c')) softmmu_ss.add(when: 'CONFIG_HDA', if_true: files('intel-hda.c', 'hda-codec.c')) softmmu_ss.add(when: 'CONFIG_MARVELL_88W8618', if_true: files('marvell_88w8618.c')) -softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-ac97.c')) softmmu_ss.add(when: 'CONFIG_PCSPK', if_true: files('pcspk.c')) softmmu_ss.add(when: 'CONFIG_PL041', if_true: files('pl041.c', 'lm4549.c')) softmmu_ss.add(when: 'CONFIG_SB16', if_true: files('sb16.c')) diff --git a/hw/audio/milkymist-ac97.c b/hw/audio/milkymist-ac97.c deleted file mode 100644 index 7d2e057038..0000000000 --- a/hw/audio/milkymist-ac97.c +++ /dev/null @@ -1,360 +0,0 @@ -/* - * QEMU model of the Milkymist System Controller. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://milkymist.walle.cc/socdoc/ac97.pdf - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "audio/audio.h" -#include "qemu/error-report.h" -#include "qemu/module.h" -#include "qom/object.h" - -enum { - R_AC97_CTRL = 0, - R_AC97_ADDR, - R_AC97_DATAOUT, - R_AC97_DATAIN, - R_D_CTRL, - R_D_ADDR, - R_D_REMAINING, - R_RESERVED, - R_U_CTRL, - R_U_ADDR, - R_U_REMAINING, - R_MAX -}; - -enum { - AC97_CTRL_RQEN = (1<<0), - AC97_CTRL_WRITE = (1<<1), -}; - -enum { - CTRL_EN = (1<<0), -}; - -#define TYPE_MILKYMIST_AC97 "milkymist-ac97" -OBJECT_DECLARE_SIMPLE_TYPE(MilkymistAC97State, MILKYMIST_AC97) - -struct MilkymistAC97State { - SysBusDevice parent_obj; - - MemoryRegion regs_region; - - QEMUSoundCard card; - SWVoiceIn *voice_in; - SWVoiceOut *voice_out; - - uint32_t regs[R_MAX]; - - qemu_irq crrequest_irq; - qemu_irq crreply_irq; - qemu_irq dmar_irq; - qemu_irq dmaw_irq; -}; - -static void update_voices(MilkymistAC97State *s) -{ - if (s->regs[R_D_CTRL] & CTRL_EN) { - AUD_set_active_out(s->voice_out, 1); - } else { - AUD_set_active_out(s->voice_out, 0); - } - - if (s->regs[R_U_CTRL] & CTRL_EN) { - AUD_set_active_in(s->voice_in, 1); - } else { - AUD_set_active_in(s->voice_in, 0); - } -} - -static uint64_t ac97_read(void *opaque, hwaddr addr, - unsigned size) -{ - MilkymistAC97State *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_AC97_CTRL: - case R_AC97_ADDR: - case R_AC97_DATAOUT: - case R_AC97_DATAIN: - case R_D_CTRL: - case R_D_ADDR: - case R_D_REMAINING: - case R_U_CTRL: - case R_U_ADDR: - case R_U_REMAINING: - r = s->regs[addr]; - break; - - default: - error_report("milkymist_ac97: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - trace_milkymist_ac97_memory_read(addr << 2, r); - - return r; -} - -static void ac97_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - MilkymistAC97State *s = opaque; - - trace_milkymist_ac97_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_AC97_CTRL: - /* always raise an IRQ according to the direction */ - if (value & AC97_CTRL_RQEN) { - if (value & AC97_CTRL_WRITE) { - trace_milkymist_ac97_pulse_irq_crrequest(); - qemu_irq_pulse(s->crrequest_irq); - } else { - trace_milkymist_ac97_pulse_irq_crreply(); - qemu_irq_pulse(s->crreply_irq); - } - } - - /* RQEN is self clearing */ - s->regs[addr] = value & ~AC97_CTRL_RQEN; - break; - case R_D_CTRL: - case R_U_CTRL: - s->regs[addr] = value; - update_voices(s); - break; - case R_AC97_ADDR: - case R_AC97_DATAOUT: - case R_AC97_DATAIN: - case R_D_ADDR: - case R_D_REMAINING: - case R_U_ADDR: - case R_U_REMAINING: - s->regs[addr] = value; - break; - - default: - error_report("milkymist_ac97: write access to unknown register 0x" - TARGET_FMT_plx, addr); - break; - } - -} - -static const MemoryRegionOps ac97_mmio_ops = { - .read = ac97_read, - .write = ac97_write, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void ac97_in_cb(void *opaque, int avail_b) -{ - MilkymistAC97State *s = opaque; - uint8_t buf[4096]; - uint32_t remaining = s->regs[R_U_REMAINING]; - int temp = MIN(remaining, avail_b); - uint32_t addr = s->regs[R_U_ADDR]; - int transferred = 0; - - trace_milkymist_ac97_in_cb(avail_b, remaining); - - /* prevent from raising an IRQ */ - if (temp == 0) { - return; - } - - while (temp) { - int acquired, to_copy; - - to_copy = MIN(temp, sizeof(buf)); - acquired = AUD_read(s->voice_in, buf, to_copy); - if (!acquired) { - break; - } - - cpu_physical_memory_write(addr, buf, acquired); - - temp -= acquired; - addr += acquired; - transferred += acquired; - } - - trace_milkymist_ac97_in_cb_transferred(transferred); - - s->regs[R_U_ADDR] = addr; - s->regs[R_U_REMAINING] -= transferred; - - if ((s->regs[R_U_CTRL] & CTRL_EN) && (s->regs[R_U_REMAINING] == 0)) { - trace_milkymist_ac97_pulse_irq_dmaw(); - qemu_irq_pulse(s->dmaw_irq); - } -} - -static void ac97_out_cb(void *opaque, int free_b) -{ - MilkymistAC97State *s = opaque; - uint8_t buf[4096]; - uint32_t remaining = s->regs[R_D_REMAINING]; - int temp = MIN(remaining, free_b); - uint32_t addr = s->regs[R_D_ADDR]; - int transferred = 0; - - trace_milkymist_ac97_out_cb(free_b, remaining); - - /* prevent from raising an IRQ */ - if (temp == 0) { - return; - } - - while (temp) { - int copied, to_copy; - - to_copy = MIN(temp, sizeof(buf)); - cpu_physical_memory_read(addr, buf, to_copy); - copied = AUD_write(s->voice_out, buf, to_copy); - if (!copied) { - break; - } - temp -= copied; - addr += copied; - transferred += copied; - } - - trace_milkymist_ac97_out_cb_transferred(transferred); - - s->regs[R_D_ADDR] = addr; - s->regs[R_D_REMAINING] -= transferred; - - if ((s->regs[R_D_CTRL] & CTRL_EN) && (s->regs[R_D_REMAINING] == 0)) { - trace_milkymist_ac97_pulse_irq_dmar(); - qemu_irq_pulse(s->dmar_irq); - } -} - -static void milkymist_ac97_reset(DeviceState *d) -{ - MilkymistAC97State *s = MILKYMIST_AC97(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } - - AUD_set_active_in(s->voice_in, 0); - AUD_set_active_out(s->voice_out, 0); -} - -static int ac97_post_load(void *opaque, int version_id) -{ - MilkymistAC97State *s = opaque; - - update_voices(s); - - return 0; -} - -static void milkymist_ac97_init(Object *obj) -{ - MilkymistAC97State *s = MILKYMIST_AC97(obj); - SysBusDevice *dev = SYS_BUS_DEVICE(obj); - - sysbus_init_irq(dev, &s->crrequest_irq); - sysbus_init_irq(dev, &s->crreply_irq); - sysbus_init_irq(dev, &s->dmar_irq); - sysbus_init_irq(dev, &s->dmaw_irq); - - memory_region_init_io(&s->regs_region, obj, &ac97_mmio_ops, s, - "milkymist-ac97", R_MAX * 4); - sysbus_init_mmio(dev, &s->regs_region); -} - -static void milkymist_ac97_realize(DeviceState *dev, Error **errp) -{ - MilkymistAC97State *s = MILKYMIST_AC97(dev); - struct audsettings as; - - AUD_register_card("Milkymist AC'97", &s->card); - - as.freq = 48000; - as.nchannels = 2; - as.fmt = AUDIO_FORMAT_S16; - as.endianness = 1; - - s->voice_in = AUD_open_in(&s->card, s->voice_in, - "mm_ac97.in", s, ac97_in_cb, &as); - s->voice_out = AUD_open_out(&s->card, s->voice_out, - "mm_ac97.out", s, ac97_out_cb, &as); -} - -static const VMStateDescription vmstate_milkymist_ac97 = { - .name = "milkymist-ac97", - .version_id = 1, - .minimum_version_id = 1, - .post_load = ac97_post_load, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, MilkymistAC97State, R_MAX), - VMSTATE_END_OF_LIST() - } -}; - -static Property milkymist_ac97_properties[] = { - DEFINE_AUDIO_PROPERTIES(MilkymistAC97State, card), - DEFINE_PROP_END_OF_LIST(), -}; - -static void milkymist_ac97_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = milkymist_ac97_realize; - dc->reset = milkymist_ac97_reset; - dc->vmsd = &vmstate_milkymist_ac97; - device_class_set_props(dc, milkymist_ac97_properties); -} - -static const TypeInfo milkymist_ac97_info = { - .name = TYPE_MILKYMIST_AC97, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(MilkymistAC97State), - .instance_init = milkymist_ac97_init, - .class_init = milkymist_ac97_class_init, -}; - -static void milkymist_ac97_register_types(void) -{ - type_register_static(&milkymist_ac97_info); -} - -type_init(milkymist_ac97_register_types) diff --git a/hw/audio/sb16.c b/hw/audio/sb16.c index 8b20700410..60f1f75e3a 100644 --- a/hw/audio/sb16.c +++ b/hw/audio/sb16.c @@ -115,6 +115,9 @@ struct SB16State { PortioList portio_list; }; +#define SAMPLE_RATE_MIN 5000 +#define SAMPLE_RATE_MAX 45000 + static void SB_audio_callback (void *opaque, int free); static int magic_of_irq (int irq) @@ -226,6 +229,23 @@ static void continue_dma8 (SB16State *s) control (s, 1); } +static inline int restrict_sampling_rate(int freq) +{ + if (freq < SAMPLE_RATE_MIN) { + qemu_log_mask(LOG_GUEST_ERROR, + "sampling range too low: %d, increasing to %u\n", + freq, SAMPLE_RATE_MIN); + return SAMPLE_RATE_MIN; + } else if (freq > SAMPLE_RATE_MAX) { + qemu_log_mask(LOG_GUEST_ERROR, + "sampling range too high: %d, decreasing to %u\n", + freq, SAMPLE_RATE_MAX); + return SAMPLE_RATE_MAX; + } else { + return freq; + } +} + static void dma_cmd8 (SB16State *s, int mask, int dma_len) { s->fmt = AUDIO_FORMAT_U8; @@ -241,6 +261,7 @@ static void dma_cmd8 (SB16State *s, int mask, int dma_len) int tmp = (256 - s->time_const); s->freq = (1000000 + (tmp / 2)) / tmp; } + s->freq = restrict_sampling_rate(s->freq); if (dma_len != -1) { s->block_size = dma_len << s->fmt_stereo; @@ -754,7 +775,7 @@ static void complete (SB16State *s) * and FT2 sets output freq with this (go figure). Compare: * http://homepages.cae.wisc.edu/~brodskye/sb16doc/sb16doc.html#SamplingRate */ - s->freq = dsp_get_hilo (s); + s->freq = restrict_sampling_rate(dsp_get_hilo(s)); ldebug ("set freq %d\n", s->freq); break; diff --git a/hw/audio/trace-events b/hw/audio/trace-events index 60556b4a97..e0e71cd9b1 100644 --- a/hw/audio/trace-events +++ b/hw/audio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # cs4231.c cs4231_mem_readl_dreg(uint32_t reg, uint32_t ret) "read dreg %d: 0x%02x" @@ -6,18 +6,6 @@ cs4231_mem_readl_reg(uint32_t reg, uint32_t ret) "read reg %d: 0x%08x" cs4231_mem_writel_reg(uint32_t reg, uint32_t old, uint32_t val) "write reg %d: 0x%08x -> 0x%08x" cs4231_mem_writel_dreg(uint32_t reg, uint32_t old, uint32_t val) "write dreg %d: 0x%02x -> 0x%02x" -# milkymist-ac97.c -milkymist_ac97_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_ac97_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_ac97_pulse_irq_crrequest(void) "Pulse IRQ CR request" -milkymist_ac97_pulse_irq_crreply(void) "Pulse IRQ CR reply" -milkymist_ac97_pulse_irq_dmaw(void) "Pulse IRQ DMA write" -milkymist_ac97_pulse_irq_dmar(void) "Pulse IRQ DMA read" -milkymist_ac97_in_cb(int avail, uint32_t remaining) "avail %d remaining %u" -milkymist_ac97_in_cb_transferred(int transferred) "transferred %d" -milkymist_ac97_out_cb(int free, uint32_t remaining) "free %d remaining %u" -milkymist_ac97_out_cb_transferred(int transferred) "transferred %d" - # hda-codec.c hda_audio_running(const char *stream, int nr, bool running) "st %s, nr %d, run %d" hda_audio_format(const char *stream, int chan, const char *fmt, int freq) "st %s, %d x %s @ %d Hz" diff --git a/hw/avr/arduino.c b/hw/avr/arduino.c index 3ff31492fa..48ef478346 100644 --- a/hw/avr/arduino.c +++ b/hw/avr/arduino.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "hw/boards.h" #include "atmega.h" #include "boot.h" #include "qom/object.h" diff --git a/hw/avr/atmega.c b/hw/avr/atmega.c index 44c6afebbb..0608e2d475 100644 --- a/hw/avr/atmega.c +++ b/hw/avr/atmega.c @@ -18,7 +18,6 @@ #include "hw/qdev-properties.h" #include "hw/sysbus.h" #include "qom/object.h" -#include "hw/boards.h" /* FIXME memory_region_allocate_system_memory for sram */ #include "hw/misc/unimp.h" #include "atmega.h" @@ -402,7 +401,7 @@ static void atmega1280_class_init(ObjectClass *oc, void *data) { AtmegaMcuClass *amc = ATMEGA_MCU_CLASS(oc); - amc->cpu_type = AVR_CPU_TYPE_NAME("avr6"); + amc->cpu_type = AVR_CPU_TYPE_NAME("avr51"); amc->flash_size = 128 * KiB; amc->eeprom_size = 4 * KiB; amc->sram_size = 8 * KiB; diff --git a/hw/block/Kconfig b/hw/block/Kconfig index 4fcd152166..9e8f28f982 100644 --- a/hw/block/Kconfig +++ b/hw/block/Kconfig @@ -1,8 +1,14 @@ config FDC bool - # FIXME: there is no separate file for the MMIO floppy disk controller, so - # select ISA_BUS here instead of polluting each board that requires one - select ISA_BUS + +config FDC_ISA + bool + depends on ISA_BUS + select FDC + +config FDC_SYSBUS + bool + select FDC config SSI_M25P80 bool @@ -25,11 +31,6 @@ config ONENAND config TC58128 bool -config NVME_PCI - bool - default y if PCI_DEVICES - depends on PCI - config VIRTIO_BLK bool default y diff --git a/hw/block/block.c b/hw/block/block.c index e2442ba613..d6f0afb812 100644 --- a/hw/block/block.c +++ b/hw/block/block.c @@ -73,24 +73,58 @@ bool blkconf_blocksizes(BlockConf *conf, Error **errp) { BlockBackend *blk = conf->blk; BlockSizes blocksizes; - int backend_ret; + BlockDriverState *bs; + bool use_blocksizes; + bool use_bs; + + switch (conf->backend_defaults) { + case ON_OFF_AUTO_AUTO: + use_blocksizes = !blk_probe_blocksizes(blk, &blocksizes); + use_bs = false; + break; + + case ON_OFF_AUTO_ON: + use_blocksizes = !blk_probe_blocksizes(blk, &blocksizes); + bs = blk_bs(blk); + use_bs = bs; + break; + + case ON_OFF_AUTO_OFF: + use_blocksizes = false; + use_bs = false; + break; + + default: + abort(); + } - backend_ret = blk_probe_blocksizes(blk, &blocksizes); /* fill in detected values if they are not defined via qemu command line */ if (!conf->physical_block_size) { - if (!backend_ret) { + if (use_blocksizes) { conf->physical_block_size = blocksizes.phys; } else { conf->physical_block_size = BDRV_SECTOR_SIZE; } } if (!conf->logical_block_size) { - if (!backend_ret) { + if (use_blocksizes) { conf->logical_block_size = blocksizes.log; } else { conf->logical_block_size = BDRV_SECTOR_SIZE; } } + if (use_bs) { + if (!conf->opt_io_size) { + conf->opt_io_size = bs->bl.opt_transfer; + } + if (conf->discard_granularity == -1) { + if (bs->bl.pdiscard_alignment) { + conf->discard_granularity = bs->bl.pdiscard_alignment; + } else if (bs->bl.request_alignment != 1) { + conf->discard_granularity = bs->bl.request_alignment; + } + } + } if (conf->logical_block_size > conf->physical_block_size) { error_setg(errp, diff --git a/hw/block/dataplane/trace-events b/hw/block/dataplane/trace-events index 843cc4e7b1..38fc3e7507 100644 --- a/hw/block/dataplane/trace-events +++ b/hw/block/dataplane/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # virtio-blk.c virtio_blk_data_plane_start(void *s) "dataplane %p" diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c index e9050c8987..252c3a7a23 100644 --- a/hw/block/dataplane/virtio-blk.c +++ b/hw/block/dataplane/virtio-blk.c @@ -198,19 +198,38 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev) goto fail_guest_notifiers; } + /* + * Batch all the host notifiers in a single transaction to avoid + * quadratic time complexity in address_space_update_ioeventfds(). + */ + memory_region_transaction_begin(); + /* Set up virtqueue notify */ for (i = 0; i < nvqs; i++) { r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, true); if (r != 0) { + int j = i; + fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r); while (i--) { virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false); + } + + /* + * The transaction expects the ioeventfds to be open when it + * commits. Do it now, before the cleanup loop. + */ + memory_region_transaction_commit(); + + while (j--) { virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i); } - goto fail_guest_notifiers; + goto fail_host_notifiers; } } + memory_region_transaction_commit(); + s->starting = false; vblk->dataplane_started = true; trace_virtio_blk_data_plane_start(s); @@ -221,7 +240,7 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev) aio_context_release(old_context); if (r < 0) { error_report_err(local_err); - goto fail_guest_notifiers; + goto fail_aio_context; } /* Process queued requests before the ones in vring */ @@ -245,6 +264,20 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev) aio_context_release(s->ctx); return 0; + fail_aio_context: + memory_region_transaction_begin(); + + for (i = 0; i < nvqs; i++) { + virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false); + } + + memory_region_transaction_commit(); + + for (i = 0; i < nvqs; i++) { + virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i); + } + fail_host_notifiers: + k->set_guest_notifiers(qbus->parent, nvqs, false); fail_guest_notifiers: /* * If we failed to set up the guest notifiers queued requests will be @@ -305,8 +338,23 @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev) aio_context_release(s->ctx); + /* + * Batch all the host notifiers in a single transaction to avoid + * quadratic time complexity in address_space_update_ioeventfds(). + */ + memory_region_transaction_begin(); + for (i = 0; i < nvqs; i++) { virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false); + } + + /* + * The transaction expects the ioeventfds to be open when it + * commits. Do it now, before the cleanup loop. + */ + memory_region_transaction_commit(); + + for (i = 0; i < nvqs; i++) { virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i); } diff --git a/hw/block/ecc.c b/hw/block/ecc.c index 1a182367ee..6e0d63842c 100644 --- a/hw/block/ecc.c +++ b/hw/block/ecc.c @@ -78,7 +78,7 @@ void ecc_reset(ECCState *s) } /* Save/restore */ -VMStateDescription vmstate_ecc_state = { +const VMStateDescription vmstate_ecc_state = { .name = "ecc-state", .version_id = 0, .minimum_version_id = 0, diff --git a/hw/block/fdc-internal.h b/hw/block/fdc-internal.h new file mode 100644 index 0000000000..036392e9fc --- /dev/null +++ b/hw/block/fdc-internal.h @@ -0,0 +1,158 @@ +/* + * QEMU Floppy disk emulator (Intel 82078) + * + * Copyright (c) 2003, 2007 Jocelyn Mayer + * Copyright (c) 2008 Hervé Poussineau + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#ifndef HW_BLOCK_FDC_INTERNAL_H +#define HW_BLOCK_FDC_INTERNAL_H + +#include "exec/memory.h" +#include "exec/ioport.h" +#include "hw/block/block.h" +#include "hw/block/fdc.h" +#include "qapi/qapi-types-block.h" + +typedef struct FDCtrl FDCtrl; + +/* Floppy bus emulation */ + +typedef struct FloppyBus { + BusState bus; + FDCtrl *fdc; +} FloppyBus; + +/* Floppy disk drive emulation */ + +typedef enum FDriveRate { + FDRIVE_RATE_500K = 0x00, /* 500 Kbps */ + FDRIVE_RATE_300K = 0x01, /* 300 Kbps */ + FDRIVE_RATE_250K = 0x02, /* 250 Kbps */ + FDRIVE_RATE_1M = 0x03, /* 1 Mbps */ +} FDriveRate; + +typedef enum FDriveSize { + FDRIVE_SIZE_UNKNOWN, + FDRIVE_SIZE_350, + FDRIVE_SIZE_525, +} FDriveSize; + +typedef struct FDFormat { + FloppyDriveType drive; + uint8_t last_sect; + uint8_t max_track; + uint8_t max_head; + FDriveRate rate; +} FDFormat; + +typedef enum FDiskFlags { + FDISK_DBL_SIDES = 0x01, +} FDiskFlags; + +typedef struct FDrive { + FDCtrl *fdctrl; + BlockBackend *blk; + BlockConf *conf; + /* Drive status */ + FloppyDriveType drive; /* CMOS drive type */ + uint8_t perpendicular; /* 2.88 MB access mode */ + /* Position */ + uint8_t head; + uint8_t track; + uint8_t sect; + /* Media */ + FloppyDriveType disk; /* Current disk type */ + FDiskFlags flags; + uint8_t last_sect; /* Nb sector per track */ + uint8_t max_track; /* Nb of tracks */ + uint16_t bps; /* Bytes per sector */ + uint8_t ro; /* Is read-only */ + uint8_t media_changed; /* Is media changed */ + uint8_t media_rate; /* Data rate of medium */ + + bool media_validated; /* Have we validated the media? */ +} FDrive; + +struct FDCtrl { + MemoryRegion iomem; + qemu_irq irq; + /* Controller state */ + QEMUTimer *result_timer; + int dma_chann; + uint8_t phase; + IsaDma *dma; + /* Controller's identification */ + uint8_t version; + /* HW */ + uint8_t sra; + uint8_t srb; + uint8_t dor; + uint8_t dor_vmstate; /* only used as temp during vmstate */ + uint8_t tdr; + uint8_t dsr; + uint8_t msr; + uint8_t cur_drv; + uint8_t status0; + uint8_t status1; + uint8_t status2; + /* Command FIFO */ + uint8_t *fifo; + int32_t fifo_size; + uint32_t data_pos; + uint32_t data_len; + uint8_t data_state; + uint8_t data_dir; + uint8_t eot; /* last wanted sector */ + /* States kept only to be returned back */ + /* precompensation */ + uint8_t precomp_trk; + uint8_t config; + uint8_t lock; + /* Power down config (also with status regB access mode */ + uint8_t pwrd; + /* Floppy drives */ + FloppyBus bus; + uint8_t num_floppies; + FDrive drives[MAX_FD]; + struct { + FloppyDriveType type; + } qdev_for_drives[MAX_FD]; + int reset_sensei; + FloppyDriveType fallback; /* type=auto failure fallback */ + /* Timers state */ + uint8_t timer0; + uint8_t timer1; + PortioList portio_list; +}; + +extern const FDFormat fd_formats[]; +extern const VMStateDescription vmstate_fdc; + +uint32_t fdctrl_read(void *opaque, uint32_t reg); +void fdctrl_write(void *opaque, uint32_t reg, uint32_t value); +void fdctrl_reset(FDCtrl *fdctrl, int do_irq); +void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp); + +int fdctrl_transfer_handler(void *opaque, int nchan, int dma_pos, int dma_len); + +void fdctrl_init_drives(FloppyBus *bus, DriveInfo **fds); + +#endif diff --git a/hw/block/fdc-isa.c b/hw/block/fdc-isa.c new file mode 100644 index 0000000000..3bf64e0665 --- /dev/null +++ b/hw/block/fdc-isa.c @@ -0,0 +1,320 @@ +/* + * QEMU Floppy disk emulator (Intel 82078) + * + * Copyright (c) 2003, 2007 Jocelyn Mayer + * Copyright (c) 2008 Hervé Poussineau + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +/* + * The controller is used in Sun4m systems in a slightly different + * way. There are changes in DOR register and DMA is not available. + */ + +#include "qemu/osdep.h" +#include "hw/block/fdc.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qemu/timer.h" +#include "hw/acpi/aml-build.h" +#include "hw/irq.h" +#include "hw/isa/isa.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" +#include "migration/vmstate.h" +#include "hw/block/block.h" +#include "sysemu/block-backend.h" +#include "sysemu/blockdev.h" +#include "sysemu/sysemu.h" +#include "qemu/log.h" +#include "qemu/main-loop.h" +#include "qemu/module.h" +#include "trace.h" +#include "qom/object.h" +#include "fdc-internal.h" + +OBJECT_DECLARE_SIMPLE_TYPE(FDCtrlISABus, ISA_FDC) + +struct FDCtrlISABus { + /*< private >*/ + ISADevice parent_obj; + /*< public >*/ + + uint32_t iobase; + uint32_t irq; + uint32_t dma; + struct FDCtrl state; + int32_t bootindexA; + int32_t bootindexB; +}; + +static void fdctrl_external_reset_isa(DeviceState *d) +{ + FDCtrlISABus *isa = ISA_FDC(d); + FDCtrl *s = &isa->state; + + fdctrl_reset(s, 0); +} + +void isa_fdc_init_drives(ISADevice *fdc, DriveInfo **fds) +{ + fdctrl_init_drives(&ISA_FDC(fdc)->state.bus, fds); +} + +static const MemoryRegionPortio fdc_portio_list[] = { + { 1, 5, 1, .read = fdctrl_read, .write = fdctrl_write }, + { 7, 1, 1, .read = fdctrl_read, .write = fdctrl_write }, + PORTIO_END_OF_LIST(), +}; + +static void isabus_fdc_realize(DeviceState *dev, Error **errp) +{ + ISADevice *isadev = ISA_DEVICE(dev); + FDCtrlISABus *isa = ISA_FDC(dev); + FDCtrl *fdctrl = &isa->state; + Error *err = NULL; + + isa_register_portio_list(isadev, &fdctrl->portio_list, + isa->iobase, fdc_portio_list, fdctrl, + "fdc"); + + isa_init_irq(isadev, &fdctrl->irq, isa->irq); + fdctrl->dma_chann = isa->dma; + if (fdctrl->dma_chann != -1) { + IsaDmaClass *k; + fdctrl->dma = isa_get_dma(isa_bus_from_device(isadev), isa->dma); + if (!fdctrl->dma) { + error_setg(errp, "ISA controller does not support DMA"); + return; + } + k = ISADMA_GET_CLASS(fdctrl->dma); + k->register_channel(fdctrl->dma, fdctrl->dma_chann, + &fdctrl_transfer_handler, fdctrl); + } + + qdev_set_legacy_instance_id(dev, isa->iobase, 2); + + fdctrl_realize_common(dev, fdctrl, &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } +} + +FloppyDriveType isa_fdc_get_drive_type(ISADevice *fdc, int i) +{ + FDCtrlISABus *isa = ISA_FDC(fdc); + + return isa->state.drives[i].drive; +} + +static void isa_fdc_get_drive_max_chs(FloppyDriveType type, uint8_t *maxc, + uint8_t *maxh, uint8_t *maxs) +{ + const FDFormat *fdf; + + *maxc = *maxh = *maxs = 0; + for (fdf = fd_formats; fdf->drive != FLOPPY_DRIVE_TYPE_NONE; fdf++) { + if (fdf->drive != type) { + continue; + } + if (*maxc < fdf->max_track) { + *maxc = fdf->max_track; + } + if (*maxh < fdf->max_head) { + *maxh = fdf->max_head; + } + if (*maxs < fdf->last_sect) { + *maxs = fdf->last_sect; + } + } + (*maxc)--; +} + +static Aml *build_fdinfo_aml(int idx, FloppyDriveType type) +{ + Aml *dev, *fdi; + uint8_t maxc, maxh, maxs; + + isa_fdc_get_drive_max_chs(type, &maxc, &maxh, &maxs); + + dev = aml_device("FLP%c", 'A' + idx); + + aml_append(dev, aml_name_decl("_ADR", aml_int(idx))); + + fdi = aml_package(16); + aml_append(fdi, aml_int(idx)); /* Drive Number */ + aml_append(fdi, + aml_int(cmos_get_fd_drive_type(type))); /* Device Type */ + /* + * the values below are the limits of the drive, and are thus independent + * of the inserted media + */ + aml_append(fdi, aml_int(maxc)); /* Maximum Cylinder Number */ + aml_append(fdi, aml_int(maxs)); /* Maximum Sector Number */ + aml_append(fdi, aml_int(maxh)); /* Maximum Head Number */ + /* + * SeaBIOS returns the below values for int 0x13 func 0x08 regardless of + * the drive type, so shall we + */ + aml_append(fdi, aml_int(0xAF)); /* disk_specify_1 */ + aml_append(fdi, aml_int(0x02)); /* disk_specify_2 */ + aml_append(fdi, aml_int(0x25)); /* disk_motor_wait */ + aml_append(fdi, aml_int(0x02)); /* disk_sector_siz */ + aml_append(fdi, aml_int(0x12)); /* disk_eot */ + aml_append(fdi, aml_int(0x1B)); /* disk_rw_gap */ + aml_append(fdi, aml_int(0xFF)); /* disk_dtl */ + aml_append(fdi, aml_int(0x6C)); /* disk_formt_gap */ + aml_append(fdi, aml_int(0xF6)); /* disk_fill */ + aml_append(fdi, aml_int(0x0F)); /* disk_head_sttl */ + aml_append(fdi, aml_int(0x08)); /* disk_motor_strt */ + + aml_append(dev, aml_name_decl("_FDI", fdi)); + return dev; +} + +int cmos_get_fd_drive_type(FloppyDriveType fd0) +{ + int val; + + switch (fd0) { + case FLOPPY_DRIVE_TYPE_144: + /* 1.44 Mb 3"5 drive */ + val = 4; + break; + case FLOPPY_DRIVE_TYPE_288: + /* 2.88 Mb 3"5 drive */ + val = 5; + break; + case FLOPPY_DRIVE_TYPE_120: + /* 1.2 Mb 5"5 drive */ + val = 2; + break; + case FLOPPY_DRIVE_TYPE_NONE: + default: + val = 0; + break; + } + return val; +} + +static void fdc_isa_build_aml(ISADevice *isadev, Aml *scope) +{ + Aml *dev; + Aml *crs; + int i; + +#define ACPI_FDE_MAX_FD 4 + uint32_t fde_buf[5] = { + 0, 0, 0, 0, /* presence of floppy drives #0 - #3 */ + cpu_to_le32(2) /* tape presence (2 == never present) */ + }; + + crs = aml_resource_template(); + aml_append(crs, aml_io(AML_DECODE16, 0x03F2, 0x03F2, 0x00, 0x04)); + aml_append(crs, aml_io(AML_DECODE16, 0x03F7, 0x03F7, 0x00, 0x01)); + aml_append(crs, aml_irq_no_flags(6)); + aml_append(crs, + aml_dma(AML_COMPATIBILITY, AML_NOTBUSMASTER, AML_TRANSFER8, 2)); + + dev = aml_device("FDC0"); + aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0700"))); + aml_append(dev, aml_name_decl("_CRS", crs)); + + for (i = 0; i < MIN(MAX_FD, ACPI_FDE_MAX_FD); i++) { + FloppyDriveType type = isa_fdc_get_drive_type(isadev, i); + + if (type < FLOPPY_DRIVE_TYPE_NONE) { + fde_buf[i] = cpu_to_le32(1); /* drive present */ + aml_append(dev, build_fdinfo_aml(i, type)); + } + } + aml_append(dev, aml_name_decl("_FDE", + aml_buffer(sizeof(fde_buf), (uint8_t *)fde_buf))); + + aml_append(scope, dev); +} + +static const VMStateDescription vmstate_isa_fdc = { + .name = "fdc", + .version_id = 2, + .minimum_version_id = 2, + .fields = (VMStateField[]) { + VMSTATE_STRUCT(state, FDCtrlISABus, 0, vmstate_fdc, FDCtrl), + VMSTATE_END_OF_LIST() + } +}; + +static Property isa_fdc_properties[] = { + DEFINE_PROP_UINT32("iobase", FDCtrlISABus, iobase, 0x3f0), + DEFINE_PROP_UINT32("irq", FDCtrlISABus, irq, 6), + DEFINE_PROP_UINT32("dma", FDCtrlISABus, dma, 2), + DEFINE_PROP_SIGNED("fdtypeA", FDCtrlISABus, state.qdev_for_drives[0].type, + FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type, + FloppyDriveType), + DEFINE_PROP_SIGNED("fdtypeB", FDCtrlISABus, state.qdev_for_drives[1].type, + FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type, + FloppyDriveType), + DEFINE_PROP_SIGNED("fallback", FDCtrlISABus, state.fallback, + FLOPPY_DRIVE_TYPE_288, qdev_prop_fdc_drive_type, + FloppyDriveType), + DEFINE_PROP_END_OF_LIST(), +}; + +static void isabus_fdc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ISADeviceClass *isa = ISA_DEVICE_CLASS(klass); + + dc->desc = "virtual floppy controller"; + dc->realize = isabus_fdc_realize; + dc->fw_name = "fdc"; + dc->reset = fdctrl_external_reset_isa; + dc->vmsd = &vmstate_isa_fdc; + isa->build_aml = fdc_isa_build_aml; + device_class_set_props(dc, isa_fdc_properties); + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); +} + +static void isabus_fdc_instance_init(Object *obj) +{ + FDCtrlISABus *isa = ISA_FDC(obj); + + device_add_bootindex_property(obj, &isa->bootindexA, + "bootindexA", "/floppy@0", + DEVICE(obj)); + device_add_bootindex_property(obj, &isa->bootindexB, + "bootindexB", "/floppy@1", + DEVICE(obj)); +} + +static const TypeInfo isa_fdc_info = { + .name = TYPE_ISA_FDC, + .parent = TYPE_ISA_DEVICE, + .instance_size = sizeof(FDCtrlISABus), + .class_init = isabus_fdc_class_init, + .instance_init = isabus_fdc_instance_init, +}; + +static void isa_fdc_register_types(void) +{ + type_register_static(&isa_fdc_info); +} + +type_init(isa_fdc_register_types) diff --git a/hw/block/fdc-sysbus.c b/hw/block/fdc-sysbus.c new file mode 100644 index 0000000000..57fc8773f1 --- /dev/null +++ b/hw/block/fdc-sysbus.c @@ -0,0 +1,251 @@ +/* + * QEMU Floppy disk emulator (Intel 82078) + * + * Copyright (c) 2003, 2007 Jocelyn Mayer + * Copyright (c) 2008 Hervé Poussineau + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qom/object.h" +#include "hw/sysbus.h" +#include "hw/block/fdc.h" +#include "migration/vmstate.h" +#include "fdc-internal.h" +#include "trace.h" + +#define TYPE_SYSBUS_FDC "base-sysbus-fdc" +typedef struct FDCtrlSysBusClass FDCtrlSysBusClass; +typedef struct FDCtrlSysBus FDCtrlSysBus; +DECLARE_OBJ_CHECKERS(FDCtrlSysBus, FDCtrlSysBusClass, + SYSBUS_FDC, TYPE_SYSBUS_FDC) + +struct FDCtrlSysBusClass { + /*< private >*/ + SysBusDeviceClass parent_class; + /*< public >*/ + + bool use_strict_io; +}; + +struct FDCtrlSysBus { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + struct FDCtrl state; +}; + +static uint64_t fdctrl_read_mem(void *opaque, hwaddr reg, unsigned ize) +{ + return fdctrl_read(opaque, (uint32_t)reg); +} + +static void fdctrl_write_mem(void *opaque, hwaddr reg, + uint64_t value, unsigned size) +{ + fdctrl_write(opaque, (uint32_t)reg, value); +} + +static const MemoryRegionOps fdctrl_mem_ops = { + .read = fdctrl_read_mem, + .write = fdctrl_write_mem, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static const MemoryRegionOps fdctrl_mem_strict_ops = { + .read = fdctrl_read_mem, + .write = fdctrl_write_mem, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 1, + }, +}; + +static void fdctrl_external_reset_sysbus(DeviceState *d) +{ + FDCtrlSysBus *sys = SYSBUS_FDC(d); + FDCtrl *s = &sys->state; + + fdctrl_reset(s, 0); +} + +static void fdctrl_handle_tc(void *opaque, int irq, int level) +{ + trace_fdctrl_tc_pulse(level); +} + +void fdctrl_init_sysbus(qemu_irq irq, int dma_chann, + hwaddr mmio_base, DriveInfo **fds) +{ + FDCtrl *fdctrl; + DeviceState *dev; + SysBusDevice *sbd; + FDCtrlSysBus *sys; + + dev = qdev_new("sysbus-fdc"); + sys = SYSBUS_FDC(dev); + fdctrl = &sys->state; + fdctrl->dma_chann = dma_chann; /* FIXME */ + sbd = SYS_BUS_DEVICE(dev); + sysbus_realize_and_unref(sbd, &error_fatal); + sysbus_connect_irq(sbd, 0, irq); + sysbus_mmio_map(sbd, 0, mmio_base); + + fdctrl_init_drives(&sys->state.bus, fds); +} + +void sun4m_fdctrl_init(qemu_irq irq, hwaddr io_base, + DriveInfo **fds, qemu_irq *fdc_tc) +{ + DeviceState *dev; + FDCtrlSysBus *sys; + + dev = qdev_new("sun-fdtwo"); + sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + sys = SYSBUS_FDC(dev); + sysbus_connect_irq(SYS_BUS_DEVICE(sys), 0, irq); + sysbus_mmio_map(SYS_BUS_DEVICE(sys), 0, io_base); + *fdc_tc = qdev_get_gpio_in(dev, 0); + + fdctrl_init_drives(&sys->state.bus, fds); +} + +static void sysbus_fdc_common_instance_init(Object *obj) +{ + DeviceState *dev = DEVICE(obj); + FDCtrlSysBusClass *sbdc = SYSBUS_FDC_GET_CLASS(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + FDCtrlSysBus *sys = SYSBUS_FDC(obj); + FDCtrl *fdctrl = &sys->state; + + qdev_set_legacy_instance_id(dev, 0 /* io */, 2); /* FIXME */ + + memory_region_init_io(&fdctrl->iomem, obj, + sbdc->use_strict_io ? &fdctrl_mem_strict_ops + : &fdctrl_mem_ops, + fdctrl, "fdc", 0x08); + sysbus_init_mmio(sbd, &fdctrl->iomem); + + sysbus_init_irq(sbd, &fdctrl->irq); + qdev_init_gpio_in(dev, fdctrl_handle_tc, 1); +} + +static void sysbus_fdc_realize(DeviceState *dev, Error **errp) +{ + FDCtrlSysBus *sys = SYSBUS_FDC(dev); + FDCtrl *fdctrl = &sys->state; + + fdctrl_realize_common(dev, fdctrl, errp); +} + +static const VMStateDescription vmstate_sysbus_fdc = { + .name = "fdc", + .version_id = 2, + .minimum_version_id = 2, + .fields = (VMStateField[]) { + VMSTATE_STRUCT(state, FDCtrlSysBus, 0, vmstate_fdc, FDCtrl), + VMSTATE_END_OF_LIST() + } +}; + +static void sysbus_fdc_common_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = sysbus_fdc_realize; + dc->reset = fdctrl_external_reset_sysbus; + dc->vmsd = &vmstate_sysbus_fdc; + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); +} + +static const TypeInfo sysbus_fdc_common_typeinfo = { + .name = TYPE_SYSBUS_FDC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(FDCtrlSysBus), + .instance_init = sysbus_fdc_common_instance_init, + .abstract = true, + .class_init = sysbus_fdc_common_class_init, + .class_size = sizeof(FDCtrlSysBusClass), +}; + +static Property sysbus_fdc_properties[] = { + DEFINE_PROP_SIGNED("fdtypeA", FDCtrlSysBus, state.qdev_for_drives[0].type, + FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type, + FloppyDriveType), + DEFINE_PROP_SIGNED("fdtypeB", FDCtrlSysBus, state.qdev_for_drives[1].type, + FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type, + FloppyDriveType), + DEFINE_PROP_SIGNED("fallback", FDCtrlSysBus, state.fallback, + FLOPPY_DRIVE_TYPE_144, qdev_prop_fdc_drive_type, + FloppyDriveType), + DEFINE_PROP_END_OF_LIST(), +}; + +static void sysbus_fdc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "virtual floppy controller"; + device_class_set_props(dc, sysbus_fdc_properties); +} + +static const TypeInfo sysbus_fdc_typeinfo = { + .name = "sysbus-fdc", + .parent = TYPE_SYSBUS_FDC, + .class_init = sysbus_fdc_class_init, +}; + +static Property sun4m_fdc_properties[] = { + DEFINE_PROP_SIGNED("fdtype", FDCtrlSysBus, state.qdev_for_drives[0].type, + FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type, + FloppyDriveType), + DEFINE_PROP_SIGNED("fallback", FDCtrlSysBus, state.fallback, + FLOPPY_DRIVE_TYPE_144, qdev_prop_fdc_drive_type, + FloppyDriveType), + DEFINE_PROP_END_OF_LIST(), +}; + +static void sun4m_fdc_class_init(ObjectClass *klass, void *data) +{ + FDCtrlSysBusClass *sbdc = SYSBUS_FDC_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + sbdc->use_strict_io = true; + dc->desc = "virtual floppy controller"; + device_class_set_props(dc, sun4m_fdc_properties); +} + +static const TypeInfo sun4m_fdc_typeinfo = { + .name = "sun-fdtwo", + .parent = TYPE_SYSBUS_FDC, + .class_init = sun4m_fdc_class_init, +}; + +static void sysbus_fdc_register_types(void) +{ + type_register_static(&sysbus_fdc_common_typeinfo); + type_register_static(&sysbus_fdc_typeinfo); + type_register_static(&sun4m_fdc_typeinfo); +} + +type_init(sysbus_fdc_register_types) diff --git a/hw/block/fdc.c b/hw/block/fdc.c index a825c2acba..9014cd30b3 100644 --- a/hw/block/fdc.c +++ b/hw/block/fdc.c @@ -32,12 +32,10 @@ #include "qapi/error.h" #include "qemu/error-report.h" #include "qemu/timer.h" -#include "hw/acpi/aml-build.h" #include "hw/irq.h" #include "hw/isa/isa.h" #include "hw/qdev-properties.h" #include "hw/qdev-properties-system.h" -#include "hw/sysbus.h" #include "migration/vmstate.h" #include "hw/block/block.h" #include "sysemu/block-backend.h" @@ -48,6 +46,7 @@ #include "qemu/module.h" #include "trace.h" #include "qom/object.h" +#include "fdc-internal.h" /********************************************************/ /* debug Floppy devices */ @@ -68,15 +67,8 @@ #define TYPE_FLOPPY_BUS "floppy-bus" OBJECT_DECLARE_SIMPLE_TYPE(FloppyBus, FLOPPY_BUS) -typedef struct FDCtrl FDCtrl; -typedef struct FDrive FDrive; static FDrive *get_drv(FDCtrl *fdctrl, int unit); -struct FloppyBus { - BusState bus; - FDCtrl *fdc; -}; - static const TypeInfo floppy_bus_info = { .name = TYPE_FLOPPY_BUS, .parent = TYPE_BUS, @@ -93,32 +85,11 @@ static void floppy_bus_create(FDCtrl *fdc, FloppyBus *bus, DeviceState *dev) /********************************************************/ /* Floppy drive emulation */ -typedef enum FDriveRate { - FDRIVE_RATE_500K = 0x00, /* 500 Kbps */ - FDRIVE_RATE_300K = 0x01, /* 300 Kbps */ - FDRIVE_RATE_250K = 0x02, /* 250 Kbps */ - FDRIVE_RATE_1M = 0x03, /* 1 Mbps */ -} FDriveRate; - -typedef enum FDriveSize { - FDRIVE_SIZE_UNKNOWN, - FDRIVE_SIZE_350, - FDRIVE_SIZE_525, -} FDriveSize; - -typedef struct FDFormat { - FloppyDriveType drive; - uint8_t last_sect; - uint8_t max_track; - uint8_t max_head; - FDriveRate rate; -} FDFormat; - /* In many cases, the total sector size of a format is enough to uniquely * identify it. However, there are some total sector collisions between * formats of different physical size, and these are noted below by * highlighting the total sector size for entries with collisions. */ -static const FDFormat fd_formats[] = { +const FDFormat fd_formats[] = { /* First entry is default format */ /* 1.44 MB 3"1/2 floppy disks */ { FLOPPY_DRIVE_TYPE_144, 18, 80, 1, FDRIVE_RATE_500K, }, /* 3.5" 2880 */ @@ -186,35 +157,6 @@ static FDriveSize drive_size(FloppyDriveType drive) #define FD_SECTOR_SC 2 /* Sector size code */ #define FD_RESET_SENSEI_COUNT 4 /* Number of sense interrupts on RESET */ -/* Floppy disk drive emulation */ -typedef enum FDiskFlags { - FDISK_DBL_SIDES = 0x01, -} FDiskFlags; - -struct FDrive { - FDCtrl *fdctrl; - BlockBackend *blk; - BlockConf *conf; - /* Drive status */ - FloppyDriveType drive; /* CMOS drive type */ - uint8_t perpendicular; /* 2.88 MB access mode */ - /* Position */ - uint8_t head; - uint8_t track; - uint8_t sect; - /* Media */ - FloppyDriveType disk; /* Current disk type */ - FDiskFlags flags; - uint8_t last_sect; /* Nb sector per track */ - uint8_t max_track; /* Nb of tracks */ - uint16_t bps; /* Bytes per sector */ - uint8_t ro; /* Is read-only */ - uint8_t media_changed; /* Is media changed */ - uint8_t media_rate; /* Data rate of medium */ - - bool media_validated; /* Have we validated the media? */ -}; - static FloppyDriveType get_fallback_drive_type(FDrive *drv); @@ -626,10 +568,7 @@ static const TypeInfo floppy_drive_info = { /********************************************************/ /* Intel 82078 floppy disk controller emulation */ -static void fdctrl_reset(FDCtrl *fdctrl, int do_irq); static void fdctrl_to_command_phase(FDCtrl *fdctrl); -static int fdctrl_transfer_handler (void *opaque, int nchan, - int dma_pos, int dma_len); static void fdctrl_raise_irq(FDCtrl *fdctrl); static FDrive *get_cur_drv(FDCtrl *fdctrl); @@ -828,88 +767,12 @@ enum { #define FD_MULTI_TRACK(state) ((state) & FD_STATE_MULTI) #define FD_FORMAT_CMD(state) ((state) & FD_STATE_FORMAT) -struct FDCtrl { - MemoryRegion iomem; - qemu_irq irq; - /* Controller state */ - QEMUTimer *result_timer; - int dma_chann; - uint8_t phase; - IsaDma *dma; - /* Controller's identification */ - uint8_t version; - /* HW */ - uint8_t sra; - uint8_t srb; - uint8_t dor; - uint8_t dor_vmstate; /* only used as temp during vmstate */ - uint8_t tdr; - uint8_t dsr; - uint8_t msr; - uint8_t cur_drv; - uint8_t status0; - uint8_t status1; - uint8_t status2; - /* Command FIFO */ - uint8_t *fifo; - int32_t fifo_size; - uint32_t data_pos; - uint32_t data_len; - uint8_t data_state; - uint8_t data_dir; - uint8_t eot; /* last wanted sector */ - /* States kept only to be returned back */ - /* precompensation */ - uint8_t precomp_trk; - uint8_t config; - uint8_t lock; - /* Power down config (also with status regB access mode */ - uint8_t pwrd; - /* Floppy drives */ - FloppyBus bus; - uint8_t num_floppies; - FDrive drives[MAX_FD]; - struct { - FloppyDriveType type; - } qdev_for_drives[MAX_FD]; - int reset_sensei; - FloppyDriveType fallback; /* type=auto failure fallback */ - /* Timers state */ - uint8_t timer0; - uint8_t timer1; - PortioList portio_list; -}; - static FloppyDriveType get_fallback_drive_type(FDrive *drv) { return drv->fdctrl->fallback; } -#define TYPE_SYSBUS_FDC "base-sysbus-fdc" -OBJECT_DECLARE_SIMPLE_TYPE(FDCtrlSysBus, SYSBUS_FDC) - -struct FDCtrlSysBus { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - struct FDCtrl state; -}; - -OBJECT_DECLARE_SIMPLE_TYPE(FDCtrlISABus, ISA_FDC) - -struct FDCtrlISABus { - ISADevice parent_obj; - - uint32_t iobase; - uint32_t irq; - uint32_t dma; - struct FDCtrl state; - int32_t bootindexA; - int32_t bootindexB; -}; - -static uint32_t fdctrl_read (void *opaque, uint32_t reg) +uint32_t fdctrl_read(void *opaque, uint32_t reg) { FDCtrl *fdctrl = opaque; uint32_t retval; @@ -946,7 +809,7 @@ static uint32_t fdctrl_read (void *opaque, uint32_t reg) return retval; } -static void fdctrl_write (void *opaque, uint32_t reg, uint32_t value) +void fdctrl_write(void *opaque, uint32_t reg, uint32_t value) { FDCtrl *fdctrl = opaque; @@ -973,34 +836,6 @@ static void fdctrl_write (void *opaque, uint32_t reg, uint32_t value) } } -static uint64_t fdctrl_read_mem (void *opaque, hwaddr reg, - unsigned ize) -{ - return fdctrl_read(opaque, (uint32_t)reg); -} - -static void fdctrl_write_mem (void *opaque, hwaddr reg, - uint64_t value, unsigned size) -{ - fdctrl_write(opaque, (uint32_t)reg, value); -} - -static const MemoryRegionOps fdctrl_mem_ops = { - .read = fdctrl_read_mem, - .write = fdctrl_write_mem, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static const MemoryRegionOps fdctrl_mem_strict_ops = { - .read = fdctrl_read_mem, - .write = fdctrl_write_mem, - .endianness = DEVICE_NATIVE_ENDIAN, - .valid = { - .min_access_size = 1, - .max_access_size = 1, - }, -}; - static bool fdrive_media_changed_needed(void *opaque) { FDrive *drive = opaque; @@ -1178,7 +1013,7 @@ static const VMStateDescription vmstate_fdc_phase = { } }; -static const VMStateDescription vmstate_fdc = { +const VMStateDescription vmstate_fdc = { .name = "fdc", .version_id = 2, .minimum_version_id = 2, @@ -1224,32 +1059,6 @@ static const VMStateDescription vmstate_fdc = { } }; -static void fdctrl_external_reset_sysbus(DeviceState *d) -{ - FDCtrlSysBus *sys = SYSBUS_FDC(d); - FDCtrl *s = &sys->state; - - fdctrl_reset(s, 0); -} - -static void fdctrl_external_reset_isa(DeviceState *d) -{ - FDCtrlISABus *isa = ISA_FDC(d); - FDCtrl *s = &isa->state; - - fdctrl_reset(s, 0); -} - -static void fdctrl_handle_tc(void *opaque, int irq, int level) -{ - //FDCtrl *s = opaque; - - if (level) { - // XXX - FLOPPY_DPRINTF("TC pulsed\n"); - } -} - /* Change IRQ state */ static void fdctrl_reset_irq(FDCtrl *fdctrl) { @@ -1273,7 +1082,7 @@ static void fdctrl_raise_irq(FDCtrl *fdctrl) } /* Reset controller */ -static void fdctrl_reset(FDCtrl *fdctrl, int do_irq) +void fdctrl_reset(FDCtrl *fdctrl, int do_irq) { int i; @@ -1752,8 +1561,7 @@ static void fdctrl_start_transfer_del(FDCtrl *fdctrl, int direction) } /* handlers for DMA transfers */ -static int fdctrl_transfer_handler (void *opaque, int nchan, - int dma_pos, int dma_len) +int fdctrl_transfer_handler(void *opaque, int nchan, int dma_pos, int dma_len) { FDCtrl *fdctrl; FDrive *cur_drv; @@ -2489,7 +2297,7 @@ static void fdctrl_result_timer(void *opaque) /* Init functions */ -static void fdctrl_init_drives(FloppyBus *bus, DriveInfo **fds) +void fdctrl_init_drives(FloppyBus *bus, DriveInfo **fds) { DeviceState *dev; int i; @@ -2506,49 +2314,7 @@ static void fdctrl_init_drives(FloppyBus *bus, DriveInfo **fds) } } -void isa_fdc_init_drives(ISADevice *fdc, DriveInfo **fds) -{ - fdctrl_init_drives(&ISA_FDC(fdc)->state.bus, fds); -} - -void fdctrl_init_sysbus(qemu_irq irq, int dma_chann, - hwaddr mmio_base, DriveInfo **fds) -{ - FDCtrl *fdctrl; - DeviceState *dev; - SysBusDevice *sbd; - FDCtrlSysBus *sys; - - dev = qdev_new("sysbus-fdc"); - sys = SYSBUS_FDC(dev); - fdctrl = &sys->state; - fdctrl->dma_chann = dma_chann; /* FIXME */ - sbd = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(sbd, &error_fatal); - sysbus_connect_irq(sbd, 0, irq); - sysbus_mmio_map(sbd, 0, mmio_base); - - fdctrl_init_drives(&sys->state.bus, fds); -} - -void sun4m_fdctrl_init(qemu_irq irq, hwaddr io_base, - DriveInfo **fds, qemu_irq *fdc_tc) -{ - DeviceState *dev; - FDCtrlSysBus *sys; - - dev = qdev_new("sun-fdtwo"); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sys = SYSBUS_FDC(dev); - sysbus_connect_irq(SYS_BUS_DEVICE(sys), 0, irq); - sysbus_mmio_map(SYS_BUS_DEVICE(sys), 0, io_base); - *fdc_tc = qdev_get_gpio_in(dev, 0); - - fdctrl_init_drives(&sys->state.bus, fds); -} - -static void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, - Error **errp) +void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, Error **errp) { int i, j; FDrive *drive; @@ -2582,14 +2348,6 @@ static void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, fdctrl->config = FD_CONFIG_EIS | FD_CONFIG_EFIFO; /* Implicit seek, polling & FIFO enabled */ fdctrl->num_floppies = MAX_FD; - if (fdctrl->dma_chann != -1) { - IsaDmaClass *k; - assert(fdctrl->dma); - k = ISADMA_GET_CLASS(fdctrl->dma); - k->register_channel(fdctrl->dma, fdctrl->dma_chann, - &fdctrl_transfer_handler, fdctrl); - } - floppy_bus_create(fdctrl, &fdctrl->bus, dev); for (i = 0; i < MAX_FD; i++) { @@ -2600,369 +2358,8 @@ static void fdctrl_realize_common(DeviceState *dev, FDCtrl *fdctrl, } } -static const MemoryRegionPortio fdc_portio_list[] = { - { 1, 5, 1, .read = fdctrl_read, .write = fdctrl_write }, - { 7, 1, 1, .read = fdctrl_read, .write = fdctrl_write }, - PORTIO_END_OF_LIST(), -}; - -static void isabus_fdc_realize(DeviceState *dev, Error **errp) -{ - ISADevice *isadev = ISA_DEVICE(dev); - FDCtrlISABus *isa = ISA_FDC(dev); - FDCtrl *fdctrl = &isa->state; - Error *err = NULL; - - isa_register_portio_list(isadev, &fdctrl->portio_list, - isa->iobase, fdc_portio_list, fdctrl, - "fdc"); - - isa_init_irq(isadev, &fdctrl->irq, isa->irq); - fdctrl->dma_chann = isa->dma; - if (fdctrl->dma_chann != -1) { - fdctrl->dma = isa_get_dma(isa_bus_from_device(isadev), isa->dma); - if (!fdctrl->dma) { - error_setg(errp, "ISA controller does not support DMA"); - return; - } - } - - qdev_set_legacy_instance_id(dev, isa->iobase, 2); - fdctrl_realize_common(dev, fdctrl, &err); - if (err != NULL) { - error_propagate(errp, err); - return; - } -} - -static void sysbus_fdc_initfn(Object *obj) -{ - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - FDCtrlSysBus *sys = SYSBUS_FDC(obj); - FDCtrl *fdctrl = &sys->state; - - fdctrl->dma_chann = -1; - - memory_region_init_io(&fdctrl->iomem, obj, &fdctrl_mem_ops, fdctrl, - "fdc", 0x08); - sysbus_init_mmio(sbd, &fdctrl->iomem); -} - -static void sun4m_fdc_initfn(Object *obj) -{ - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - FDCtrlSysBus *sys = SYSBUS_FDC(obj); - FDCtrl *fdctrl = &sys->state; - - fdctrl->dma_chann = -1; - - memory_region_init_io(&fdctrl->iomem, obj, &fdctrl_mem_strict_ops, - fdctrl, "fdctrl", 0x08); - sysbus_init_mmio(sbd, &fdctrl->iomem); -} - -static void sysbus_fdc_common_initfn(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - FDCtrlSysBus *sys = SYSBUS_FDC(obj); - FDCtrl *fdctrl = &sys->state; - - qdev_set_legacy_instance_id(dev, 0 /* io */, 2); /* FIXME */ - - sysbus_init_irq(sbd, &fdctrl->irq); - qdev_init_gpio_in(dev, fdctrl_handle_tc, 1); -} - -static void sysbus_fdc_common_realize(DeviceState *dev, Error **errp) -{ - FDCtrlSysBus *sys = SYSBUS_FDC(dev); - FDCtrl *fdctrl = &sys->state; - - fdctrl_realize_common(dev, fdctrl, errp); -} - -FloppyDriveType isa_fdc_get_drive_type(ISADevice *fdc, int i) -{ - FDCtrlISABus *isa = ISA_FDC(fdc); - - return isa->state.drives[i].drive; -} - -static void isa_fdc_get_drive_max_chs(FloppyDriveType type, uint8_t *maxc, - uint8_t *maxh, uint8_t *maxs) -{ - const FDFormat *fdf; - - *maxc = *maxh = *maxs = 0; - for (fdf = fd_formats; fdf->drive != FLOPPY_DRIVE_TYPE_NONE; fdf++) { - if (fdf->drive != type) { - continue; - } - if (*maxc < fdf->max_track) { - *maxc = fdf->max_track; - } - if (*maxh < fdf->max_head) { - *maxh = fdf->max_head; - } - if (*maxs < fdf->last_sect) { - *maxs = fdf->last_sect; - } - } - (*maxc)--; -} - -static Aml *build_fdinfo_aml(int idx, FloppyDriveType type) -{ - Aml *dev, *fdi; - uint8_t maxc, maxh, maxs; - - isa_fdc_get_drive_max_chs(type, &maxc, &maxh, &maxs); - - dev = aml_device("FLP%c", 'A' + idx); - - aml_append(dev, aml_name_decl("_ADR", aml_int(idx))); - - fdi = aml_package(16); - aml_append(fdi, aml_int(idx)); /* Drive Number */ - aml_append(fdi, - aml_int(cmos_get_fd_drive_type(type))); /* Device Type */ - /* - * the values below are the limits of the drive, and are thus independent - * of the inserted media - */ - aml_append(fdi, aml_int(maxc)); /* Maximum Cylinder Number */ - aml_append(fdi, aml_int(maxs)); /* Maximum Sector Number */ - aml_append(fdi, aml_int(maxh)); /* Maximum Head Number */ - /* - * SeaBIOS returns the below values for int 0x13 func 0x08 regardless of - * the drive type, so shall we - */ - aml_append(fdi, aml_int(0xAF)); /* disk_specify_1 */ - aml_append(fdi, aml_int(0x02)); /* disk_specify_2 */ - aml_append(fdi, aml_int(0x25)); /* disk_motor_wait */ - aml_append(fdi, aml_int(0x02)); /* disk_sector_siz */ - aml_append(fdi, aml_int(0x12)); /* disk_eot */ - aml_append(fdi, aml_int(0x1B)); /* disk_rw_gap */ - aml_append(fdi, aml_int(0xFF)); /* disk_dtl */ - aml_append(fdi, aml_int(0x6C)); /* disk_formt_gap */ - aml_append(fdi, aml_int(0xF6)); /* disk_fill */ - aml_append(fdi, aml_int(0x0F)); /* disk_head_sttl */ - aml_append(fdi, aml_int(0x08)); /* disk_motor_strt */ - - aml_append(dev, aml_name_decl("_FDI", fdi)); - return dev; -} - -int cmos_get_fd_drive_type(FloppyDriveType fd0) -{ - int val; - - switch (fd0) { - case FLOPPY_DRIVE_TYPE_144: - /* 1.44 Mb 3"5 drive */ - val = 4; - break; - case FLOPPY_DRIVE_TYPE_288: - /* 2.88 Mb 3"5 drive */ - val = 5; - break; - case FLOPPY_DRIVE_TYPE_120: - /* 1.2 Mb 5"5 drive */ - val = 2; - break; - case FLOPPY_DRIVE_TYPE_NONE: - default: - val = 0; - break; - } - return val; -} - -static void fdc_isa_build_aml(ISADevice *isadev, Aml *scope) -{ - Aml *dev; - Aml *crs; - int i; - -#define ACPI_FDE_MAX_FD 4 - uint32_t fde_buf[5] = { - 0, 0, 0, 0, /* presence of floppy drives #0 - #3 */ - cpu_to_le32(2) /* tape presence (2 == never present) */ - }; - - crs = aml_resource_template(); - aml_append(crs, aml_io(AML_DECODE16, 0x03F2, 0x03F2, 0x00, 0x04)); - aml_append(crs, aml_io(AML_DECODE16, 0x03F7, 0x03F7, 0x00, 0x01)); - aml_append(crs, aml_irq_no_flags(6)); - aml_append(crs, - aml_dma(AML_COMPATIBILITY, AML_NOTBUSMASTER, AML_TRANSFER8, 2)); - - dev = aml_device("FDC0"); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0700"))); - aml_append(dev, aml_name_decl("_CRS", crs)); - - for (i = 0; i < MIN(MAX_FD, ACPI_FDE_MAX_FD); i++) { - FloppyDriveType type = isa_fdc_get_drive_type(isadev, i); - - if (type < FLOPPY_DRIVE_TYPE_NONE) { - fde_buf[i] = cpu_to_le32(1); /* drive present */ - aml_append(dev, build_fdinfo_aml(i, type)); - } - } - aml_append(dev, aml_name_decl("_FDE", - aml_buffer(sizeof(fde_buf), (uint8_t *)fde_buf))); - - aml_append(scope, dev); -} - -static const VMStateDescription vmstate_isa_fdc ={ - .name = "fdc", - .version_id = 2, - .minimum_version_id = 2, - .fields = (VMStateField[]) { - VMSTATE_STRUCT(state, FDCtrlISABus, 0, vmstate_fdc, FDCtrl), - VMSTATE_END_OF_LIST() - } -}; - -static Property isa_fdc_properties[] = { - DEFINE_PROP_UINT32("iobase", FDCtrlISABus, iobase, 0x3f0), - DEFINE_PROP_UINT32("irq", FDCtrlISABus, irq, 6), - DEFINE_PROP_UINT32("dma", FDCtrlISABus, dma, 2), - DEFINE_PROP_SIGNED("fdtypeA", FDCtrlISABus, state.qdev_for_drives[0].type, - FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type, - FloppyDriveType), - DEFINE_PROP_SIGNED("fdtypeB", FDCtrlISABus, state.qdev_for_drives[1].type, - FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type, - FloppyDriveType), - DEFINE_PROP_SIGNED("fallback", FDCtrlISABus, state.fallback, - FLOPPY_DRIVE_TYPE_288, qdev_prop_fdc_drive_type, - FloppyDriveType), - DEFINE_PROP_END_OF_LIST(), -}; - -static void isabus_fdc_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - ISADeviceClass *isa = ISA_DEVICE_CLASS(klass); - - dc->realize = isabus_fdc_realize; - dc->fw_name = "fdc"; - dc->reset = fdctrl_external_reset_isa; - dc->vmsd = &vmstate_isa_fdc; - isa->build_aml = fdc_isa_build_aml; - device_class_set_props(dc, isa_fdc_properties); - set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); -} - -static void isabus_fdc_instance_init(Object *obj) -{ - FDCtrlISABus *isa = ISA_FDC(obj); - - device_add_bootindex_property(obj, &isa->bootindexA, - "bootindexA", "/floppy@0", - DEVICE(obj)); - device_add_bootindex_property(obj, &isa->bootindexB, - "bootindexB", "/floppy@1", - DEVICE(obj)); -} - -static const TypeInfo isa_fdc_info = { - .name = TYPE_ISA_FDC, - .parent = TYPE_ISA_DEVICE, - .instance_size = sizeof(FDCtrlISABus), - .class_init = isabus_fdc_class_init, - .instance_init = isabus_fdc_instance_init, -}; - -static const VMStateDescription vmstate_sysbus_fdc ={ - .name = "fdc", - .version_id = 2, - .minimum_version_id = 2, - .fields = (VMStateField[]) { - VMSTATE_STRUCT(state, FDCtrlSysBus, 0, vmstate_fdc, FDCtrl), - VMSTATE_END_OF_LIST() - } -}; - -static Property sysbus_fdc_properties[] = { - DEFINE_PROP_SIGNED("fdtypeA", FDCtrlSysBus, state.qdev_for_drives[0].type, - FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type, - FloppyDriveType), - DEFINE_PROP_SIGNED("fdtypeB", FDCtrlSysBus, state.qdev_for_drives[1].type, - FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type, - FloppyDriveType), - DEFINE_PROP_SIGNED("fallback", FDCtrlSysBus, state.fallback, - FLOPPY_DRIVE_TYPE_144, qdev_prop_fdc_drive_type, - FloppyDriveType), - DEFINE_PROP_END_OF_LIST(), -}; - -static void sysbus_fdc_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - device_class_set_props(dc, sysbus_fdc_properties); - set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); -} - -static const TypeInfo sysbus_fdc_info = { - .name = "sysbus-fdc", - .parent = TYPE_SYSBUS_FDC, - .instance_init = sysbus_fdc_initfn, - .class_init = sysbus_fdc_class_init, -}; - -static Property sun4m_fdc_properties[] = { - DEFINE_PROP_SIGNED("fdtype", FDCtrlSysBus, state.qdev_for_drives[0].type, - FLOPPY_DRIVE_TYPE_AUTO, qdev_prop_fdc_drive_type, - FloppyDriveType), - DEFINE_PROP_SIGNED("fallback", FDCtrlSysBus, state.fallback, - FLOPPY_DRIVE_TYPE_144, qdev_prop_fdc_drive_type, - FloppyDriveType), - DEFINE_PROP_END_OF_LIST(), -}; - -static void sun4m_fdc_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - device_class_set_props(dc, sun4m_fdc_properties); - set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); -} - -static const TypeInfo sun4m_fdc_info = { - .name = "sun-fdtwo", - .parent = TYPE_SYSBUS_FDC, - .instance_init = sun4m_fdc_initfn, - .class_init = sun4m_fdc_class_init, -}; - -static void sysbus_fdc_common_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = sysbus_fdc_common_realize; - dc->reset = fdctrl_external_reset_sysbus; - dc->vmsd = &vmstate_sysbus_fdc; -} - -static const TypeInfo sysbus_fdc_type_info = { - .name = TYPE_SYSBUS_FDC, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(FDCtrlSysBus), - .instance_init = sysbus_fdc_common_initfn, - .abstract = true, - .class_init = sysbus_fdc_common_class_init, -}; - static void fdc_register_types(void) { - type_register_static(&isa_fdc_info); - type_register_static(&sysbus_fdc_type_info); - type_register_static(&sysbus_fdc_info); - type_register_static(&sun4m_fdc_info); type_register_static(&floppy_bus_info); type_register_static(&floppy_drive_info); } diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index 183d3f44c2..b77503dc84 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -259,6 +259,8 @@ static const FlashPartInfo known_devices[] = { { INFO_STACKED("n25q00a", 0x20bb21, 0x1000, 64 << 10, 2048, ER_4K, 4) }, { INFO_STACKED("mt25ql01g", 0x20ba21, 0x1040, 64 << 10, 2048, ER_4K, 2) }, { INFO_STACKED("mt25qu01g", 0x20bb21, 0x1040, 64 << 10, 2048, ER_4K, 2) }, + { INFO_STACKED("mt25ql02g", 0x20ba22, 0x1040, 64 << 10, 4096, ER_4K | ER_32K, 2) }, + { INFO_STACKED("mt25qu02g", 0x20bb22, 0x1040, 64 << 10, 4096, ER_4K | ER_32K, 2) }, /* Spansion -- single (large) sector size only, at least * for the chips listed here (without boot sectors). diff --git a/hw/block/meson.build b/hw/block/meson.build index 5b4a7699f9..2389326112 100644 --- a/hw/block/meson.build +++ b/hw/block/meson.build @@ -5,6 +5,8 @@ softmmu_ss.add(files( )) softmmu_ss.add(when: 'CONFIG_ECC', if_true: files('ecc.c')) softmmu_ss.add(when: 'CONFIG_FDC', if_true: files('fdc.c')) +softmmu_ss.add(when: 'CONFIG_FDC_ISA', if_true: files('fdc-isa.c')) +softmmu_ss.add(when: 'CONFIG_FDC_SYSBUS', if_true: files('fdc-sysbus.c')) softmmu_ss.add(when: 'CONFIG_NAND', if_true: files('nand.c')) softmmu_ss.add(when: 'CONFIG_ONENAND', if_true: files('onenand.c')) softmmu_ss.add(when: 'CONFIG_PFLASH_CFI01', if_true: files('pflash_cfi01.c')) @@ -13,7 +15,6 @@ softmmu_ss.add(when: 'CONFIG_SSI_M25P80', if_true: files('m25p80.c')) softmmu_ss.add(when: 'CONFIG_SWIM', if_true: files('swim.c')) softmmu_ss.add(when: 'CONFIG_XEN', if_true: files('xen-block.c')) softmmu_ss.add(when: 'CONFIG_TC58128', if_true: files('tc58128.c')) -softmmu_ss.add(when: 'CONFIG_NVME_PCI', if_true: files('nvme.c', 'nvme-ns.c', 'nvme-subsys.c', 'nvme-dif.c')) specific_ss.add(when: 'CONFIG_VIRTIO_BLK', if_true: files('virtio-blk.c')) specific_ss.add(when: 'CONFIG_VHOST_USER_BLK', if_true: files('vhost-user-blk.c')) diff --git a/hw/block/nvme-dif.h b/hw/block/nvme-dif.h deleted file mode 100644 index 524faffbd7..0000000000 --- a/hw/block/nvme-dif.h +++ /dev/null @@ -1,63 +0,0 @@ -/* - * QEMU NVM Express End-to-End Data Protection support - * - * Copyright (c) 2021 Samsung Electronics Co., Ltd. - * - * Authors: - * Klaus Jensen - * Gollu Appalanaidu - */ - -#ifndef HW_NVME_DIF_H -#define HW_NVME_DIF_H - -/* from Linux kernel (crypto/crct10dif_common.c) */ -static const uint16_t t10_dif_crc_table[256] = { - 0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B, - 0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6, - 0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6, - 0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B, - 0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1, - 0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C, - 0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C, - 0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781, - 0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8, - 0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255, - 0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925, - 0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698, - 0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472, - 0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF, - 0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF, - 0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02, - 0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA, - 0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067, - 0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17, - 0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA, - 0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640, - 0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD, - 0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D, - 0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30, - 0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759, - 0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4, - 0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394, - 0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29, - 0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3, - 0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E, - 0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E, - 0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3 -}; - -uint16_t nvme_check_prinfo(NvmeNamespace *ns, uint16_t ctrl, uint64_t slba, - uint32_t reftag); -uint16_t nvme_dif_mangle_mdata(NvmeNamespace *ns, uint8_t *mbuf, size_t mlen, - uint64_t slba); -void nvme_dif_pract_generate_dif(NvmeNamespace *ns, uint8_t *buf, size_t len, - uint8_t *mbuf, size_t mlen, uint16_t apptag, - uint32_t reftag); -uint16_t nvme_dif_check(NvmeNamespace *ns, uint8_t *buf, size_t len, - uint8_t *mbuf, size_t mlen, uint16_t ctrl, - uint64_t slba, uint16_t apptag, - uint16_t appmask, uint32_t reftag); -uint16_t nvme_dif_rw(NvmeCtrl *n, NvmeRequest *req); - -#endif /* HW_NVME_DIF_H */ diff --git a/hw/block/nvme-ns.h b/hw/block/nvme-ns.h deleted file mode 100644 index fb0a41f912..0000000000 --- a/hw/block/nvme-ns.h +++ /dev/null @@ -1,229 +0,0 @@ -/* - * QEMU NVM Express Virtual Namespace - * - * Copyright (c) 2019 CNEX Labs - * Copyright (c) 2020 Samsung Electronics - * - * Authors: - * Klaus Jensen - * - * This work is licensed under the terms of the GNU GPL, version 2. See the - * COPYING file in the top-level directory. - * - */ - -#ifndef NVME_NS_H -#define NVME_NS_H - -#include "qemu/uuid.h" - -#define TYPE_NVME_NS "nvme-ns" -#define NVME_NS(obj) \ - OBJECT_CHECK(NvmeNamespace, (obj), TYPE_NVME_NS) - -typedef struct NvmeZone { - NvmeZoneDescr d; - uint64_t w_ptr; - QTAILQ_ENTRY(NvmeZone) entry; -} NvmeZone; - -typedef struct NvmeNamespaceParams { - bool detached; - bool shared; - uint32_t nsid; - QemuUUID uuid; - - uint16_t ms; - uint8_t mset; - uint8_t pi; - uint8_t pil; - - uint16_t mssrl; - uint32_t mcl; - uint8_t msrc; - - bool zoned; - bool cross_zone_read; - uint64_t zone_size_bs; - uint64_t zone_cap_bs; - uint32_t max_active_zones; - uint32_t max_open_zones; - uint32_t zd_extension_size; -} NvmeNamespaceParams; - -typedef struct NvmeNamespace { - DeviceState parent_obj; - BlockConf blkconf; - int32_t bootindex; - int64_t size; - int64_t mdata_offset; - NvmeIdNs id_ns; - const uint32_t *iocs; - uint8_t csi; - uint16_t status; - int attached; - - QTAILQ_ENTRY(NvmeNamespace) entry; - - NvmeIdNsZoned *id_ns_zoned; - NvmeZone *zone_array; - QTAILQ_HEAD(, NvmeZone) exp_open_zones; - QTAILQ_HEAD(, NvmeZone) imp_open_zones; - QTAILQ_HEAD(, NvmeZone) closed_zones; - QTAILQ_HEAD(, NvmeZone) full_zones; - uint32_t num_zones; - uint64_t zone_size; - uint64_t zone_capacity; - uint32_t zone_size_log2; - uint8_t *zd_extensions; - int32_t nr_open_zones; - int32_t nr_active_zones; - - NvmeNamespaceParams params; - - struct { - uint32_t err_rec; - } features; -} NvmeNamespace; - -static inline uint16_t nvme_ns_status(NvmeNamespace *ns) -{ - return ns->status; -} - -static inline uint32_t nvme_nsid(NvmeNamespace *ns) -{ - if (ns) { - return ns->params.nsid; - } - - return 0; -} - -static inline NvmeLBAF *nvme_ns_lbaf(NvmeNamespace *ns) -{ - NvmeIdNs *id_ns = &ns->id_ns; - return &id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(id_ns->flbas)]; -} - -static inline uint8_t nvme_ns_lbads(NvmeNamespace *ns) -{ - return nvme_ns_lbaf(ns)->ds; -} - -/* convert an LBA to the equivalent in bytes */ -static inline size_t nvme_l2b(NvmeNamespace *ns, uint64_t lba) -{ - return lba << nvme_ns_lbads(ns); -} - -static inline size_t nvme_lsize(NvmeNamespace *ns) -{ - return 1 << nvme_ns_lbads(ns); -} - -static inline uint16_t nvme_msize(NvmeNamespace *ns) -{ - return nvme_ns_lbaf(ns)->ms; -} - -static inline size_t nvme_m2b(NvmeNamespace *ns, uint64_t lba) -{ - return nvme_msize(ns) * lba; -} - -static inline bool nvme_ns_ext(NvmeNamespace *ns) -{ - return !!NVME_ID_NS_FLBAS_EXTENDED(ns->id_ns.flbas); -} - -/* calculate the number of LBAs that the namespace can accomodate */ -static inline uint64_t nvme_ns_nlbas(NvmeNamespace *ns) -{ - if (nvme_msize(ns)) { - return ns->size / (nvme_lsize(ns) + nvme_msize(ns)); - } - return ns->size >> nvme_ns_lbads(ns); -} - -typedef struct NvmeCtrl NvmeCtrl; - -static inline NvmeZoneState nvme_get_zone_state(NvmeZone *zone) -{ - return zone->d.zs >> 4; -} - -static inline void nvme_set_zone_state(NvmeZone *zone, NvmeZoneState state) -{ - zone->d.zs = state << 4; -} - -static inline uint64_t nvme_zone_rd_boundary(NvmeNamespace *ns, NvmeZone *zone) -{ - return zone->d.zslba + ns->zone_size; -} - -static inline uint64_t nvme_zone_wr_boundary(NvmeZone *zone) -{ - return zone->d.zslba + zone->d.zcap; -} - -static inline bool nvme_wp_is_valid(NvmeZone *zone) -{ - uint8_t st = nvme_get_zone_state(zone); - - return st != NVME_ZONE_STATE_FULL && - st != NVME_ZONE_STATE_READ_ONLY && - st != NVME_ZONE_STATE_OFFLINE; -} - -static inline uint8_t *nvme_get_zd_extension(NvmeNamespace *ns, - uint32_t zone_idx) -{ - return &ns->zd_extensions[zone_idx * ns->params.zd_extension_size]; -} - -static inline void nvme_aor_inc_open(NvmeNamespace *ns) -{ - assert(ns->nr_open_zones >= 0); - if (ns->params.max_open_zones) { - ns->nr_open_zones++; - assert(ns->nr_open_zones <= ns->params.max_open_zones); - } -} - -static inline void nvme_aor_dec_open(NvmeNamespace *ns) -{ - if (ns->params.max_open_zones) { - assert(ns->nr_open_zones > 0); - ns->nr_open_zones--; - } - assert(ns->nr_open_zones >= 0); -} - -static inline void nvme_aor_inc_active(NvmeNamespace *ns) -{ - assert(ns->nr_active_zones >= 0); - if (ns->params.max_active_zones) { - ns->nr_active_zones++; - assert(ns->nr_active_zones <= ns->params.max_active_zones); - } -} - -static inline void nvme_aor_dec_active(NvmeNamespace *ns) -{ - if (ns->params.max_active_zones) { - assert(ns->nr_active_zones > 0); - ns->nr_active_zones--; - assert(ns->nr_active_zones >= ns->nr_open_zones); - } - assert(ns->nr_active_zones >= 0); -} - -void nvme_ns_init_format(NvmeNamespace *ns); -int nvme_ns_setup(NvmeCtrl *n, NvmeNamespace *ns, Error **errp); -void nvme_ns_drain(NvmeNamespace *ns); -void nvme_ns_shutdown(NvmeNamespace *ns); -void nvme_ns_cleanup(NvmeNamespace *ns); - -#endif /* NVME_NS_H */ diff --git a/hw/block/nvme-subsys.h b/hw/block/nvme-subsys.h deleted file mode 100644 index 7d7ef5f7f1..0000000000 --- a/hw/block/nvme-subsys.h +++ /dev/null @@ -1,59 +0,0 @@ -/* - * QEMU NVM Express Subsystem: nvme-subsys - * - * Copyright (c) 2021 Minwoo Im - * - * This code is licensed under the GNU GPL v2. Refer COPYING. - */ - -#ifndef NVME_SUBSYS_H -#define NVME_SUBSYS_H - -#define TYPE_NVME_SUBSYS "nvme-subsys" -#define NVME_SUBSYS(obj) \ - OBJECT_CHECK(NvmeSubsystem, (obj), TYPE_NVME_SUBSYS) - -#define NVME_SUBSYS_MAX_CTRLS 32 -#define NVME_MAX_NAMESPACES 256 - -typedef struct NvmeCtrl NvmeCtrl; -typedef struct NvmeNamespace NvmeNamespace; -typedef struct NvmeSubsystem { - DeviceState parent_obj; - uint8_t subnqn[256]; - - NvmeCtrl *ctrls[NVME_SUBSYS_MAX_CTRLS]; - /* Allocated namespaces for this subsystem */ - NvmeNamespace *namespaces[NVME_MAX_NAMESPACES + 1]; - - struct { - char *nqn; - } params; -} NvmeSubsystem; - -int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp); - -static inline NvmeCtrl *nvme_subsys_ctrl(NvmeSubsystem *subsys, - uint32_t cntlid) -{ - if (!subsys || cntlid >= NVME_SUBSYS_MAX_CTRLS) { - return NULL; - } - - return subsys->ctrls[cntlid]; -} - -/* - * Return allocated namespace of the specified nsid in the subsystem. - */ -static inline NvmeNamespace *nvme_subsys_ns(NvmeSubsystem *subsys, - uint32_t nsid) -{ - if (!subsys || !nsid || nsid > NVME_MAX_NAMESPACES) { - return NULL; - } - - return subsys->namespaces[nsid]; -} - -#endif /* NVME_SUBSYS_H */ diff --git a/hw/block/nvme.h b/hw/block/nvme.h deleted file mode 100644 index 5d05ec368f..0000000000 --- a/hw/block/nvme.h +++ /dev/null @@ -1,266 +0,0 @@ -#ifndef HW_NVME_H -#define HW_NVME_H - -#include "block/nvme.h" -#include "hw/pci/pci.h" -#include "nvme-subsys.h" -#include "nvme-ns.h" - -#define NVME_DEFAULT_ZONE_SIZE (128 * MiB) -#define NVME_DEFAULT_MAX_ZA_SIZE (128 * KiB) - -typedef struct NvmeParams { - char *serial; - uint32_t num_queues; /* deprecated since 5.1 */ - uint32_t max_ioqpairs; - uint16_t msix_qsize; - uint32_t cmb_size_mb; - uint8_t aerl; - uint32_t aer_max_queued; - uint8_t mdts; - uint8_t vsl; - bool use_intel_id; - uint8_t zasl; - bool legacy_cmb; -} NvmeParams; - -typedef struct NvmeAsyncEvent { - QTAILQ_ENTRY(NvmeAsyncEvent) entry; - NvmeAerResult result; -} NvmeAsyncEvent; - -enum { - NVME_SG_ALLOC = 1 << 0, - NVME_SG_DMA = 1 << 1, -}; - -typedef struct NvmeSg { - int flags; - - union { - QEMUSGList qsg; - QEMUIOVector iov; - }; -} NvmeSg; - -typedef struct NvmeRequest { - struct NvmeSQueue *sq; - struct NvmeNamespace *ns; - BlockAIOCB *aiocb; - uint16_t status; - void *opaque; - NvmeCqe cqe; - NvmeCmd cmd; - BlockAcctCookie acct; - NvmeSg sg; - QTAILQ_ENTRY(NvmeRequest)entry; -} NvmeRequest; - -typedef struct NvmeBounceContext { - NvmeRequest *req; - - struct { - QEMUIOVector iov; - uint8_t *bounce; - } data, mdata; -} NvmeBounceContext; - -static inline const char *nvme_adm_opc_str(uint8_t opc) -{ - switch (opc) { - case NVME_ADM_CMD_DELETE_SQ: return "NVME_ADM_CMD_DELETE_SQ"; - case NVME_ADM_CMD_CREATE_SQ: return "NVME_ADM_CMD_CREATE_SQ"; - case NVME_ADM_CMD_GET_LOG_PAGE: return "NVME_ADM_CMD_GET_LOG_PAGE"; - case NVME_ADM_CMD_DELETE_CQ: return "NVME_ADM_CMD_DELETE_CQ"; - case NVME_ADM_CMD_CREATE_CQ: return "NVME_ADM_CMD_CREATE_CQ"; - case NVME_ADM_CMD_IDENTIFY: return "NVME_ADM_CMD_IDENTIFY"; - case NVME_ADM_CMD_ABORT: return "NVME_ADM_CMD_ABORT"; - case NVME_ADM_CMD_SET_FEATURES: return "NVME_ADM_CMD_SET_FEATURES"; - case NVME_ADM_CMD_GET_FEATURES: return "NVME_ADM_CMD_GET_FEATURES"; - case NVME_ADM_CMD_ASYNC_EV_REQ: return "NVME_ADM_CMD_ASYNC_EV_REQ"; - case NVME_ADM_CMD_NS_ATTACHMENT: return "NVME_ADM_CMD_NS_ATTACHMENT"; - case NVME_ADM_CMD_FORMAT_NVM: return "NVME_ADM_CMD_FORMAT_NVM"; - default: return "NVME_ADM_CMD_UNKNOWN"; - } -} - -static inline const char *nvme_io_opc_str(uint8_t opc) -{ - switch (opc) { - case NVME_CMD_FLUSH: return "NVME_NVM_CMD_FLUSH"; - case NVME_CMD_WRITE: return "NVME_NVM_CMD_WRITE"; - case NVME_CMD_READ: return "NVME_NVM_CMD_READ"; - case NVME_CMD_COMPARE: return "NVME_NVM_CMD_COMPARE"; - case NVME_CMD_WRITE_ZEROES: return "NVME_NVM_CMD_WRITE_ZEROES"; - case NVME_CMD_DSM: return "NVME_NVM_CMD_DSM"; - case NVME_CMD_VERIFY: return "NVME_NVM_CMD_VERIFY"; - case NVME_CMD_COPY: return "NVME_NVM_CMD_COPY"; - case NVME_CMD_ZONE_MGMT_SEND: return "NVME_ZONED_CMD_MGMT_SEND"; - case NVME_CMD_ZONE_MGMT_RECV: return "NVME_ZONED_CMD_MGMT_RECV"; - case NVME_CMD_ZONE_APPEND: return "NVME_ZONED_CMD_ZONE_APPEND"; - default: return "NVME_NVM_CMD_UNKNOWN"; - } -} - -typedef struct NvmeSQueue { - struct NvmeCtrl *ctrl; - uint16_t sqid; - uint16_t cqid; - uint32_t head; - uint32_t tail; - uint32_t size; - uint64_t dma_addr; - QEMUTimer *timer; - NvmeRequest *io_req; - QTAILQ_HEAD(, NvmeRequest) req_list; - QTAILQ_HEAD(, NvmeRequest) out_req_list; - QTAILQ_ENTRY(NvmeSQueue) entry; -} NvmeSQueue; - -typedef struct NvmeCQueue { - struct NvmeCtrl *ctrl; - uint8_t phase; - uint16_t cqid; - uint16_t irq_enabled; - uint32_t head; - uint32_t tail; - uint32_t vector; - uint32_t size; - uint64_t dma_addr; - QEMUTimer *timer; - QTAILQ_HEAD(, NvmeSQueue) sq_list; - QTAILQ_HEAD(, NvmeRequest) req_list; -} NvmeCQueue; - -#define TYPE_NVME_BUS "nvme-bus" -#define NVME_BUS(obj) OBJECT_CHECK(NvmeBus, (obj), TYPE_NVME_BUS) - -typedef struct NvmeBus { - BusState parent_bus; -} NvmeBus; - -#define TYPE_NVME "nvme" -#define NVME(obj) \ - OBJECT_CHECK(NvmeCtrl, (obj), TYPE_NVME) - -typedef struct NvmeFeatureVal { - struct { - uint16_t temp_thresh_hi; - uint16_t temp_thresh_low; - }; - uint32_t async_config; -} NvmeFeatureVal; - -typedef struct NvmeCtrl { - PCIDevice parent_obj; - MemoryRegion bar0; - MemoryRegion iomem; - NvmeBar bar; - NvmeParams params; - NvmeBus bus; - - uint16_t cntlid; - bool qs_created; - uint32_t page_size; - uint16_t page_bits; - uint16_t max_prp_ents; - uint16_t cqe_size; - uint16_t sqe_size; - uint32_t reg_size; - uint32_t num_namespaces; - uint32_t max_q_ents; - uint8_t outstanding_aers; - uint32_t irq_status; - uint64_t host_timestamp; /* Timestamp sent by the host */ - uint64_t timestamp_set_qemu_clock_ms; /* QEMU clock time */ - uint64_t starttime_ms; - uint16_t temperature; - uint8_t smart_critical_warning; - - struct { - MemoryRegion mem; - uint8_t *buf; - bool cmse; - hwaddr cba; - } cmb; - - struct { - HostMemoryBackend *dev; - bool cmse; - hwaddr cba; - } pmr; - - uint8_t aer_mask; - NvmeRequest **aer_reqs; - QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue; - int aer_queued; - - uint32_t dmrsl; - - /* Namespace ID is started with 1 so bitmap should be 1-based */ -#define NVME_CHANGED_NSID_SIZE (NVME_MAX_NAMESPACES + 1) - DECLARE_BITMAP(changed_nsids, NVME_CHANGED_NSID_SIZE); - - NvmeSubsystem *subsys; - - NvmeNamespace namespace; - /* - * Attached namespaces to this controller. If subsys is not given, all - * namespaces in this list will always be attached. - */ - NvmeNamespace *namespaces[NVME_MAX_NAMESPACES]; - NvmeSQueue **sq; - NvmeCQueue **cq; - NvmeSQueue admin_sq; - NvmeCQueue admin_cq; - NvmeIdCtrl id_ctrl; - NvmeFeatureVal features; -} NvmeCtrl; - -static inline NvmeNamespace *nvme_ns(NvmeCtrl *n, uint32_t nsid) -{ - if (!nsid || nsid > n->num_namespaces) { - return NULL; - } - - return n->namespaces[nsid - 1]; -} - -static inline NvmeCQueue *nvme_cq(NvmeRequest *req) -{ - NvmeSQueue *sq = req->sq; - NvmeCtrl *n = sq->ctrl; - - return n->cq[sq->cqid]; -} - -static inline NvmeCtrl *nvme_ctrl(NvmeRequest *req) -{ - NvmeSQueue *sq = req->sq; - return sq->ctrl; -} - -static inline uint16_t nvme_cid(NvmeRequest *req) -{ - if (!req) { - return 0xffff; - } - - return le16_to_cpu(req->cqe.cid); -} - -typedef enum NvmeTxDirection { - NVME_TX_DIRECTION_TO_DEVICE = 0, - NVME_TX_DIRECTION_FROM_DEVICE = 1, -} NvmeTxDirection; - -void nvme_attach_ns(NvmeCtrl *n, NvmeNamespace *ns); -uint16_t nvme_bounce_data(NvmeCtrl *n, uint8_t *ptr, uint32_t len, - NvmeTxDirection dir, NvmeRequest *req); -uint16_t nvme_bounce_mdata(NvmeCtrl *n, uint8_t *ptr, uint32_t len, - NvmeTxDirection dir, NvmeRequest *req); -void nvme_rw_complete_cb(void *opaque, int ret); -uint16_t nvme_map_dptr(NvmeCtrl *n, NvmeSg *sg, size_t len, - NvmeCmd *cmd); - -#endif /* HW_NVME_H */ diff --git a/hw/block/pflash_cfi02.c b/hw/block/pflash_cfi02.c index 25c053693c..02c514fb6e 100644 --- a/hw/block/pflash_cfi02.c +++ b/hw/block/pflash_cfi02.c @@ -173,7 +173,6 @@ static void pflash_setup_mappings(PFlashCFI02 *pfl) "pflash-alias", &pfl->orig_mem, 0, size); memory_region_add_subregion(&pfl->mem, i * size, &pfl->mem_mappings[i]); } - pfl->rom_mode = true; } static void pflash_reset_state_machine(PFlashCFI02 *pfl) @@ -917,8 +916,13 @@ static void pflash_cfi02_realize(DeviceState *dev, Error **errp) /* Allocate memory for a bitmap for sectors being erased. */ pfl->sector_erase_map = bitmap_new(pfl->total_sectors); - pflash_setup_mappings(pfl); - sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem); + pfl->rom_mode = true; + if (pfl->mappings > 1) { + pflash_setup_mappings(pfl); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem); + } else { + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->orig_mem); + } timer_init_ns(&pfl->timer, QEMU_CLOCK_VIRTUAL, pflash_timer, pfl); pfl->status = 0; diff --git a/hw/block/trace-events b/hw/block/trace-events index fa12e3a67a..d86b53520c 100644 --- a/hw/block/trace-events +++ b/hw/block/trace-events @@ -1,9 +1,12 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # fdc.c fdc_ioport_read(uint8_t reg, uint8_t value) "read reg 0x%02x val 0x%02x" fdc_ioport_write(uint8_t reg, uint8_t value) "write reg 0x%02x val 0x%02x" +# fdc-sysbus.c +fdctrl_tc_pulse(int level) "TC pulse: %u" + # pflash_cfi01.c # pflash_cfi02.c pflash_chip_erase_invalid(const char *name, uint64_t offset) "%s: chip erase: invalid address 0x%" PRIx64 @@ -49,212 +52,6 @@ virtio_blk_submit_multireq(void *vdev, void *mrb, int start, int num_reqs, uint6 hd_geometry_lchs_guess(void *blk, int cyls, int heads, int secs) "blk %p LCHS %d %d %d" hd_geometry_guess(void *blk, uint32_t cyls, uint32_t heads, uint32_t secs, int trans) "blk %p CHS %u %u %u trans %d" -# nvme.c -# nvme traces for successful events -pci_nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u" -pci_nvme_irq_pin(void) "pulsing IRQ pin" -pci_nvme_irq_masked(void) "IRQ is masked" -pci_nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64"" -pci_nvme_map_addr(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" -pci_nvme_map_addr_cmb(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" -pci_nvme_map_prp(uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d" -pci_nvme_map_sgl(uint8_t typ, uint64_t len) "type 0x%"PRIx8" len %"PRIu64"" -pci_nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode, const char *opname) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8" opname '%s'" -pci_nvme_admin_cmd(uint16_t cid, uint16_t sqid, uint8_t opcode, const char *opname) "cid %"PRIu16" sqid %"PRIu16" opc 0x%"PRIx8" opname '%s'" -pci_nvme_flush(uint16_t cid, uint32_t nsid) "cid %"PRIu16" nsid %"PRIu32"" -pci_nvme_format(uint16_t cid, uint32_t nsid, uint8_t lbaf, uint8_t mset, uint8_t pi, uint8_t pil) "cid %"PRIu16" nsid %"PRIu32" lbaf %"PRIu8" mset %"PRIu8" pi %"PRIu8" pil %"PRIu8"" -pci_nvme_format_ns(uint16_t cid, uint32_t nsid, uint8_t lbaf, uint8_t mset, uint8_t pi, uint8_t pil) "cid %"PRIu16" nsid %"PRIu32" lbaf %"PRIu8" mset %"PRIu8" pi %"PRIu8" pil %"PRIu8"" -pci_nvme_format_cb(uint16_t cid, uint32_t nsid) "cid %"PRIu16" nsid %"PRIu32"" -pci_nvme_read(uint16_t cid, uint32_t nsid, uint32_t nlb, uint64_t count, uint64_t lba) "cid %"PRIu16" nsid %"PRIu32" nlb %"PRIu32" count %"PRIu64" lba 0x%"PRIx64"" -pci_nvme_write(uint16_t cid, const char *verb, uint32_t nsid, uint32_t nlb, uint64_t count, uint64_t lba) "cid %"PRIu16" opname '%s' nsid %"PRIu32" nlb %"PRIu32" count %"PRIu64" lba 0x%"PRIx64"" -pci_nvme_rw_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" -pci_nvme_misc_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" -pci_nvme_dif_rw(uint8_t pract, uint8_t prinfo) "pract 0x%"PRIx8" prinfo 0x%"PRIx8"" -pci_nvme_dif_rw_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" -pci_nvme_dif_rw_mdata_in_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" -pci_nvme_dif_rw_mdata_out_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" -pci_nvme_dif_rw_check_cb(uint16_t cid, uint8_t prinfo, uint16_t apptag, uint16_t appmask, uint32_t reftag) "cid %"PRIu16" prinfo 0x%"PRIx8" apptag 0x%"PRIx16" appmask 0x%"PRIx16" reftag 0x%"PRIx32"" -pci_nvme_dif_pract_generate_dif(size_t len, size_t lba_size, size_t chksum_len, uint16_t apptag, uint32_t reftag) "len %zu lba_size %zu chksum_len %zu apptag 0x%"PRIx16" reftag 0x%"PRIx32"" -pci_nvme_dif_check(uint8_t prinfo, uint16_t chksum_len) "prinfo 0x%"PRIx8" chksum_len %"PRIu16"" -pci_nvme_dif_prchk_disabled(uint16_t apptag, uint32_t reftag) "apptag 0x%"PRIx16" reftag 0x%"PRIx32"" -pci_nvme_dif_prchk_guard(uint16_t guard, uint16_t crc) "guard 0x%"PRIx16" crc 0x%"PRIx16"" -pci_nvme_dif_prchk_apptag(uint16_t apptag, uint16_t elbat, uint16_t elbatm) "apptag 0x%"PRIx16" elbat 0x%"PRIx16" elbatm 0x%"PRIx16"" -pci_nvme_dif_prchk_reftag(uint32_t reftag, uint32_t elbrt) "reftag 0x%"PRIx32" elbrt 0x%"PRIx32"" -pci_nvme_copy(uint16_t cid, uint32_t nsid, uint16_t nr, uint8_t format) "cid %"PRIu16" nsid %"PRIu32" nr %"PRIu16" format 0x%"PRIx8"" -pci_nvme_copy_source_range(uint64_t slba, uint32_t nlb) "slba 0x%"PRIx64" nlb %"PRIu32"" -pci_nvme_copy_in_complete(uint16_t cid) "cid %"PRIu16"" -pci_nvme_copy_cb(uint16_t cid) "cid %"PRIu16"" -pci_nvme_verify(uint16_t cid, uint32_t nsid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" nsid %"PRIu32" slba 0x%"PRIx64" nlb %"PRIu32"" -pci_nvme_verify_mdata_in_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" -pci_nvme_verify_cb(uint16_t cid, uint8_t prinfo, uint16_t apptag, uint16_t appmask, uint32_t reftag) "cid %"PRIu16" prinfo 0x%"PRIx8" apptag 0x%"PRIx16" appmask 0x%"PRIx16" reftag 0x%"PRIx32"" -pci_nvme_rw_complete_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" -pci_nvme_block_status(int64_t offset, int64_t bytes, int64_t pnum, int ret, bool zeroed) "offset %"PRId64" bytes %"PRId64" pnum %"PRId64" ret 0x%x zeroed %d" -pci_nvme_dsm(uint16_t cid, uint32_t nsid, uint32_t nr, uint32_t attr) "cid %"PRIu16" nsid %"PRIu32" nr %"PRIu32" attr 0x%"PRIx32"" -pci_nvme_dsm_deallocate(uint16_t cid, uint32_t nsid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" nsid %"PRIu32" slba %"PRIu64" nlb %"PRIu32"" -pci_nvme_dsm_single_range_limit_exceeded(uint32_t nlb, uint32_t dmrsl) "nlb %"PRIu32" dmrsl %"PRIu32"" -pci_nvme_compare(uint16_t cid, uint32_t nsid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" nsid %"PRIu32" slba 0x%"PRIx64" nlb %"PRIu32"" -pci_nvme_compare_data_cb(uint16_t cid) "cid %"PRIu16"" -pci_nvme_compare_mdata_cb(uint16_t cid) "cid %"PRIu16"" -pci_nvme_aio_discard_cb(uint16_t cid) "cid %"PRIu16"" -pci_nvme_aio_copy_in_cb(uint16_t cid) "cid %"PRIu16"" -pci_nvme_aio_zone_reset_cb(uint16_t cid, uint64_t zslba) "cid %"PRIu16" zslba 0x%"PRIx64"" -pci_nvme_aio_flush_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" -pci_nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16"" -pci_nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d" -pci_nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16"" -pci_nvme_del_cq(uint16_t cqid) "deleted completion queue, cqid=%"PRIu16"" -pci_nvme_identify(uint16_t cid, uint8_t cns, uint16_t ctrlid, uint8_t csi) "cid %"PRIu16" cns 0x%"PRIx8" ctrlid %"PRIu16" csi 0x%"PRIx8"" -pci_nvme_identify_ctrl(void) "identify controller" -pci_nvme_identify_ctrl_csi(uint8_t csi) "identify controller, csi=0x%"PRIx8"" -pci_nvme_identify_ns(uint32_t ns) "nsid %"PRIu32"" -pci_nvme_identify_ns_attached_list(uint16_t cntid) "cntid=%"PRIu16"" -pci_nvme_identify_ns_csi(uint32_t ns, uint8_t csi) "nsid=%"PRIu32", csi=0x%"PRIx8"" -pci_nvme_identify_nslist(uint32_t ns) "nsid %"PRIu32"" -pci_nvme_identify_nslist_csi(uint16_t ns, uint8_t csi) "nsid=%"PRIu16", csi=0x%"PRIx8"" -pci_nvme_identify_cmd_set(void) "identify i/o command set" -pci_nvme_identify_ns_descr_list(uint32_t ns) "nsid %"PRIu32"" -pci_nvme_get_log(uint16_t cid, uint8_t lid, uint8_t lsp, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx8" lsp 0x%"PRIx8" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64"" -pci_nvme_getfeat(uint16_t cid, uint32_t nsid, uint8_t fid, uint8_t sel, uint32_t cdw11) "cid %"PRIu16" nsid 0x%"PRIx32" fid 0x%"PRIx8" sel 0x%"PRIx8" cdw11 0x%"PRIx32"" -pci_nvme_setfeat(uint16_t cid, uint32_t nsid, uint8_t fid, uint8_t save, uint32_t cdw11) "cid %"PRIu16" nsid 0x%"PRIx32" fid 0x%"PRIx8" save 0x%"PRIx8" cdw11 0x%"PRIx32"" -pci_nvme_getfeat_vwcache(const char* result) "get feature volatile write cache, result=%s" -pci_nvme_getfeat_numq(int result) "get feature number of queues, result=%d" -pci_nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d" -pci_nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64"" -pci_nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64"" -pci_nvme_process_aers(int queued) "queued %d" -pci_nvme_aer(uint16_t cid) "cid %"PRIu16"" -pci_nvme_aer_aerl_exceeded(void) "aerl exceeded" -pci_nvme_aer_masked(uint8_t type, uint8_t mask) "type 0x%"PRIx8" mask 0x%"PRIx8"" -pci_nvme_aer_post_cqe(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8"" -pci_nvme_ns_attachment(uint16_t cid, uint8_t sel) "cid %"PRIu16", sel=0x%"PRIx8"" -pci_nvme_ns_attachment_attach(uint16_t cntlid, uint32_t nsid) "cntlid=0x%"PRIx16", nsid=0x%"PRIx32"" -pci_nvme_enqueue_event(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8"" -pci_nvme_enqueue_event_noqueue(int queued) "queued %d" -pci_nvme_enqueue_event_masked(uint8_t typ) "type 0x%"PRIx8"" -pci_nvme_no_outstanding_aers(void) "ignoring event; no outstanding AERs" -pci_nvme_enqueue_req_completion(uint16_t cid, uint16_t cqid, uint16_t status) "cid %"PRIu16" cqid %"PRIu16" status 0x%"PRIx16"" -pci_nvme_mmio_read(uint64_t addr, unsigned size) "addr 0x%"PRIx64" size %d" -pci_nvme_mmio_write(uint64_t addr, uint64_t data, unsigned size) "addr 0x%"PRIx64" data 0x%"PRIx64" size %d" -pci_nvme_mmio_doorbell_cq(uint16_t cqid, uint16_t new_head) "cqid %"PRIu16" new_head %"PRIu16"" -pci_nvme_mmio_doorbell_sq(uint16_t sqid, uint16_t new_tail) "sqid %"PRIu16" new_tail %"PRIu16"" -pci_nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64"" -pci_nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64"" -pci_nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64"" -pci_nvme_mmio_aqattr(uint64_t data) "wrote MMIO, admin queue attributes=0x%"PRIx64"" -pci_nvme_mmio_asqaddr(uint64_t data) "wrote MMIO, admin submission queue address=0x%"PRIx64"" -pci_nvme_mmio_acqaddr(uint64_t data) "wrote MMIO, admin completion queue address=0x%"PRIx64"" -pci_nvme_mmio_asqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin submission queue high half=0x%"PRIx64", new_address=0x%"PRIx64"" -pci_nvme_mmio_acqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin completion queue high half=0x%"PRIx64", new_address=0x%"PRIx64"" -pci_nvme_mmio_start_success(void) "setting controller enable bit succeeded" -pci_nvme_mmio_stopped(void) "cleared controller enable bit" -pci_nvme_mmio_shutdown_set(void) "shutdown bit set" -pci_nvme_mmio_shutdown_cleared(void) "shutdown bit cleared" -pci_nvme_open_zone(uint64_t slba, uint32_t zone_idx, int all) "open zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32"" -pci_nvme_close_zone(uint64_t slba, uint32_t zone_idx, int all) "close zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32"" -pci_nvme_finish_zone(uint64_t slba, uint32_t zone_idx, int all) "finish zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32"" -pci_nvme_reset_zone(uint64_t slba, uint32_t zone_idx, int all) "reset zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32"" -pci_nvme_offline_zone(uint64_t slba, uint32_t zone_idx, int all) "offline zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32"" -pci_nvme_set_descriptor_extension(uint64_t slba, uint32_t zone_idx) "set zone descriptor extension, slba=%"PRIu64", idx=%"PRIu32"" -pci_nvme_zd_extension_set(uint32_t zone_idx) "set descriptor extension for zone_idx=%"PRIu32"" -pci_nvme_clear_ns_close(uint32_t state, uint64_t slba) "zone state=%"PRIu32", slba=%"PRIu64" transitioned to Closed state" -pci_nvme_clear_ns_reset(uint32_t state, uint64_t slba) "zone state=%"PRIu32", slba=%"PRIu64" transitioned to Empty state" - -# nvme traces for error conditions -pci_nvme_err_mdts(size_t len) "len %zu" -pci_nvme_err_zasl(size_t len) "len %zu" -pci_nvme_err_req_status(uint16_t cid, uint32_t nsid, uint16_t status, uint8_t opc) "cid %"PRIu16" nsid %"PRIu32" status 0x%"PRIx16" opc 0x%"PRIx8"" -pci_nvme_err_addr_read(uint64_t addr) "addr 0x%"PRIx64"" -pci_nvme_err_addr_write(uint64_t addr) "addr 0x%"PRIx64"" -pci_nvme_err_cfs(void) "controller fatal status" -pci_nvme_err_aio(uint16_t cid, const char *errname, uint16_t status) "cid %"PRIu16" err '%s' status 0x%"PRIx16"" -pci_nvme_err_copy_invalid_format(uint8_t format) "format 0x%"PRIx8"" -pci_nvme_err_invalid_sgld(uint16_t cid, uint8_t typ) "cid %"PRIu16" type 0x%"PRIx8"" -pci_nvme_err_invalid_num_sgld(uint16_t cid, uint8_t typ) "cid %"PRIu16" type 0x%"PRIx8"" -pci_nvme_err_invalid_sgl_excess_length(uint32_t residual) "residual %"PRIu32"" -pci_nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size" -pci_nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is not page aligned: 0x%"PRIx64"" -pci_nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64"" -pci_nvme_err_invalid_opc(uint8_t opc) "invalid opcode 0x%"PRIx8"" -pci_nvme_err_invalid_admin_opc(uint8_t opc) "invalid admin opcode 0x%"PRIx8"" -pci_nvme_err_invalid_lba_range(uint64_t start, uint64_t len, uint64_t limit) "Invalid LBA start=%"PRIu64" len=%"PRIu64" limit=%"PRIu64"" -pci_nvme_err_invalid_log_page_offset(uint64_t ofs, uint64_t size) "must be <= %"PRIu64", got %"PRIu64"" -pci_nvme_err_cmb_invalid_cba(uint64_t cmbmsc) "cmbmsc 0x%"PRIx64"" -pci_nvme_err_cmb_not_enabled(uint64_t cmbmsc) "cmbmsc 0x%"PRIx64"" -pci_nvme_err_unaligned_zone_cmd(uint8_t action, uint64_t slba, uint64_t zslba) "unaligned zone op 0x%"PRIx32", got slba=%"PRIu64", zslba=%"PRIu64"" -pci_nvme_err_invalid_zone_state_transition(uint8_t action, uint64_t slba, uint8_t attrs) "action=0x%"PRIx8", slba=%"PRIu64", attrs=0x%"PRIx32"" -pci_nvme_err_write_not_at_wp(uint64_t slba, uint64_t zone, uint64_t wp) "writing at slba=%"PRIu64", zone=%"PRIu64", but wp=%"PRIu64"" -pci_nvme_err_append_not_at_start(uint64_t slba, uint64_t zone) "appending at slba=%"PRIu64", but zone=%"PRIu64"" -pci_nvme_err_zone_is_full(uint64_t zslba) "zslba 0x%"PRIx64"" -pci_nvme_err_zone_is_read_only(uint64_t zslba) "zslba 0x%"PRIx64"" -pci_nvme_err_zone_is_offline(uint64_t zslba) "zslba 0x%"PRIx64"" -pci_nvme_err_zone_boundary(uint64_t slba, uint32_t nlb, uint64_t zcap) "lba 0x%"PRIx64" nlb %"PRIu32" zcap 0x%"PRIx64"" -pci_nvme_err_zone_invalid_write(uint64_t slba, uint64_t wp) "lba 0x%"PRIx64" wp 0x%"PRIx64"" -pci_nvme_err_zone_write_not_ok(uint64_t slba, uint32_t nlb, uint16_t status) "slba=%"PRIu64", nlb=%"PRIu32", status=0x%"PRIx16"" -pci_nvme_err_zone_read_not_ok(uint64_t slba, uint32_t nlb, uint16_t status) "slba=%"PRIu64", nlb=%"PRIu32", status=0x%"PRIx16"" -pci_nvme_err_insuff_active_res(uint32_t max_active) "max_active=%"PRIu32" zone limit exceeded" -pci_nvme_err_insuff_open_res(uint32_t max_open) "max_open=%"PRIu32" zone limit exceeded" -pci_nvme_err_zd_extension_map_error(uint32_t zone_idx) "can't map descriptor extension for zone_idx=%"PRIu32"" -pci_nvme_err_invalid_iocsci(uint32_t idx) "unsupported command set combination index %"PRIu32"" -pci_nvme_err_invalid_del_sq(uint16_t qid) "invalid submission queue deletion, sid=%"PRIu16"" -pci_nvme_err_invalid_create_sq_cqid(uint16_t cqid) "failed creating submission queue, invalid cqid=%"PRIu16"" -pci_nvme_err_invalid_create_sq_sqid(uint16_t sqid) "failed creating submission queue, invalid sqid=%"PRIu16"" -pci_nvme_err_invalid_create_sq_size(uint16_t qsize) "failed creating submission queue, invalid qsize=%"PRIu16"" -pci_nvme_err_invalid_create_sq_addr(uint64_t addr) "failed creating submission queue, addr=0x%"PRIx64"" -pci_nvme_err_invalid_create_sq_qflags(uint16_t qflags) "failed creating submission queue, qflags=%"PRIu16"" -pci_nvme_err_invalid_del_cq_cqid(uint16_t cqid) "failed deleting completion queue, cqid=%"PRIu16"" -pci_nvme_err_invalid_del_cq_notempty(uint16_t cqid) "failed deleting completion queue, it is not empty, cqid=%"PRIu16"" -pci_nvme_err_invalid_create_cq_cqid(uint16_t cqid) "failed creating completion queue, cqid=%"PRIu16"" -pci_nvme_err_invalid_create_cq_size(uint16_t size) "failed creating completion queue, size=%"PRIu16"" -pci_nvme_err_invalid_create_cq_addr(uint64_t addr) "failed creating completion queue, addr=0x%"PRIx64"" -pci_nvme_err_invalid_create_cq_vector(uint16_t vector) "failed creating completion queue, vector=%"PRIu16"" -pci_nvme_err_invalid_create_cq_qflags(uint16_t qflags) "failed creating completion queue, qflags=%"PRIu16"" -pci_nvme_err_invalid_identify_cns(uint16_t cns) "identify, invalid cns=0x%"PRIx16"" -pci_nvme_err_invalid_getfeat(int dw10) "invalid get features, dw10=0x%"PRIx32"" -pci_nvme_err_invalid_setfeat(uint32_t dw10) "invalid set features, dw10=0x%"PRIx32"" -pci_nvme_err_invalid_log_page(uint16_t cid, uint16_t lid) "cid %"PRIu16" lid 0x%"PRIx16"" -pci_nvme_err_startfail_cq(void) "nvme_start_ctrl failed because there are non-admin completion queues" -pci_nvme_err_startfail_sq(void) "nvme_start_ctrl failed because there are non-admin submission queues" -pci_nvme_err_startfail_nbarasq(void) "nvme_start_ctrl failed because the admin submission queue address is null" -pci_nvme_err_startfail_nbaracq(void) "nvme_start_ctrl failed because the admin completion queue address is null" -pci_nvme_err_startfail_asq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin submission queue address is misaligned: 0x%"PRIx64"" -pci_nvme_err_startfail_acq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin completion queue address is misaligned: 0x%"PRIx64"" -pci_nvme_err_startfail_page_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too small: log2size=%u, min=%u" -pci_nvme_err_startfail_page_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too large: log2size=%u, max=%u" -pci_nvme_err_startfail_cqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too small: log2size=%u, min=%u" -pci_nvme_err_startfail_cqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too large: log2size=%u, max=%u" -pci_nvme_err_startfail_sqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too small: log2size=%u, min=%u" -pci_nvme_err_startfail_sqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too large: log2size=%u, max=%u" -pci_nvme_err_startfail_css(uint8_t css) "nvme_start_ctrl failed because invalid command set selected:%u" -pci_nvme_err_startfail_asqent_sz_zero(void) "nvme_start_ctrl failed because the admin submission queue size is zero" -pci_nvme_err_startfail_acqent_sz_zero(void) "nvme_start_ctrl failed because the admin completion queue size is zero" -pci_nvme_err_startfail_zasl_too_small(uint32_t zasl, uint32_t pagesz) "nvme_start_ctrl failed because zone append size limit %"PRIu32" is too small, needs to be >= %"PRIu32"" -pci_nvme_err_startfail(void) "setting controller enable bit failed" -pci_nvme_err_invalid_mgmt_action(uint8_t action) "action=0x%"PRIx8"" - -# Traces for undefined behavior -pci_nvme_ub_mmiowr_misaligned32(uint64_t offset) "MMIO write not 32-bit aligned, offset=0x%"PRIx64"" -pci_nvme_ub_mmiowr_toosmall(uint64_t offset, unsigned size) "MMIO write smaller than 32 bits, offset=0x%"PRIx64", size=%u" -pci_nvme_ub_mmiowr_intmask_with_msix(void) "undefined access to interrupt mask set when MSI-X is enabled" -pci_nvme_ub_mmiowr_ro_csts(void) "attempted to set a read only bit of controller status" -pci_nvme_ub_mmiowr_ssreset_w1c_unsupported(void) "attempted to W1C CSTS.NSSRO but CAP.NSSRS is zero (not supported)" -pci_nvme_ub_mmiowr_ssreset_unsupported(void) "attempted NVM subsystem reset but CAP.NSSRS is zero (not supported)" -pci_nvme_ub_mmiowr_cmbloc_reserved(void) "invalid write to reserved CMBLOC when CMBSZ is zero, ignored" -pci_nvme_ub_mmiowr_cmbsz_readonly(void) "invalid write to read only CMBSZ, ignored" -pci_nvme_ub_mmiowr_pmrcap_readonly(void) "invalid write to read only PMRCAP, ignored" -pci_nvme_ub_mmiowr_pmrsts_readonly(void) "invalid write to read only PMRSTS, ignored" -pci_nvme_ub_mmiowr_pmrebs_readonly(void) "invalid write to read only PMREBS, ignored" -pci_nvme_ub_mmiowr_pmrswtp_readonly(void) "invalid write to read only PMRSWTP, ignored" -pci_nvme_ub_mmiowr_invalid(uint64_t offset, uint64_t data) "invalid MMIO write, offset=0x%"PRIx64", data=0x%"PRIx64"" -pci_nvme_ub_mmiord_misaligned32(uint64_t offset) "MMIO read not 32-bit aligned, offset=0x%"PRIx64"" -pci_nvme_ub_mmiord_toosmall(uint64_t offset) "MMIO read smaller than 32-bits, offset=0x%"PRIx64"" -pci_nvme_ub_mmiord_invalid_ofs(uint64_t offset) "MMIO read beyond last register, offset=0x%"PRIx64", returning 0" -pci_nvme_ub_db_wr_misaligned(uint64_t offset) "doorbell write not 32-bit aligned, offset=0x%"PRIx64", ignoring" -pci_nvme_ub_db_wr_invalid_cq(uint32_t qid) "completion queue doorbell write for nonexistent queue, cqid=%"PRIu32", ignoring" -pci_nvme_ub_db_wr_invalid_cqhead(uint32_t qid, uint16_t new_head) "completion queue doorbell write value beyond queue size, cqid=%"PRIu32", new_head=%"PRIu16", ignoring" -pci_nvme_ub_db_wr_invalid_sq(uint32_t qid) "submission queue doorbell write for nonexistent queue, sqid=%"PRIu32", ignoring" -pci_nvme_ub_db_wr_invalid_sqtail(uint32_t qid, uint16_t new_tail) "submission queue doorbell write value beyond queue size, sqid=%"PRIu32", new_head=%"PRIu16", ignoring" -pci_nvme_ub_unknown_css_value(void) "unknown value in cc.css field" - # xen-block.c xen_block_realize(const char *type, uint32_t disk, uint32_t partition) "%s d%up%u" xen_block_connect(const char *type, uint32_t disk, uint32_t partition) "%s d%up%u" diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c index 0b5b9d44cd..ba13cb87e5 100644 --- a/hw/block/vhost-user-blk.c +++ b/hw/block/vhost-user-blk.c @@ -31,6 +31,8 @@ #include "sysemu/sysemu.h" #include "sysemu/runstate.h" +#define REALIZE_CONNECTION_RETRIES 3 + static const int user_feature_bits[] = { VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_SEG_MAX, @@ -47,9 +49,13 @@ static const int user_feature_bits[] = { VIRTIO_RING_F_INDIRECT_DESC, VIRTIO_RING_F_EVENT_IDX, VIRTIO_F_NOTIFY_ON_EMPTY, + VIRTIO_F_RING_PACKED, + VIRTIO_F_IOMMU_PLATFORM, VHOST_INVALID_FEATURE_BIT }; +static void vhost_user_blk_event(void *opaque, QEMUChrEvent event); + static void vhost_user_blk_update_config(VirtIODevice *vdev, uint8_t *config) { VHostUserBlk *s = VHOST_USER_BLK(vdev); @@ -87,11 +93,13 @@ static int vhost_user_blk_handle_config_change(struct vhost_dev *dev) int ret; struct virtio_blk_config blkcfg; VHostUserBlk *s = VHOST_USER_BLK(dev->vdev); + Error *local_err = NULL; ret = vhost_dev_get_config(dev, (uint8_t *)&blkcfg, - sizeof(struct virtio_blk_config)); + sizeof(struct virtio_blk_config), + &local_err); if (ret < 0) { - error_report("get config space failed"); + error_report_err(local_err); return -1; } @@ -109,7 +117,7 @@ const VhostDevConfigOps blk_ops = { .vhost_dev_config_notifier = vhost_user_blk_handle_config_change, }; -static int vhost_user_blk_start(VirtIODevice *vdev) +static int vhost_user_blk_start(VirtIODevice *vdev, Error **errp) { VHostUserBlk *s = VHOST_USER_BLK(vdev); BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); @@ -117,19 +125,19 @@ static int vhost_user_blk_start(VirtIODevice *vdev) int i, ret; if (!k->set_guest_notifiers) { - error_report("binding does not support guest notifiers"); + error_setg(errp, "binding does not support guest notifiers"); return -ENOSYS; } ret = vhost_dev_enable_notifiers(&s->dev, vdev); if (ret < 0) { - error_report("Error enabling host notifiers: %d", -ret); + error_setg_errno(errp, -ret, "Error enabling host notifiers"); return ret; } ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true); if (ret < 0) { - error_report("Error binding guest notifier: %d", -ret); + error_setg_errno(errp, -ret, "Error binding guest notifier"); goto err_host_notifiers; } @@ -137,27 +145,27 @@ static int vhost_user_blk_start(VirtIODevice *vdev) ret = vhost_dev_prepare_inflight(&s->dev, vdev); if (ret < 0) { - error_report("Error set inflight format: %d", -ret); + error_setg_errno(errp, -ret, "Error setting inflight format"); goto err_guest_notifiers; } if (!s->inflight->addr) { ret = vhost_dev_get_inflight(&s->dev, s->queue_size, s->inflight); if (ret < 0) { - error_report("Error get inflight: %d", -ret); + error_setg_errno(errp, -ret, "Error getting inflight"); goto err_guest_notifiers; } } ret = vhost_dev_set_inflight(&s->dev, s->inflight); if (ret < 0) { - error_report("Error set inflight: %d", -ret); + error_setg_errno(errp, -ret, "Error setting inflight"); goto err_guest_notifiers; } ret = vhost_dev_start(&s->dev, vdev); if (ret < 0) { - error_report("Error starting vhost: %d", -ret); + error_setg_errno(errp, -ret, "Error starting vhost"); goto err_guest_notifiers; } s->started_vu = true; @@ -210,6 +218,7 @@ static void vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status) { VHostUserBlk *s = VHOST_USER_BLK(vdev); bool should_start = virtio_device_started(vdev, status); + Error *local_err = NULL; int ret; if (!vdev->vm_running) { @@ -225,10 +234,9 @@ static void vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status) } if (should_start) { - ret = vhost_user_blk_start(vdev); + ret = vhost_user_blk_start(vdev, &local_err); if (ret < 0) { - error_report("vhost-user-blk: vhost start failed: %s", - strerror(-ret)); + error_reportf_err(local_err, "vhost-user-blk: vhost start failed: "); qemu_chr_fe_disconnect(&s->chardev); } } else { @@ -266,6 +274,7 @@ static uint64_t vhost_user_blk_get_features(VirtIODevice *vdev, static void vhost_user_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq) { VHostUserBlk *s = VHOST_USER_BLK(vdev); + Error *local_err = NULL; int i, ret; if (!vdev->start_on_kick) { @@ -283,10 +292,9 @@ static void vhost_user_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq) /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start * vhost here instead of waiting for .set_status(). */ - ret = vhost_user_blk_start(vdev); + ret = vhost_user_blk_start(vdev, &local_err); if (ret < 0) { - error_report("vhost-user-blk: vhost start failed: %s", - strerror(-ret)); + error_reportf_err(local_err, "vhost-user-blk: vhost start failed: "); qemu_chr_fe_disconnect(&s->chardev); return; } @@ -309,7 +317,7 @@ static void vhost_user_blk_reset(VirtIODevice *vdev) vhost_dev_free_inflight(s->inflight); } -static int vhost_user_blk_connect(DeviceState *dev) +static int vhost_user_blk_connect(DeviceState *dev, Error **errp) { VirtIODevice *vdev = VIRTIO_DEVICE(dev); VHostUserBlk *s = VHOST_USER_BLK(vdev); @@ -320,6 +328,7 @@ static int vhost_user_blk_connect(DeviceState *dev) } s->connected = true; + s->dev.num_queues = s->num_queues; s->dev.nvqs = s->num_queues; s->dev.vqs = s->vhost_vqs; s->dev.vq_index = 0; @@ -327,19 +336,16 @@ static int vhost_user_blk_connect(DeviceState *dev) vhost_dev_set_config_notifier(&s->dev, &blk_ops); - ret = vhost_dev_init(&s->dev, &s->vhost_user, VHOST_BACKEND_TYPE_USER, 0); + ret = vhost_dev_init(&s->dev, &s->vhost_user, VHOST_BACKEND_TYPE_USER, 0, + errp); if (ret < 0) { - error_report("vhost-user-blk: vhost initialization failed: %s", - strerror(-ret)); return ret; } /* restore vhost state */ if (virtio_device_started(vdev, vdev->status)) { - ret = vhost_user_blk_start(vdev); + ret = vhost_user_blk_start(vdev, errp); if (ret < 0) { - error_report("vhost-user-blk: vhost start failed: %s", - strerror(-ret)); return ret; } } @@ -362,19 +368,6 @@ static void vhost_user_blk_disconnect(DeviceState *dev) vhost_dev_cleanup(&s->dev); } -static void vhost_user_blk_event(void *opaque, QEMUChrEvent event, - bool realized); - -static void vhost_user_blk_event_realize(void *opaque, QEMUChrEvent event) -{ - vhost_user_blk_event(opaque, event, false); -} - -static void vhost_user_blk_event_oper(void *opaque, QEMUChrEvent event) -{ - vhost_user_blk_event(opaque, event, true); -} - static void vhost_user_blk_chr_closed_bh(void *opaque) { DeviceState *dev = opaque; @@ -382,36 +375,27 @@ static void vhost_user_blk_chr_closed_bh(void *opaque) VHostUserBlk *s = VHOST_USER_BLK(vdev); vhost_user_blk_disconnect(dev); - qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, - vhost_user_blk_event_oper, NULL, opaque, NULL, true); + qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, vhost_user_blk_event, + NULL, opaque, NULL, true); } -static void vhost_user_blk_event(void *opaque, QEMUChrEvent event, - bool realized) +static void vhost_user_blk_event(void *opaque, QEMUChrEvent event) { DeviceState *dev = opaque; VirtIODevice *vdev = VIRTIO_DEVICE(dev); VHostUserBlk *s = VHOST_USER_BLK(vdev); + Error *local_err = NULL; switch (event) { case CHR_EVENT_OPENED: - if (vhost_user_blk_connect(dev) < 0) { + if (vhost_user_blk_connect(dev, &local_err) < 0) { + error_report_err(local_err); qemu_chr_fe_disconnect(&s->chardev); return; } break; case CHR_EVENT_CLOSED: - /* - * Closing the connection should happen differently on device - * initialization and operation stages. - * On initalization, we want to re-start vhost_dev initialization - * from the very beginning right away when the connection is closed, - * so we clean up vhost_dev on each connection closing. - * On operation, we want to postpone vhost_dev cleanup to let the - * other code perform its own cleanup sequence using vhost_dev data - * (e.g. vhost_dev_set_log). - */ - if (realized && !runstate_check(RUN_STATE_SHUTDOWN)) { + if (!runstate_check(RUN_STATE_SHUTDOWN)) { /* * A close event may happen during a read/write, but vhost * code assumes the vhost_dev remains setup, so delay the @@ -431,8 +415,6 @@ static void vhost_user_blk_event(void *opaque, QEMUChrEvent event, * knowing its type (in this case vhost-user). */ s->dev.started = false; - } else { - vhost_user_blk_disconnect(dev); } break; case CHR_EVENT_BREAK: @@ -443,15 +425,46 @@ static void vhost_user_blk_event(void *opaque, QEMUChrEvent event, } } +static int vhost_user_blk_realize_connect(VHostUserBlk *s, Error **errp) +{ + DeviceState *dev = &s->parent_obj.parent_obj; + int ret; + + s->connected = false; + + ret = qemu_chr_fe_wait_connected(&s->chardev, errp); + if (ret < 0) { + return ret; + } + + ret = vhost_user_blk_connect(dev, errp); + if (ret < 0) { + qemu_chr_fe_disconnect(&s->chardev); + return ret; + } + assert(s->connected); + + ret = vhost_dev_get_config(&s->dev, (uint8_t *)&s->blkcfg, + sizeof(struct virtio_blk_config), errp); + if (ret < 0) { + qemu_chr_fe_disconnect(&s->chardev); + vhost_dev_cleanup(&s->dev); + return ret; + } + + return 0; +} + static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp) { + ERRP_GUARD(); VirtIODevice *vdev = VIRTIO_DEVICE(dev); VHostUserBlk *s = VHOST_USER_BLK(vdev); - Error *err = NULL; + int retries; int i, ret; if (!s->chardev.chr) { - error_setg(errp, "vhost-user-blk: chardev is mandatory"); + error_setg(errp, "chardev is mandatory"); return; } @@ -459,12 +472,17 @@ static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp) s->num_queues = 1; } if (!s->num_queues || s->num_queues > VIRTIO_QUEUE_MAX) { - error_setg(errp, "vhost-user-blk: invalid number of IO queues"); + error_setg(errp, "invalid number of IO queues"); return; } if (!s->queue_size) { - error_setg(errp, "vhost-user-blk: queue size must be non-zero"); + error_setg(errp, "queue size must be non-zero"); + return; + } + if (s->queue_size > VIRTQUEUE_MAX_SIZE) { + error_setg(errp, "queue size must not exceed %d", + VIRTQUEUE_MAX_SIZE); return; } @@ -483,33 +501,25 @@ static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp) s->inflight = g_new0(struct vhost_inflight, 1); s->vhost_vqs = g_new0(struct vhost_virtqueue, s->num_queues); - s->connected = false; - qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, - vhost_user_blk_event_realize, NULL, (void *)dev, - NULL, true); + retries = REALIZE_CONNECTION_RETRIES; + assert(!*errp); + do { + if (*errp) { + error_prepend(errp, "Reconnecting after error: "); + error_report_err(*errp); + *errp = NULL; + } + ret = vhost_user_blk_realize_connect(s, errp); + } while (ret == -EPROTO && retries--); -reconnect: - if (qemu_chr_fe_wait_connected(&s->chardev, &err) < 0) { - error_report_err(err); + if (ret < 0) { goto virtio_err; } - /* check whether vhost_user_blk_connect() failed or not */ - if (!s->connected) { - goto reconnect; - } - - ret = vhost_dev_get_config(&s->dev, (uint8_t *)&s->blkcfg, - sizeof(struct virtio_blk_config)); - if (ret < 0) { - error_report("vhost-user-blk: get block config failed"); - goto reconnect; - } - - /* we're fully initialized, now we can operate, so change the handler */ + /* we're fully initialized, now we can operate, so add the handler */ qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, - vhost_user_blk_event_oper, NULL, (void *)dev, + vhost_user_blk_event, NULL, (void *)dev, NULL, true); return; diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index d28979efb8..f139cd7cc9 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -40,7 +40,7 @@ * Starting from the discard feature, we can use this array to properly * set the config size depending on the features enabled. */ -static VirtIOFeature feature_sizes[] = { +static const VirtIOFeature feature_sizes[] = { {.flags = 1ULL << VIRTIO_BLK_F_DISCARD, .end = endof(struct virtio_blk_config, discard_sector_alignment)}, {.flags = 1ULL << VIRTIO_BLK_F_WRITE_ZEROES, diff --git a/hw/block/xen-block.c b/hw/block/xen-block.c index 83754a4344..674953f1ad 100644 --- a/hw/block/xen-block.c +++ b/hw/block/xen-block.c @@ -728,6 +728,8 @@ static XenBlockDrive *xen_block_drive_create(const char *id, XenBlockDrive *drive = NULL; QDict *file_layer; QDict *driver_layer; + struct stat st; + int rc; if (params) { char **v = g_strsplit(params, ":", 2); @@ -761,7 +763,17 @@ static XenBlockDrive *xen_block_drive_create(const char *id, file_layer = qdict_new(); driver_layer = qdict_new(); - qdict_put_str(file_layer, "driver", "file"); + rc = stat(filename, &st); + if (rc) { + error_setg_errno(errp, errno, "Could not stat file '%s'", filename); + goto done; + } + if (S_ISBLK(st.st_mode)) { + qdict_put_str(file_layer, "driver", "host_device"); + } else { + qdict_put_str(file_layer, "driver", "file"); + } + qdict_put_str(file_layer, "filename", filename); g_free(filename); diff --git a/hw/char/Kconfig b/hw/char/Kconfig index 4cf36ac637..2e4f620b13 100644 --- a/hw/char/Kconfig +++ b/hw/char/Kconfig @@ -61,6 +61,7 @@ config AVR_USART config MCHP_PFSOC_MMUART bool + select SERIAL config SIFIVE_UART bool diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index ceb677bc5a..b4b5e8a3ee 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -288,7 +288,7 @@ static void uart_write_rx_fifo(void *opaque, const uint8_t *buf, int size) uart_update_status(s); } -static gboolean cadence_uart_xmit(GIOChannel *chan, GIOCondition cond, +static gboolean cadence_uart_xmit(void *do_not_use, GIOCondition cond, void *opaque) { CadenceUARTState *s = opaque; diff --git a/hw/char/cmsdk-apb-uart.c b/hw/char/cmsdk-apb-uart.c index ba2cbbee3d..f8dc89ee3d 100644 --- a/hw/char/cmsdk-apb-uart.c +++ b/hw/char/cmsdk-apb-uart.c @@ -191,7 +191,7 @@ static uint64_t uart_read(void *opaque, hwaddr offset, unsigned size) /* Try to send tx data, and arrange to be called back later if * we can't (ie the char backend is busy/blocking). */ -static gboolean uart_transmit(GIOChannel *chan, GIOCondition cond, void *opaque) +static gboolean uart_transmit(void *do_not_use, GIOCondition cond, void *opaque) { CMSDKAPBUART *s = CMSDK_APB_UART(opaque); int ret; diff --git a/hw/char/ibex_uart.c b/hw/char/ibex_uart.c index 73b8f2e45b..9b0a817713 100644 --- a/hw/char/ibex_uart.c +++ b/hw/char/ibex_uart.c @@ -35,6 +35,44 @@ #include "qemu/log.h" #include "qemu/module.h" +REG32(INTR_STATE, 0x00) + FIELD(INTR_STATE, TX_WATERMARK, 0, 1) + FIELD(INTR_STATE, RX_WATERMARK, 1, 1) + FIELD(INTR_STATE, TX_EMPTY, 2, 1) + FIELD(INTR_STATE, RX_OVERFLOW, 3, 1) +REG32(INTR_ENABLE, 0x04) +REG32(INTR_TEST, 0x08) +REG32(ALERT_TEST, 0x0C) +REG32(CTRL, 0x10) + FIELD(CTRL, TX_ENABLE, 0, 1) + FIELD(CTRL, RX_ENABLE, 1, 1) + FIELD(CTRL, NF, 2, 1) + FIELD(CTRL, SLPBK, 4, 1) + FIELD(CTRL, LLPBK, 5, 1) + FIELD(CTRL, PARITY_EN, 6, 1) + FIELD(CTRL, PARITY_ODD, 7, 1) + FIELD(CTRL, RXBLVL, 8, 2) + FIELD(CTRL, NCO, 16, 16) +REG32(STATUS, 0x14) + FIELD(STATUS, TXFULL, 0, 1) + FIELD(STATUS, RXFULL, 1, 1) + FIELD(STATUS, TXEMPTY, 2, 1) + FIELD(STATUS, RXIDLE, 4, 1) + FIELD(STATUS, RXEMPTY, 5, 1) +REG32(RDATA, 0x18) +REG32(WDATA, 0x1C) +REG32(FIFO_CTRL, 0x20) + FIELD(FIFO_CTRL, RXRST, 0, 1) + FIELD(FIFO_CTRL, TXRST, 1, 1) + FIELD(FIFO_CTRL, RXILVL, 2, 3) + FIELD(FIFO_CTRL, TXILVL, 5, 2) +REG32(FIFO_STATUS, 0x24) + FIELD(FIFO_STATUS, TXLVL, 0, 5) + FIELD(FIFO_STATUS, RXLVL, 16, 5) +REG32(OVRD, 0x28) +REG32(VAL, 0x2C) +REG32(TIMEOUT_CTRL, 0x30) + static void ibex_uart_update_irqs(IbexUartState *s) { if (s->uart_intr_state & s->uart_intr_enable & R_INTR_STATE_TX_WATERMARK_MASK) { @@ -97,7 +135,7 @@ static void ibex_uart_receive(void *opaque, const uint8_t *buf, int size) ibex_uart_update_irqs(s); } -static gboolean ibex_uart_xmit(GIOChannel *chan, GIOCondition cond, +static gboolean ibex_uart_xmit(void *do_not_use, GIOCondition cond, void *opaque) { IbexUartState *s = opaque; diff --git a/hw/char/lm32_juart.c b/hw/char/lm32_juart.c deleted file mode 100644 index ce30279650..0000000000 --- a/hw/char/lm32_juart.c +++ /dev/null @@ -1,166 +0,0 @@ -/* - * LatticeMico32 JTAG UART model. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - */ - -#include "qemu/osdep.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "qemu/module.h" -#include "trace.h" -#include "chardev/char-fe.h" - -#include "hw/char/lm32_juart.h" -#include "hw/qdev-properties.h" -#include "hw/qdev-properties-system.h" -#include "qom/object.h" - -enum { - LM32_JUART_MIN_SAVE_VERSION = 0, - LM32_JUART_CURRENT_SAVE_VERSION = 0, - LM32_JUART_MAX_SAVE_VERSION = 0, -}; - -enum { - JTX_FULL = (1<<8), -}; - -enum { - JRX_FULL = (1<<8), -}; - -OBJECT_DECLARE_SIMPLE_TYPE(LM32JuartState, LM32_JUART) - -struct LM32JuartState { - SysBusDevice parent_obj; - - CharBackend chr; - - uint32_t jtx; - uint32_t jrx; -}; - -uint32_t lm32_juart_get_jtx(DeviceState *d) -{ - LM32JuartState *s = LM32_JUART(d); - - trace_lm32_juart_get_jtx(s->jtx); - return s->jtx; -} - -uint32_t lm32_juart_get_jrx(DeviceState *d) -{ - LM32JuartState *s = LM32_JUART(d); - - trace_lm32_juart_get_jrx(s->jrx); - return s->jrx; -} - -void lm32_juart_set_jtx(DeviceState *d, uint32_t jtx) -{ - LM32JuartState *s = LM32_JUART(d); - unsigned char ch = jtx & 0xff; - - trace_lm32_juart_set_jtx(s->jtx); - - s->jtx = jtx; - /* XXX this blocks entire thread. Rewrite to use - * qemu_chr_fe_write and background I/O callbacks */ - qemu_chr_fe_write_all(&s->chr, &ch, 1); -} - -void lm32_juart_set_jrx(DeviceState *d, uint32_t jtx) -{ - LM32JuartState *s = LM32_JUART(d); - - trace_lm32_juart_set_jrx(s->jrx); - s->jrx &= ~JRX_FULL; -} - -static void juart_rx(void *opaque, const uint8_t *buf, int size) -{ - LM32JuartState *s = opaque; - - s->jrx = *buf | JRX_FULL; -} - -static int juart_can_rx(void *opaque) -{ - LM32JuartState *s = opaque; - - return !(s->jrx & JRX_FULL); -} - -static void juart_event(void *opaque, QEMUChrEvent event) -{ -} - -static void juart_reset(DeviceState *d) -{ - LM32JuartState *s = LM32_JUART(d); - - s->jtx = 0; - s->jrx = 0; -} - -static void lm32_juart_realize(DeviceState *dev, Error **errp) -{ - LM32JuartState *s = LM32_JUART(dev); - - qemu_chr_fe_set_handlers(&s->chr, juart_can_rx, juart_rx, - juart_event, NULL, s, NULL, true); -} - -static const VMStateDescription vmstate_lm32_juart = { - .name = "lm32-juart", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32(jtx, LM32JuartState), - VMSTATE_UINT32(jrx, LM32JuartState), - VMSTATE_END_OF_LIST() - } -}; - -static Property lm32_juart_properties[] = { - DEFINE_PROP_CHR("chardev", LM32JuartState, chr), - DEFINE_PROP_END_OF_LIST(), -}; - -static void lm32_juart_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->reset = juart_reset; - dc->vmsd = &vmstate_lm32_juart; - device_class_set_props(dc, lm32_juart_properties); - dc->realize = lm32_juart_realize; -} - -static const TypeInfo lm32_juart_info = { - .name = TYPE_LM32_JUART, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(LM32JuartState), - .class_init = lm32_juart_class_init, -}; - -static void lm32_juart_register_types(void) -{ - type_register_static(&lm32_juart_info); -} - -type_init(lm32_juart_register_types) diff --git a/hw/char/lm32_uart.c b/hw/char/lm32_uart.c deleted file mode 100644 index d8e0331311..0000000000 --- a/hw/char/lm32_uart.c +++ /dev/null @@ -1,314 +0,0 @@ -/* - * QEMU model of the LatticeMico32 UART block. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://www.latticesemi.com/documents/mico32uart.pdf - */ - - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/qdev-properties.h" -#include "hw/qdev-properties-system.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "chardev/char-fe.h" -#include "qemu/error-report.h" -#include "qemu/module.h" -#include "qom/object.h" - -enum { - R_RXTX = 0, - R_IER, - R_IIR, - R_LCR, - R_MCR, - R_LSR, - R_MSR, - R_DIV, - R_MAX -}; - -enum { - IER_RBRI = (1<<0), - IER_THRI = (1<<1), - IER_RLSI = (1<<2), - IER_MSI = (1<<3), -}; - -enum { - IIR_STAT = (1<<0), - IIR_ID0 = (1<<1), - IIR_ID1 = (1<<2), -}; - -enum { - LCR_WLS0 = (1<<0), - LCR_WLS1 = (1<<1), - LCR_STB = (1<<2), - LCR_PEN = (1<<3), - LCR_EPS = (1<<4), - LCR_SP = (1<<5), - LCR_SB = (1<<6), -}; - -enum { - MCR_DTR = (1<<0), - MCR_RTS = (1<<1), -}; - -enum { - LSR_DR = (1<<0), - LSR_OE = (1<<1), - LSR_PE = (1<<2), - LSR_FE = (1<<3), - LSR_BI = (1<<4), - LSR_THRE = (1<<5), - LSR_TEMT = (1<<6), -}; - -enum { - MSR_DCTS = (1<<0), - MSR_DDSR = (1<<1), - MSR_TERI = (1<<2), - MSR_DDCD = (1<<3), - MSR_CTS = (1<<4), - MSR_DSR = (1<<5), - MSR_RI = (1<<6), - MSR_DCD = (1<<7), -}; - -#define TYPE_LM32_UART "lm32-uart" -OBJECT_DECLARE_SIMPLE_TYPE(LM32UartState, LM32_UART) - -struct LM32UartState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - CharBackend chr; - qemu_irq irq; - - uint32_t regs[R_MAX]; -}; - -static void uart_update_irq(LM32UartState *s) -{ - unsigned int irq; - - if ((s->regs[R_LSR] & (LSR_OE | LSR_PE | LSR_FE | LSR_BI)) - && (s->regs[R_IER] & IER_RLSI)) { - irq = 1; - s->regs[R_IIR] = IIR_ID1 | IIR_ID0; - } else if ((s->regs[R_LSR] & LSR_DR) && (s->regs[R_IER] & IER_RBRI)) { - irq = 1; - s->regs[R_IIR] = IIR_ID1; - } else if ((s->regs[R_LSR] & LSR_THRE) && (s->regs[R_IER] & IER_THRI)) { - irq = 1; - s->regs[R_IIR] = IIR_ID0; - } else if ((s->regs[R_MSR] & 0x0f) && (s->regs[R_IER] & IER_MSI)) { - irq = 1; - s->regs[R_IIR] = 0; - } else { - irq = 0; - s->regs[R_IIR] = IIR_STAT; - } - - trace_lm32_uart_irq_state(irq); - qemu_set_irq(s->irq, irq); -} - -static uint64_t uart_read(void *opaque, hwaddr addr, - unsigned size) -{ - LM32UartState *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_RXTX: - r = s->regs[R_RXTX]; - s->regs[R_LSR] &= ~LSR_DR; - uart_update_irq(s); - qemu_chr_fe_accept_input(&s->chr); - break; - case R_IIR: - case R_LSR: - case R_MSR: - r = s->regs[addr]; - break; - case R_IER: - case R_LCR: - case R_MCR: - case R_DIV: - error_report("lm32_uart: read access to write only register 0x" - TARGET_FMT_plx, addr << 2); - break; - default: - error_report("lm32_uart: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - trace_lm32_uart_memory_read(addr << 2, r); - return r; -} - -static void uart_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - LM32UartState *s = opaque; - unsigned char ch = value; - - trace_lm32_uart_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_RXTX: - /* XXX this blocks entire thread. Rewrite to use - * qemu_chr_fe_write and background I/O callbacks */ - qemu_chr_fe_write_all(&s->chr, &ch, 1); - break; - case R_IER: - case R_LCR: - case R_MCR: - case R_DIV: - s->regs[addr] = value; - break; - case R_IIR: - case R_LSR: - case R_MSR: - error_report("lm32_uart: write access to read only register 0x" - TARGET_FMT_plx, addr << 2); - break; - default: - error_report("lm32_uart: write access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - uart_update_irq(s); -} - -static const MemoryRegionOps uart_ops = { - .read = uart_read, - .write = uart_write, - .endianness = DEVICE_NATIVE_ENDIAN, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, -}; - -static void uart_rx(void *opaque, const uint8_t *buf, int size) -{ - LM32UartState *s = opaque; - - if (s->regs[R_LSR] & LSR_DR) { - s->regs[R_LSR] |= LSR_OE; - } - - s->regs[R_LSR] |= LSR_DR; - s->regs[R_RXTX] = *buf; - - uart_update_irq(s); -} - -static int uart_can_rx(void *opaque) -{ - LM32UartState *s = opaque; - - return !(s->regs[R_LSR] & LSR_DR); -} - -static void uart_event(void *opaque, QEMUChrEvent event) -{ -} - -static void uart_reset(DeviceState *d) -{ - LM32UartState *s = LM32_UART(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } - - /* defaults */ - s->regs[R_LSR] = LSR_THRE | LSR_TEMT; -} - -static void lm32_uart_init(Object *obj) -{ - LM32UartState *s = LM32_UART(obj); - SysBusDevice *dev = SYS_BUS_DEVICE(obj); - - sysbus_init_irq(dev, &s->irq); - - memory_region_init_io(&s->iomem, obj, &uart_ops, s, - "uart", R_MAX * 4); - sysbus_init_mmio(dev, &s->iomem); -} - -static void lm32_uart_realize(DeviceState *dev, Error **errp) -{ - LM32UartState *s = LM32_UART(dev); - - qemu_chr_fe_set_handlers(&s->chr, uart_can_rx, uart_rx, - uart_event, NULL, s, NULL, true); -} - -static const VMStateDescription vmstate_lm32_uart = { - .name = "lm32-uart", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, LM32UartState, R_MAX), - VMSTATE_END_OF_LIST() - } -}; - -static Property lm32_uart_properties[] = { - DEFINE_PROP_CHR("chardev", LM32UartState, chr), - DEFINE_PROP_END_OF_LIST(), -}; - -static void lm32_uart_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->reset = uart_reset; - dc->vmsd = &vmstate_lm32_uart; - device_class_set_props(dc, lm32_uart_properties); - dc->realize = lm32_uart_realize; -} - -static const TypeInfo lm32_uart_info = { - .name = TYPE_LM32_UART, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(LM32UartState), - .instance_init = lm32_uart_init, - .class_init = lm32_uart_class_init, -}; - -static void lm32_uart_register_types(void) -{ - type_register_static(&lm32_uart_info); -} - -type_init(lm32_uart_register_types) diff --git a/hw/char/mchp_pfsoc_mmuart.c b/hw/char/mchp_pfsoc_mmuart.c index 8a002b0a19..2facf85c2d 100644 --- a/hw/char/mchp_pfsoc_mmuart.c +++ b/hw/char/mchp_pfsoc_mmuart.c @@ -23,7 +23,6 @@ #include "qemu/osdep.h" #include "qemu/log.h" #include "chardev/char.h" -#include "exec/address-spaces.h" #include "hw/char/mchp_pfsoc_mmuart.h" static uint64_t mchp_pfsoc_mmuart_read(void *opaque, hwaddr addr, unsigned size) diff --git a/hw/char/meson.build b/hw/char/meson.build index da5bb8b762..8361d0ab28 100644 --- a/hw/char/meson.build +++ b/hw/char/meson.build @@ -8,9 +8,6 @@ softmmu_ss.add(when: 'CONFIG_IMX', if_true: files('imx_serial.c')) softmmu_ss.add(when: 'CONFIG_IPACK', if_true: files('ipoctal232.c')) softmmu_ss.add(when: 'CONFIG_ISA_BUS', if_true: files('parallel-isa.c')) softmmu_ss.add(when: 'CONFIG_ISA_DEBUG', if_true: files('debugcon.c')) -softmmu_ss.add(when: 'CONFIG_LM32_DEVICES', if_true: files('lm32_juart.c')) -softmmu_ss.add(when: 'CONFIG_LM32_DEVICES', if_true: files('lm32_uart.c')) -softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-uart.c')) softmmu_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_uart.c')) softmmu_ss.add(when: 'CONFIG_PARALLEL', if_true: files('parallel.c')) softmmu_ss.add(when: 'CONFIG_PL011', if_true: files('pl011.c')) @@ -19,6 +16,7 @@ softmmu_ss.add(when: 'CONFIG_SERIAL', if_true: files('serial.c')) softmmu_ss.add(when: 'CONFIG_SERIAL_ISA', if_true: files('serial-isa.c')) softmmu_ss.add(when: 'CONFIG_SERIAL_PCI', if_true: files('serial-pci.c')) softmmu_ss.add(when: 'CONFIG_SERIAL_PCI_MULTI', if_true: files('serial-pci-multi.c')) +softmmu_ss.add(when: 'CONFIG_SHAKTI', if_true: files('shakti_uart.c')) softmmu_ss.add(when: 'CONFIG_VIRTIO_SERIAL', if_true: files('virtio-console.c')) softmmu_ss.add(when: 'CONFIG_XEN', if_true: files('xen_console.c')) softmmu_ss.add(when: 'CONFIG_XILINX', if_true: files('xilinx_uartlite.c')) diff --git a/hw/char/milkymist-uart.c b/hw/char/milkymist-uart.c deleted file mode 100644 index cb1b3470ad..0000000000 --- a/hw/char/milkymist-uart.c +++ /dev/null @@ -1,258 +0,0 @@ -/* - * QEMU model of the Milkymist UART block. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://milkymist.walle.cc/socdoc/uart.pdf - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/qdev-properties.h" -#include "hw/qdev-properties-system.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "chardev/char-fe.h" -#include "qemu/error-report.h" -#include "qemu/module.h" -#include "qom/object.h" - -enum { - R_RXTX = 0, - R_DIV, - R_STAT, - R_CTRL, - R_DBG, - R_MAX -}; - -enum { - STAT_THRE = (1<<0), - STAT_RX_EVT = (1<<1), - STAT_TX_EVT = (1<<2), -}; - -enum { - CTRL_RX_IRQ_EN = (1<<0), - CTRL_TX_IRQ_EN = (1<<1), - CTRL_THRU_EN = (1<<2), -}; - -enum { - DBG_BREAK_EN = (1<<0), -}; - -#define TYPE_MILKYMIST_UART "milkymist-uart" -OBJECT_DECLARE_SIMPLE_TYPE(MilkymistUartState, MILKYMIST_UART) - -struct MilkymistUartState { - SysBusDevice parent_obj; - - MemoryRegion regs_region; - CharBackend chr; - qemu_irq irq; - - uint32_t regs[R_MAX]; -}; - -static void uart_update_irq(MilkymistUartState *s) -{ - int rx_event = s->regs[R_STAT] & STAT_RX_EVT; - int tx_event = s->regs[R_STAT] & STAT_TX_EVT; - int rx_irq_en = s->regs[R_CTRL] & CTRL_RX_IRQ_EN; - int tx_irq_en = s->regs[R_CTRL] & CTRL_TX_IRQ_EN; - - if ((rx_irq_en && rx_event) || (tx_irq_en && tx_event)) { - trace_milkymist_uart_raise_irq(); - qemu_irq_raise(s->irq); - } else { - trace_milkymist_uart_lower_irq(); - qemu_irq_lower(s->irq); - } -} - -static uint64_t uart_read(void *opaque, hwaddr addr, - unsigned size) -{ - MilkymistUartState *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_RXTX: - r = s->regs[addr]; - break; - case R_DIV: - case R_STAT: - case R_CTRL: - case R_DBG: - r = s->regs[addr]; - break; - - default: - error_report("milkymist_uart: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - trace_milkymist_uart_memory_read(addr << 2, r); - - return r; -} - -static void uart_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - MilkymistUartState *s = opaque; - unsigned char ch = value; - - trace_milkymist_uart_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_RXTX: - qemu_chr_fe_write_all(&s->chr, &ch, 1); - s->regs[R_STAT] |= STAT_TX_EVT; - break; - case R_DIV: - case R_CTRL: - case R_DBG: - s->regs[addr] = value; - break; - - case R_STAT: - /* write one to clear bits */ - s->regs[addr] &= ~(value & (STAT_RX_EVT | STAT_TX_EVT)); - qemu_chr_fe_accept_input(&s->chr); - break; - - default: - error_report("milkymist_uart: write access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - uart_update_irq(s); -} - -static const MemoryRegionOps uart_mmio_ops = { - .read = uart_read, - .write = uart_write, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void uart_rx(void *opaque, const uint8_t *buf, int size) -{ - MilkymistUartState *s = opaque; - - assert(!(s->regs[R_STAT] & STAT_RX_EVT)); - - s->regs[R_STAT] |= STAT_RX_EVT; - s->regs[R_RXTX] = *buf; - - uart_update_irq(s); -} - -static int uart_can_rx(void *opaque) -{ - MilkymistUartState *s = opaque; - - return !(s->regs[R_STAT] & STAT_RX_EVT); -} - -static void uart_event(void *opaque, QEMUChrEvent event) -{ -} - -static void milkymist_uart_reset(DeviceState *d) -{ - MilkymistUartState *s = MILKYMIST_UART(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } - - /* THRE is always set */ - s->regs[R_STAT] = STAT_THRE; -} - -static void milkymist_uart_realize(DeviceState *dev, Error **errp) -{ - MilkymistUartState *s = MILKYMIST_UART(dev); - - qemu_chr_fe_set_handlers(&s->chr, uart_can_rx, uart_rx, - uart_event, NULL, s, NULL, true); -} - -static void milkymist_uart_init(Object *obj) -{ - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - MilkymistUartState *s = MILKYMIST_UART(obj); - - sysbus_init_irq(sbd, &s->irq); - - memory_region_init_io(&s->regs_region, OBJECT(s), &uart_mmio_ops, s, - "milkymist-uart", R_MAX * 4); - sysbus_init_mmio(sbd, &s->regs_region); -} - -static const VMStateDescription vmstate_milkymist_uart = { - .name = "milkymist-uart", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, MilkymistUartState, R_MAX), - VMSTATE_END_OF_LIST() - } -}; - -static Property milkymist_uart_properties[] = { - DEFINE_PROP_CHR("chardev", MilkymistUartState, chr), - DEFINE_PROP_END_OF_LIST(), -}; - -static void milkymist_uart_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = milkymist_uart_realize; - dc->reset = milkymist_uart_reset; - dc->vmsd = &vmstate_milkymist_uart; - device_class_set_props(dc, milkymist_uart_properties); -} - -static const TypeInfo milkymist_uart_info = { - .name = TYPE_MILKYMIST_UART, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(MilkymistUartState), - .instance_init = milkymist_uart_init, - .class_init = milkymist_uart_class_init, -}; - -static void milkymist_uart_register_types(void) -{ - type_register_static(&milkymist_uart_info); -} - -type_init(milkymist_uart_register_types) diff --git a/hw/char/nrf51_uart.c b/hw/char/nrf51_uart.c index 045ca5fa40..3c6f982de9 100644 --- a/hw/char/nrf51_uart.c +++ b/hw/char/nrf51_uart.c @@ -75,7 +75,7 @@ static uint64_t uart_read(void *opaque, hwaddr addr, unsigned int size) return r; } -static gboolean uart_transmit(GIOChannel *chan, GIOCondition cond, void *opaque) +static gboolean uart_transmit(void *do_not_use, GIOCondition cond, void *opaque) { NRF51UARTState *s = NRF51_UART(opaque); int r; diff --git a/hw/char/riscv_htif.c b/hw/char/riscv_htif.c index ba1af1cfc4..ddae738d56 100644 --- a/hw/char/riscv_htif.c +++ b/hw/char/riscv_htif.c @@ -23,7 +23,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu/log.h" -#include "hw/sysbus.h" #include "hw/char/riscv_htif.h" #include "hw/char/serial.h" #include "chardev/char.h" diff --git a/hw/char/serial.c b/hw/char/serial.c index bc2e322970..7061aacbce 100644 --- a/hw/char/serial.c +++ b/hw/char/serial.c @@ -220,7 +220,7 @@ static void serial_update_msl(SerialState *s) } } -static gboolean serial_watch_cb(GIOChannel *chan, GIOCondition cond, +static gboolean serial_watch_cb(void *do_not_use, GIOCondition cond, void *opaque) { SerialState *s = opaque; diff --git a/hw/char/shakti_uart.c b/hw/char/shakti_uart.c new file mode 100644 index 0000000000..6870821325 --- /dev/null +++ b/hw/char/shakti_uart.c @@ -0,0 +1,185 @@ +/* + * SHAKTI UART + * + * Copyright (c) 2021 Vijai Kumar K + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "hw/char/shakti_uart.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" +#include "qemu/log.h" + +static uint64_t shakti_uart_read(void *opaque, hwaddr addr, unsigned size) +{ + ShaktiUartState *s = opaque; + + switch (addr) { + case SHAKTI_UART_BAUD: + return s->uart_baud; + case SHAKTI_UART_RX: + qemu_chr_fe_accept_input(&s->chr); + s->uart_status &= ~SHAKTI_UART_STATUS_RX_NOT_EMPTY; + return s->uart_rx; + case SHAKTI_UART_STATUS: + return s->uart_status; + case SHAKTI_UART_DELAY: + return s->uart_delay; + case SHAKTI_UART_CONTROL: + return s->uart_control; + case SHAKTI_UART_INT_EN: + return s->uart_interrupt; + case SHAKTI_UART_IQ_CYCLES: + return s->uart_iq_cycles; + case SHAKTI_UART_RX_THRES: + return s->uart_rx_threshold; + default: + /* Also handles TX REG which is write only */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%"HWADDR_PRIx"\n", __func__, addr); + } + + return 0; +} + +static void shakti_uart_write(void *opaque, hwaddr addr, + uint64_t data, unsigned size) +{ + ShaktiUartState *s = opaque; + uint32_t value = data; + uint8_t ch; + + switch (addr) { + case SHAKTI_UART_BAUD: + s->uart_baud = value; + break; + case SHAKTI_UART_TX: + ch = value; + qemu_chr_fe_write_all(&s->chr, &ch, 1); + s->uart_status &= ~SHAKTI_UART_STATUS_TX_FULL; + break; + case SHAKTI_UART_STATUS: + s->uart_status = value; + break; + case SHAKTI_UART_DELAY: + s->uart_delay = value; + break; + case SHAKTI_UART_CONTROL: + s->uart_control = value; + break; + case SHAKTI_UART_INT_EN: + s->uart_interrupt = value; + break; + case SHAKTI_UART_IQ_CYCLES: + s->uart_iq_cycles = value; + break; + case SHAKTI_UART_RX_THRES: + s->uart_rx_threshold = value; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%"HWADDR_PRIx"\n", __func__, addr); + } +} + +static const MemoryRegionOps shakti_uart_ops = { + .read = shakti_uart_read, + .write = shakti_uart_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = {.min_access_size = 1, .max_access_size = 4}, + .valid = {.min_access_size = 1, .max_access_size = 4}, +}; + +static void shakti_uart_reset(DeviceState *dev) +{ + ShaktiUartState *s = SHAKTI_UART(dev); + + s->uart_baud = SHAKTI_UART_BAUD_DEFAULT; + s->uart_tx = 0x0; + s->uart_rx = 0x0; + s->uart_status = 0x0000; + s->uart_delay = 0x0000; + s->uart_control = SHAKTI_UART_CONTROL_DEFAULT; + s->uart_interrupt = 0x0000; + s->uart_iq_cycles = 0x00; + s->uart_rx_threshold = 0x00; +} + +static int shakti_uart_can_receive(void *opaque) +{ + ShaktiUartState *s = opaque; + + return !(s->uart_status & SHAKTI_UART_STATUS_RX_NOT_EMPTY); +} + +static void shakti_uart_receive(void *opaque, const uint8_t *buf, int size) +{ + ShaktiUartState *s = opaque; + + s->uart_rx = *buf; + s->uart_status |= SHAKTI_UART_STATUS_RX_NOT_EMPTY; +} + +static void shakti_uart_realize(DeviceState *dev, Error **errp) +{ + ShaktiUartState *sus = SHAKTI_UART(dev); + qemu_chr_fe_set_handlers(&sus->chr, shakti_uart_can_receive, + shakti_uart_receive, NULL, NULL, sus, NULL, true); +} + +static void shakti_uart_instance_init(Object *obj) +{ + ShaktiUartState *sus = SHAKTI_UART(obj); + memory_region_init_io(&sus->mmio, + obj, + &shakti_uart_ops, + sus, + TYPE_SHAKTI_UART, + 0x1000); + sysbus_init_mmio(SYS_BUS_DEVICE(obj), &sus->mmio); +} + +static Property shakti_uart_properties[] = { + DEFINE_PROP_CHR("chardev", ShaktiUartState, chr), + DEFINE_PROP_END_OF_LIST(), +}; + +static void shakti_uart_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + dc->reset = shakti_uart_reset; + dc->realize = shakti_uart_realize; + device_class_set_props(dc, shakti_uart_properties); +} + +static const TypeInfo shakti_uart_info = { + .name = TYPE_SHAKTI_UART, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(ShaktiUartState), + .class_init = shakti_uart_class_init, + .instance_init = shakti_uart_instance_init, +}; + +static void shakti_uart_register_types(void) +{ + type_register_static(&shakti_uart_info); +} +type_init(shakti_uart_register_types) diff --git a/hw/char/sifive_uart.c b/hw/char/sifive_uart.c index 3a00ba7f00..278e21c434 100644 --- a/hw/char/sifive_uart.c +++ b/hw/char/sifive_uart.c @@ -19,12 +19,12 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu/log.h" -#include "hw/sysbus.h" +#include "migration/vmstate.h" #include "chardev/char.h" #include "chardev/char-fe.h" -#include "hw/hw.h" #include "hw/irq.h" #include "hw/char/sifive_uart.h" +#include "hw/qdev-properties-system.h" /* * Not yet implemented: @@ -33,7 +33,7 @@ */ /* Returns the state of the IP (interrupt pending) register */ -static uint64_t uart_ip(SiFiveUARTState *s) +static uint64_t sifive_uart_ip(SiFiveUARTState *s) { uint64_t ret = 0; @@ -50,7 +50,7 @@ static uint64_t uart_ip(SiFiveUARTState *s) return ret; } -static void update_irq(SiFiveUARTState *s) +static void sifive_uart_update_irq(SiFiveUARTState *s) { int cond = 0; if ((s->ie & SIFIVE_UART_IE_TXWM) || @@ -65,7 +65,7 @@ static void update_irq(SiFiveUARTState *s) } static uint64_t -uart_read(void *opaque, hwaddr addr, unsigned int size) +sifive_uart_read(void *opaque, hwaddr addr, unsigned int size) { SiFiveUARTState *s = opaque; unsigned char r; @@ -76,7 +76,7 @@ uart_read(void *opaque, hwaddr addr, unsigned int size) memmove(s->rx_fifo, s->rx_fifo + 1, s->rx_fifo_len - 1); s->rx_fifo_len--; qemu_chr_fe_accept_input(&s->chr); - update_irq(s); + sifive_uart_update_irq(s); return r; } return 0x80000000; @@ -86,7 +86,7 @@ uart_read(void *opaque, hwaddr addr, unsigned int size) case SIFIVE_UART_IE: return s->ie; case SIFIVE_UART_IP: - return uart_ip(s); + return sifive_uart_ip(s); case SIFIVE_UART_TXCTRL: return s->txctrl; case SIFIVE_UART_RXCTRL: @@ -101,8 +101,8 @@ uart_read(void *opaque, hwaddr addr, unsigned int size) } static void -uart_write(void *opaque, hwaddr addr, - uint64_t val64, unsigned int size) +sifive_uart_write(void *opaque, hwaddr addr, + uint64_t val64, unsigned int size) { SiFiveUARTState *s = opaque; uint32_t value = val64; @@ -111,11 +111,11 @@ uart_write(void *opaque, hwaddr addr, switch (addr) { case SIFIVE_UART_TXFIFO: qemu_chr_fe_write(&s->chr, &ch, 1); - update_irq(s); + sifive_uart_update_irq(s); return; case SIFIVE_UART_IE: s->ie = val64; - update_irq(s); + sifive_uart_update_irq(s); return; case SIFIVE_UART_TXCTRL: s->txctrl = val64; @@ -131,9 +131,9 @@ uart_write(void *opaque, hwaddr addr, __func__, (int)addr, (int)value); } -static const MemoryRegionOps uart_ops = { - .read = uart_read, - .write = uart_write, +static const MemoryRegionOps sifive_uart_ops = { + .read = sifive_uart_read, + .write = sifive_uart_write, .endianness = DEVICE_NATIVE_ENDIAN, .valid = { .min_access_size = 4, @@ -141,7 +141,7 @@ static const MemoryRegionOps uart_ops = { } }; -static void uart_rx(void *opaque, const uint8_t *buf, int size) +static void sifive_uart_rx(void *opaque, const uint8_t *buf, int size) { SiFiveUARTState *s = opaque; @@ -152,43 +152,137 @@ static void uart_rx(void *opaque, const uint8_t *buf, int size) } s->rx_fifo[s->rx_fifo_len++] = *buf; - update_irq(s); + sifive_uart_update_irq(s); } -static int uart_can_rx(void *opaque) +static int sifive_uart_can_rx(void *opaque) { SiFiveUARTState *s = opaque; return s->rx_fifo_len < sizeof(s->rx_fifo); } -static void uart_event(void *opaque, QEMUChrEvent event) +static void sifive_uart_event(void *opaque, QEMUChrEvent event) { } -static int uart_be_change(void *opaque) +static int sifive_uart_be_change(void *opaque) { SiFiveUARTState *s = opaque; - qemu_chr_fe_set_handlers(&s->chr, uart_can_rx, uart_rx, uart_event, - uart_be_change, s, NULL, true); + qemu_chr_fe_set_handlers(&s->chr, sifive_uart_can_rx, sifive_uart_rx, + sifive_uart_event, sifive_uart_be_change, s, + NULL, true); return 0; } +static Property sifive_uart_properties[] = { + DEFINE_PROP_CHR("chardev", SiFiveUARTState, chr), + DEFINE_PROP_END_OF_LIST(), +}; + +static void sifive_uart_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + SiFiveUARTState *s = SIFIVE_UART(obj); + + memory_region_init_io(&s->mmio, OBJECT(s), &sifive_uart_ops, s, + TYPE_SIFIVE_UART, SIFIVE_UART_MAX); + sysbus_init_mmio(sbd, &s->mmio); + sysbus_init_irq(sbd, &s->irq); +} + +static void sifive_uart_realize(DeviceState *dev, Error **errp) +{ + SiFiveUARTState *s = SIFIVE_UART(dev); + + qemu_chr_fe_set_handlers(&s->chr, sifive_uart_can_rx, sifive_uart_rx, + sifive_uart_event, sifive_uart_be_change, s, + NULL, true); + +} + +static void sifive_uart_reset_enter(Object *obj, ResetType type) +{ + SiFiveUARTState *s = SIFIVE_UART(obj); + s->ie = 0; + s->ip = 0; + s->txctrl = 0; + s->rxctrl = 0; + s->div = 0; + s->rx_fifo_len = 0; +} + +static void sifive_uart_reset_hold(Object *obj) +{ + SiFiveUARTState *s = SIFIVE_UART(obj); + qemu_irq_lower(s->irq); +} + +static const VMStateDescription vmstate_sifive_uart = { + .name = TYPE_SIFIVE_UART, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8_ARRAY(rx_fifo, SiFiveUARTState, + SIFIVE_UART_RX_FIFO_SIZE), + VMSTATE_UINT8(rx_fifo_len, SiFiveUARTState), + VMSTATE_UINT32(ie, SiFiveUARTState), + VMSTATE_UINT32(ip, SiFiveUARTState), + VMSTATE_UINT32(txctrl, SiFiveUARTState), + VMSTATE_UINT32(rxctrl, SiFiveUARTState), + VMSTATE_UINT32(div, SiFiveUARTState), + VMSTATE_END_OF_LIST() + }, +}; + + +static void sifive_uart_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + ResettableClass *rc = RESETTABLE_CLASS(oc); + + dc->realize = sifive_uart_realize; + dc->vmsd = &vmstate_sifive_uart; + rc->phases.enter = sifive_uart_reset_enter; + rc->phases.hold = sifive_uart_reset_hold; + device_class_set_props(dc, sifive_uart_properties); +} + +static const TypeInfo sifive_uart_info = { + .name = TYPE_SIFIVE_UART, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(SiFiveUARTState), + .instance_init = sifive_uart_init, + .class_init = sifive_uart_class_init, +}; + +static void sifive_uart_register_types(void) +{ + type_register_static(&sifive_uart_info); +} + +type_init(sifive_uart_register_types) + /* * Create UART device. */ SiFiveUARTState *sifive_uart_create(MemoryRegion *address_space, hwaddr base, Chardev *chr, qemu_irq irq) { - SiFiveUARTState *s = g_malloc0(sizeof(SiFiveUARTState)); - s->irq = irq; - qemu_chr_fe_init(&s->chr, chr, &error_abort); - qemu_chr_fe_set_handlers(&s->chr, uart_can_rx, uart_rx, uart_event, - uart_be_change, s, NULL, true); - memory_region_init_io(&s->mmio, NULL, &uart_ops, s, - TYPE_SIFIVE_UART, SIFIVE_UART_MAX); - memory_region_add_subregion(address_space, base, &s->mmio); - return s; + DeviceState *dev; + SysBusDevice *s; + SiFiveUARTState *r; + + dev = qdev_new("riscv.sifive.uart"); + s = SYS_BUS_DEVICE(dev); + qdev_prop_set_chr(dev, "chardev", chr); + sysbus_realize_and_unref(s, &error_fatal); + memory_region_add_subregion(address_space, base, + sysbus_mmio_get_region(s, 0)); + sysbus_connect_irq(s, 0, irq); + + r = SIFIVE_UART(dev); + return r; } diff --git a/hw/char/spapr_vty.c b/hw/char/spapr_vty.c index 79eaa2fa52..91eae1a598 100644 --- a/hw/char/spapr_vty.c +++ b/hw/char/spapr_vty.c @@ -2,7 +2,6 @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "qapi/error.h" -#include "cpu.h" #include "migration/vmstate.h" #include "chardev/char-fe.h" #include "hw/ppc/spapr.h" diff --git a/hw/char/trace-events b/hw/char/trace-events index 76d52938ea..1436fb462d 100644 --- a/hw/char/trace-events +++ b/hw/char/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # parallel.c parallel_ioport_read(const char *desc, uint16_t addr, uint8_t value) "read [%s] addr 0x%02x val 0x%02x" @@ -35,23 +35,6 @@ grlib_apbuart_event(int event) "event:%d" grlib_apbuart_writel_unknown(uint64_t addr, uint32_t value) "addr 0x%"PRIx64" value 0x%x" grlib_apbuart_readl_unknown(uint64_t addr) "addr 0x%"PRIx64 -# lm32_juart.c -lm32_juart_get_jtx(uint32_t value) "jtx 0x%08x" -lm32_juart_set_jtx(uint32_t value) "jtx 0x%08x" -lm32_juart_get_jrx(uint32_t value) "jrx 0x%08x" -lm32_juart_set_jrx(uint32_t value) "jrx 0x%08x" - -# lm32_uart.c -lm32_uart_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -lm32_uart_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -lm32_uart_irq_state(int level) "irq state %d" - -# milkymist-uart.c -milkymist_uart_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_uart_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_uart_raise_irq(void) "Raise IRQ" -milkymist_uart_lower_irq(void) "Lower IRQ" - # escc.c escc_put_queue(char channel, int b) "channel %c put: 0x%02x" escc_get_queue(char channel, int val) "channel %c get 0x%02x" @@ -90,6 +73,10 @@ cmsdk_apb_uart_set_params(int speed) "CMSDK APB UART: params set to %d 8N1" nrf51_uart_read(uint64_t addr, uint64_t r, unsigned int size) "addr 0x%" PRIx64 " value 0x%" PRIx64 " size %u" nrf51_uart_write(uint64_t addr, uint64_t value, unsigned int size) "addr 0x%" PRIx64 " value 0x%" PRIx64 " size %u" +# shakti_uart.c +shakti_uart_read(uint64_t addr, uint16_t r, unsigned int size) "addr 0x%" PRIx64 " value 0x%" PRIx16 " size %u" +shakti_uart_write(uint64_t addr, uint64_t value, unsigned int size) "addr 0x%" PRIx64 " value 0x%" PRIx64 " size %u" + # exynos4210_uart.c exynos_uart_dmabusy(uint32_t channel) "UART%d: DMA busy (Rx buffer empty)" exynos_uart_dmaready(uint32_t channel) "UART%d: DMA ready" diff --git a/hw/char/virtio-console.c b/hw/char/virtio-console.c index 6b132caa29..dd5a02e339 100644 --- a/hw/char/virtio-console.c +++ b/hw/char/virtio-console.c @@ -38,7 +38,7 @@ struct VirtConsole { * Callback function that's called from chardevs when backend becomes * writable. */ -static gboolean chr_write_unblocked(GIOChannel *chan, GIOCondition cond, +static gboolean chr_write_unblocked(void *do_not_use, GIOCondition cond, void *opaque) { VirtConsole *vcon = opaque; diff --git a/hw/char/virtio-serial-bus.c b/hw/char/virtio-serial-bus.c index b20038991a..dd6bc27b3b 100644 --- a/hw/char/virtio-serial-bus.c +++ b/hw/char/virtio-serial-bus.c @@ -28,7 +28,6 @@ #include "qemu/error-report.h" #include "qemu/queue.h" #include "hw/qdev-properties.h" -#include "hw/sysbus.h" #include "trace.h" #include "hw/virtio/virtio-serial.h" #include "hw/virtio/virtio-access.h" diff --git a/hw/core/cpu.c b/hw/core/cpu-common.c similarity index 71% rename from hw/core/cpu.c rename to hw/core/cpu-common.c index f79c2b875d..b05d1db7df 100644 --- a/hw/core/cpu.c +++ b/hw/core/cpu-common.c @@ -34,7 +34,6 @@ #include "hw/qdev-properties.h" #include "trace/trace-root.h" #include "qemu/plugin.h" -#include "sysemu/hw_accel.h" CPUState *cpu_by_arch_id(int64_t id) { @@ -67,33 +66,6 @@ CPUState *cpu_create(const char *typename) return cpu; } -bool cpu_paging_enabled(const CPUState *cpu) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - return cc->get_paging_enabled(cpu); -} - -static bool cpu_common_get_paging_enabled(const CPUState *cpu) -{ - return false; -} - -void cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list, - Error **errp) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - cc->get_memory_mapping(cpu, list, errp); -} - -static void cpu_common_get_memory_mapping(CPUState *cpu, - MemoryMappingList *list, - Error **errp) -{ - error_setg(errp, "Obtaining memory mappings is unsupported on this CPU."); -} - /* Resetting the IRQ comes from across the code base so we take the * BQL here if we need to. cpu_interrupt assumes it is held.*/ void cpu_reset_interrupt(CPUState *cpu, int mask) @@ -117,65 +89,6 @@ void cpu_exit(CPUState *cpu) qatomic_set(&cpu->icount_decr_ptr->u16.high, -1); } -int cpu_write_elf32_qemunote(WriteCoreDumpFunction f, CPUState *cpu, - void *opaque) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - return (*cc->write_elf32_qemunote)(f, cpu, opaque); -} - -static int cpu_common_write_elf32_qemunote(WriteCoreDumpFunction f, - CPUState *cpu, void *opaque) -{ - return 0; -} - -int cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cpu, - int cpuid, void *opaque) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - return (*cc->write_elf32_note)(f, cpu, cpuid, opaque); -} - -static int cpu_common_write_elf32_note(WriteCoreDumpFunction f, - CPUState *cpu, int cpuid, - void *opaque) -{ - return -1; -} - -int cpu_write_elf64_qemunote(WriteCoreDumpFunction f, CPUState *cpu, - void *opaque) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - return (*cc->write_elf64_qemunote)(f, cpu, opaque); -} - -static int cpu_common_write_elf64_qemunote(WriteCoreDumpFunction f, - CPUState *cpu, void *opaque) -{ - return 0; -} - -int cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cpu, - int cpuid, void *opaque) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - return (*cc->write_elf64_note)(f, cpu, cpuid, opaque); -} - -static int cpu_common_write_elf64_note(WriteCoreDumpFunction f, - CPUState *cpu, int cpuid, - void *opaque) -{ - return -1; -} - - static int cpu_common_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg) { return 0; @@ -186,28 +99,6 @@ static int cpu_common_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg) return 0; } -static bool cpu_common_virtio_is_big_endian(CPUState *cpu) -{ - return target_words_bigendian(); -} - -/* - * XXX the following #if is always true because this is a common_ss - * module, so target CONFIG_* is never defined. - */ -#if !defined(CONFIG_USER_ONLY) -GuestPanicInformation *cpu_get_crash_info(CPUState *cpu) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - GuestPanicInformation *res = NULL; - - if (cc->get_crash_info) { - res = cc->get_crash_info(cpu); - } - return res; -} -#endif - void cpu_dump_state(CPUState *cpu, FILE *f, int flags) { CPUClass *cc = CPU_GET_CLASS(cpu); @@ -218,15 +109,6 @@ void cpu_dump_state(CPUState *cpu, FILE *f, int flags) } } -void cpu_dump_statistics(CPUState *cpu, int flags) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - if (cc->dump_statistics) { - cc->dump_statistics(cpu, flags); - } -} - void cpu_reset(CPUState *cpu) { device_cold_reset(DEVICE(cpu)); @@ -399,15 +281,8 @@ static void cpu_class_init(ObjectClass *klass, void *data) k->parse_features = cpu_common_parse_features; k->get_arch_id = cpu_common_get_arch_id; k->has_work = cpu_common_has_work; - k->get_paging_enabled = cpu_common_get_paging_enabled; - k->get_memory_mapping = cpu_common_get_memory_mapping; - k->write_elf32_qemunote = cpu_common_write_elf32_qemunote; - k->write_elf32_note = cpu_common_write_elf32_note; - k->write_elf64_qemunote = cpu_common_write_elf64_qemunote; - k->write_elf64_note = cpu_common_write_elf64_note; k->gdb_read_register = cpu_common_gdb_read_register; k->gdb_write_register = cpu_common_gdb_write_register; - k->virtio_is_big_endian = cpu_common_virtio_is_big_endian; set_bit(DEVICE_CATEGORY_CPU, dc->categories); dc->realize = cpu_common_realizefn; dc->unrealize = cpu_common_unrealizefn; diff --git a/hw/core/cpu-sysemu.c b/hw/core/cpu-sysemu.c new file mode 100644 index 0000000000..00253f8929 --- /dev/null +++ b/hw/core/cpu-sysemu.c @@ -0,0 +1,145 @@ +/* + * QEMU CPU model (system emulation specific) + * + * Copyright (c) 2012-2014 SUSE LINUX Products GmbH + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see + * + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/core/cpu.h" +#include "hw/core/sysemu-cpu-ops.h" + +bool cpu_paging_enabled(const CPUState *cpu) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (cc->sysemu_ops->get_paging_enabled) { + return cc->sysemu_ops->get_paging_enabled(cpu); + } + + return false; +} + +void cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list, + Error **errp) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (cc->sysemu_ops->get_memory_mapping) { + cc->sysemu_ops->get_memory_mapping(cpu, list, errp); + return; + } + + error_setg(errp, "Obtaining memory mappings is unsupported on this CPU."); +} + +hwaddr cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, + MemTxAttrs *attrs) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (cc->sysemu_ops->get_phys_page_attrs_debug) { + return cc->sysemu_ops->get_phys_page_attrs_debug(cpu, addr, attrs); + } + /* Fallback for CPUs which don't implement the _attrs_ hook */ + *attrs = MEMTXATTRS_UNSPECIFIED; + return cc->sysemu_ops->get_phys_page_debug(cpu, addr); +} + +hwaddr cpu_get_phys_page_debug(CPUState *cpu, vaddr addr) +{ + MemTxAttrs attrs = {}; + + return cpu_get_phys_page_attrs_debug(cpu, addr, &attrs); +} + +int cpu_asidx_from_attrs(CPUState *cpu, MemTxAttrs attrs) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + int ret = 0; + + if (cc->sysemu_ops->asidx_from_attrs) { + ret = cc->sysemu_ops->asidx_from_attrs(cpu, attrs); + assert(ret < cpu->num_ases && ret >= 0); + } + return ret; +} + +int cpu_write_elf32_qemunote(WriteCoreDumpFunction f, CPUState *cpu, + void *opaque) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (!cc->sysemu_ops->write_elf32_qemunote) { + return 0; + } + return (*cc->sysemu_ops->write_elf32_qemunote)(f, cpu, opaque); +} + +int cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cpu, + int cpuid, void *opaque) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (!cc->sysemu_ops->write_elf32_note) { + return -1; + } + return (*cc->sysemu_ops->write_elf32_note)(f, cpu, cpuid, opaque); +} + +int cpu_write_elf64_qemunote(WriteCoreDumpFunction f, CPUState *cpu, + void *opaque) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (!cc->sysemu_ops->write_elf64_qemunote) { + return 0; + } + return (*cc->sysemu_ops->write_elf64_qemunote)(f, cpu, opaque); +} + +int cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cpu, + int cpuid, void *opaque) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (!cc->sysemu_ops->write_elf64_note) { + return -1; + } + return (*cc->sysemu_ops->write_elf64_note)(f, cpu, cpuid, opaque); +} + +bool cpu_virtio_is_big_endian(CPUState *cpu) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + + if (cc->sysemu_ops->virtio_is_big_endian) { + return cc->sysemu_ops->virtio_is_big_endian(cpu); + } + return target_words_bigendian(); +} + +GuestPanicInformation *cpu_get_crash_info(CPUState *cpu) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + GuestPanicInformation *res = NULL; + + if (cc->sysemu_ops->get_crash_info) { + res = cc->sysemu_ops->get_crash_info(cpu); + } + return res; +} diff --git a/hw/core/generic-loader.c b/hw/core/generic-loader.c index 2b2a7b5e9a..d14f932eea 100644 --- a/hw/core/generic-loader.c +++ b/hw/core/generic-loader.c @@ -32,7 +32,6 @@ #include "qemu/osdep.h" #include "hw/core/cpu.h" -#include "hw/sysbus.h" #include "sysemu/dma.h" #include "sysemu/reset.h" #include "hw/boards.h" diff --git a/hw/core/guest-loader.c b/hw/core/guest-loader.c index bde44e27b4..d3f9d1a06e 100644 --- a/hw/core/guest-loader.c +++ b/hw/core/guest-loader.c @@ -26,7 +26,6 @@ #include "qemu/osdep.h" #include "hw/core/cpu.h" -#include "hw/sysbus.h" #include "sysemu/dma.h" #include "hw/loader.h" #include "hw/qdev-properties.h" diff --git a/hw/core/loader.c b/hw/core/loader.c index d3e5f3b423..5b34869a54 100644 --- a/hw/core/loader.c +++ b/hw/core/loader.c @@ -57,7 +57,6 @@ #include "hw/loader.h" #include "hw/nvram/fw_cfg.h" #include "exec/memory.h" -#include "exec/address-spaces.h" #include "hw/boards.h" #include "qemu/cutils.h" #include "sysemu/runstate.h" diff --git a/hw/core/machine-hmp-cmds.c b/hw/core/machine-hmp-cmds.c index 58248cffa3..76b22b00d6 100644 --- a/hw/core/machine-hmp-cmds.c +++ b/hw/core/machine-hmp-cmds.c @@ -110,6 +110,12 @@ void hmp_info_memdev(Monitor *mon, const QDict *qdict) m->value->dump ? "true" : "false"); monitor_printf(mon, " prealloc: %s\n", m->value->prealloc ? "true" : "false"); + monitor_printf(mon, " share: %s\n", + m->value->share ? "true" : "false"); + if (m->value->has_reserve) { + monitor_printf(mon, " reserve: %s\n", + m->value->reserve ? "true" : "false"); + } monitor_printf(mon, " policy: %s\n", HostMemPolicy_str(m->value->policy)); visit_complete(v, &str); diff --git a/hw/core/machine-qmp-cmds.c b/hw/core/machine-qmp-cmds.c index 68a942595a..216fdfaf3a 100644 --- a/hw/core/machine-qmp-cmds.c +++ b/hw/core/machine-qmp-cmds.c @@ -8,7 +8,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "hw/boards.h" #include "qapi/error.h" #include "qapi/qapi-builtin-visit.h" @@ -22,7 +21,6 @@ #include "sysemu/hw_accel.h" #include "sysemu/numa.h" #include "sysemu/runstate.h" -#include "sysemu/sysemu.h" static void cpustate_to_cpuinfo_s390(CpuInfoS390 *info, const CPUState *cpu) { @@ -159,6 +157,7 @@ void qmp_set_numa_node(NumaOptions *cmd, Error **errp) static int query_memdev(Object *obj, void *opaque) { + Error *err = NULL; MemdevList **list = opaque; Memdev *m; QObject *host_nodes; @@ -174,6 +173,13 @@ static int query_memdev(Object *obj, void *opaque) m->merge = object_property_get_bool(obj, "merge", &error_abort); m->dump = object_property_get_bool(obj, "dump", &error_abort); m->prealloc = object_property_get_bool(obj, "prealloc", &error_abort); + m->share = object_property_get_bool(obj, "share", &error_abort); + m->reserve = object_property_get_bool(obj, "reserve", &err); + if (err) { + error_free_or_abort(&err); + } else { + m->has_reserve = true; + } m->policy = object_property_get_enum(obj, "policy", "HostMemPolicy", &error_abort); host_nodes = object_property_get_qobject(obj, diff --git a/hw/core/machine.c b/hw/core/machine.c index 40def78183..54e040587d 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -19,6 +19,7 @@ #include "hw/loader.h" #include "qapi/error.h" #include "qapi/qapi-visit-common.h" +#include "qapi/qapi-visit-machine.h" #include "qapi/visitor.h" #include "hw/sysbus.h" #include "sysemu/cpus.h" @@ -36,6 +37,15 @@ #include "hw/virtio/virtio.h" #include "hw/virtio/virtio-pci.h" +GlobalProperty hw_compat_6_0[] = { + { "gpex-pcihost", "allow-unmapped-accesses", "false" }, + { "i8042", "extended-state", "false"}, + { "nvme-ns", "eui64-default", "off"}, + { "e1000", "init-vet", "off" }, + { "e1000e", "init-vet", "off" }, +}; +const size_t hw_compat_6_0_len = G_N_ELEMENTS(hw_compat_6_0); + GlobalProperty hw_compat_5_2[] = { { "ICH9-LPC", "smm-compat", "on"}, { "PIIX4_PM", "smm-compat", "on"}, @@ -576,7 +586,6 @@ static void machine_set_memdev(Object *obj, const char *value, Error **errp) ms->ram_memdev_id = g_strdup(value); } - static void machine_init_notify(Notifier *notifier, void *data) { MachineState *machine = MACHINE(qdev_get_machine()); @@ -720,7 +729,8 @@ void machine_set_cpu_numa_node(MachineState *machine, if ((numa_info[props->node_id].initiator < MAX_NODES) && (props->node_id != numa_info[props->node_id].initiator)) { error_setg(errp, "The initiator of CPU NUMA node %" PRId64 - " should be itself", props->node_id); + " should be itself (got %" PRIu16 ")", + props->node_id, numa_info[props->node_id].initiator); return; } numa_info[props->node_id].has_cpu = true; @@ -733,69 +743,115 @@ void machine_set_cpu_numa_node(MachineState *machine, } } -static void smp_parse(MachineState *ms, QemuOpts *opts) +static void smp_parse(MachineState *ms, SMPConfiguration *config, Error **errp) { - if (opts) { - unsigned cpus = qemu_opt_get_number(opts, "cpus", 0); - unsigned sockets = qemu_opt_get_number(opts, "sockets", 0); - unsigned cores = qemu_opt_get_number(opts, "cores", 0); - unsigned threads = qemu_opt_get_number(opts, "threads", 0); + unsigned cpus = config->has_cpus ? config->cpus : 0; + unsigned sockets = config->has_sockets ? config->sockets : 0; + unsigned cores = config->has_cores ? config->cores : 0; + unsigned threads = config->has_threads ? config->threads : 0; - /* compute missing values, prefer sockets over cores over threads */ - if (cpus == 0 || sockets == 0) { - cores = cores > 0 ? cores : 1; - threads = threads > 0 ? threads : 1; - if (cpus == 0) { - sockets = sockets > 0 ? sockets : 1; - cpus = cores * threads * sockets; - } else { - ms->smp.max_cpus = - qemu_opt_get_number(opts, "maxcpus", cpus); - sockets = ms->smp.max_cpus / (cores * threads); - } - } else if (cores == 0) { - threads = threads > 0 ? threads : 1; - cores = cpus / (sockets * threads); - cores = cores > 0 ? cores : 1; - } else if (threads == 0) { - threads = cpus / (cores * sockets); - threads = threads > 0 ? threads : 1; - } else if (sockets * cores * threads < cpus) { - error_report("cpu topology: " - "sockets (%u) * cores (%u) * threads (%u) < " - "smp_cpus (%u)", - sockets, cores, threads, cpus); - exit(1); - } - - ms->smp.max_cpus = - qemu_opt_get_number(opts, "maxcpus", cpus); - - if (ms->smp.max_cpus < cpus) { - error_report("maxcpus must be equal to or greater than smp"); - exit(1); - } - - if (sockets * cores * threads != ms->smp.max_cpus) { - error_report("Invalid CPU topology: " - "sockets (%u) * cores (%u) * threads (%u) " - "!= maxcpus (%u)", - sockets, cores, threads, - ms->smp.max_cpus); - exit(1); - } - - ms->smp.cpus = cpus; - ms->smp.cores = cores; - ms->smp.threads = threads; - ms->smp.sockets = sockets; + if (config->has_dies && config->dies != 0 && config->dies != 1) { + error_setg(errp, "dies not supported by this machine's CPU topology"); + return; } - if (ms->smp.cpus > 1) { - Error *blocker = NULL; - error_setg(&blocker, QERR_REPLAY_NOT_SUPPORTED, "smp"); - replay_add_blocker(blocker); + /* compute missing values, prefer sockets over cores over threads */ + if (cpus == 0 || sockets == 0) { + cores = cores > 0 ? cores : 1; + threads = threads > 0 ? threads : 1; + if (cpus == 0) { + sockets = sockets > 0 ? sockets : 1; + cpus = cores * threads * sockets; + } else { + ms->smp.max_cpus = config->has_maxcpus ? config->maxcpus : cpus; + sockets = ms->smp.max_cpus / (cores * threads); + } + } else if (cores == 0) { + threads = threads > 0 ? threads : 1; + cores = cpus / (sockets * threads); + cores = cores > 0 ? cores : 1; + } else if (threads == 0) { + threads = cpus / (cores * sockets); + threads = threads > 0 ? threads : 1; + } else if (sockets * cores * threads < cpus) { + error_setg(errp, "cpu topology: " + "sockets (%u) * cores (%u) * threads (%u) < " + "smp_cpus (%u)", + sockets, cores, threads, cpus); + return; } + + ms->smp.max_cpus = config->has_maxcpus ? config->maxcpus : cpus; + + if (ms->smp.max_cpus < cpus) { + error_setg(errp, "maxcpus must be equal to or greater than smp"); + return; + } + + if (sockets * cores * threads != ms->smp.max_cpus) { + error_setg(errp, "Invalid CPU topology: " + "sockets (%u) * cores (%u) * threads (%u) " + "!= maxcpus (%u)", + sockets, cores, threads, + ms->smp.max_cpus); + return; + } + + ms->smp.cpus = cpus; + ms->smp.cores = cores; + ms->smp.threads = threads; + ms->smp.sockets = sockets; +} + +static void machine_get_smp(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + MachineState *ms = MACHINE(obj); + SMPConfiguration *config = &(SMPConfiguration){ + .has_cores = true, .cores = ms->smp.cores, + .has_sockets = true, .sockets = ms->smp.sockets, + .has_dies = true, .dies = ms->smp.dies, + .has_threads = true, .threads = ms->smp.threads, + .has_cpus = true, .cpus = ms->smp.cpus, + .has_maxcpus = true, .maxcpus = ms->smp.max_cpus, + }; + if (!visit_type_SMPConfiguration(v, name, &config, &error_abort)) { + return; + } +} + +static void machine_set_smp(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + MachineClass *mc = MACHINE_GET_CLASS(obj); + MachineState *ms = MACHINE(obj); + SMPConfiguration *config; + ERRP_GUARD(); + + if (!visit_type_SMPConfiguration(v, name, &config, errp)) { + return; + } + + mc->smp_parse(ms, config, errp); + if (*errp) { + goto out_free; + } + + /* sanity-check smp_cpus and max_cpus against mc */ + if (ms->smp.cpus < mc->min_cpus) { + error_setg(errp, "Invalid SMP CPUs %d. The min CPUs " + "supported by machine '%s' is %d", + ms->smp.cpus, + mc->name, mc->min_cpus); + } else if (ms->smp.max_cpus > mc->max_cpus) { + error_setg(errp, "Invalid SMP CPUs %d. The max CPUs " + "supported by machine '%s' is %d", + current_machine->smp.max_cpus, + mc->name, mc->max_cpus); + } + +out_free: + qapi_free_SMPConfiguration(config); } static void machine_class_init(ObjectClass *oc, void *data) @@ -837,6 +893,12 @@ static void machine_class_init(ObjectClass *oc, void *data) object_class_property_set_description(oc, "dumpdtb", "Dump current dtb to a file and quit"); + object_class_property_add(oc, "smp", "SMPConfiguration", + machine_get_smp, machine_set_smp, + NULL, NULL); + object_class_property_set_description(oc, "smp", + "CPU topology"); + object_class_property_add(oc, "phandle-start", "int", machine_get_phandle_start, machine_set_phandle_start, NULL, NULL); @@ -964,6 +1026,7 @@ static void machine_initfn(Object *obj) ms->smp.cpus = mc->default_cpus; ms->smp.max_cpus = mc->default_cpus; ms->smp.cores = 1; + ms->smp.dies = 1; ms->smp.threads = 1; ms->smp.sockets = 1; } @@ -1124,29 +1187,6 @@ MemoryRegion *machine_consume_memdev(MachineState *machine, return ret; } -bool machine_smp_parse(MachineState *ms, QemuOpts *opts, Error **errp) -{ - MachineClass *mc = MACHINE_GET_CLASS(ms); - - mc->smp_parse(ms, opts); - - /* sanity-check smp_cpus and max_cpus against mc */ - if (ms->smp.cpus < mc->min_cpus) { - error_setg(errp, "Invalid SMP CPUs %d. The min CPUs " - "supported by machine '%s' is %d", - ms->smp.cpus, - mc->name, mc->min_cpus); - return false; - } else if (ms->smp.max_cpus > mc->max_cpus) { - error_setg(errp, "Invalid SMP CPUs %d. The max CPUs " - "supported by machine '%s' is %d", - current_machine->smp.max_cpus, - mc->name, mc->max_cpus); - return false; - } - return true; -} - void machine_run_board_init(MachineState *machine) { MachineClass *machine_class = MACHINE_GET_CLASS(machine); @@ -1229,6 +1269,7 @@ void machine_run_board_init(MachineState *machine) "on", false); } + accel_init_interfaces(ACCEL_GET_CLASS(machine->accelerator)); machine_class->init(machine); phase_advance(PHASE_MACHINE_INITIALIZED); } diff --git a/hw/core/meson.build b/hw/core/meson.build index 59f1605bb0..18f44fb7c2 100644 --- a/hw/core/meson.build +++ b/hw/core/meson.build @@ -13,7 +13,7 @@ hwcore_files = files( 'qdev-clock.c', ) -common_ss.add(files('cpu.c')) +common_ss.add(files('cpu-common.c')) common_ss.add(when: 'CONFIG_FITLOADER', if_true: files('loader-fit.c')) common_ss.add(when: 'CONFIG_GENERIC_LOADER', if_true: files('generic-loader.c')) common_ss.add(when: ['CONFIG_GUEST_LOADER', fdt], if_true: files('guest-loader.c')) @@ -25,6 +25,7 @@ common_ss.add(when: 'CONFIG_SPLIT_IRQ', if_true: files('split-irq.c')) common_ss.add(when: 'CONFIG_XILINX_AXI', if_true: files('stream.c')) softmmu_ss.add(files( + 'cpu-sysemu.c', 'fw-path-provider.c', 'loader.c', 'machine-hmp-cmds.c', diff --git a/hw/core/null-machine.c b/hw/core/null-machine.c index 7e693523d7..f586a4bef5 100644 --- a/hw/core/null-machine.c +++ b/hw/core/null-machine.c @@ -14,7 +14,6 @@ #include "qemu/osdep.h" #include "qemu/error-report.h" #include "hw/boards.h" -#include "sysemu/sysemu.h" #include "exec/address-spaces.h" #include "hw/core/cpu.h" diff --git a/hw/core/numa.c b/hw/core/numa.c index 68cee65f61..510d096a88 100644 --- a/hw/core/numa.c +++ b/hw/core/numa.c @@ -26,7 +26,6 @@ #include "qemu/units.h" #include "sysemu/hostmem.h" #include "sysemu/numa.h" -#include "sysemu/sysemu.h" #include "exec/cpu-common.h" #include "exec/ramlist.h" #include "qemu/bitmap.h" @@ -89,6 +88,29 @@ static void parse_numa_node(MachineState *ms, NumaNodeOptions *node, return; } + /* + * If not set the initiator, set it to MAX_NODES. And if + * HMAT is enabled and this node has no cpus, QEMU will raise error. + */ + numa_info[nodenr].initiator = MAX_NODES; + if (node->has_initiator) { + if (!ms->numa_state->hmat_enabled) { + error_setg(errp, "ACPI Heterogeneous Memory Attribute Table " + "(HMAT) is disabled, enable it with -machine hmat=on " + "before using any of hmat specific options"); + return; + } + + if (node->initiator >= MAX_NODES) { + error_report("The initiator id %" PRIu16 " expects an integer " + "between 0 and %d", node->initiator, + MAX_NODES - 1); + return; + } + + numa_info[nodenr].initiator = node->initiator; + } + for (cpus = node->cpus; cpus; cpus = cpus->next) { CpuInstanceProperties props; if (cpus->value >= max_cpus) { @@ -143,28 +165,6 @@ static void parse_numa_node(MachineState *ms, NumaNodeOptions *node, numa_info[nodenr].node_memdev = MEMORY_BACKEND(o); } - /* - * If not set the initiator, set it to MAX_NODES. And if - * HMAT is enabled and this node has no cpus, QEMU will raise error. - */ - numa_info[nodenr].initiator = MAX_NODES; - if (node->has_initiator) { - if (!ms->numa_state->hmat_enabled) { - error_setg(errp, "ACPI Heterogeneous Memory Attribute Table " - "(HMAT) is disabled, enable it with -machine hmat=on " - "before using any of hmat specific options"); - return; - } - - if (node->initiator >= MAX_NODES) { - error_report("The initiator id %" PRIu16 " expects an integer " - "between 0 and %d", node->initiator, - MAX_NODES - 1); - return; - } - - numa_info[nodenr].initiator = node->initiator; - } numa_info[nodenr].present = true; max_numa_nodeid = MAX(max_numa_nodeid, nodenr + 1); ms->numa_state->num_nodes++; @@ -803,9 +803,27 @@ void query_numa_node_mem(NumaNodeMem node_mem[], MachineState *ms) } } +static int ram_block_notify_add_single(RAMBlock *rb, void *opaque) +{ + const ram_addr_t max_size = qemu_ram_get_max_length(rb); + const ram_addr_t size = qemu_ram_get_used_length(rb); + void *host = qemu_ram_get_host_addr(rb); + RAMBlockNotifier *notifier = opaque; + + if (host) { + notifier->ram_block_added(notifier, host, size, max_size); + } + return 0; +} + void ram_block_notifier_add(RAMBlockNotifier *n) { QLIST_INSERT_HEAD(&ram_list.ramblock_notifiers, n, next); + + /* Notify about all existing ram blocks. */ + if (n->ram_block_added) { + qemu_ram_foreach_block(ram_block_notify_add_single, n); + } } void ram_block_notifier_remove(RAMBlockNotifier *n) @@ -813,20 +831,35 @@ void ram_block_notifier_remove(RAMBlockNotifier *n) QLIST_REMOVE(n, next); } -void ram_block_notify_add(void *host, size_t size) +void ram_block_notify_add(void *host, size_t size, size_t max_size) { RAMBlockNotifier *notifier; QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) { - notifier->ram_block_added(notifier, host, size); + if (notifier->ram_block_added) { + notifier->ram_block_added(notifier, host, size, max_size); + } } } -void ram_block_notify_remove(void *host, size_t size) +void ram_block_notify_remove(void *host, size_t size, size_t max_size) { RAMBlockNotifier *notifier; QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) { - notifier->ram_block_removed(notifier, host, size); + if (notifier->ram_block_removed) { + notifier->ram_block_removed(notifier, host, size, max_size); + } + } +} + +void ram_block_notify_resize(void *host, size_t old_size, size_t new_size) +{ + RAMBlockNotifier *notifier; + + QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) { + if (notifier->ram_block_resized) { + notifier->ram_block_resized(notifier, host, old_size, new_size); + } } } diff --git a/hw/cris/axis_dev88.c b/hw/cris/axis_dev88.c index af5a0e3517..d82050d927 100644 --- a/hw/cris/axis_dev88.c +++ b/hw/cris/axis_dev88.c @@ -34,7 +34,6 @@ #include "hw/loader.h" #include "elf.h" #include "boot.h" -#include "exec/address-spaces.h" #include "sysemu/qtest.h" #include "sysemu/sysemu.h" diff --git a/hw/display/Kconfig b/hw/display/Kconfig index ca46b5830e..a2306b67d8 100644 --- a/hw/display/Kconfig +++ b/hw/display/Kconfig @@ -72,10 +72,6 @@ config BLIZZARD config FRAMEBUFFER bool -config MILKYMIST_TMU2 - bool - depends on OPENGL && X11 - config SM501 bool select I2C diff --git a/hw/display/ati.c b/hw/display/ati.c index 4c3ad8f47b..31f22754dc 100644 --- a/hw/display/ati.c +++ b/hw/display/ati.c @@ -968,7 +968,7 @@ static void ati_vga_realize(PCIDevice *dev, Error **errp) I2CBus *i2cbus = i2c_init_bus(DEVICE(s), "ati-vga.ddc"); bitbang_i2c_init(&s->bbi2c, i2cbus); I2CSlave *i2cddc = I2C_SLAVE(qdev_new(TYPE_I2CDDC)); - i2c_set_slave_address(i2cddc, 0x50); + i2c_slave_set_address(i2cddc, 0x50); qdev_realize_and_unref(DEVICE(i2cddc), BUS(i2cbus), &error_abort); /* mmio register space */ diff --git a/hw/display/edid-generate.c b/hw/display/edid-generate.c index a1bea9a3aa..f2b874d5e3 100644 --- a/hw/display/edid-generate.c +++ b/hw/display/edid-generate.c @@ -45,6 +45,35 @@ static const struct edid_mode { { .xres = 640, .yres = 480, .byte = 35, .bit = 5 }, }; +typedef struct Timings { + uint32_t xfront; + uint32_t xsync; + uint32_t xblank; + + uint32_t yfront; + uint32_t ysync; + uint32_t yblank; + + uint64_t clock; +} Timings; + +static void generate_timings(Timings *timings, uint32_t refresh_rate, + uint32_t xres, uint32_t yres) +{ + /* pull some realistic looking timings out of thin air */ + timings->xfront = xres * 25 / 100; + timings->xsync = xres * 3 / 100; + timings->xblank = xres * 35 / 100; + + timings->yfront = yres * 5 / 1000; + timings->ysync = yres * 5 / 1000; + timings->yblank = yres * 35 / 1000; + + timings->clock = ((uint64_t)refresh_rate * + (xres + timings->xblank) * + (yres + timings->yblank)) / 10000000; +} + static void edid_ext_dta(uint8_t *dta) { dta[0] = 0x02; @@ -130,20 +159,39 @@ static void edid_fill_modes(uint8_t *edid, uint8_t *xtra3, uint8_t *dta, } } -static void edid_checksum(uint8_t *edid) +static void edid_checksum(uint8_t *edid, size_t len) { uint32_t sum = 0; int i; - for (i = 0; i < 127; i++) { + for (i = 0; i < len; i++) { sum += edid[i]; } sum &= 0xff; if (sum) { - edid[127] = 0x100 - sum; + edid[len] = 0x100 - sum; } } +static uint8_t *edid_desc_next(uint8_t *edid, uint8_t *dta, uint8_t *desc) +{ + if (desc == NULL) { + return NULL; + } + if (desc + 18 + 18 < edid + 127) { + return desc + 18; + } + if (dta) { + if (desc < edid + 127) { + return dta + dta[2]; + } + if (desc + 18 + 18 < dta + 127) { + return desc + 18; + } + } + return NULL; +} + static void edid_desc_type(uint8_t *desc, uint8_t type) { desc[0] = 0; @@ -181,8 +229,8 @@ static void edid_desc_ranges(uint8_t *desc) desc[7] = 30; desc[8] = 160; - /* max dot clock (1200 MHz) */ - desc[9] = 1200 / 10; + /* max dot clock (2550 MHz) */ + desc[9] = 2550 / 10; /* no extended timing information */ desc[10] = 0x01; @@ -204,42 +252,33 @@ static void edid_desc_dummy(uint8_t *desc) edid_desc_type(desc, 0x10); } -static void edid_desc_timing(uint8_t *desc, +static void edid_desc_timing(uint8_t *desc, uint32_t refresh_rate, uint32_t xres, uint32_t yres, uint32_t xmm, uint32_t ymm) { - /* pull some realistic looking timings out of thin air */ - uint32_t xfront = xres * 25 / 100; - uint32_t xsync = xres * 3 / 100; - uint32_t xblank = xres * 35 / 100; - - uint32_t yfront = yres * 5 / 1000; - uint32_t ysync = yres * 5 / 1000; - uint32_t yblank = yres * 35 / 1000; - - uint32_t clock = 75 * (xres + xblank) * (yres + yblank); - - stl_le_p(desc, clock / 10000); + Timings timings; + generate_timings(&timings, refresh_rate, xres, yres); + stl_le_p(desc, timings.clock); desc[2] = xres & 0xff; - desc[3] = xblank & 0xff; + desc[3] = timings.xblank & 0xff; desc[4] = (((xres & 0xf00) >> 4) | - ((xblank & 0xf00) >> 8)); + ((timings.xblank & 0xf00) >> 8)); desc[5] = yres & 0xff; - desc[6] = yblank & 0xff; + desc[6] = timings.yblank & 0xff; desc[7] = (((yres & 0xf00) >> 4) | - ((yblank & 0xf00) >> 8)); + ((timings.yblank & 0xf00) >> 8)); - desc[8] = xfront & 0xff; - desc[9] = xsync & 0xff; + desc[8] = timings.xfront & 0xff; + desc[9] = timings.xsync & 0xff; - desc[10] = (((yfront & 0x00f) << 4) | - ((ysync & 0x00f) << 0)); - desc[11] = (((xfront & 0x300) >> 2) | - ((xsync & 0x300) >> 4) | - ((yfront & 0x030) >> 2) | - ((ysync & 0x030) >> 4)); + desc[10] = (((timings.yfront & 0x00f) << 4) | + ((timings.ysync & 0x00f) << 0)); + desc[11] = (((timings.xfront & 0x300) >> 2) | + ((timings.xsync & 0x300) >> 4) | + ((timings.yfront & 0x030) >> 2) | + ((timings.ysync & 0x030) >> 4)); desc[12] = xmm & 0xff; desc[13] = ymm & 0xff; @@ -297,14 +336,61 @@ uint32_t qemu_edid_dpi_to_mm(uint32_t dpi, uint32_t res) return res * 254 / 10 / dpi; } +static void init_displayid(uint8_t *did) +{ + did[0] = 0x70; /* display id extension */ + did[1] = 0x13; /* version 1.3 */ + did[2] = 4; /* length */ + did[3] = 0x03; /* product type (0x03 == standalone display device) */ + edid_checksum(did + 1, did[2] + 4); +} + +static void qemu_displayid_generate(uint8_t *did, uint32_t refresh_rate, + uint32_t xres, uint32_t yres, + uint32_t xmm, uint32_t ymm) +{ + Timings timings; + generate_timings(&timings, refresh_rate, xres, yres); + + did[0] = 0x70; /* display id extension */ + did[1] = 0x13; /* version 1.3 */ + did[2] = 23; /* length */ + did[3] = 0x03; /* product type (0x03 == standalone display device) */ + + did[5] = 0x03; /* Detailed Timings Data Block */ + did[6] = 0x00; /* revision */ + did[7] = 0x14; /* block length */ + + did[8] = timings.clock & 0xff; + did[9] = (timings.clock & 0xff00) >> 8; + did[10] = (timings.clock & 0xff0000) >> 16; + + did[11] = 0x88; /* leave aspect ratio undefined */ + + stw_le_p(did + 12, 0xffff & (xres - 1)); + stw_le_p(did + 14, 0xffff & (timings.xblank - 1)); + stw_le_p(did + 16, 0xffff & (timings.xfront - 1)); + stw_le_p(did + 18, 0xffff & (timings.xsync - 1)); + + stw_le_p(did + 20, 0xffff & (yres - 1)); + stw_le_p(did + 22, 0xffff & (timings.yblank - 1)); + stw_le_p(did + 24, 0xffff & (timings.yfront - 1)); + stw_le_p(did + 26, 0xffff & (timings.ysync - 1)); + + edid_checksum(did + 1, did[2] + 4); +} + void qemu_edid_generate(uint8_t *edid, size_t size, qemu_edid_info *info) { - uint32_t desc = 54; + uint8_t *desc = edid + 54; uint8_t *xtra3 = NULL; uint8_t *dta = NULL; + uint8_t *did = NULL; uint32_t width_mm, height_mm; + uint32_t refresh_rate = info->refresh_rate ? info->refresh_rate : 75000; uint32_t dpi = 100; /* if no width_mm/height_mm */ + uint32_t large_screen = 0; /* =============== set defaults =============== */ @@ -320,6 +406,9 @@ void qemu_edid_generate(uint8_t *edid, size_t size, if (!info->prefy) { info->prefy = 768; } + if (info->prefx >= 4096 || info->prefy >= 4096) { + large_screen = 1; + } if (info->width_mm && info->height_mm) { width_mm = info->width_mm; height_mm = info->height_mm; @@ -337,6 +426,12 @@ void qemu_edid_generate(uint8_t *edid, size_t size, edid_ext_dta(dta); } + if (size >= 384 && large_screen) { + did = edid + 256; + edid[126]++; + init_displayid(did); + } + /* =============== header information =============== */ /* fixed */ @@ -401,40 +496,55 @@ void qemu_edid_generate(uint8_t *edid, size_t size, /* =============== descriptor blocks =============== */ - edid_desc_timing(edid + desc, info->prefx, info->prefy, - width_mm, height_mm); - desc += 18; - - edid_desc_ranges(edid + desc); - desc += 18; - - if (info->name) { - edid_desc_text(edid + desc, 0xfc, info->name); - desc += 18; + if (!large_screen) { + /* The DTD section has only 12 bits to store the resolution */ + edid_desc_timing(desc, refresh_rate, info->prefx, info->prefy, + width_mm, height_mm); + desc = edid_desc_next(edid, dta, desc); } - if (info->serial) { - edid_desc_text(edid + desc, 0xff, info->serial); - desc += 18; + xtra3 = desc; + edid_desc_xtra3_std(xtra3); + desc = edid_desc_next(edid, dta, desc); + edid_fill_modes(edid, xtra3, dta, info->maxx, info->maxy); + /* + * dta video data block is finished at thus point, + * so dta descriptor offsets don't move any more. + */ + + edid_desc_ranges(desc); + desc = edid_desc_next(edid, dta, desc); + + if (desc && info->name) { + edid_desc_text(desc, 0xfc, info->name); + desc = edid_desc_next(edid, dta, desc); } - if (desc < 126) { - xtra3 = edid + desc; - edid_desc_xtra3_std(xtra3); - desc += 18; + if (desc && info->serial) { + edid_desc_text(desc, 0xff, info->serial); + desc = edid_desc_next(edid, dta, desc); } - while (desc < 126) { - edid_desc_dummy(edid + desc); - desc += 18; + while (desc) { + edid_desc_dummy(desc); + desc = edid_desc_next(edid, dta, desc); + } + + /* =============== display id extensions =============== */ + + if (did && large_screen) { + qemu_displayid_generate(did, refresh_rate, info->prefx, info->prefy, + width_mm, height_mm); } /* =============== finish up =============== */ - edid_fill_modes(edid, xtra3, dta, info->maxx, info->maxy); - edid_checksum(edid); + edid_checksum(edid, 127); if (dta) { - edid_checksum(dta); + edid_checksum(dta, 127); + } + if (did) { + edid_checksum(did, 127); } } diff --git a/hw/display/g364fb.c b/hw/display/g364fb.c index 8f1725432c..caca86d773 100644 --- a/hw/display/g364fb.c +++ b/hw/display/g364fb.c @@ -22,6 +22,7 @@ #include "hw/hw.h" #include "hw/irq.h" #include "hw/qdev-properties.h" +#include "qapi/error.h" #include "qemu/error-report.h" #include "qemu/module.h" #include "ui/console.h" @@ -33,7 +34,6 @@ typedef struct G364State { /* hardware */ - uint8_t *vram; uint32_t vram_size; qemu_irq irq; MemoryRegion mem_vram; @@ -125,7 +125,7 @@ static void g364fb_draw_graphic8(G364State *s) xcursor = ycursor = -65; } - vram = s->vram + s->top_of_screen; + vram = memory_region_get_ram_ptr(&s->mem_vram) + s->top_of_screen; /* XXX: out of range in vram? */ data_display = dd = surface_data(surface); snap = memory_region_snapshot_and_clear_dirty(&s->mem_vram, 0, s->vram_size, @@ -274,6 +274,8 @@ static inline void g364fb_invalidate_display(void *opaque) static void g364fb_reset(G364State *s) { + uint8_t *vram = memory_region_get_ram_ptr(&s->mem_vram); + qemu_irq_lower(s->irq); memset(s->color_palette, 0, sizeof(s->color_palette)); @@ -283,7 +285,7 @@ static void g364fb_reset(G364State *s) s->ctla = 0; s->top_of_screen = 0; s->width = s->height = 0; - memset(s->vram, 0, s->vram_size); + memset(vram, 0, s->vram_size); g364fb_invalidate_display(s); } @@ -450,11 +452,10 @@ static int g364fb_post_load(void *opaque, int version_id) static const VMStateDescription vmstate_g364fb = { .name = "g364fb", - .version_id = 1, - .minimum_version_id = 1, + .version_id = 2, + .minimum_version_id = 2, .post_load = g364fb_post_load, .fields = (VMStateField[]) { - VMSTATE_VBUFFER_UINT32(vram, G364State, 1, NULL, vram_size), VMSTATE_BUFFER_UNSAFE(color_palette, G364State, 0, 256 * 3), VMSTATE_BUFFER_UNSAFE(cursor_palette, G364State, 0, 9), VMSTATE_UINT16_ARRAY(cursor, G364State, 512), @@ -474,15 +475,12 @@ static const GraphicHwOps g364fb_ops = { static void g364fb_init(DeviceState *dev, G364State *s) { - s->vram = g_malloc0(s->vram_size); - s->con = graphic_console_init(dev, 0, &g364fb_ops, s); memory_region_init_io(&s->mem_ctrl, OBJECT(dev), &g364fb_ctrl_ops, s, "ctrl", 0x180000); - memory_region_init_ram_ptr(&s->mem_vram, NULL, "vram", - s->vram_size, s->vram); - vmstate_register_ram(&s->mem_vram, dev); + memory_region_init_ram(&s->mem_vram, NULL, "g364fb.vram", s->vram_size, + &error_fatal); memory_region_set_log(&s->mem_vram, true, DIRTY_MEMORY_VGA); } @@ -519,6 +517,16 @@ static Property g364fb_sysbus_properties[] = { DEFINE_PROP_END_OF_LIST(), }; +static const VMStateDescription vmstate_g364fb_sysbus = { + .name = "g364fb-sysbus", + .version_id = 2, + .minimum_version_id = 2, + .fields = (VMStateField[]) { + VMSTATE_STRUCT(g364, G364SysBusState, 2, vmstate_g364fb, G364State), + VMSTATE_END_OF_LIST() + } +}; + static void g364fb_sysbus_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -527,7 +535,7 @@ static void g364fb_sysbus_class_init(ObjectClass *klass, void *data) set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories); dc->desc = "G364 framebuffer"; dc->reset = g364fb_sysbus_reset; - dc->vmsd = &vmstate_g364fb; + dc->vmsd = &vmstate_g364fb_sysbus; device_class_set_props(dc, g364fb_sysbus_properties); } diff --git a/hw/display/macfb.c b/hw/display/macfb.c index ff8bdb846b..d8183b9bbd 100644 --- a/hw/display/macfb.c +++ b/hw/display/macfb.c @@ -450,6 +450,7 @@ static void macfb_nubus_class_init(ObjectClass *klass, void *data) dc->desc = "Nubus Macintosh framebuffer"; dc->reset = macfb_nubus_reset; dc->vmsd = &vmstate_macfb; + set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories); device_class_set_props(dc, macfb_nubus_properties); } diff --git a/hw/display/meson.build b/hw/display/meson.build index 9d79e3951d..1e6b707d3c 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -48,7 +48,6 @@ endif softmmu_ss.add(when: 'CONFIG_DPCD', if_true: files('dpcd.c')) softmmu_ss.add(when: 'CONFIG_XLNX_ZYNQMP_ARM', if_true: files('xlnx_dp.c')) -softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-vgafb.c')) softmmu_ss.add(when: 'CONFIG_ARTIST', if_true: files('artist.c')) softmmu_ss.add(when: [pixman, 'CONFIG_ATI_VGA'], if_true: files('ati.c', 'ati_2d.c', 'ati_dbg.c')) @@ -56,11 +55,15 @@ softmmu_ss.add(when: [pixman, 'CONFIG_ATI_VGA'], if_true: files('ati.c', 'ati_2d if config_all_devices.has_key('CONFIG_VIRTIO_GPU') virtio_gpu_ss = ss.source_set() virtio_gpu_ss.add(when: 'CONFIG_VIRTIO_GPU', - if_true: [files('virtio-gpu-base.c', 'virtio-gpu.c'), pixman, virgl]) - virtio_gpu_ss.add(when: ['CONFIG_VIRTIO_GPU', 'CONFIG_VIRGL'], - if_true: [files('virtio-gpu-3d.c'), pixman, virgl]) + if_true: [files('virtio-gpu-base.c', 'virtio-gpu.c'), pixman]) + virtio_gpu_ss.add(when: 'CONFIG_LINUX', if_true: files('virtio-gpu-udmabuf.c')) virtio_gpu_ss.add(when: 'CONFIG_VHOST_USER_GPU', if_true: files('vhost-user-gpu.c')) hw_display_modules += {'virtio-gpu': virtio_gpu_ss} + + virtio_gpu_gl_ss = ss.source_set() + virtio_gpu_gl_ss.add(when: ['CONFIG_VIRTIO_GPU', virgl, opengl], + if_true: [files('virtio-gpu-gl.c', 'virtio-gpu-virgl.c'), pixman, virgl]) + hw_display_modules += {'virtio-gpu-gl': virtio_gpu_gl_ss} endif if config_all_devices.has_key('CONFIG_VIRTIO_PCI') @@ -70,6 +73,11 @@ if config_all_devices.has_key('CONFIG_VIRTIO_PCI') virtio_gpu_pci_ss.add(when: ['CONFIG_VHOST_USER_GPU', 'CONFIG_VIRTIO_PCI'], if_true: files('vhost-user-gpu-pci.c')) hw_display_modules += {'virtio-gpu-pci': virtio_gpu_pci_ss} + + virtio_gpu_pci_gl_ss = ss.source_set() + virtio_gpu_pci_gl_ss.add(when: ['CONFIG_VIRTIO_GPU', 'CONFIG_VIRTIO_PCI', virgl, opengl], + if_true: [files('virtio-gpu-pci-gl.c'), pixman]) + hw_display_modules += {'virtio-gpu-pci-gl': virtio_gpu_pci_gl_ss} endif if config_all_devices.has_key('CONFIG_VIRTIO_VGA') @@ -79,9 +87,13 @@ if config_all_devices.has_key('CONFIG_VIRTIO_VGA') virtio_vga_ss.add(when: 'CONFIG_VHOST_USER_VGA', if_true: files('vhost-user-vga.c')) hw_display_modules += {'virtio-vga': virtio_vga_ss} + + virtio_vga_gl_ss = ss.source_set() + virtio_vga_gl_ss.add(when: ['CONFIG_VIRTIO_VGA', virgl, opengl], + if_true: [files('virtio-vga-gl.c'), pixman]) + hw_display_modules += {'virtio-vga-gl': virtio_vga_gl_ss} endif -specific_ss.add(when: [x11, opengl, 'CONFIG_MILKYMIST_TMU2'], if_true: files('milkymist-tmu2.c')) specific_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_lcdc.c')) modules += { 'hw-display': hw_display_modules } diff --git a/hw/display/milkymist-tmu2.c b/hw/display/milkymist-tmu2.c deleted file mode 100644 index 02a28c807b..0000000000 --- a/hw/display/milkymist-tmu2.c +++ /dev/null @@ -1,551 +0,0 @@ -/* - * QEMU model of the Milkymist texture mapping unit. - * - * Copyright (c) 2010 Michael Walle - * Copyright (c) 2010 Sebastien Bourdeauducq - * - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://milkymist.walle.cc/socdoc/tmu2.pdf - * - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "qapi/error.h" -#include "qemu/error-report.h" -#include "qemu/module.h" -#include "qapi/error.h" -#include "hw/display/milkymist_tmu2.h" - -#include -#include -#include -#include "qom/object.h" - -enum { - R_CTL = 0, - R_HMESHLAST, - R_VMESHLAST, - R_BRIGHTNESS, - R_CHROMAKEY, - R_VERTICESADDR, - R_TEXFBUF, - R_TEXHRES, - R_TEXVRES, - R_TEXHMASK, - R_TEXVMASK, - R_DSTFBUF, - R_DSTHRES, - R_DSTVRES, - R_DSTHOFFSET, - R_DSTVOFFSET, - R_DSTSQUAREW, - R_DSTSQUAREH, - R_ALPHA, - R_MAX -}; - -enum { - CTL_START_BUSY = (1<<0), - CTL_CHROMAKEY = (1<<1), -}; - -enum { - MAX_BRIGHTNESS = 63, - MAX_ALPHA = 63, -}; - -enum { - MESH_MAXSIZE = 128, -}; - -struct vertex { - int x; - int y; -} QEMU_PACKED; - -#define TYPE_MILKYMIST_TMU2 "milkymist-tmu2" -OBJECT_DECLARE_SIMPLE_TYPE(MilkymistTMU2State, MILKYMIST_TMU2) - -struct MilkymistTMU2State { - SysBusDevice parent_obj; - - MemoryRegion regs_region; - Chardev *chr; - qemu_irq irq; - - uint32_t regs[R_MAX]; - - Display *dpy; - GLXFBConfig glx_fb_config; - GLXContext glx_context; -}; - -static const int glx_fbconfig_attr[] = { - GLX_GREEN_SIZE, 5, - GLX_GREEN_SIZE, 6, - GLX_BLUE_SIZE, 5, - None -}; - -static int tmu2_glx_init(MilkymistTMU2State *s) -{ - GLXFBConfig *configs; - int nelements; - - s->dpy = XOpenDisplay(NULL); /* FIXME: call XCloseDisplay() */ - if (s->dpy == NULL) { - return 1; - } - - configs = glXChooseFBConfig(s->dpy, 0, glx_fbconfig_attr, &nelements); - if (configs == NULL) { - return 1; - } - - s->glx_fb_config = *configs; - XFree(configs); - - /* FIXME: call glXDestroyContext() */ - s->glx_context = glXCreateNewContext(s->dpy, s->glx_fb_config, - GLX_RGBA_TYPE, NULL, 1); - if (s->glx_context == NULL) { - return 1; - } - - return 0; -} - -static void tmu2_gl_map(struct vertex *mesh, int texhres, int texvres, - int hmeshlast, int vmeshlast, int ho, int vo, int sw, int sh) -{ - int x, y; - int x0, y0, x1, y1; - int u0, v0, u1, v1, u2, v2, u3, v3; - double xscale = 1.0 / ((double)(64 * texhres)); - double yscale = 1.0 / ((double)(64 * texvres)); - - glLoadIdentity(); - glTranslatef(ho, vo, 0); - glEnable(GL_TEXTURE_2D); - glBegin(GL_QUADS); - - for (y = 0; y < vmeshlast; y++) { - y0 = y * sh; - y1 = y0 + sh; - for (x = 0; x < hmeshlast; x++) { - x0 = x * sw; - x1 = x0 + sw; - - u0 = be32_to_cpu(mesh[MESH_MAXSIZE * y + x].x); - v0 = be32_to_cpu(mesh[MESH_MAXSIZE * y + x].y); - u1 = be32_to_cpu(mesh[MESH_MAXSIZE * y + x + 1].x); - v1 = be32_to_cpu(mesh[MESH_MAXSIZE * y + x + 1].y); - u2 = be32_to_cpu(mesh[MESH_MAXSIZE * (y + 1) + x + 1].x); - v2 = be32_to_cpu(mesh[MESH_MAXSIZE * (y + 1) + x + 1].y); - u3 = be32_to_cpu(mesh[MESH_MAXSIZE * (y + 1) + x].x); - v3 = be32_to_cpu(mesh[MESH_MAXSIZE * (y + 1) + x].y); - - glTexCoord2d(((double)u0) * xscale, ((double)v0) * yscale); - glVertex3i(x0, y0, 0); - glTexCoord2d(((double)u1) * xscale, ((double)v1) * yscale); - glVertex3i(x1, y0, 0); - glTexCoord2d(((double)u2) * xscale, ((double)v2) * yscale); - glVertex3i(x1, y1, 0); - glTexCoord2d(((double)u3) * xscale, ((double)v3) * yscale); - glVertex3i(x0, y1, 0); - } - } - - glEnd(); -} - -static void tmu2_start(MilkymistTMU2State *s) -{ - int pbuffer_attrib[6] = { - GLX_PBUFFER_WIDTH, - 0, - GLX_PBUFFER_HEIGHT, - 0, - GLX_PRESERVED_CONTENTS, - True - }; - - GLXPbuffer pbuffer; - GLuint texture; - void *fb; - hwaddr fb_len; - void *mesh; - hwaddr mesh_len; - float m; - - trace_milkymist_tmu2_start(); - - /* Create and set up a suitable OpenGL context */ - pbuffer_attrib[1] = s->regs[R_DSTHRES]; - pbuffer_attrib[3] = s->regs[R_DSTVRES]; - pbuffer = glXCreatePbuffer(s->dpy, s->glx_fb_config, pbuffer_attrib); - glXMakeContextCurrent(s->dpy, pbuffer, pbuffer, s->glx_context); - - /* Fixup endianness. TODO: would it work on BE hosts? */ - glPixelStorei(GL_UNPACK_SWAP_BYTES, 1); - glPixelStorei(GL_PACK_SWAP_BYTES, 1); - - /* Row alignment */ - glPixelStorei(GL_UNPACK_ALIGNMENT, 2); - glPixelStorei(GL_PACK_ALIGNMENT, 2); - - /* Read the QEMU source framebuffer into an OpenGL texture */ - glGenTextures(1, &texture); - glBindTexture(GL_TEXTURE_2D, texture); - fb_len = 2ULL * s->regs[R_TEXHRES] * s->regs[R_TEXVRES]; - fb = cpu_physical_memory_map(s->regs[R_TEXFBUF], &fb_len, false); - if (fb == NULL) { - glDeleteTextures(1, &texture); - glXMakeContextCurrent(s->dpy, None, None, NULL); - glXDestroyPbuffer(s->dpy, pbuffer); - return; - } - glTexImage2D(GL_TEXTURE_2D, 0, 3, s->regs[R_TEXHRES], s->regs[R_TEXVRES], - 0, GL_RGB, GL_UNSIGNED_SHORT_5_6_5, fb); - cpu_physical_memory_unmap(fb, fb_len, 0, fb_len); - - /* Set up texturing options */ - /* WARNING: - * Many cases of TMU2 masking are not supported by OpenGL. - * We only implement the most common ones: - * - full bilinear filtering vs. nearest texel - * - texture clamping vs. texture wrapping - */ - if ((s->regs[R_TEXHMASK] & 0x3f) > 0x20) { - glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR); - glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR); - } else { - glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST); - glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST); - } - if ((s->regs[R_TEXHMASK] >> 6) & s->regs[R_TEXHRES]) { - glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_CLAMP); - } else { - glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_REPEAT); - } - if ((s->regs[R_TEXVMASK] >> 6) & s->regs[R_TEXVRES]) { - glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP); - } else { - glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_REPEAT); - } - - /* Translucency and decay */ - glEnable(GL_BLEND); - glBlendFunc(GL_SRC_ALPHA, GL_ONE_MINUS_SRC_ALPHA); - m = (float)(s->regs[R_BRIGHTNESS] + 1) / 64.0f; - glColor4f(m, m, m, (float)(s->regs[R_ALPHA] + 1) / 64.0f); - - /* Read the QEMU dest. framebuffer into the OpenGL framebuffer */ - fb_len = 2ULL * s->regs[R_DSTHRES] * s->regs[R_DSTVRES]; - fb = cpu_physical_memory_map(s->regs[R_DSTFBUF], &fb_len, false); - if (fb == NULL) { - glDeleteTextures(1, &texture); - glXMakeContextCurrent(s->dpy, None, None, NULL); - glXDestroyPbuffer(s->dpy, pbuffer); - return; - } - - glDrawPixels(s->regs[R_DSTHRES], s->regs[R_DSTVRES], GL_RGB, - GL_UNSIGNED_SHORT_5_6_5, fb); - cpu_physical_memory_unmap(fb, fb_len, 0, fb_len); - glViewport(0, 0, s->regs[R_DSTHRES], s->regs[R_DSTVRES]); - glMatrixMode(GL_PROJECTION); - glLoadIdentity(); - glOrtho(0.0, s->regs[R_DSTHRES], 0.0, s->regs[R_DSTVRES], -1.0, 1.0); - glMatrixMode(GL_MODELVIEW); - - /* Map the texture */ - mesh_len = MESH_MAXSIZE*MESH_MAXSIZE*sizeof(struct vertex); - mesh = cpu_physical_memory_map(s->regs[R_VERTICESADDR], &mesh_len, false); - if (mesh == NULL) { - glDeleteTextures(1, &texture); - glXMakeContextCurrent(s->dpy, None, None, NULL); - glXDestroyPbuffer(s->dpy, pbuffer); - return; - } - - tmu2_gl_map((struct vertex *)mesh, - s->regs[R_TEXHRES], s->regs[R_TEXVRES], - s->regs[R_HMESHLAST], s->regs[R_VMESHLAST], - s->regs[R_DSTHOFFSET], s->regs[R_DSTVOFFSET], - s->regs[R_DSTSQUAREW], s->regs[R_DSTSQUAREH]); - cpu_physical_memory_unmap(mesh, mesh_len, 0, mesh_len); - - /* Write back the OpenGL framebuffer to the QEMU framebuffer */ - fb_len = 2ULL * s->regs[R_DSTHRES] * s->regs[R_DSTVRES]; - fb = cpu_physical_memory_map(s->regs[R_DSTFBUF], &fb_len, true); - if (fb == NULL) { - glDeleteTextures(1, &texture); - glXMakeContextCurrent(s->dpy, None, None, NULL); - glXDestroyPbuffer(s->dpy, pbuffer); - return; - } - - glReadPixels(0, 0, s->regs[R_DSTHRES], s->regs[R_DSTVRES], GL_RGB, - GL_UNSIGNED_SHORT_5_6_5, fb); - cpu_physical_memory_unmap(fb, fb_len, 1, fb_len); - - /* Free OpenGL allocs */ - glDeleteTextures(1, &texture); - glXMakeContextCurrent(s->dpy, None, None, NULL); - glXDestroyPbuffer(s->dpy, pbuffer); - - s->regs[R_CTL] &= ~CTL_START_BUSY; - - trace_milkymist_tmu2_pulse_irq(); - qemu_irq_pulse(s->irq); -} - -static uint64_t tmu2_read(void *opaque, hwaddr addr, - unsigned size) -{ - MilkymistTMU2State *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_CTL: - case R_HMESHLAST: - case R_VMESHLAST: - case R_BRIGHTNESS: - case R_CHROMAKEY: - case R_VERTICESADDR: - case R_TEXFBUF: - case R_TEXHRES: - case R_TEXVRES: - case R_TEXHMASK: - case R_TEXVMASK: - case R_DSTFBUF: - case R_DSTHRES: - case R_DSTVRES: - case R_DSTHOFFSET: - case R_DSTVOFFSET: - case R_DSTSQUAREW: - case R_DSTSQUAREH: - case R_ALPHA: - r = s->regs[addr]; - break; - - default: - error_report("milkymist_tmu2: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - trace_milkymist_tmu2_memory_read(addr << 2, r); - - return r; -} - -static void tmu2_check_registers(MilkymistTMU2State *s) -{ - if (s->regs[R_BRIGHTNESS] > MAX_BRIGHTNESS) { - error_report("milkymist_tmu2: max brightness is %d", MAX_BRIGHTNESS); - } - - if (s->regs[R_ALPHA] > MAX_ALPHA) { - error_report("milkymist_tmu2: max alpha is %d", MAX_ALPHA); - } - - if (s->regs[R_VERTICESADDR] & 0x07) { - error_report("milkymist_tmu2: vertex mesh address has to be 64-bit " - "aligned"); - } - - if (s->regs[R_TEXFBUF] & 0x01) { - error_report("milkymist_tmu2: texture buffer address has to be " - "16-bit aligned"); - } -} - -static void tmu2_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - MilkymistTMU2State *s = opaque; - - trace_milkymist_tmu2_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_CTL: - s->regs[addr] = value; - if (value & CTL_START_BUSY) { - tmu2_start(s); - } - break; - case R_BRIGHTNESS: - case R_HMESHLAST: - case R_VMESHLAST: - case R_CHROMAKEY: - case R_VERTICESADDR: - case R_TEXFBUF: - case R_TEXHRES: - case R_TEXVRES: - case R_TEXHMASK: - case R_TEXVMASK: - case R_DSTFBUF: - case R_DSTHRES: - case R_DSTVRES: - case R_DSTHOFFSET: - case R_DSTVOFFSET: - case R_DSTSQUAREW: - case R_DSTSQUAREH: - case R_ALPHA: - s->regs[addr] = value; - break; - - default: - error_report("milkymist_tmu2: write access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - tmu2_check_registers(s); -} - -static const MemoryRegionOps tmu2_mmio_ops = { - .read = tmu2_read, - .write = tmu2_write, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void milkymist_tmu2_reset(DeviceState *d) -{ - MilkymistTMU2State *s = MILKYMIST_TMU2(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } -} - -static void milkymist_tmu2_init(Object *obj) -{ - MilkymistTMU2State *s = MILKYMIST_TMU2(obj); - SysBusDevice *dev = SYS_BUS_DEVICE(obj); - - sysbus_init_irq(dev, &s->irq); - - memory_region_init_io(&s->regs_region, obj, &tmu2_mmio_ops, s, - "milkymist-tmu2", R_MAX * 4); - sysbus_init_mmio(dev, &s->regs_region); -} - -static void milkymist_tmu2_realize(DeviceState *dev, Error **errp) -{ - MilkymistTMU2State *s = MILKYMIST_TMU2(dev); - - if (tmu2_glx_init(s)) { - error_setg(errp, "tmu2_glx_init failed"); - } -} - -static const VMStateDescription vmstate_milkymist_tmu2 = { - .name = "milkymist-tmu2", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, MilkymistTMU2State, R_MAX), - VMSTATE_END_OF_LIST() - } -}; - -static void milkymist_tmu2_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = milkymist_tmu2_realize; - dc->reset = milkymist_tmu2_reset; - dc->vmsd = &vmstate_milkymist_tmu2; -} - -static const TypeInfo milkymist_tmu2_info = { - .name = TYPE_MILKYMIST_TMU2, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(MilkymistTMU2State), - .instance_init = milkymist_tmu2_init, - .class_init = milkymist_tmu2_class_init, -}; - -static void milkymist_tmu2_register_types(void) -{ - type_register_static(&milkymist_tmu2_info); -} - -type_init(milkymist_tmu2_register_types) - -DeviceState *milkymist_tmu2_create(hwaddr base, qemu_irq irq) -{ - DeviceState *dev; - Display *d; - GLXFBConfig *configs; - int nelements; - int ver_major, ver_minor; - - /* check that GLX will work */ - d = XOpenDisplay(NULL); - if (d == NULL) { - return NULL; - } - - if (!glXQueryVersion(d, &ver_major, &ver_minor)) { - /* - * Yeah, sometimes getting the GLX version can fail. - * Isn't X beautiful? - */ - XCloseDisplay(d); - return NULL; - } - - if ((ver_major < 1) || ((ver_major == 1) && (ver_minor < 3))) { - printf("Your GLX version is %d.%d," - "but TMU emulation needs at least 1.3. TMU disabled.\n", - ver_major, ver_minor); - XCloseDisplay(d); - return NULL; - } - - configs = glXChooseFBConfig(d, 0, glx_fbconfig_attr, &nelements); - if (configs == NULL) { - XCloseDisplay(d); - return NULL; - } - - XFree(configs); - XCloseDisplay(d); - - dev = qdev_new(TYPE_MILKYMIST_TMU2); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq); - - return dev; -} diff --git a/hw/display/milkymist-vgafb.c b/hw/display/milkymist-vgafb.c deleted file mode 100644 index e2c587e2df..0000000000 --- a/hw/display/milkymist-vgafb.c +++ /dev/null @@ -1,360 +0,0 @@ - -/* - * QEMU model of the Milkymist VGA framebuffer. - * - * Copyright (c) 2010-2012 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://milkymist.walle.cc/socdoc/vgafb.pdf - */ - -#include "qemu/osdep.h" -#include "hw/hw.h" -#include "hw/qdev-properties.h" -#include "hw/sysbus.h" -#include "trace.h" -#include "ui/console.h" -#include "framebuffer.h" -#include "ui/pixel_ops.h" -#include "qemu/error-report.h" -#include "qemu/module.h" -#include "qom/object.h" - -#define BITS 8 -#include "migration/vmstate.h" -#include "milkymist-vgafb_template.h" -#define BITS 15 -#include "milkymist-vgafb_template.h" -#define BITS 16 -#include "milkymist-vgafb_template.h" -#define BITS 24 -#include "milkymist-vgafb_template.h" -#define BITS 32 -#include "milkymist-vgafb_template.h" - -enum { - R_CTRL = 0, - R_HRES, - R_HSYNC_START, - R_HSYNC_END, - R_HSCAN, - R_VRES, - R_VSYNC_START, - R_VSYNC_END, - R_VSCAN, - R_BASEADDRESS, - R_BASEADDRESS_ACT, - R_BURST_COUNT, - R_DDC, - R_SOURCE_CLOCK, - R_MAX -}; - -enum { - CTRL_RESET = (1<<0), -}; - -#define TYPE_MILKYMIST_VGAFB "milkymist-vgafb" -OBJECT_DECLARE_SIMPLE_TYPE(MilkymistVgafbState, MILKYMIST_VGAFB) - -struct MilkymistVgafbState { - SysBusDevice parent_obj; - - MemoryRegion regs_region; - MemoryRegionSection fbsection; - QemuConsole *con; - - int invalidate; - uint32_t fb_offset; - uint32_t fb_mask; - - uint32_t regs[R_MAX]; -}; - -static int vgafb_enabled(MilkymistVgafbState *s) -{ - return !(s->regs[R_CTRL] & CTRL_RESET); -} - -static void vgafb_update_display(void *opaque) -{ - MilkymistVgafbState *s = opaque; - SysBusDevice *sbd; - DisplaySurface *surface = qemu_console_surface(s->con); - int src_width; - int first = 0; - int last = 0; - drawfn fn; - - if (!vgafb_enabled(s)) { - return; - } - - sbd = SYS_BUS_DEVICE(s); - int dest_width = s->regs[R_HRES]; - - switch (surface_bits_per_pixel(surface)) { - case 0: - return; - case 8: - fn = draw_line_8; - break; - case 15: - fn = draw_line_15; - dest_width *= 2; - break; - case 16: - fn = draw_line_16; - dest_width *= 2; - break; - case 24: - fn = draw_line_24; - dest_width *= 3; - break; - case 32: - fn = draw_line_32; - dest_width *= 4; - break; - default: - hw_error("milkymist_vgafb: bad color depth\n"); - break; - } - - src_width = s->regs[R_HRES] * 2; - if (s->invalidate) { - framebuffer_update_memory_section(&s->fbsection, - sysbus_address_space(sbd), - s->regs[R_BASEADDRESS] + s->fb_offset, - s->regs[R_VRES], src_width); - } - - framebuffer_update_display(surface, &s->fbsection, - s->regs[R_HRES], - s->regs[R_VRES], - src_width, - dest_width, - 0, - s->invalidate, - fn, - NULL, - &first, &last); - - if (first >= 0) { - dpy_gfx_update(s->con, 0, first, s->regs[R_HRES], last - first + 1); - } - s->invalidate = 0; -} - -static void vgafb_invalidate_display(void *opaque) -{ - MilkymistVgafbState *s = opaque; - s->invalidate = 1; -} - -static void vgafb_resize(MilkymistVgafbState *s) -{ - if (!vgafb_enabled(s)) { - return; - } - - qemu_console_resize(s->con, s->regs[R_HRES], s->regs[R_VRES]); - s->invalidate = 1; -} - -static uint64_t vgafb_read(void *opaque, hwaddr addr, - unsigned size) -{ - MilkymistVgafbState *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_CTRL: - case R_HRES: - case R_HSYNC_START: - case R_HSYNC_END: - case R_HSCAN: - case R_VRES: - case R_VSYNC_START: - case R_VSYNC_END: - case R_VSCAN: - case R_BASEADDRESS: - case R_BURST_COUNT: - case R_DDC: - case R_SOURCE_CLOCK: - r = s->regs[addr]; - break; - case R_BASEADDRESS_ACT: - r = s->regs[R_BASEADDRESS]; - break; - - default: - error_report("milkymist_vgafb: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - trace_milkymist_vgafb_memory_read(addr << 2, r); - - return r; -} - -static void vgafb_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - MilkymistVgafbState *s = opaque; - - trace_milkymist_vgafb_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_CTRL: - s->regs[addr] = value; - vgafb_resize(s); - break; - case R_HSYNC_START: - case R_HSYNC_END: - case R_HSCAN: - case R_VSYNC_START: - case R_VSYNC_END: - case R_VSCAN: - case R_BURST_COUNT: - case R_DDC: - case R_SOURCE_CLOCK: - s->regs[addr] = value; - break; - case R_BASEADDRESS: - if (value & 0x1f) { - error_report("milkymist_vgafb: framebuffer base address have to " - "be 32 byte aligned"); - break; - } - s->regs[addr] = value & s->fb_mask; - s->invalidate = 1; - break; - case R_HRES: - case R_VRES: - s->regs[addr] = value; - vgafb_resize(s); - break; - case R_BASEADDRESS_ACT: - error_report("milkymist_vgafb: write to read-only register 0x" - TARGET_FMT_plx, addr << 2); - break; - - default: - error_report("milkymist_vgafb: write access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } -} - -static const MemoryRegionOps vgafb_mmio_ops = { - .read = vgafb_read, - .write = vgafb_write, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void milkymist_vgafb_reset(DeviceState *d) -{ - MilkymistVgafbState *s = MILKYMIST_VGAFB(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } - - /* defaults */ - s->regs[R_CTRL] = CTRL_RESET; - s->regs[R_HRES] = 640; - s->regs[R_VRES] = 480; - s->regs[R_BASEADDRESS] = 0; -} - -static const GraphicHwOps vgafb_ops = { - .invalidate = vgafb_invalidate_display, - .gfx_update = vgafb_update_display, -}; - -static void milkymist_vgafb_init(Object *obj) -{ - MilkymistVgafbState *s = MILKYMIST_VGAFB(obj); - SysBusDevice *dev = SYS_BUS_DEVICE(obj); - - memory_region_init_io(&s->regs_region, OBJECT(s), &vgafb_mmio_ops, s, - "milkymist-vgafb", R_MAX * 4); - sysbus_init_mmio(dev, &s->regs_region); -} - -static void milkymist_vgafb_realize(DeviceState *dev, Error **errp) -{ - MilkymistVgafbState *s = MILKYMIST_VGAFB(dev); - - s->con = graphic_console_init(dev, 0, &vgafb_ops, s); -} - -static int vgafb_post_load(void *opaque, int version_id) -{ - vgafb_invalidate_display(opaque); - return 0; -} - -static const VMStateDescription vmstate_milkymist_vgafb = { - .name = "milkymist-vgafb", - .version_id = 1, - .minimum_version_id = 1, - .post_load = vgafb_post_load, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, MilkymistVgafbState, R_MAX), - VMSTATE_END_OF_LIST() - } -}; - -static Property milkymist_vgafb_properties[] = { - DEFINE_PROP_UINT32("fb_offset", MilkymistVgafbState, fb_offset, 0x0), - DEFINE_PROP_UINT32("fb_mask", MilkymistVgafbState, fb_mask, 0xffffffff), - DEFINE_PROP_END_OF_LIST(), -}; - -static void milkymist_vgafb_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->reset = milkymist_vgafb_reset; - dc->vmsd = &vmstate_milkymist_vgafb; - device_class_set_props(dc, milkymist_vgafb_properties); - dc->realize = milkymist_vgafb_realize; -} - -static const TypeInfo milkymist_vgafb_info = { - .name = TYPE_MILKYMIST_VGAFB, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(MilkymistVgafbState), - .instance_init = milkymist_vgafb_init, - .class_init = milkymist_vgafb_class_init, -}; - -static void milkymist_vgafb_register_types(void) -{ - type_register_static(&milkymist_vgafb_info); -} - -type_init(milkymist_vgafb_register_types) diff --git a/hw/display/milkymist-vgafb_template.h b/hw/display/milkymist-vgafb_template.h deleted file mode 100644 index 96137f9709..0000000000 --- a/hw/display/milkymist-vgafb_template.h +++ /dev/null @@ -1,74 +0,0 @@ -/* - * QEMU model of the Milkymist VGA framebuffer. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - */ - -#if BITS == 8 -#define COPY_PIXEL(to, r, g, b) \ - do { \ - *to = rgb_to_pixel8(r, g, b); \ - to += 1; \ - } while (0) -#elif BITS == 15 -#define COPY_PIXEL(to, r, g, b) \ - do { \ - *(uint16_t *)to = rgb_to_pixel15(r, g, b); \ - to += 2; \ - } while (0) -#elif BITS == 16 -#define COPY_PIXEL(to, r, g, b) \ - do { \ - *(uint16_t *)to = rgb_to_pixel16(r, g, b); \ - to += 2; \ - } while (0) -#elif BITS == 24 -#define COPY_PIXEL(to, r, g, b) \ - do { \ - uint32_t tmp = rgb_to_pixel24(r, g, b); \ - *(to++) = tmp & 0xff; \ - *(to++) = (tmp >> 8) & 0xff; \ - *(to++) = (tmp >> 16) & 0xff; \ - } while (0) -#elif BITS == 32 -#define COPY_PIXEL(to, r, g, b) \ - do { \ - *(uint32_t *)to = rgb_to_pixel32(r, g, b); \ - to += 4; \ - } while (0) -#else -#error unknown bit depth -#endif - -static void glue(draw_line_, BITS)(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t rgb565; - uint8_t r, g, b; - - while (width--) { - rgb565 = lduw_be_p(s); - r = ((rgb565 >> 11) & 0x1f) << 3; - g = ((rgb565 >> 5) & 0x3f) << 2; - b = ((rgb565 >> 0) & 0x1f) << 3; - COPY_PIXEL(d, r, g, b); - s += 2; - } -} - -#undef BITS -#undef COPY_PIXEL diff --git a/hw/display/next-fb.c b/hw/display/next-fb.c index e2d895109d..dd6a1aa8ae 100644 --- a/hw/display/next-fb.c +++ b/hw/display/next-fb.c @@ -24,8 +24,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "ui/console.h" -#include "hw/hw.h" -#include "hw/boards.h" #include "hw/loader.h" #include "framebuffer.h" #include "ui/pixel_ops.h" diff --git a/hw/display/qxl.c b/hw/display/qxl.c index 93907e82a3..43482d4364 100644 --- a/hw/display/qxl.c +++ b/hw/display/qxl.c @@ -30,7 +30,6 @@ #include "qemu/module.h" #include "hw/qdev-properties.h" #include "sysemu/runstate.h" -#include "migration/blocker.h" #include "migration/vmstate.h" #include "trace.h" @@ -321,7 +320,7 @@ static ram_addr_t qxl_rom_size(void) #define QXL_ROM_SZ 8192 QEMU_BUILD_BUG_ON(QXL_REQUIRED_SZ > QXL_ROM_SZ); - return QXL_ROM_SZ; + return QEMU_ALIGN_UP(QXL_REQUIRED_SZ, qemu_real_host_page_size); } static void init_qxl_rom(PCIQXLDevice *d) @@ -666,30 +665,6 @@ static int interface_get_command(QXLInstance *sin, struct QXLCommandExt *ext) qxl->guest_primary.commands++; qxl_track_command(qxl, ext); qxl_log_command(qxl, "cmd", ext); - { - /* - * Windows 8 drivers place qxl commands in the vram - * (instead of the ram) bar. We can't live migrate such a - * guest, so add a migration blocker in case we detect - * this, to avoid triggering the assert in pre_save(). - * - * https://cgit.freedesktop.org/spice/win32/qxl-wddm-dod/commit/?id=f6e099db39e7d0787f294d5fd0dce328b5210faa - */ - void *msg = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id); - if (msg != NULL && ( - msg < (void *)qxl->vga.vram_ptr || - msg > ((void *)qxl->vga.vram_ptr + qxl->vga.vram_size))) { - if (!qxl->migration_blocker) { - Error *local_err = NULL; - error_setg(&qxl->migration_blocker, - "qxl: guest bug: command not in ram bar"); - migrate_add_blocker(qxl->migration_blocker, &local_err); - if (local_err) { - error_report_err(local_err); - } - } - } - } trace_qxl_ring_command_get(qxl->id, qxl_mode_to_string(qxl->mode)); return true; default: @@ -1283,12 +1258,6 @@ static void qxl_hard_reset(PCIQXLDevice *d, int loadvm) qemu_spice_create_host_memslot(&d->ssd); qxl_soft_reset(d); - if (d->migration_blocker) { - migrate_del_blocker(d->migration_blocker); - error_free(d->migration_blocker); - d->migration_blocker = NULL; - } - if (startstop) { qemu_spice_display_start(); } @@ -2283,7 +2252,9 @@ static int qxl_pre_save(void *opaque) } else { d->last_release_offset = (uint8_t *)d->last_release - ram_start; } - assert(d->last_release_offset < d->vga.vram_size); + if (d->last_release_offset < d->vga.vram_size) { + return 1; + } return 0; } @@ -2384,7 +2355,7 @@ static bool qxl_monitors_config_needed(void *opaque) } -static VMStateDescription qxl_memslot = { +static const VMStateDescription qxl_memslot = { .name = "qxl-memslot", .version_id = QXL_SAVE_VERSION, .minimum_version_id = QXL_SAVE_VERSION, @@ -2396,7 +2367,7 @@ static VMStateDescription qxl_memslot = { } }; -static VMStateDescription qxl_surface = { +static const VMStateDescription qxl_surface = { .name = "qxl-surface", .version_id = QXL_SAVE_VERSION, .minimum_version_id = QXL_SAVE_VERSION, @@ -2414,7 +2385,7 @@ static VMStateDescription qxl_surface = { } }; -static VMStateDescription qxl_vmstate_monitors_config = { +static const VMStateDescription qxl_vmstate_monitors_config = { .name = "qxl/monitors-config", .version_id = 1, .minimum_version_id = 1, @@ -2425,7 +2396,7 @@ static VMStateDescription qxl_vmstate_monitors_config = { }, }; -static VMStateDescription qxl_vmstate = { +static const VMStateDescription qxl_vmstate = { .name = "qxl", .version_id = QXL_SAVE_VERSION, .minimum_version_id = QXL_SAVE_VERSION, @@ -2522,6 +2493,7 @@ static const TypeInfo qxl_primary_info = { .parent = TYPE_PCI_QXL, .class_init = qxl_primary_class_init, }; +module_obj("qxl-vga"); static void qxl_secondary_class_init(ObjectClass *klass, void *data) { @@ -2538,6 +2510,7 @@ static const TypeInfo qxl_secondary_info = { .parent = TYPE_PCI_QXL, .class_init = qxl_secondary_class_init, }; +module_obj("qxl"); static void qxl_register_types(void) { @@ -2547,3 +2520,5 @@ static void qxl_register_types(void) } type_init(qxl_register_types) + +module_dep("ui-spice-core"); diff --git a/hw/display/qxl.h b/hw/display/qxl.h index 379d3304ab..30d21f4d0b 100644 --- a/hw/display/qxl.h +++ b/hw/display/qxl.h @@ -39,7 +39,6 @@ struct PCIQXLDevice { uint32_t cmdlog; uint32_t guest_bug; - Error *migration_blocker; enum qxl_mode mode; uint32_t cmdflags; diff --git a/hw/display/sm501.c b/hw/display/sm501.c index 8789722ef2..663c37e7f2 100644 --- a/hw/display/sm501.c +++ b/hw/display/sm501.c @@ -1033,16 +1033,18 @@ static void sm501_i2c_write(void *opaque, hwaddr addr, uint64_t value, case SM501_I2C_CONTROL: if (value & SM501_I2C_CONTROL_ENABLE) { if (value & SM501_I2C_CONTROL_START) { + bool is_recv = s->i2c_addr & 1; int res = i2c_start_transfer(s->i2c_bus, s->i2c_addr >> 1, - s->i2c_addr & 1); - s->i2c_status |= (res ? SM501_I2C_STATUS_ERROR : 0); - if (!res) { + is_recv); + if (res) { + s->i2c_status |= SM501_I2C_STATUS_ERROR; + } else { int i; for (i = 0; i <= s->i2c_byte_count; i++) { - res = i2c_send_recv(s->i2c_bus, &s->i2c_data[i], - !(s->i2c_addr & 1)); - if (res) { + if (is_recv) { + s->i2c_data[i] = i2c_recv(s->i2c_bus); + } else if (i2c_send(s->i2c_bus, s->i2c_data[i]) < 0) { s->i2c_status |= SM501_I2C_STATUS_ERROR; return; } @@ -1826,7 +1828,7 @@ static void sm501_init(SM501State *s, DeviceState *dev, s->i2c_bus = i2c_init_bus(dev, "sm501.i2c"); /* ddc */ I2CDDCState *ddc = I2CDDC(qdev_new(TYPE_I2CDDC)); - i2c_set_slave_address(I2C_SLAVE(ddc), 0x50); + i2c_slave_set_address(I2C_SLAVE(ddc), 0x50); qdev_realize_and_unref(DEVICE(ddc), BUS(s->i2c_bus), &error_abort); /* mmio */ diff --git a/hw/display/trace-events b/hw/display/trace-events index 957b8ba994..f03f6655bc 100644 --- a/hw/display/trace-events +++ b/hw/display/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # jazz_led.c jazz_led_read(uint64_t addr, uint8_t val) "read addr=0x%"PRIx64": 0x%x" @@ -13,16 +13,6 @@ xenfb_input_connected(void *xendev, int abs_pointer_wanted) "%p abs %d" g364fb_read(uint64_t addr, uint32_t val) "read addr=0x%"PRIx64": 0x%x" g364fb_write(uint64_t addr, uint32_t new) "write addr=0x%"PRIx64": 0x%x" -# milkymist-tmu2.c -milkymist_tmu2_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_tmu2_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_tmu2_start(void) "Start TMU" -milkymist_tmu2_pulse_irq(void) "Pulse IRQ" - -# milkymist-vgafb.c -milkymist_vgafb_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_vgafb_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" - # vmware_vga.c vmware_value_read(uint32_t index, uint32_t value) "index %d, value 0x%x" vmware_value_write(uint32_t index, uint32_t value) "index %d, value 0x%x" @@ -40,8 +30,10 @@ virtio_gpu_features(bool virgl) "virgl %d" virtio_gpu_cmd_get_display_info(void) "" virtio_gpu_cmd_get_edid(uint32_t scanout) "scanout %d" virtio_gpu_cmd_set_scanout(uint32_t id, uint32_t res, uint32_t w, uint32_t h, uint32_t x, uint32_t y) "id %d, res 0x%x, w %d, h %d, x %d, y %d" +virtio_gpu_cmd_set_scanout_blob(uint32_t id, uint32_t res, uint32_t w, uint32_t h, uint32_t x, uint32_t y) "id %d, res 0x%x, w %d, h %d, x %d, y %d" virtio_gpu_cmd_res_create_2d(uint32_t res, uint32_t fmt, uint32_t w, uint32_t h) "res 0x%x, fmt 0x%x, w %d, h %d" virtio_gpu_cmd_res_create_3d(uint32_t res, uint32_t fmt, uint32_t w, uint32_t h, uint32_t d) "res 0x%x, fmt 0x%x, w %d, h %d, d %d" +virtio_gpu_cmd_res_create_blob(uint32_t res, uint64_t size) "res 0x%x, size %" PRId64 virtio_gpu_cmd_res_unref(uint32_t res) "res 0x%x" virtio_gpu_cmd_res_back_attach(uint32_t res) "res 0x%x" virtio_gpu_cmd_res_back_detach(uint32_t res) "res 0x%x" diff --git a/hw/display/vga-pci.c b/hw/display/vga-pci.c index 48d29630ab..62fb5c38c1 100644 --- a/hw/display/vga-pci.c +++ b/hw/display/vga-pci.c @@ -49,7 +49,7 @@ struct PCIVGAState { qemu_edid_info edid_info; MemoryRegion mmio; MemoryRegion mrs[4]; - uint8_t edid[256]; + uint8_t edid[384]; }; #define TYPE_PCI_VGA "pci-vga" diff --git a/hw/display/vga.c b/hw/display/vga.c index 836ad50c7b..9d1f66af40 100644 --- a/hw/display/vga.c +++ b/hw/display/vga.c @@ -39,6 +39,8 @@ //#define DEBUG_VGA_MEM //#define DEBUG_VGA_REG +bool have_vga = true; + /* 16 state changes per vertical frame @60 Hz */ #define VGA_TEXT_CURSOR_PERIOD_MS (1000 * 2 * 16 / 60) @@ -750,7 +752,8 @@ void vbe_ioport_write_data(void *opaque, uint32_t addr, uint32_t val) val == VBE_DISPI_ID1 || val == VBE_DISPI_ID2 || val == VBE_DISPI_ID3 || - val == VBE_DISPI_ID4) { + val == VBE_DISPI_ID4 || + val == VBE_DISPI_ID5) { s->vbe_regs[s->vbe_index] = val; } break; diff --git a/hw/display/vhost-user-gpu-pci.c b/hw/display/vhost-user-gpu-pci.c index a02b23ecaf..daefcf7101 100644 --- a/hw/display/vhost-user-gpu-pci.c +++ b/hw/display/vhost-user-gpu-pci.c @@ -43,6 +43,7 @@ static const VirtioPCIDeviceTypeInfo vhost_user_gpu_pci_info = { .instance_size = sizeof(VhostUserGPUPCI), .instance_init = vhost_user_gpu_pci_initfn, }; +module_obj(TYPE_VHOST_USER_GPU_PCI); static void vhost_user_gpu_pci_register_types(void) { diff --git a/hw/display/vhost-user-gpu.c b/hw/display/vhost-user-gpu.c index 6cdaa1c73b..49df56cd14 100644 --- a/hw/display/vhost-user-gpu.c +++ b/hw/display/vhost-user-gpu.c @@ -415,14 +415,16 @@ vhost_user_gpu_get_config(VirtIODevice *vdev, uint8_t *config_data) VirtIOGPUBase *b = VIRTIO_GPU_BASE(vdev); struct virtio_gpu_config *vgconfig = (struct virtio_gpu_config *)config_data; + Error *local_err = NULL; int ret; memset(config_data, 0, sizeof(struct virtio_gpu_config)); ret = vhost_dev_get_config(&g->vhost->dev, - config_data, sizeof(struct virtio_gpu_config)); + config_data, sizeof(struct virtio_gpu_config), + &local_err); if (ret) { - error_report("vhost-user-gpu: get device config space failed"); + error_report_err(local_err); return; } @@ -596,6 +598,7 @@ static const TypeInfo vhost_user_gpu_info = { .instance_finalize = vhost_user_gpu_instance_finalize, .class_init = vhost_user_gpu_class_init, }; +module_obj(TYPE_VHOST_USER_GPU); static void vhost_user_gpu_register_types(void) { diff --git a/hw/display/vhost-user-vga.c b/hw/display/vhost-user-vga.c index a34a99856d..072c9c65bc 100644 --- a/hw/display/vhost-user-vga.c +++ b/hw/display/vhost-user-vga.c @@ -44,6 +44,7 @@ static const VirtioPCIDeviceTypeInfo vhost_user_vga_info = { .instance_size = sizeof(VhostUserVGA), .instance_init = vhost_user_vga_inst_initfn, }; +module_obj(TYPE_VHOST_USER_VGA); static void vhost_user_vga_register_types(void) { diff --git a/hw/display/virtio-gpu-base.c b/hw/display/virtio-gpu-base.c index 25f8920fdb..c8da4806e0 100644 --- a/hw/display/virtio-gpu-base.c +++ b/hw/display/virtio-gpu-base.c @@ -25,7 +25,6 @@ virtio_gpu_base_reset(VirtIOGPUBase *g) int i; g->enable = 0; - g->use_virgl_renderer = false; for (i = 0; i < g->conf.max_outputs; i++) { g->scanout[i].resource_id = 0; @@ -162,7 +161,6 @@ virtio_gpu_base_device_realize(DeviceState *qdev, return false; } - g->use_virgl_renderer = false; if (virtio_gpu_virgl_enabled(g->conf)) { error_setg(&g->migration_blocker, "virgl is not yet migratable"); if (migrate_add_blocker(g->migration_blocker, errp) < 0) { @@ -210,6 +208,9 @@ virtio_gpu_base_get_features(VirtIODevice *vdev, uint64_t features, if (virtio_gpu_edid_enabled(g->conf)) { features |= (1 << VIRTIO_GPU_F_EDID); } + if (virtio_gpu_blob_enabled(g->conf)) { + features |= (1 << VIRTIO_GPU_F_RESOURCE_BLOB); + } return features; } @@ -218,10 +219,8 @@ static void virtio_gpu_base_set_features(VirtIODevice *vdev, uint64_t features) { static const uint32_t virgl = (1 << VIRTIO_GPU_F_VIRGL); - VirtIOGPUBase *g = VIRTIO_GPU_BASE(vdev); - g->use_virgl_renderer = ((features & virgl) == virgl); - trace_virtio_gpu_features(g->use_virgl_renderer); + trace_virtio_gpu_features(((features & virgl) == virgl)); } static void @@ -257,6 +256,7 @@ static const TypeInfo virtio_gpu_base_info = { .class_init = virtio_gpu_base_class_init, .abstract = true }; +module_obj(TYPE_VIRTIO_GPU_BASE); static void virtio_register_types(void) diff --git a/hw/display/virtio-gpu-gl.c b/hw/display/virtio-gpu-gl.c new file mode 100644 index 0000000000..6cc4313b1a --- /dev/null +++ b/hw/display/virtio-gpu-gl.c @@ -0,0 +1,171 @@ +/* + * Virtio GPU Device + * + * Copyright Red Hat, Inc. 2013-2014 + * + * Authors: + * Dave Airlie + * Gerd Hoffmann + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/iov.h" +#include "qemu/module.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include "sysemu/sysemu.h" +#include "hw/virtio/virtio.h" +#include "hw/virtio/virtio-gpu.h" +#include "hw/virtio/virtio-gpu-bswap.h" +#include "hw/virtio/virtio-gpu-pixman.h" +#include "hw/qdev-properties.h" + +#include + +static void virtio_gpu_gl_update_cursor_data(VirtIOGPU *g, + struct virtio_gpu_scanout *s, + uint32_t resource_id) +{ + uint32_t width, height; + uint32_t pixels, *data; + + data = virgl_renderer_get_cursor_data(resource_id, &width, &height); + if (!data) { + return; + } + + if (width != s->current_cursor->width || + height != s->current_cursor->height) { + free(data); + return; + } + + pixels = s->current_cursor->width * s->current_cursor->height; + memcpy(s->current_cursor->data, data, pixels * sizeof(uint32_t)); + free(data); +} + +static void virtio_gpu_gl_flushed(VirtIOGPUBase *b) +{ + VirtIOGPU *g = VIRTIO_GPU(b); + + virtio_gpu_process_cmdq(g); +} + +static void virtio_gpu_gl_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) +{ + VirtIOGPU *g = VIRTIO_GPU(vdev); + VirtIOGPUGL *gl = VIRTIO_GPU_GL(vdev); + struct virtio_gpu_ctrl_command *cmd; + + if (!virtio_queue_ready(vq)) { + return; + } + + if (!gl->renderer_inited) { + virtio_gpu_virgl_init(g); + gl->renderer_inited = true; + } + if (gl->renderer_reset) { + gl->renderer_reset = false; + virtio_gpu_virgl_reset(g); + } + + cmd = virtqueue_pop(vq, sizeof(struct virtio_gpu_ctrl_command)); + while (cmd) { + cmd->vq = vq; + cmd->error = 0; + cmd->finished = false; + QTAILQ_INSERT_TAIL(&g->cmdq, cmd, next); + cmd = virtqueue_pop(vq, sizeof(struct virtio_gpu_ctrl_command)); + } + + virtio_gpu_process_cmdq(g); + virtio_gpu_virgl_fence_poll(g); +} + +static void virtio_gpu_gl_reset(VirtIODevice *vdev) +{ + VirtIOGPU *g = VIRTIO_GPU(vdev); + VirtIOGPUGL *gl = VIRTIO_GPU_GL(vdev); + + virtio_gpu_reset(vdev); + + /* + * GL functions must be called with the associated GL context in main + * thread, and when the renderer is unblocked. + */ + if (gl->renderer_inited && !gl->renderer_reset) { + virtio_gpu_virgl_reset_scanout(g); + gl->renderer_reset = true; + } +} + +static void virtio_gpu_gl_device_realize(DeviceState *qdev, Error **errp) +{ + VirtIOGPU *g = VIRTIO_GPU(qdev); + +#if defined(HOST_WORDS_BIGENDIAN) + error_setg(errp, "virgl is not supported on bigendian platforms"); + return; +#endif + + if (!object_resolve_path_type("", TYPE_VIRTIO_GPU_GL, NULL)) { + error_setg(errp, "at most one %s device is permitted", TYPE_VIRTIO_GPU_GL); + return; + } + + if (!display_opengl) { + error_setg(errp, "opengl is not available"); + return; + } + + g->parent_obj.conf.flags |= (1 << VIRTIO_GPU_FLAG_VIRGL_ENABLED); + VIRTIO_GPU_BASE(g)->virtio_config.num_capsets = + virtio_gpu_virgl_get_num_capsets(g); + + virtio_gpu_device_realize(qdev, errp); +} + +static Property virtio_gpu_gl_properties[] = { + DEFINE_PROP_BIT("stats", VirtIOGPU, parent_obj.conf.flags, + VIRTIO_GPU_FLAG_STATS_ENABLED, false), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_gpu_gl_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + VirtIOGPUBaseClass *vbc = VIRTIO_GPU_BASE_CLASS(klass); + VirtIOGPUClass *vgc = VIRTIO_GPU_CLASS(klass); + + vbc->gl_flushed = virtio_gpu_gl_flushed; + vgc->handle_ctrl = virtio_gpu_gl_handle_ctrl; + vgc->process_cmd = virtio_gpu_virgl_process_cmd; + vgc->update_cursor_data = virtio_gpu_gl_update_cursor_data; + + vdc->realize = virtio_gpu_gl_device_realize; + vdc->reset = virtio_gpu_gl_reset; + device_class_set_props(dc, virtio_gpu_gl_properties); +} + +static const TypeInfo virtio_gpu_gl_info = { + .name = TYPE_VIRTIO_GPU_GL, + .parent = TYPE_VIRTIO_GPU, + .instance_size = sizeof(VirtIOGPUGL), + .class_init = virtio_gpu_gl_class_init, +}; +module_obj(TYPE_VIRTIO_GPU_GL); + +static void virtio_register_types(void) +{ + type_register_static(&virtio_gpu_gl_info); +} + +type_init(virtio_register_types) + +module_dep("hw-display-virtio-gpu"); diff --git a/hw/display/virtio-gpu-pci-gl.c b/hw/display/virtio-gpu-pci-gl.c new file mode 100644 index 0000000000..99b14a0718 --- /dev/null +++ b/hw/display/virtio-gpu-pci-gl.c @@ -0,0 +1,58 @@ +/* + * Virtio video device + * + * Copyright Red Hat + * + * Authors: + * Dave Airlie + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/module.h" +#include "hw/pci/pci.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/virtio.h" +#include "hw/virtio/virtio-bus.h" +#include "hw/virtio/virtio-gpu-pci.h" +#include "qom/object.h" + +#define TYPE_VIRTIO_GPU_GL_PCI "virtio-gpu-gl-pci" +typedef struct VirtIOGPUGLPCI VirtIOGPUGLPCI; +DECLARE_INSTANCE_CHECKER(VirtIOGPUGLPCI, VIRTIO_GPU_GL_PCI, + TYPE_VIRTIO_GPU_GL_PCI) + +struct VirtIOGPUGLPCI { + VirtIOGPUPCIBase parent_obj; + VirtIOGPUGL vdev; +}; + +static void virtio_gpu_gl_initfn(Object *obj) +{ + VirtIOGPUGLPCI *dev = VIRTIO_GPU_GL_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_GPU_GL); + VIRTIO_GPU_PCI_BASE(obj)->vgpu = VIRTIO_GPU_BASE(&dev->vdev); +} + +static const VirtioPCIDeviceTypeInfo virtio_gpu_gl_pci_info = { + .generic_name = TYPE_VIRTIO_GPU_GL_PCI, + .parent = TYPE_VIRTIO_GPU_PCI_BASE, + .instance_size = sizeof(VirtIOGPUGLPCI), + .instance_init = virtio_gpu_gl_initfn, +}; +module_obj(TYPE_VIRTIO_GPU_GL_PCI); + +static void virtio_gpu_gl_pci_register_types(void) +{ + virtio_pci_types_register(&virtio_gpu_gl_pci_info); +} + +type_init(virtio_gpu_gl_pci_register_types) + +module_dep("hw-display-virtio-gpu-pci"); diff --git a/hw/display/virtio-gpu-pci.c b/hw/display/virtio-gpu-pci.c index d742a30aec..e36eee0c40 100644 --- a/hw/display/virtio-gpu-pci.c +++ b/hw/display/virtio-gpu-pci.c @@ -64,6 +64,7 @@ static const TypeInfo virtio_gpu_pci_base_info = { .class_init = virtio_gpu_pci_base_class_init, .abstract = true }; +module_obj(TYPE_VIRTIO_GPU_PCI_BASE); #define TYPE_VIRTIO_GPU_PCI "virtio-gpu-pci" typedef struct VirtIOGPUPCI VirtIOGPUPCI; @@ -90,6 +91,7 @@ static const VirtioPCIDeviceTypeInfo virtio_gpu_pci_info = { .instance_size = sizeof(VirtIOGPUPCI), .instance_init = virtio_gpu_initfn, }; +module_obj(TYPE_VIRTIO_GPU_PCI); static void virtio_gpu_pci_register_types(void) { diff --git a/hw/display/virtio-gpu-udmabuf.c b/hw/display/virtio-gpu-udmabuf.c new file mode 100644 index 0000000000..3c01a415e7 --- /dev/null +++ b/hw/display/virtio-gpu-udmabuf.c @@ -0,0 +1,223 @@ +/* + * Virtio GPU Device + * + * Copyright Red Hat, Inc. 2013-2014 + * + * Authors: + * Dave Airlie + * Gerd Hoffmann + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qemu-common.h" +#include "qemu/iov.h" +#include "ui/console.h" +#include "hw/virtio/virtio-gpu.h" +#include "hw/virtio/virtio-gpu-pixman.h" +#include "trace.h" +#include "exec/ramblock.h" +#include "sysemu/hostmem.h" +#include +#include +#include +#include "qemu/memfd.h" +#include "standard-headers/linux/udmabuf.h" + +static void virtio_gpu_create_udmabuf(struct virtio_gpu_simple_resource *res) +{ + struct udmabuf_create_list *list; + RAMBlock *rb; + ram_addr_t offset; + int udmabuf, i; + + udmabuf = udmabuf_fd(); + if (udmabuf < 0) { + return; + } + + list = g_malloc0(sizeof(struct udmabuf_create_list) + + sizeof(struct udmabuf_create_item) * res->iov_cnt); + + for (i = 0; i < res->iov_cnt; i++) { + rcu_read_lock(); + rb = qemu_ram_block_from_host(res->iov[i].iov_base, false, &offset); + rcu_read_unlock(); + + if (!rb || rb->fd < 0) { + g_free(list); + return; + } + + list->list[i].memfd = rb->fd; + list->list[i].offset = offset; + list->list[i].size = res->iov[i].iov_len; + } + + list->count = res->iov_cnt; + list->flags = UDMABUF_FLAGS_CLOEXEC; + + res->dmabuf_fd = ioctl(udmabuf, UDMABUF_CREATE_LIST, list); + if (res->dmabuf_fd < 0) { + warn_report("%s: UDMABUF_CREATE_LIST: %s", __func__, + strerror(errno)); + } + g_free(list); +} + +static void virtio_gpu_remap_udmabuf(struct virtio_gpu_simple_resource *res) +{ + res->remapped = mmap(NULL, res->blob_size, PROT_READ, + MAP_SHARED, res->dmabuf_fd, 0); + if (res->remapped == MAP_FAILED) { + warn_report("%s: dmabuf mmap failed: %s", __func__, + strerror(errno)); + res->remapped = NULL; + } +} + +static void virtio_gpu_destroy_udmabuf(struct virtio_gpu_simple_resource *res) +{ + if (res->remapped) { + munmap(res->remapped, res->blob_size); + res->remapped = NULL; + } + if (res->dmabuf_fd >= 0) { + close(res->dmabuf_fd); + res->dmabuf_fd = -1; + } +} + +static int find_memory_backend_type(Object *obj, void *opaque) +{ + bool *memfd_backend = opaque; + int ret; + + if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) { + HostMemoryBackend *backend = MEMORY_BACKEND(obj); + RAMBlock *rb = backend->mr.ram_block; + + if (rb && rb->fd > 0) { + ret = fcntl(rb->fd, F_GET_SEALS); + if (ret > 0) { + *memfd_backend = true; + } + } + } + + return 0; +} + +bool virtio_gpu_have_udmabuf(void) +{ + Object *memdev_root; + int udmabuf; + bool memfd_backend = false; + + udmabuf = udmabuf_fd(); + if (udmabuf < 0) { + return false; + } + + memdev_root = object_resolve_path("/objects", NULL); + object_child_foreach(memdev_root, find_memory_backend_type, &memfd_backend); + + return memfd_backend; +} + +void virtio_gpu_init_udmabuf(struct virtio_gpu_simple_resource *res) +{ + void *pdata = NULL; + + res->dmabuf_fd = -1; + if (res->iov_cnt == 1) { + pdata = res->iov[0].iov_base; + } else { + virtio_gpu_create_udmabuf(res); + if (res->dmabuf_fd < 0) { + return; + } + virtio_gpu_remap_udmabuf(res); + if (!res->remapped) { + return; + } + pdata = res->remapped; + } + + res->blob = pdata; +} + +void virtio_gpu_fini_udmabuf(struct virtio_gpu_simple_resource *res) +{ + if (res->remapped) { + virtio_gpu_destroy_udmabuf(res); + } +} + +static void virtio_gpu_free_dmabuf(VirtIOGPU *g, VGPUDMABuf *dmabuf) +{ + struct virtio_gpu_scanout *scanout; + + scanout = &g->parent_obj.scanout[dmabuf->scanout_id]; + dpy_gl_release_dmabuf(scanout->con, &dmabuf->buf); + QTAILQ_REMOVE(&g->dmabuf.bufs, dmabuf, next); + g_free(dmabuf); +} + +static VGPUDMABuf +*virtio_gpu_create_dmabuf(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_framebuffer *fb) +{ + VGPUDMABuf *dmabuf; + + if (res->dmabuf_fd < 0) { + return NULL; + } + + dmabuf = g_new0(VGPUDMABuf, 1); + dmabuf->buf.width = fb->width; + dmabuf->buf.height = fb->height; + dmabuf->buf.stride = fb->stride; + dmabuf->buf.fourcc = qemu_pixman_to_drm_format(fb->format); + dmabuf->buf.fd = res->dmabuf_fd; + + dmabuf->scanout_id = scanout_id; + QTAILQ_INSERT_HEAD(&g->dmabuf.bufs, dmabuf, next); + + return dmabuf; +} + +int virtio_gpu_update_dmabuf(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_framebuffer *fb) +{ + struct virtio_gpu_scanout *scanout = &g->parent_obj.scanout[scanout_id]; + VGPUDMABuf *new_primary, *old_primary = NULL; + + new_primary = virtio_gpu_create_dmabuf(g, scanout_id, res, fb); + if (!new_primary) { + return -EINVAL; + } + + if (g->dmabuf.primary) { + old_primary = g->dmabuf.primary; + } + + g->dmabuf.primary = new_primary; + qemu_console_resize(scanout->con, + new_primary->buf.width, + new_primary->buf.height); + dpy_gl_scanout_dmabuf(scanout->con, &new_primary->buf); + + if (old_primary) { + virtio_gpu_free_dmabuf(g, old_primary); + } + + return 0; +} diff --git a/hw/display/virtio-gpu-3d.c b/hw/display/virtio-gpu-virgl.c similarity index 98% rename from hw/display/virtio-gpu-3d.c rename to hw/display/virtio-gpu-virgl.c index d98964858e..18d054922f 100644 --- a/hw/display/virtio-gpu-3d.c +++ b/hw/display/virtio-gpu-virgl.c @@ -283,22 +283,24 @@ static void virgl_resource_attach_backing(VirtIOGPU *g, { struct virtio_gpu_resource_attach_backing att_rb; struct iovec *res_iovs; + uint32_t res_niov; int ret; VIRTIO_GPU_FILL_CMD(att_rb); trace_virtio_gpu_cmd_res_back_attach(att_rb.resource_id); - ret = virtio_gpu_create_mapping_iov(g, &att_rb, cmd, NULL, &res_iovs); + ret = virtio_gpu_create_mapping_iov(g, att_rb.nr_entries, sizeof(att_rb), + cmd, NULL, &res_iovs, &res_niov); if (ret != 0) { cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; return; } ret = virgl_renderer_resource_attach_iov(att_rb.resource_id, - res_iovs, att_rb.nr_entries); + res_iovs, res_niov); if (ret != 0) - virtio_gpu_cleanup_mapping_iov(g, res_iovs, att_rb.nr_entries); + virtio_gpu_cleanup_mapping_iov(g, res_iovs, res_niov); } static void virgl_resource_detach_backing(VirtIOGPU *g, @@ -586,17 +588,21 @@ void virtio_gpu_virgl_fence_poll(VirtIOGPU *g) virtio_gpu_fence_poll(g); } -void virtio_gpu_virgl_reset(VirtIOGPU *g) +void virtio_gpu_virgl_reset_scanout(VirtIOGPU *g) { int i; - virgl_renderer_reset(); for (i = 0; i < g->parent_obj.conf.max_outputs; i++) { dpy_gfx_replace_surface(g->parent_obj.scanout[i].con, NULL); dpy_gl_scanout_disable(g->parent_obj.scanout[i].con); } } +void virtio_gpu_virgl_reset(VirtIOGPU *g) +{ + virgl_renderer_reset(); +} + int virtio_gpu_virgl_init(VirtIOGPU *g) { int ret; diff --git a/hw/display/virtio-gpu.c b/hw/display/virtio-gpu.c index c9f5e36fd0..990e71fd40 100644 --- a/hw/display/virtio-gpu.c +++ b/hw/display/virtio-gpu.c @@ -35,80 +35,51 @@ static struct virtio_gpu_simple_resource* virtio_gpu_find_resource(VirtIOGPU *g, uint32_t resource_id); +static struct virtio_gpu_simple_resource * +virtio_gpu_find_check_resource(VirtIOGPU *g, uint32_t resource_id, + bool require_backing, + const char *caller, uint32_t *error); static void virtio_gpu_cleanup_mapping(VirtIOGPU *g, struct virtio_gpu_simple_resource *res); -#ifdef CONFIG_VIRGL -#include -#define VIRGL(_g, _virgl, _simple, ...) \ - do { \ - if (_g->parent_obj.use_virgl_renderer) { \ - _virgl(__VA_ARGS__); \ - } else { \ - _simple(__VA_ARGS__); \ - } \ - } while (0) -#else -#define VIRGL(_g, _virgl, _simple, ...) \ - do { \ - _simple(__VA_ARGS__); \ - } while (0) -#endif - -static void update_cursor_data_simple(VirtIOGPU *g, - struct virtio_gpu_scanout *s, - uint32_t resource_id) +void virtio_gpu_update_cursor_data(VirtIOGPU *g, + struct virtio_gpu_scanout *s, + uint32_t resource_id) { struct virtio_gpu_simple_resource *res; uint32_t pixels; + void *data; - res = virtio_gpu_find_resource(g, resource_id); + res = virtio_gpu_find_check_resource(g, resource_id, false, + __func__, NULL); if (!res) { return; } - if (pixman_image_get_width(res->image) != s->current_cursor->width || - pixman_image_get_height(res->image) != s->current_cursor->height) { - return; + if (res->blob_size) { + if (res->blob_size < (s->current_cursor->width * + s->current_cursor->height * 4)) { + return; + } + data = res->blob; + } else { + if (pixman_image_get_width(res->image) != s->current_cursor->width || + pixman_image_get_height(res->image) != s->current_cursor->height) { + return; + } + data = pixman_image_get_data(res->image); } pixels = s->current_cursor->width * s->current_cursor->height; - memcpy(s->current_cursor->data, - pixman_image_get_data(res->image), + memcpy(s->current_cursor->data, data, pixels * sizeof(uint32_t)); } -#ifdef CONFIG_VIRGL - -static void update_cursor_data_virgl(VirtIOGPU *g, - struct virtio_gpu_scanout *s, - uint32_t resource_id) -{ - uint32_t width, height; - uint32_t pixels, *data; - - data = virgl_renderer_get_cursor_data(resource_id, &width, &height); - if (!data) { - return; - } - - if (width != s->current_cursor->width || - height != s->current_cursor->height) { - free(data); - return; - } - - pixels = s->current_cursor->width * s->current_cursor->height; - memcpy(s->current_cursor->data, data, pixels * sizeof(uint32_t)); - free(data); -} - -#endif - static void update_cursor(VirtIOGPU *g, struct virtio_gpu_update_cursor *cursor) { struct virtio_gpu_scanout *s; + VirtIOGPUClass *vgc = VIRTIO_GPU_GET_CLASS(g); bool move = cursor->hdr.type == VIRTIO_GPU_CMD_MOVE_CURSOR; if (cursor->pos.scanout_id >= g->parent_obj.conf.max_outputs) { @@ -131,8 +102,7 @@ static void update_cursor(VirtIOGPU *g, struct virtio_gpu_update_cursor *cursor) s->current_cursor->hot_y = cursor->hot_y; if (cursor->resource_id > 0) { - VIRGL(g, update_cursor_data_virgl, update_cursor_data_simple, - g, s, cursor->resource_id); + vgc->update_cursor_data(g, s, cursor->resource_id); } dpy_cursor_define(s->con, s->current_cursor); @@ -158,6 +128,37 @@ virtio_gpu_find_resource(VirtIOGPU *g, uint32_t resource_id) return NULL; } +static struct virtio_gpu_simple_resource * +virtio_gpu_find_check_resource(VirtIOGPU *g, uint32_t resource_id, + bool require_backing, + const char *caller, uint32_t *error) +{ + struct virtio_gpu_simple_resource *res; + + res = virtio_gpu_find_resource(g, resource_id); + if (!res) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid resource specified %d\n", + caller, resource_id); + if (error) { + *error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; + } + return NULL; + } + + if (require_backing) { + if (!res->iov || (!res->image && !res->blob)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: no backing storage %d\n", + caller, resource_id); + if (error) { + *error = VIRTIO_GPU_RESP_ERR_UNSPEC; + } + return NULL; + } + } + + return res; +} + void virtio_gpu_ctrl_response(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd, struct virtio_gpu_ctrl_hdr *resp, @@ -321,6 +322,56 @@ static void virtio_gpu_resource_create_2d(VirtIOGPU *g, g->hostmem += res->hostmem; } +static void virtio_gpu_resource_create_blob(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_resource_create_blob cblob; + int ret; + + VIRTIO_GPU_FILL_CMD(cblob); + virtio_gpu_create_blob_bswap(&cblob); + trace_virtio_gpu_cmd_res_create_blob(cblob.resource_id, cblob.size); + + if (cblob.resource_id == 0) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: resource id 0 is not allowed\n", + __func__); + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; + return; + } + + if (cblob.blob_mem != VIRTIO_GPU_BLOB_MEM_GUEST && + cblob.blob_flags != VIRTIO_GPU_BLOB_FLAG_USE_SHAREABLE) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid memory type\n", + __func__); + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + return; + } + + if (virtio_gpu_find_resource(g, cblob.resource_id)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: resource already exists %d\n", + __func__, cblob.resource_id); + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; + return; + } + + res = g_new0(struct virtio_gpu_simple_resource, 1); + res->resource_id = cblob.resource_id; + res->blob_size = cblob.size; + + ret = virtio_gpu_create_mapping_iov(g, cblob.nr_entries, sizeof(cblob), + cmd, &res->addrs, &res->iov, + &res->iov_cnt); + if (ret != 0 || res->iov) { + cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; + g_free(res); + return; + } + + virtio_gpu_init_udmabuf(res); + QTAILQ_INSERT_HEAD(&g->reslist, res, next); +} + static void virtio_gpu_disable_scanout(VirtIOGPU *g, int scanout_id) { struct virtio_gpu_scanout *scanout = &g->parent_obj.scanout[scanout_id]; @@ -355,7 +406,7 @@ static void virtio_gpu_resource_destroy(VirtIOGPU *g, } } - pixman_image_unref(res->image); + qemu_pixman_image_unref(res->image); virtio_gpu_cleanup_mapping(g, res); QTAILQ_REMOVE(&g->reslist, res, next); g->hostmem -= res->hostmem; @@ -396,11 +447,9 @@ static void virtio_gpu_transfer_to_host_2d(VirtIOGPU *g, virtio_gpu_t2d_bswap(&t2d); trace_virtio_gpu_cmd_res_xfer_toh_2d(t2d.resource_id); - res = virtio_gpu_find_resource(g, t2d.resource_id); - if (!res || !res->iov) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n", - __func__, t2d.resource_id); - cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; + res = virtio_gpu_find_check_resource(g, t2d.resource_id, true, + __func__, &cmd->error); + if (!res || res->blob) { return; } @@ -446,6 +495,7 @@ static void virtio_gpu_resource_flush(VirtIOGPU *g, { struct virtio_gpu_simple_resource *res; struct virtio_gpu_resource_flush rf; + struct virtio_gpu_scanout *scanout; pixman_region16_t flush_region; int i; @@ -454,20 +504,31 @@ static void virtio_gpu_resource_flush(VirtIOGPU *g, trace_virtio_gpu_cmd_res_flush(rf.resource_id, rf.r.width, rf.r.height, rf.r.x, rf.r.y); - res = virtio_gpu_find_resource(g, rf.resource_id); + res = virtio_gpu_find_check_resource(g, rf.resource_id, false, + __func__, &cmd->error); if (!res) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n", - __func__, rf.resource_id); - cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; return; } - if (rf.r.x > res->width || + if (res->blob) { + for (i = 0; i < g->parent_obj.conf.max_outputs; i++) { + scanout = &g->parent_obj.scanout[i]; + if (scanout->resource_id == res->resource_id && + console_has_gl(scanout->con)) { + dpy_gl_update(scanout->con, 0, 0, scanout->width, + scanout->height); + return; + } + } + } + + if (!res->blob && + (rf.r.x > res->width || rf.r.y > res->height || rf.r.width > res->width || rf.r.height > res->height || rf.r.x + rf.r.width > res->width || - rf.r.y + rf.r.height > res->height) { + rf.r.y + rf.r.height > res->height)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: flush bounds outside resource" " bounds for resource %d: %d %d %d %d vs %d %d\n", __func__, rf.resource_id, rf.r.x, rf.r.y, @@ -479,7 +540,6 @@ static void virtio_gpu_resource_flush(VirtIOGPU *g, pixman_region_init_rect(&flush_region, rf.r.x, rf.r.y, rf.r.width, rf.r.height); for (i = 0; i < g->parent_obj.conf.max_outputs; i++) { - struct virtio_gpu_scanout *scanout; pixman_region16_t region, finalregion; pixman_box16_t *extents; @@ -512,14 +572,109 @@ static void virtio_unref_resource(pixman_image_t *image, void *data) pixman_image_unref(data); } +static void virtio_gpu_update_scanout(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_rect *r) +{ + struct virtio_gpu_simple_resource *ores; + struct virtio_gpu_scanout *scanout; + + scanout = &g->parent_obj.scanout[scanout_id]; + ores = virtio_gpu_find_resource(g, scanout->resource_id); + if (ores) { + ores->scanout_bitmask &= ~(1 << scanout_id); + } + + res->scanout_bitmask |= (1 << scanout_id); + scanout->resource_id = res->resource_id; + scanout->x = r->x; + scanout->y = r->y; + scanout->width = r->width; + scanout->height = r->height; +} + +static void virtio_gpu_do_set_scanout(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_framebuffer *fb, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_rect *r, + uint32_t *error) +{ + struct virtio_gpu_scanout *scanout; + uint8_t *data; + + scanout = &g->parent_obj.scanout[scanout_id]; + + if (r->x > fb->width || + r->y > fb->height || + r->width < 16 || + r->height < 16 || + r->width > fb->width || + r->height > fb->height || + r->x + r->width > fb->width || + r->y + r->height > fb->height) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal scanout %d bounds for" + " resource %d, rect (%d,%d)+%d,%d, fb %d %d\n", + __func__, scanout_id, res->resource_id, + r->x, r->y, r->width, r->height, + fb->width, fb->height); + *error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + return; + } + + g->parent_obj.enable = 1; + + if (res->blob) { + if (console_has_gl(scanout->con)) { + if (!virtio_gpu_update_dmabuf(g, scanout_id, res, fb)) { + virtio_gpu_update_scanout(g, scanout_id, res, r); + return; + } + } + + data = res->blob; + } else { + data = (uint8_t *)pixman_image_get_data(res->image); + } + + /* create a surface for this scanout */ + if ((res->blob && !console_has_gl(scanout->con)) || + !scanout->ds || + surface_data(scanout->ds) != data + fb->offset || + scanout->width != r->width || + scanout->height != r->height) { + pixman_image_t *rect; + void *ptr = data + fb->offset; + rect = pixman_image_create_bits(fb->format, r->width, r->height, + ptr, fb->stride); + + if (res->image) { + pixman_image_ref(res->image); + pixman_image_set_destroy_function(rect, virtio_unref_resource, + res->image); + } + + /* realloc the surface ptr */ + scanout->ds = qemu_create_displaysurface_pixman(rect); + if (!scanout->ds) { + *error = VIRTIO_GPU_RESP_ERR_UNSPEC; + return; + } + + pixman_image_unref(rect); + dpy_gfx_replace_surface(g->parent_obj.scanout[scanout_id].con, + scanout->ds); + } + + virtio_gpu_update_scanout(g, scanout_id, res, r); +} + static void virtio_gpu_set_scanout(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd) { - struct virtio_gpu_simple_resource *res, *ores; - struct virtio_gpu_scanout *scanout; - pixman_format_code_t format; - uint32_t offset; - int bpp; + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_framebuffer fb = { 0 }; struct virtio_gpu_set_scanout ss; VIRTIO_GPU_FILL_CMD(ss); @@ -534,97 +689,111 @@ static void virtio_gpu_set_scanout(VirtIOGPU *g, return; } - g->parent_obj.enable = 1; if (ss.resource_id == 0) { virtio_gpu_disable_scanout(g, ss.scanout_id); return; } - /* create a surface for this scanout */ - res = virtio_gpu_find_resource(g, ss.resource_id); + res = virtio_gpu_find_check_resource(g, ss.resource_id, true, + __func__, &cmd->error); if (!res) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n", - __func__, ss.resource_id); - cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; return; } - if (ss.r.x > res->width || - ss.r.y > res->height || - ss.r.width < 16 || - ss.r.height < 16 || - ss.r.width > res->width || - ss.r.height > res->height || - ss.r.x + ss.r.width > res->width || - ss.r.y + ss.r.height > res->height) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal scanout %d bounds for" - " resource %d, (%d,%d)+%d,%d vs %d %d\n", - __func__, ss.scanout_id, ss.resource_id, ss.r.x, ss.r.y, - ss.r.width, ss.r.height, res->width, res->height); + fb.format = pixman_image_get_format(res->image); + fb.bytes_pp = DIV_ROUND_UP(PIXMAN_FORMAT_BPP(fb.format), 8); + fb.width = pixman_image_get_width(res->image); + fb.height = pixman_image_get_height(res->image); + fb.stride = pixman_image_get_stride(res->image); + fb.offset = ss.r.x * fb.bytes_pp + ss.r.y * fb.stride; + + virtio_gpu_do_set_scanout(g, ss.scanout_id, + &fb, res, &ss.r, &cmd->error); +} + +static void virtio_gpu_set_scanout_blob(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_framebuffer fb = { 0 }; + struct virtio_gpu_set_scanout_blob ss; + uint64_t fbend; + + VIRTIO_GPU_FILL_CMD(ss); + virtio_gpu_scanout_blob_bswap(&ss); + trace_virtio_gpu_cmd_set_scanout_blob(ss.scanout_id, ss.resource_id, + ss.r.width, ss.r.height, ss.r.x, + ss.r.y); + + if (ss.scanout_id >= g->parent_obj.conf.max_outputs) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal scanout id specified %d", + __func__, ss.scanout_id); + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_SCANOUT_ID; + return; + } + + if (ss.resource_id == 0) { + virtio_gpu_disable_scanout(g, ss.scanout_id); + return; + } + + res = virtio_gpu_find_check_resource(g, ss.resource_id, true, + __func__, &cmd->error); + if (!res) { + return; + } + + fb.format = virtio_gpu_get_pixman_format(ss.format); + if (!fb.format) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: host couldn't handle guest format %d\n", + __func__, ss.format); cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; return; } - scanout = &g->parent_obj.scanout[ss.scanout_id]; + fb.bytes_pp = DIV_ROUND_UP(PIXMAN_FORMAT_BPP(fb.format), 8); + fb.width = ss.width; + fb.height = ss.height; + fb.stride = ss.strides[0]; + fb.offset = ss.offsets[0] + ss.r.x * fb.bytes_pp + ss.r.y * fb.stride; - format = pixman_image_get_format(res->image); - bpp = DIV_ROUND_UP(PIXMAN_FORMAT_BPP(format), 8); - offset = (ss.r.x * bpp) + ss.r.y * pixman_image_get_stride(res->image); - if (!scanout->ds || surface_data(scanout->ds) - != ((uint8_t *)pixman_image_get_data(res->image) + offset) || - scanout->width != ss.r.width || - scanout->height != ss.r.height) { - pixman_image_t *rect; - void *ptr = (uint8_t *)pixman_image_get_data(res->image) + offset; - rect = pixman_image_create_bits(format, ss.r.width, ss.r.height, ptr, - pixman_image_get_stride(res->image)); - pixman_image_ref(res->image); - pixman_image_set_destroy_function(rect, virtio_unref_resource, - res->image); - /* realloc the surface ptr */ - scanout->ds = qemu_create_displaysurface_pixman(rect); - if (!scanout->ds) { - cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; - return; - } - pixman_image_unref(rect); - dpy_gfx_replace_surface(g->parent_obj.scanout[ss.scanout_id].con, - scanout->ds); + fbend = fb.offset; + fbend += fb.stride * (ss.r.height - 1); + fbend += fb.bytes_pp * ss.r.width; + if (fbend > res->blob_size) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: fb end out of range\n", + __func__); + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + return; } - ores = virtio_gpu_find_resource(g, scanout->resource_id); - if (ores) { - ores->scanout_bitmask &= ~(1 << ss.scanout_id); - } - - res->scanout_bitmask |= (1 << ss.scanout_id); - scanout->resource_id = ss.resource_id; - scanout->x = ss.r.x; - scanout->y = ss.r.y; - scanout->width = ss.r.width; - scanout->height = ss.r.height; + virtio_gpu_do_set_scanout(g, ss.scanout_id, + &fb, res, &ss.r, &cmd->error); } int virtio_gpu_create_mapping_iov(VirtIOGPU *g, - struct virtio_gpu_resource_attach_backing *ab, + uint32_t nr_entries, uint32_t offset, struct virtio_gpu_ctrl_command *cmd, - uint64_t **addr, struct iovec **iov) + uint64_t **addr, struct iovec **iov, + uint32_t *niov) { struct virtio_gpu_mem_entry *ents; size_t esize, s; - int i; + int e, v; - if (ab->nr_entries > 16384) { + if (nr_entries > 16384) { qemu_log_mask(LOG_GUEST_ERROR, "%s: nr_entries is too big (%d > 16384)\n", - __func__, ab->nr_entries); + __func__, nr_entries); return -1; } - esize = sizeof(*ents) * ab->nr_entries; + esize = sizeof(*ents) * nr_entries; ents = g_malloc(esize); s = iov_to_buf(cmd->elem.out_sg, cmd->elem.out_num, - sizeof(*ab), ents, esize); + offset, ents, esize); if (s != esize) { qemu_log_mask(LOG_GUEST_ERROR, "%s: command data size incorrect %zu vs %zu\n", @@ -633,37 +802,52 @@ int virtio_gpu_create_mapping_iov(VirtIOGPU *g, return -1; } - *iov = g_malloc0(sizeof(struct iovec) * ab->nr_entries); + *iov = NULL; if (addr) { - *addr = g_malloc0(sizeof(uint64_t) * ab->nr_entries); + *addr = NULL; } - for (i = 0; i < ab->nr_entries; i++) { - uint64_t a = le64_to_cpu(ents[i].addr); - uint32_t l = le32_to_cpu(ents[i].length); - hwaddr len = l; - (*iov)[i].iov_base = dma_memory_map(VIRTIO_DEVICE(g)->dma_as, - a, &len, DMA_DIRECTION_TO_DEVICE); - (*iov)[i].iov_len = len; - if (addr) { - (*addr)[i] = a; - } - if (!(*iov)[i].iov_base || len != l) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: failed to map MMIO memory for" - " resource %d element %d\n", - __func__, ab->resource_id, i); - if ((*iov)[i].iov_base) { - i++; /* cleanup the 'i'th map */ + for (e = 0, v = 0; e < nr_entries; e++) { + uint64_t a = le64_to_cpu(ents[e].addr); + uint32_t l = le32_to_cpu(ents[e].length); + hwaddr len; + void *map; + + do { + len = l; + map = dma_memory_map(VIRTIO_DEVICE(g)->dma_as, + a, &len, DMA_DIRECTION_TO_DEVICE); + if (!map) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: failed to map MMIO memory for" + " element %d\n", __func__, e); + virtio_gpu_cleanup_mapping_iov(g, *iov, v); + g_free(ents); + *iov = NULL; + if (addr) { + g_free(*addr); + *addr = NULL; + } + return -1; } - virtio_gpu_cleanup_mapping_iov(g, *iov, i); - g_free(ents); - *iov = NULL; + + if (!(v % 16)) { + *iov = g_realloc(*iov, sizeof(struct iovec) * (v + 16)); + if (addr) { + *addr = g_realloc(*addr, sizeof(uint64_t) * (v + 16)); + } + } + (*iov)[v].iov_base = map; + (*iov)[v].iov_len = len; if (addr) { - g_free(*addr); - *addr = NULL; + (*addr)[v] = a; } - return -1; - } + + a += len; + l -= len; + v += 1; + } while (l > 0); } + *niov = v; + g_free(ents); return 0; } @@ -690,6 +874,10 @@ static void virtio_gpu_cleanup_mapping(VirtIOGPU *g, res->iov_cnt = 0; g_free(res->addrs); res->addrs = NULL; + + if (res->blob) { + virtio_gpu_fini_udmabuf(res); + } } static void @@ -717,13 +905,12 @@ virtio_gpu_resource_attach_backing(VirtIOGPU *g, return; } - ret = virtio_gpu_create_mapping_iov(g, &ab, cmd, &res->addrs, &res->iov); + ret = virtio_gpu_create_mapping_iov(g, ab.nr_entries, sizeof(ab), cmd, + &res->addrs, &res->iov, &res->iov_cnt); if (ret != 0) { cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; return; } - - res->iov_cnt = ab.nr_entries; } static void @@ -737,18 +924,16 @@ virtio_gpu_resource_detach_backing(VirtIOGPU *g, virtio_gpu_bswap_32(&detach, sizeof(detach)); trace_virtio_gpu_cmd_res_back_detach(detach.resource_id); - res = virtio_gpu_find_resource(g, detach.resource_id); - if (!res || !res->iov) { - qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n", - __func__, detach.resource_id); - cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID; + res = virtio_gpu_find_check_resource(g, detach.resource_id, true, + __func__, &cmd->error); + if (!res) { return; } virtio_gpu_cleanup_mapping(g, res); } -static void virtio_gpu_simple_process_cmd(VirtIOGPU *g, - struct virtio_gpu_ctrl_command *cmd) +void virtio_gpu_simple_process_cmd(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) { VIRTIO_GPU_FILL_CMD(cmd->cmd_hdr); virtio_gpu_ctrl_hdr_bswap(&cmd->cmd_hdr); @@ -763,6 +948,13 @@ static void virtio_gpu_simple_process_cmd(VirtIOGPU *g, case VIRTIO_GPU_CMD_RESOURCE_CREATE_2D: virtio_gpu_resource_create_2d(g, cmd); break; + case VIRTIO_GPU_CMD_RESOURCE_CREATE_BLOB: + if (!virtio_gpu_blob_enabled(g->parent_obj.conf)) { + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + break; + } + virtio_gpu_resource_create_blob(g, cmd); + break; case VIRTIO_GPU_CMD_RESOURCE_UNREF: virtio_gpu_resource_unref(g, cmd); break; @@ -775,6 +967,13 @@ static void virtio_gpu_simple_process_cmd(VirtIOGPU *g, case VIRTIO_GPU_CMD_SET_SCANOUT: virtio_gpu_set_scanout(g, cmd); break; + case VIRTIO_GPU_CMD_SET_SCANOUT_BLOB: + if (!virtio_gpu_blob_enabled(g->parent_obj.conf)) { + cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER; + break; + } + virtio_gpu_set_scanout_blob(g, cmd); + break; case VIRTIO_GPU_CMD_RESOURCE_ATTACH_BACKING: virtio_gpu_resource_attach_backing(g, cmd); break; @@ -806,6 +1005,7 @@ static void virtio_gpu_handle_cursor_cb(VirtIODevice *vdev, VirtQueue *vq) void virtio_gpu_process_cmdq(VirtIOGPU *g) { struct virtio_gpu_ctrl_command *cmd; + VirtIOGPUClass *vgc = VIRTIO_GPU_GET_CLASS(g); if (g->processing_cmdq) { return; @@ -819,8 +1019,7 @@ void virtio_gpu_process_cmdq(VirtIOGPU *g) } /* process command */ - VIRGL(g, virtio_gpu_virgl_process_cmd, virtio_gpu_simple_process_cmd, - g, cmd); + vgc->process_cmd(g, cmd); QTAILQ_REMOVE(&g->cmdq, cmd, next); if (virtio_gpu_stats_enabled(g->parent_obj.conf)) { @@ -843,19 +1042,6 @@ void virtio_gpu_process_cmdq(VirtIOGPU *g) g->processing_cmdq = false; } -static void virtio_gpu_gl_flushed(VirtIOGPUBase *b) -{ - VirtIOGPU *g = VIRTIO_GPU(b); - -#ifdef CONFIG_VIRGL - if (g->renderer_reset) { - g->renderer_reset = false; - virtio_gpu_virgl_reset(g); - } -#endif - virtio_gpu_process_cmdq(g); -} - static void virtio_gpu_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) { VirtIOGPU *g = VIRTIO_GPU(vdev); @@ -865,13 +1051,6 @@ static void virtio_gpu_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) return; } -#ifdef CONFIG_VIRGL - if (!g->renderer_inited && g->parent_obj.use_virgl_renderer) { - virtio_gpu_virgl_init(g); - g->renderer_inited = true; - } -#endif - cmd = virtqueue_pop(vq, sizeof(struct virtio_gpu_ctrl_command)); while (cmd) { cmd->vq = vq; @@ -882,18 +1061,14 @@ static void virtio_gpu_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) } virtio_gpu_process_cmdq(g); - -#ifdef CONFIG_VIRGL - if (g->parent_obj.use_virgl_renderer) { - virtio_gpu_virgl_fence_poll(g); - } -#endif } static void virtio_gpu_ctrl_bh(void *opaque) { VirtIOGPU *g = opaque; - virtio_gpu_handle_ctrl(&g->parent_obj.parent_obj, g->ctrl_vq); + VirtIOGPUClass *vgc = VIRTIO_GPU_GET_CLASS(g); + + vgc->handle_ctrl(&g->parent_obj.parent_obj, g->ctrl_vq); } static void virtio_gpu_handle_cursor(VirtIODevice *vdev, VirtQueue *vq) @@ -1105,24 +1280,21 @@ static int virtio_gpu_load(QEMUFile *f, void *opaque, size_t size, return 0; } -static void virtio_gpu_device_realize(DeviceState *qdev, Error **errp) +void virtio_gpu_device_realize(DeviceState *qdev, Error **errp) { VirtIODevice *vdev = VIRTIO_DEVICE(qdev); VirtIOGPU *g = VIRTIO_GPU(qdev); - bool have_virgl; -#if !defined(CONFIG_VIRGL) || defined(HOST_WORDS_BIGENDIAN) - have_virgl = false; -#else - have_virgl = display_opengl; -#endif - if (!have_virgl) { - g->parent_obj.conf.flags &= ~(1 << VIRTIO_GPU_FLAG_VIRGL_ENABLED); - } else { -#if defined(CONFIG_VIRGL) - VIRTIO_GPU_BASE(g)->virtio_config.num_capsets = - virtio_gpu_virgl_get_num_capsets(g); -#endif + if (virtio_gpu_blob_enabled(g->parent_obj.conf)) { + if (!virtio_gpu_have_udmabuf()) { + error_setg(errp, "cannot enable blob resources without udmabuf"); + return; + } + + if (virtio_gpu_virgl_enabled(g->parent_obj.conf)) { + error_setg(errp, "blobs and virgl are not compatible (yet)"); + return; + } } if (!virtio_gpu_base_device_realize(qdev, @@ -1141,18 +1313,12 @@ static void virtio_gpu_device_realize(DeviceState *qdev, Error **errp) QTAILQ_INIT(&g->fenceq); } -static void virtio_gpu_reset(VirtIODevice *vdev) +void virtio_gpu_reset(VirtIODevice *vdev) { VirtIOGPU *g = VIRTIO_GPU(vdev); struct virtio_gpu_simple_resource *res, *tmp; struct virtio_gpu_ctrl_command *cmd; -#ifdef CONFIG_VIRGL - if (g->parent_obj.use_virgl_renderer) { - virtio_gpu_virgl_reset(g); - } -#endif - QTAILQ_FOREACH_SAFE(res, &g->reslist, next, tmp) { virtio_gpu_resource_destroy(g, res); } @@ -1170,17 +1336,6 @@ static void virtio_gpu_reset(VirtIODevice *vdev) g_free(cmd); } -#ifdef CONFIG_VIRGL - if (g->parent_obj.use_virgl_renderer) { - if (g->parent_obj.renderer_blocked) { - g->renderer_reset = true; - } else { - virtio_gpu_virgl_reset(g); - } - g->parent_obj.use_virgl_renderer = false; - } -#endif - virtio_gpu_base_reset(VIRTIO_GPU_BASE(vdev)); } @@ -1235,12 +1390,8 @@ static Property virtio_gpu_properties[] = { VIRTIO_GPU_BASE_PROPERTIES(VirtIOGPU, parent_obj.conf), DEFINE_PROP_SIZE("max_hostmem", VirtIOGPU, conf_max_hostmem, 256 * MiB), -#ifdef CONFIG_VIRGL - DEFINE_PROP_BIT("virgl", VirtIOGPU, parent_obj.conf.flags, - VIRTIO_GPU_FLAG_VIRGL_ENABLED, true), - DEFINE_PROP_BIT("stats", VirtIOGPU, parent_obj.conf.flags, - VIRTIO_GPU_FLAG_STATS_ENABLED, false), -#endif + DEFINE_PROP_BIT("blob", VirtIOGPU, parent_obj.conf.flags, + VIRTIO_GPU_FLAG_BLOB_ENABLED, false), DEFINE_PROP_END_OF_LIST(), }; @@ -1248,9 +1399,12 @@ static void virtio_gpu_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); - VirtIOGPUBaseClass *vgc = VIRTIO_GPU_BASE_CLASS(klass); + VirtIOGPUClass *vgc = VIRTIO_GPU_CLASS(klass); + + vgc->handle_ctrl = virtio_gpu_handle_ctrl; + vgc->process_cmd = virtio_gpu_simple_process_cmd; + vgc->update_cursor_data = virtio_gpu_update_cursor_data; - vgc->gl_flushed = virtio_gpu_gl_flushed; vdc->realize = virtio_gpu_device_realize; vdc->reset = virtio_gpu_reset; vdc->get_config = virtio_gpu_get_config; @@ -1264,8 +1418,10 @@ static const TypeInfo virtio_gpu_info = { .name = TYPE_VIRTIO_GPU, .parent = TYPE_VIRTIO_GPU_BASE, .instance_size = sizeof(VirtIOGPU), + .class_size = sizeof(VirtIOGPUClass), .class_init = virtio_gpu_class_init, }; +module_obj(TYPE_VIRTIO_GPU); static void virtio_register_types(void) { diff --git a/hw/display/virtio-vga-gl.c b/hw/display/virtio-vga-gl.c new file mode 100644 index 0000000000..f22549097c --- /dev/null +++ b/hw/display/virtio-vga-gl.c @@ -0,0 +1,50 @@ +#include "qemu/osdep.h" +#include "hw/pci/pci.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/virtio-gpu.h" +#include "hw/display/vga.h" +#include "qapi/error.h" +#include "qemu/module.h" +#include "virtio-vga.h" +#include "qom/object.h" + +#define TYPE_VIRTIO_VGA_GL "virtio-vga-gl" + +typedef struct VirtIOVGAGL VirtIOVGAGL; +DECLARE_INSTANCE_CHECKER(VirtIOVGAGL, VIRTIO_VGA_GL, + TYPE_VIRTIO_VGA_GL) + +struct VirtIOVGAGL { + VirtIOVGABase parent_obj; + + VirtIOGPUGL vdev; +}; + +static void virtio_vga_gl_inst_initfn(Object *obj) +{ + VirtIOVGAGL *dev = VIRTIO_VGA_GL(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_GPU_GL); + VIRTIO_VGA_BASE(dev)->vgpu = VIRTIO_GPU_BASE(&dev->vdev); +} + + +static VirtioPCIDeviceTypeInfo virtio_vga_gl_info = { + .generic_name = TYPE_VIRTIO_VGA_GL, + .parent = TYPE_VIRTIO_VGA_BASE, + .instance_size = sizeof(VirtIOVGAGL), + .instance_init = virtio_vga_gl_inst_initfn, +}; +module_obj(TYPE_VIRTIO_VGA_GL); + +static void virtio_vga_register_types(void) +{ + if (have_vga) { + virtio_pci_types_register(&virtio_vga_gl_info); + } +} + +type_init(virtio_vga_register_types) + +module_dep("hw-display-virtio-vga"); diff --git a/hw/display/virtio-vga.c b/hw/display/virtio-vga.c index d3c6404061..9e57f61e9e 100644 --- a/hw/display/virtio-vga.c +++ b/hw/display/virtio-vga.c @@ -239,6 +239,7 @@ static TypeInfo virtio_vga_base_info = { .class_init = virtio_vga_base_class_init, .abstract = true, }; +module_obj(TYPE_VIRTIO_VGA_BASE); #define TYPE_VIRTIO_VGA "virtio-vga" @@ -268,6 +269,7 @@ static VirtioPCIDeviceTypeInfo virtio_vga_info = { .instance_size = sizeof(VirtIOVGA), .instance_init = virtio_vga_inst_initfn, }; +module_obj(TYPE_VIRTIO_VGA); static void virtio_vga_register_types(void) { diff --git a/hw/display/xlnx_dp.c b/hw/display/xlnx_dp.c index 4fd6aeb18b..2bb7a5441a 100644 --- a/hw/display/xlnx_dp.c +++ b/hw/display/xlnx_dp.c @@ -1253,7 +1253,7 @@ static void xlnx_dp_init(Object *obj) object_property_add_child(OBJECT(s), "dpcd", OBJECT(s->dpcd)); s->edid = I2CDDC(qdev_new("i2c-ddc")); - i2c_set_slave_address(I2C_SLAVE(s->edid), 0x50); + i2c_slave_set_address(I2C_SLAVE(s->edid), 0x50); object_property_add_child(OBJECT(s), "edid", OBJECT(s->edid)); fifo8_create(&s->rx_fifo, 16); diff --git a/hw/dma/meson.build b/hw/dma/meson.build index 5c78a4e05f..f3f0661bc3 100644 --- a/hw/dma/meson.build +++ b/hw/dma/meson.build @@ -1,4 +1,3 @@ -softmmu_ss.add(when: 'CONFIG_PUV3', if_true: files('puv3_dma.c')) softmmu_ss.add(when: 'CONFIG_RC4030', if_true: files('rc4030.c')) softmmu_ss.add(when: 'CONFIG_PL080', if_true: files('pl080.c')) softmmu_ss.add(when: 'CONFIG_PL330', if_true: files('pl330.c')) diff --git a/hw/dma/pl080.c b/hw/dma/pl080.c index f1a586b1d7..2627307cc8 100644 --- a/hw/dma/pl080.c +++ b/hw/dma/pl080.c @@ -10,7 +10,6 @@ #include "qemu/osdep.h" #include "hw/sysbus.h" #include "migration/vmstate.h" -#include "exec/address-spaces.h" #include "qemu/log.h" #include "qemu/module.h" #include "hw/dma/pl080.h" diff --git a/hw/dma/puv3_dma.c b/hw/dma/puv3_dma.c deleted file mode 100644 index cca1e9ec21..0000000000 --- a/hw/dma/puv3_dma.c +++ /dev/null @@ -1,119 +0,0 @@ -/* - * DMA device simulation in PKUnity SoC - * - * Copyright (C) 2010-2012 Guan Xuetao - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation, or any later version. - * See the COPYING file in the top-level directory. - */ - -#include "qemu/osdep.h" -#include "hw/sysbus.h" -#include "qom/object.h" - -#undef DEBUG_PUV3 -#include "hw/unicore32/puv3.h" -#include "qemu/module.h" -#include "qemu/log.h" - -#define PUV3_DMA_CH_NR (6) -#define PUV3_DMA_CH_MASK (0xff) -#define PUV3_DMA_CH(offset) ((offset) >> 8) - -#define TYPE_PUV3_DMA "puv3_dma" -OBJECT_DECLARE_SIMPLE_TYPE(PUV3DMAState, PUV3_DMA) - -struct PUV3DMAState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - uint32_t reg_CFG[PUV3_DMA_CH_NR]; -}; - -static uint64_t puv3_dma_read(void *opaque, hwaddr offset, - unsigned size) -{ - PUV3DMAState *s = opaque; - uint32_t ret = 0; - - assert(PUV3_DMA_CH(offset) < PUV3_DMA_CH_NR); - - switch (offset & PUV3_DMA_CH_MASK) { - case 0x10: - ret = s->reg_CFG[PUV3_DMA_CH(offset)]; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } - DPRINTF("offset 0x%x, value 0x%x\n", offset, ret); - - return ret; -} - -static void puv3_dma_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PUV3DMAState *s = opaque; - - assert(PUV3_DMA_CH(offset) < PUV3_DMA_CH_NR); - - switch (offset & PUV3_DMA_CH_MASK) { - case 0x10: - s->reg_CFG[PUV3_DMA_CH(offset)] = value; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } - DPRINTF("offset 0x%x, value 0x%x\n", offset, value); -} - -static const MemoryRegionOps puv3_dma_ops = { - .read = puv3_dma_read, - .write = puv3_dma_write, - .impl = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void puv3_dma_realize(DeviceState *dev, Error **errp) -{ - PUV3DMAState *s = PUV3_DMA(dev); - int i; - - for (i = 0; i < PUV3_DMA_CH_NR; i++) { - s->reg_CFG[i] = 0x0; - } - - memory_region_init_io(&s->iomem, OBJECT(s), &puv3_dma_ops, s, "puv3_dma", - PUV3_REGS_OFFSET); - sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); -} - -static void puv3_dma_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = puv3_dma_realize; -} - -static const TypeInfo puv3_dma_info = { - .name = TYPE_PUV3_DMA, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PUV3DMAState), - .class_init = puv3_dma_class_init, -}; - -static void puv3_dma_register_type(void) -{ - type_register_static(&puv3_dma_info); -} - -type_init(puv3_dma_register_type) diff --git a/hw/dma/pxa2xx_dma.c b/hw/dma/pxa2xx_dma.c index b3707ff3de..fa896f7edf 100644 --- a/hw/dma/pxa2xx_dma.c +++ b/hw/dma/pxa2xx_dma.c @@ -525,7 +525,7 @@ static bool is_version_0(void *opaque, int version_id) return version_id == 0; } -static VMStateDescription vmstate_pxa2xx_dma_chan = { +static const VMStateDescription vmstate_pxa2xx_dma_chan = { .name = "pxa2xx_dma_chan", .version_id = 1, .minimum_version_id = 1, @@ -540,7 +540,7 @@ static VMStateDescription vmstate_pxa2xx_dma_chan = { }, }; -static VMStateDescription vmstate_pxa2xx_dma = { +static const VMStateDescription vmstate_pxa2xx_dma = { .name = "pxa2xx_dma", .version_id = 1, .minimum_version_id = 0, diff --git a/hw/dma/sifive_pdma.c b/hw/dma/sifive_pdma.c index e1f6fedbda..9b2ac2017d 100644 --- a/hw/dma/sifive_pdma.c +++ b/hw/dma/sifive_pdma.c @@ -24,7 +24,6 @@ #include "qemu/bitops.h" #include "qemu/log.h" #include "qapi/error.h" -#include "hw/hw.h" #include "hw/irq.h" #include "hw/qdev-properties.h" #include "hw/sysbus.h" diff --git a/hw/dma/trace-events b/hw/dma/trace-events index 44893995f6..3c47df54e4 100644 --- a/hw/dma/trace-events +++ b/hw/dma/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # rc4030.c jazzio_read(uint64_t addr, uint32_t ret) "read reg[0x%"PRIx64"] = 0x%x" diff --git a/hw/dma/xlnx_csu_dma.c b/hw/dma/xlnx_csu_dma.c index 98324dadcd..797b4fed8f 100644 --- a/hw/dma/xlnx_csu_dma.c +++ b/hw/dma/xlnx_csu_dma.c @@ -21,7 +21,6 @@ #include "qemu/osdep.h" #include "qemu/log.h" #include "qapi/error.h" -#include "hw/hw.h" #include "hw/irq.h" #include "hw/qdev-properties.h" #include "hw/sysbus.h" diff --git a/hw/gpio/aspeed_gpio.c b/hw/gpio/aspeed_gpio.c index 985a259e05..b3dec44480 100644 --- a/hw/gpio/aspeed_gpio.c +++ b/hw/gpio/aspeed_gpio.c @@ -10,7 +10,7 @@ #include "qemu/host-utils.h" #include "qemu/log.h" #include "hw/gpio/aspeed_gpio.h" -#include "include/hw/misc/aspeed_scu.h" +#include "hw/misc/aspeed_scu.h" #include "qapi/error.h" #include "qapi/visitor.h" #include "hw/irq.h" @@ -170,7 +170,7 @@ /* AST2600 only - 1.8V gpios */ /* * The AST2600 has same 3.6V gpios as the AST2400 (memory offsets 0x0-0x198) - * and addtional 1.8V gpios (memory offsets 0x800-0x9D4). + * and additional 1.8V gpios (memory offsets 0x800-0x9D4). */ #define GPIO_1_8V_REG_OFFSET 0x800 #define GPIO_1_8V_ABCD_DATA_VALUE ((0x800 - GPIO_1_8V_REG_OFFSET) >> 2) @@ -207,7 +207,6 @@ #define GPIO_1_8V_MEM_SIZE 0x9D8 #define GPIO_1_8V_REG_ARRAY_SIZE ((GPIO_1_8V_MEM_SIZE - \ GPIO_1_8V_REG_OFFSET) >> 2) -#define GPIO_MAX_MEM_SIZE MAX(GPIO_3_6V_MEM_SIZE, GPIO_1_8V_MEM_SIZE) static int aspeed_evaluate_irq(GPIOSets *regs, int gpio_prev_high, int gpio) { @@ -849,7 +848,7 @@ static void aspeed_gpio_realize(DeviceState *dev, Error **errp) } memory_region_init_io(&s->iomem, OBJECT(s), &aspeed_gpio_ops, s, - TYPE_ASPEED_GPIO, GPIO_MAX_MEM_SIZE); + TYPE_ASPEED_GPIO, 0x800); sysbus_init_mmio(sbd, &s->iomem); } diff --git a/hw/gpio/gpio_pwr.c b/hw/gpio/gpio_pwr.c index 7714fa0dc4..dbaf1c70c8 100644 --- a/hw/gpio/gpio_pwr.c +++ b/hw/gpio/gpio_pwr.c @@ -43,7 +43,7 @@ static void gpio_pwr_reset(void *opaque, int n, int level) static void gpio_pwr_shutdown(void *opaque, int n, int level) { if (level) { - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); } } diff --git a/hw/gpio/meson.build b/hw/gpio/meson.build index 79568f00ce..7bd6a57264 100644 --- a/hw/gpio/meson.build +++ b/hw/gpio/meson.build @@ -3,7 +3,6 @@ softmmu_ss.add(when: 'CONFIG_GPIO_KEY', if_true: files('gpio_key.c')) softmmu_ss.add(when: 'CONFIG_GPIO_PWR', if_true: files('gpio_pwr.c')) softmmu_ss.add(when: 'CONFIG_MAX7310', if_true: files('max7310.c')) softmmu_ss.add(when: 'CONFIG_PL061', if_true: files('pl061.c')) -softmmu_ss.add(when: 'CONFIG_PUV3', if_true: files('puv3_gpio.c')) softmmu_ss.add(when: 'CONFIG_ZAURUS', if_true: files('zaurus.c')) softmmu_ss.add(when: 'CONFIG_IMX', if_true: files('imx_gpio.c')) diff --git a/hw/gpio/pl061.c b/hw/gpio/pl061.c index e72e77572a..899be861cc 100644 --- a/hw/gpio/pl061.c +++ b/hw/gpio/pl061.c @@ -6,28 +6,39 @@ * Written by Paul Brook * * This code is licensed under the GPL. + * + * QEMU interface: + * + sysbus MMIO region 0: the device registers + * + sysbus IRQ: the GPIOINTR interrupt line + * + unnamed GPIO inputs 0..7: inputs to connect to the emulated GPIO lines + * + unnamed GPIO outputs 0..7: the emulated GPIO lines, considered as + * outputs + * + QOM property "pullups": an integer defining whether non-floating lines + * configured as inputs should be pulled up to logical 1 (ie whether in + * real hardware they have a pullup resistor on the line out of the PL061). + * This should be an 8-bit value, where bit 0 is 1 if GPIO line 0 should + * be pulled high, bit 1 configures line 1, and so on. The default is 0xff, + * indicating that all GPIO lines are pulled up to logical 1. + * + QOM property "pulldowns": an integer defining whether non-floating lines + * configured as inputs should be pulled down to logical 0 (ie whether in + * real hardware they have a pulldown resistor on the line out of the PL061). + * This should be an 8-bit value, where bit 0 is 1 if GPIO line 0 should + * be pulled low, bit 1 configures line 1, and so on. The default is 0x0. + * It is an error to set a bit in both "pullups" and "pulldowns". If a bit + * is 0 in both, then the line is considered to be floating, and it will + * not have qemu_set_irq() called on it when it is configured as an input. */ #include "qemu/osdep.h" #include "hw/irq.h" #include "hw/sysbus.h" +#include "hw/qdev-properties.h" #include "migration/vmstate.h" +#include "qapi/error.h" #include "qemu/log.h" #include "qemu/module.h" #include "qom/object.h" - -//#define DEBUG_PL061 1 - -#ifdef DEBUG_PL061 -#define DPRINTF(fmt, ...) \ -do { printf("pl061: " fmt , ## __VA_ARGS__); } while (0) -#define BADF(fmt, ...) \ -do { fprintf(stderr, "pl061: error: " fmt , ## __VA_ARGS__); exit(1);} while (0) -#else -#define DPRINTF(fmt, ...) do {} while(0) -#define BADF(fmt, ...) \ -do { fprintf(stderr, "pl061: error: " fmt , ## __VA_ARGS__);} while (0) -#endif +#include "trace.h" static const uint8_t pl061_id[12] = { 0x00, 0x00, 0x00, 0x00, 0x61, 0x10, 0x04, 0x00, 0x0d, 0xf0, 0x05, 0xb1 }; @@ -67,7 +78,9 @@ struct PL061State { qemu_irq irq; qemu_irq out[N_GPIOS]; const unsigned char *id; - uint32_t rsvd_start; /* reserved area: [rsvd_start, 0xfcc] */ + /* Properties, for non-Luminary PL061 */ + uint32_t pullups; + uint32_t pulldowns; }; static const VMStateDescription vmstate_pl061 = { @@ -100,26 +113,75 @@ static const VMStateDescription vmstate_pl061 = { } }; +static uint8_t pl061_floating(PL061State *s) +{ + /* + * Return mask of bits which correspond to pins configured as inputs + * and which are floating (neither pulled up to 1 nor down to 0). + */ + uint8_t floating; + + if (s->id == pl061_id_luminary) { + /* + * If both PUR and PDR bits are clear, there is neither a pullup + * nor a pulldown in place, and the output truly floats. + */ + floating = ~(s->pur | s->pdr); + } else { + floating = ~(s->pullups | s->pulldowns); + } + return floating & ~s->dir; +} + +static uint8_t pl061_pullups(PL061State *s) +{ + /* + * Return mask of bits which correspond to pins configured as inputs + * and which are pulled up to 1. + */ + uint8_t pullups; + + if (s->id == pl061_id_luminary) { + /* + * The Luminary variant of the PL061 has an extra registers which + * the guest can use to configure whether lines should be pullup + * or pulldown. + */ + pullups = s->pur; + } else { + pullups = s->pullups; + } + return pullups & ~s->dir; +} + static void pl061_update(PL061State *s) { uint8_t changed; uint8_t mask; uint8_t out; int i; + uint8_t pullups = pl061_pullups(s); + uint8_t floating = pl061_floating(s); - DPRINTF("dir = %d, data = %d\n", s->dir, s->data); + trace_pl061_update(DEVICE(s)->canonical_path, s->dir, s->data, + pullups, floating); - /* Outputs float high. */ - /* FIXME: This is board dependent. */ - out = (s->data & s->dir) | ~s->dir; + /* + * Pins configured as output are driven from the data register; + * otherwise if they're pulled up they're 1, and if they're floating + * then we give them the same value they had previously, so we don't + * report any change to the other end. + */ + out = (s->data & s->dir) | pullups | (s->old_out_data & floating); changed = s->old_out_data ^ out; if (changed) { s->old_out_data = out; for (i = 0; i < N_GPIOS; i++) { mask = 1 << i; if (changed & mask) { - DPRINTF("Set output %d = %d\n", i, (out & mask) != 0); - qemu_set_irq(s->out[i], (out & mask) != 0); + int level = (out & mask) != 0; + trace_pl061_set_output(DEVICE(s)->canonical_path, i, level); + qemu_set_irq(s->out[i], level); } } } @@ -131,7 +193,8 @@ static void pl061_update(PL061State *s) for (i = 0; i < N_GPIOS; i++) { mask = 1 << i; if (changed & mask) { - DPRINTF("Changed input %d = %d\n", i, (s->data & mask) != 0); + trace_pl061_input_change(DEVICE(s)->canonical_path, i, + (s->data & mask) != 0); if (!(s->isense & mask)) { /* Edge interrupt */ @@ -150,7 +213,8 @@ static void pl061_update(PL061State *s) /* Level interrupt */ s->istate |= ~(s->data ^ s->iev) & s->isense; - DPRINTF("istate = %02X\n", s->istate); + trace_pl061_update_istate(DEVICE(s)->canonical_path, + s->istate, s->im, (s->istate & s->im) != 0); qemu_set_irq(s->irq, (s->istate & s->im) != 0); } @@ -159,62 +223,114 @@ static uint64_t pl061_read(void *opaque, hwaddr offset, unsigned size) { PL061State *s = (PL061State *)opaque; + uint64_t r = 0; - if (offset < 0x400) { - return s->data & (offset >> 2); - } - if (offset >= s->rsvd_start && offset <= 0xfcc) { - goto err_out; - } - if (offset >= 0xfd0 && offset < 0x1000) { - return s->id[(offset - 0xfd0) >> 2]; - } switch (offset) { + case 0x0 ... 0x3ff: /* Data */ + r = s->data & (offset >> 2); + break; case 0x400: /* Direction */ - return s->dir; + r = s->dir; + break; case 0x404: /* Interrupt sense */ - return s->isense; + r = s->isense; + break; case 0x408: /* Interrupt both edges */ - return s->ibe; + r = s->ibe; + break; case 0x40c: /* Interrupt event */ - return s->iev; + r = s->iev; + break; case 0x410: /* Interrupt mask */ - return s->im; + r = s->im; + break; case 0x414: /* Raw interrupt status */ - return s->istate; + r = s->istate; + break; case 0x418: /* Masked interrupt status */ - return s->istate & s->im; + r = s->istate & s->im; + break; case 0x420: /* Alternate function select */ - return s->afsel; + r = s->afsel; + break; case 0x500: /* 2mA drive */ - return s->dr2r; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->dr2r; + break; case 0x504: /* 4mA drive */ - return s->dr4r; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->dr4r; + break; case 0x508: /* 8mA drive */ - return s->dr8r; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->dr8r; + break; case 0x50c: /* Open drain */ - return s->odr; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->odr; + break; case 0x510: /* Pull-up */ - return s->pur; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->pur; + break; case 0x514: /* Pull-down */ - return s->pdr; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->pdr; + break; case 0x518: /* Slew rate control */ - return s->slr; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->slr; + break; case 0x51c: /* Digital enable */ - return s->den; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->den; + break; case 0x520: /* Lock */ - return s->locked; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->locked; + break; case 0x524: /* Commit */ - return s->cr; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->cr; + break; case 0x528: /* Analog mode select */ - return s->amsel; + if (s->id != pl061_id_luminary) { + goto bad_offset; + } + r = s->amsel; + break; + case 0xfd0 ... 0xfff: /* ID registers */ + r = s->id[(offset - 0xfd0) >> 2]; + break; default: + bad_offset: + qemu_log_mask(LOG_GUEST_ERROR, + "pl061_read: Bad offset %x\n", (int)offset); break; } -err_out: - qemu_log_mask(LOG_GUEST_ERROR, - "pl061_read: Bad offset %x\n", (int)offset); - return 0; + + trace_pl061_read(DEVICE(s)->canonical_path, offset, r); + return r; } static void pl061_write(void *opaque, hwaddr offset, @@ -223,16 +339,14 @@ static void pl061_write(void *opaque, hwaddr offset, PL061State *s = (PL061State *)opaque; uint8_t mask; - if (offset < 0x400) { + trace_pl061_write(DEVICE(s)->canonical_path, offset, value); + + switch (offset) { + case 0 ... 0x3ff: mask = (offset >> 2) & s->dir; s->data = (s->data & ~mask) | (value & mask); pl061_update(s); return; - } - if (offset >= s->rsvd_start) { - goto err_out; - } - switch (offset) { case 0x400: /* Direction */ s->dir = value & 0xff; break; @@ -256,56 +370,99 @@ static void pl061_write(void *opaque, hwaddr offset, s->afsel = (s->afsel & ~mask) | (value & mask); break; case 0x500: /* 2mA drive */ + if (s->id != pl061_id_luminary) { + goto bad_offset; + } s->dr2r = value & 0xff; break; case 0x504: /* 4mA drive */ + if (s->id != pl061_id_luminary) { + goto bad_offset; + } s->dr4r = value & 0xff; break; case 0x508: /* 8mA drive */ + if (s->id != pl061_id_luminary) { + goto bad_offset; + } s->dr8r = value & 0xff; break; case 0x50c: /* Open drain */ + if (s->id != pl061_id_luminary) { + goto bad_offset; + } s->odr = value & 0xff; break; case 0x510: /* Pull-up */ + if (s->id != pl061_id_luminary) { + goto bad_offset; + } s->pur = value & 0xff; break; case 0x514: /* Pull-down */ + if (s->id != pl061_id_luminary) { + goto bad_offset; + } s->pdr = value & 0xff; break; case 0x518: /* Slew rate control */ + if (s->id != pl061_id_luminary) { + goto bad_offset; + } s->slr = value & 0xff; break; case 0x51c: /* Digital enable */ + if (s->id != pl061_id_luminary) { + goto bad_offset; + } s->den = value & 0xff; break; case 0x520: /* Lock */ + if (s->id != pl061_id_luminary) { + goto bad_offset; + } s->locked = (value != 0xacce551); break; case 0x524: /* Commit */ + if (s->id != pl061_id_luminary) { + goto bad_offset; + } if (!s->locked) s->cr = value & 0xff; break; case 0x528: + if (s->id != pl061_id_luminary) { + goto bad_offset; + } s->amsel = value & 0xff; break; default: - goto err_out; + bad_offset: + qemu_log_mask(LOG_GUEST_ERROR, + "pl061_write: Bad offset %x\n", (int)offset); + return; } pl061_update(s); return; -err_out: - qemu_log_mask(LOG_GUEST_ERROR, - "pl061_write: Bad offset %x\n", (int)offset); } -static void pl061_reset(DeviceState *dev) +static void pl061_enter_reset(Object *obj, ResetType type) { - PL061State *s = PL061(dev); + PL061State *s = PL061(obj); + + trace_pl061_reset(DEVICE(s)->canonical_path); /* reset values from PL061 TRM, Stellaris LM3S5P31 & LM3S8962 Data Sheet */ + + /* + * FIXME: For the LM3S6965, not all of the PL061 instances have the + * same reset values for GPIOPUR, GPIOAFSEL and GPIODEN, so in theory + * we should allow the board to configure these via properties. + * In practice, we don't wire anything up to the affected GPIO lines + * (PB7, PC0, PC1, PC2, PC3 -- they're used for JTAG), so we can + * get away with this inaccuracy. + */ s->data = 0; - s->old_out_data = 0; s->old_in_data = 0; s->dir = 0; s->isense = 0; @@ -327,6 +484,24 @@ static void pl061_reset(DeviceState *dev) s->amsel = 0; } +static void pl061_hold_reset(Object *obj) +{ + PL061State *s = PL061(obj); + int i, level; + uint8_t floating = pl061_floating(s); + uint8_t pullups = pl061_pullups(s); + + for (i = 0; i < N_GPIOS; i++) { + if (extract32(floating, i, 1)) { + continue; + } + level = extract32(pullups, i, 1); + trace_pl061_set_output(DEVICE(s)->canonical_path, i, level); + qemu_set_irq(s->out[i], level); + } + s->old_out_data = pullups; +} + static void pl061_set_irq(void * opaque, int irq, int level) { PL061State *s = (PL061State *)opaque; @@ -352,7 +527,6 @@ static void pl061_luminary_init(Object *obj) PL061State *s = PL061(obj); s->id = pl061_id_luminary; - s->rsvd_start = 0x52c; } static void pl061_init(Object *obj) @@ -362,7 +536,6 @@ static void pl061_init(Object *obj) SysBusDevice *sbd = SYS_BUS_DEVICE(obj); s->id = pl061_id; - s->rsvd_start = 0x424; memory_region_init_io(&s->iomem, obj, &pl061_ops, s, "pl061", 0x1000); sysbus_init_mmio(sbd, &s->iomem); @@ -371,12 +544,40 @@ static void pl061_init(Object *obj) qdev_init_gpio_out(dev, s->out, N_GPIOS); } +static void pl061_realize(DeviceState *dev, Error **errp) +{ + PL061State *s = PL061(dev); + + if (s->pullups > 0xff) { + error_setg(errp, "pullups property must be between 0 and 0xff"); + return; + } + if (s->pulldowns > 0xff) { + error_setg(errp, "pulldowns property must be between 0 and 0xff"); + return; + } + if (s->pullups & s->pulldowns) { + error_setg(errp, "no bit may be set both in pullups and pulldowns"); + return; + } +} + +static Property pl061_props[] = { + DEFINE_PROP_UINT32("pullups", PL061State, pullups, 0xff), + DEFINE_PROP_UINT32("pulldowns", PL061State, pulldowns, 0x0), + DEFINE_PROP_END_OF_LIST() +}; + static void pl061_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); dc->vmsd = &vmstate_pl061; - dc->reset = &pl061_reset; + dc->realize = pl061_realize; + device_class_set_props(dc, pl061_props); + rc->phases.enter = pl061_enter_reset; + rc->phases.hold = pl061_hold_reset; } static const TypeInfo pl061_info = { diff --git a/hw/gpio/puv3_gpio.c b/hw/gpio/puv3_gpio.c deleted file mode 100644 index e003ae505c..0000000000 --- a/hw/gpio/puv3_gpio.c +++ /dev/null @@ -1,154 +0,0 @@ -/* - * GPIO device simulation in PKUnity SoC - * - * Copyright (C) 2010-2012 Guan Xuetao - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation, or any later version. - * See the COPYING file in the top-level directory. - */ - -#include "qemu/osdep.h" -#include "hw/sysbus.h" -#include "qom/object.h" - -#undef DEBUG_PUV3 -#include "hw/unicore32/puv3.h" -#include "qemu/module.h" -#include "qemu/log.h" - -#define TYPE_PUV3_GPIO "puv3_gpio" -OBJECT_DECLARE_SIMPLE_TYPE(PUV3GPIOState, PUV3_GPIO) - -struct PUV3GPIOState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - qemu_irq irq[9]; - - uint32_t reg_GPLR; - uint32_t reg_GPDR; - uint32_t reg_GPIR; -}; - -static uint64_t puv3_gpio_read(void *opaque, hwaddr offset, - unsigned size) -{ - PUV3GPIOState *s = opaque; - uint32_t ret = 0; - - switch (offset) { - case 0x00: - ret = s->reg_GPLR; - break; - case 0x04: - ret = s->reg_GPDR; - break; - case 0x20: - ret = s->reg_GPIR; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } - DPRINTF("offset 0x%x, value 0x%x\n", offset, ret); - - return ret; -} - -static void puv3_gpio_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PUV3GPIOState *s = opaque; - - DPRINTF("offset 0x%x, value 0x%x\n", offset, value); - switch (offset) { - case 0x04: - s->reg_GPDR = value; - break; - case 0x08: - if (s->reg_GPDR & value) { - s->reg_GPLR |= value; - } else { - qemu_log_mask(LOG_GUEST_ERROR, "%s: Write gpio input port\n", - __func__); - } - break; - case 0x0c: - if (s->reg_GPDR & value) { - s->reg_GPLR &= ~value; - } else { - qemu_log_mask(LOG_GUEST_ERROR, "%s: Write gpio input port\n", - __func__); - } - break; - case 0x10: /* GRER */ - case 0x14: /* GFER */ - case 0x18: /* GEDR */ - break; - case 0x20: /* GPIR */ - s->reg_GPIR = value; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } -} - -static const MemoryRegionOps puv3_gpio_ops = { - .read = puv3_gpio_read, - .write = puv3_gpio_write, - .impl = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void puv3_gpio_realize(DeviceState *dev, Error **errp) -{ - PUV3GPIOState *s = PUV3_GPIO(dev); - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - - s->reg_GPLR = 0; - s->reg_GPDR = 0; - - /* FIXME: these irqs not handled yet */ - sysbus_init_irq(sbd, &s->irq[PUV3_IRQS_GPIOLOW0]); - sysbus_init_irq(sbd, &s->irq[PUV3_IRQS_GPIOLOW1]); - sysbus_init_irq(sbd, &s->irq[PUV3_IRQS_GPIOLOW2]); - sysbus_init_irq(sbd, &s->irq[PUV3_IRQS_GPIOLOW3]); - sysbus_init_irq(sbd, &s->irq[PUV3_IRQS_GPIOLOW4]); - sysbus_init_irq(sbd, &s->irq[PUV3_IRQS_GPIOLOW5]); - sysbus_init_irq(sbd, &s->irq[PUV3_IRQS_GPIOLOW6]); - sysbus_init_irq(sbd, &s->irq[PUV3_IRQS_GPIOLOW7]); - sysbus_init_irq(sbd, &s->irq[PUV3_IRQS_GPIOHIGH]); - - memory_region_init_io(&s->iomem, OBJECT(s), &puv3_gpio_ops, s, "puv3_gpio", - PUV3_REGS_OFFSET); - sysbus_init_mmio(sbd, &s->iomem); -} - -static void puv3_gpio_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = puv3_gpio_realize; -} - -static const TypeInfo puv3_gpio_info = { - .name = TYPE_PUV3_GPIO, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PUV3GPIOState), - .class_init = puv3_gpio_class_init, -}; - -static void puv3_gpio_register_type(void) -{ - type_register_static(&puv3_gpio_info); -} - -type_init(puv3_gpio_register_type) diff --git a/hw/gpio/trace-events b/hw/gpio/trace-events index 46ab9323bd..1dab99c560 100644 --- a/hw/gpio/trace-events +++ b/hw/gpio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # npcm7xx_gpio.c npcm7xx_gpio_read(const char *id, uint64_t offset, uint64_t value) " %s offset: 0x%04" PRIx64 " value 0x%08" PRIx64 @@ -13,6 +13,15 @@ nrf51_gpio_write(uint64_t offset, uint64_t value) "offset 0x%" PRIx64 " value 0x nrf51_gpio_set(int64_t line, int64_t value) "line %" PRIi64 " value %" PRIi64 nrf51_gpio_update_output_irq(int64_t line, int64_t value) "line %" PRIi64 " value %" PRIi64 +# pl061.c +pl061_update(const char *id, uint32_t dir, uint32_t data, uint32_t pullups, uint32_t floating) "%s GPIODIR 0x%x GPIODATA 0x%x pullups 0x%x floating 0x%x" +pl061_set_output(const char *id, int gpio, int level) "%s setting output %d to %d" +pl061_input_change(const char *id, int gpio, int level) "%s input %d changed to %d" +pl061_update_istate(const char *id, uint32_t istate, uint32_t im, int level) "%s GPIORIS 0x%x GPIOIE 0x%x interrupt level %d" +pl061_read(const char *id, uint64_t offset, uint64_t r) "%s offset 0x%" PRIx64 " value 0x%" PRIx64 +pl061_write(const char *id, uint64_t offset, uint64_t value) "%s offset 0x%" PRIx64 " value 0x%" PRIx64 +pl061_reset(const char *id) "%s reset" + # sifive_gpio.c sifive_gpio_read(uint64_t offset, uint64_t r) "offset 0x%" PRIx64 " value 0x%" PRIx64 sifive_gpio_write(uint64_t offset, uint64_t value) "offset 0x%" PRIx64 " value 0x%" PRIx64 diff --git a/hw/hppa/dino.c b/hw/hppa/dino.c index 5b82c9440d..eab96dd84e 100644 --- a/hw/hppa/dino.c +++ b/hw/hppa/dino.c @@ -14,13 +14,11 @@ #include "qemu/module.h" #include "qemu/units.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/irq.h" #include "hw/pci/pci.h" #include "hw/pci/pci_bus.h" #include "migration/vmstate.h" #include "hppa_sys.h" -#include "exec/address-spaces.h" #include "trace.h" #include "qom/object.h" diff --git a/hw/hppa/lasi.c b/hw/hppa/lasi.c index 1a85657948..88c3791eb6 100644 --- a/hw/hppa/lasi.c +++ b/hw/hppa/lasi.c @@ -13,9 +13,7 @@ #include "qemu/units.h" #include "qemu/log.h" #include "qapi/error.h" -#include "cpu.h" #include "trace.h" -#include "hw/hw.h" #include "hw/irq.h" #include "sysemu/sysemu.h" #include "sysemu/runstate.h" @@ -24,7 +22,6 @@ #include "hw/char/parallel.h" #include "hw/char/serial.h" #include "hw/input/lasips2.h" -#include "exec/address-spaces.h" #include "migration/vmstate.h" #include "qom/object.h" diff --git a/hw/hppa/machine.c b/hw/hppa/machine.c index f2b71db9bd..2a46af5bc9 100644 --- a/hw/hppa/machine.c +++ b/hw/hppa/machine.c @@ -9,7 +9,6 @@ #include "cpu.h" #include "elf.h" #include "hw/loader.h" -#include "hw/boards.h" #include "qemu/error-report.h" #include "sysemu/reset.h" #include "sysemu/sysemu.h" diff --git a/hw/hppa/trace-events b/hw/hppa/trace-events index 3ff620319a..3f42be9056 100644 --- a/hw/hppa/trace-events +++ b/hw/hppa/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pci.c hppa_pci_iack_write(void) "" diff --git a/hw/hyperv/vmbus.c b/hw/hyperv/vmbus.c index 984caf898d..c9887d5a7b 100644 --- a/hw/hyperv/vmbus.c +++ b/hw/hyperv/vmbus.c @@ -2372,6 +2372,14 @@ static void vmbus_dev_realize(DeviceState *dev, Error **errp) assert(!qemu_uuid_is_null(&vdev->instanceid)); + if (!qemu_uuid_is_null(&vdc->instanceid)) { + /* Class wants to only have a single instance with a fixed UUID */ + if (!qemu_uuid_is_equal(&vdev->instanceid, &vdc->instanceid)) { + error_setg(&err, "instance id can't be changed"); + goto error_out; + } + } + /* Check for instance id collision for this class id */ QTAILQ_FOREACH(child, &BUS(vmbus)->children, sibling) { VMBusDevice *child_dev = VMBUS_DEVICE(child->child); @@ -2438,18 +2446,22 @@ static void vmbus_dev_unrealize(DeviceState *dev) free_channels(vdev); } +static Property vmbus_dev_props[] = { + DEFINE_PROP_UUID("instanceid", VMBusDevice, instanceid), + DEFINE_PROP_END_OF_LIST() +}; + + static void vmbus_dev_class_init(ObjectClass *klass, void *data) { DeviceClass *kdev = DEVICE_CLASS(klass); + device_class_set_props(kdev, vmbus_dev_props); kdev->bus_type = TYPE_VMBUS; kdev->realize = vmbus_dev_realize; kdev->unrealize = vmbus_dev_unrealize; kdev->reset = vmbus_dev_reset; } -static Property vmbus_dev_instanceid = - DEFINE_PROP_UUID("instanceid", VMBusDevice, instanceid); - static void vmbus_dev_instance_init(Object *obj) { VMBusDevice *vdev = VMBUS_DEVICE(obj); @@ -2458,8 +2470,6 @@ static void vmbus_dev_instance_init(Object *obj) if (!qemu_uuid_is_null(&vdc->instanceid)) { /* Class wants to only have a single instance with a fixed UUID */ vdev->instanceid = vdc->instanceid; - } else { - qdev_property_add_static(DEVICE(vdev), &vmbus_dev_instanceid); } } diff --git a/hw/i2c/Kconfig b/hw/i2c/Kconfig index 09642a6dcb..8217cb5041 100644 --- a/hw/i2c/Kconfig +++ b/hw/i2c/Kconfig @@ -28,3 +28,11 @@ config IMX_I2C config MPC_I2C bool select I2C + +config PCA954X + bool + select I2C + +config PMBUS + bool + select SMBUS diff --git a/hw/i2c/aspeed_i2c.c b/hw/i2c/aspeed_i2c.c index 518a3f5c6f..8d276d9ed3 100644 --- a/hw/i2c/aspeed_i2c.c +++ b/hw/i2c/aspeed_i2c.c @@ -601,7 +601,7 @@ static void aspeed_i2c_bus_write(void *opaque, hwaddr offset, break; } - bus->dma_addr = value & 0xfffffffc; + bus->dma_addr = value & 0x3ffffffc; break; case I2CD_DMA_LEN: @@ -816,7 +816,8 @@ static void aspeed_i2c_realize(DeviceState *dev, Error **errp) return; } - address_space_init(&s->dram_as, s->dram_mr, "dma-dram"); + address_space_init(&s->dram_as, s->dram_mr, + TYPE_ASPEED_I2C "-dma-dram"); } } diff --git a/hw/i2c/core.c b/hw/i2c/core.c index 21ec52ac5a..416372ad00 100644 --- a/hw/i2c/core.c +++ b/hw/i2c/core.c @@ -66,7 +66,7 @@ I2CBus *i2c_init_bus(DeviceState *parent, const char *name) return bus; } -void i2c_set_slave_address(I2CSlave *dev, uint8_t address) +void i2c_slave_set_address(I2CSlave *dev, uint8_t address) { dev->address = address; } @@ -77,6 +77,30 @@ int i2c_bus_busy(I2CBus *bus) return !QLIST_EMPTY(&bus->current_devs); } +bool i2c_scan_bus(I2CBus *bus, uint8_t address, bool broadcast, + I2CNodeList *current_devs) +{ + BusChild *kid; + + QTAILQ_FOREACH(kid, &bus->qbus.children, sibling) { + DeviceState *qdev = kid->child; + I2CSlave *candidate = I2C_SLAVE(qdev); + I2CSlaveClass *sc = I2C_SLAVE_GET_CLASS(candidate); + + if (sc->match_and_add(candidate, address, broadcast, current_devs)) { + if (!broadcast) { + return true; + } + } + } + + /* + * If broadcast was true, and the list was full or empty, return true. If + * broadcast was false, return false. + */ + return broadcast; +} + /* TODO: Make this handle multiple masters. */ /* * Start or continue an i2c transaction. When this is called for the @@ -90,10 +114,12 @@ int i2c_bus_busy(I2CBus *bus) * protocol uses a start transfer to switch from write to read mode * without releasing the bus. If that fails, the bus is still * in a transaction. + * + * @event must be I2C_START_RECV or I2C_START_SEND. */ -int i2c_start_transfer(I2CBus *bus, uint8_t address, int recv) +static int i2c_do_start_transfer(I2CBus *bus, uint8_t address, + enum i2c_event event) { - BusChild *kid; I2CSlaveClass *sc; I2CNode *node; bool bus_scanned = false; @@ -115,18 +141,8 @@ int i2c_start_transfer(I2CBus *bus, uint8_t address, int recv) * terminating the previous transaction. */ if (QLIST_EMPTY(&bus->current_devs)) { - QTAILQ_FOREACH(kid, &bus->qbus.children, sibling) { - DeviceState *qdev = kid->child; - I2CSlave *candidate = I2C_SLAVE(qdev); - if ((candidate->address == address) || (bus->broadcast)) { - node = g_malloc(sizeof(struct I2CNode)); - node->elt = candidate; - QLIST_INSERT_HEAD(&bus->current_devs, node, next); - if (!bus->broadcast) { - break; - } - } - } + /* Disregard whether devices were found. */ + (void)i2c_scan_bus(bus, address, bus->broadcast, &bus->current_devs); bus_scanned = true; } @@ -144,7 +160,7 @@ int i2c_start_transfer(I2CBus *bus, uint8_t address, int recv) if (sc->event) { trace_i2c_event("start", s->address); - rv = sc->event(s, recv ? I2C_START_RECV : I2C_START_SEND); + rv = sc->event(s, event); if (rv && !bus->broadcast) { if (bus_scanned) { /* First call, terminate the transfer. */ @@ -157,6 +173,23 @@ int i2c_start_transfer(I2CBus *bus, uint8_t address, int recv) return 0; } +int i2c_start_transfer(I2CBus *bus, uint8_t address, bool is_recv) +{ + return i2c_do_start_transfer(bus, address, is_recv + ? I2C_START_RECV + : I2C_START_SEND); +} + +int i2c_start_recv(I2CBus *bus, uint8_t address) +{ + return i2c_do_start_transfer(bus, address, I2C_START_RECV); +} + +int i2c_start_send(I2CBus *bus, uint8_t address) +{ + return i2c_do_start_transfer(bus, address, I2C_START_SEND); +} + void i2c_end_transfer(I2CBus *bus) { I2CSlaveClass *sc; @@ -175,50 +208,42 @@ void i2c_end_transfer(I2CBus *bus) bus->broadcast = false; } -int i2c_send_recv(I2CBus *bus, uint8_t *data, bool send) +int i2c_send(I2CBus *bus, uint8_t data) { I2CSlaveClass *sc; I2CSlave *s; I2CNode *node; int ret = 0; - if (send) { - QLIST_FOREACH(node, &bus->current_devs, next) { - s = node->elt; - sc = I2C_SLAVE_GET_CLASS(s); - if (sc->send) { - trace_i2c_send(s->address, *data); - ret = ret || sc->send(s, *data); - } else { - ret = -1; - } + QLIST_FOREACH(node, &bus->current_devs, next) { + s = node->elt; + sc = I2C_SLAVE_GET_CLASS(s); + if (sc->send) { + trace_i2c_send(s->address, data); + ret = ret || sc->send(s, data); + } else { + ret = -1; } - return ret ? -1 : 0; - } else { - ret = 0xff; - if (!QLIST_EMPTY(&bus->current_devs) && !bus->broadcast) { - sc = I2C_SLAVE_GET_CLASS(QLIST_FIRST(&bus->current_devs)->elt); - if (sc->recv) { - s = QLIST_FIRST(&bus->current_devs)->elt; - ret = sc->recv(s); - trace_i2c_recv(s->address, ret); - } - } - *data = ret; - return 0; } -} -int i2c_send(I2CBus *bus, uint8_t data) -{ - return i2c_send_recv(bus, &data, true); + return ret ? -1 : 0; } uint8_t i2c_recv(I2CBus *bus) { uint8_t data = 0xff; + I2CSlaveClass *sc; + I2CSlave *s; + + if (!QLIST_EMPTY(&bus->current_devs) && !bus->broadcast) { + sc = I2C_SLAVE_GET_CLASS(QLIST_FIRST(&bus->current_devs)->elt); + if (sc->recv) { + s = QLIST_FIRST(&bus->current_devs)->elt; + data = sc->recv(s); + trace_i2c_recv(s->address, data); + } + } - i2c_send_recv(bus, &data, false); return data; } @@ -290,12 +315,28 @@ I2CSlave *i2c_slave_create_simple(I2CBus *bus, const char *name, uint8_t addr) return dev; } +static bool i2c_slave_match(I2CSlave *candidate, uint8_t address, + bool broadcast, I2CNodeList *current_devs) +{ + if ((candidate->address == address) || (broadcast)) { + I2CNode *node = g_malloc(sizeof(struct I2CNode)); + node->elt = candidate; + QLIST_INSERT_HEAD(current_devs, node, next); + return true; + } + + /* Not found and not broadcast. */ + return false; +} + static void i2c_slave_class_init(ObjectClass *klass, void *data) { DeviceClass *k = DEVICE_CLASS(klass); + I2CSlaveClass *sc = I2C_SLAVE_CLASS(klass); set_bit(DEVICE_CATEGORY_MISC, k->categories); k->bus_type = TYPE_I2C_BUS; device_class_set_props(k, i2c_props); + sc->match_and_add = i2c_slave_match; } static const TypeInfo i2c_slave_type_info = { diff --git a/hw/i2c/i2c_mux_pca954x.c b/hw/i2c/i2c_mux_pca954x.c new file mode 100644 index 0000000000..847c59921c --- /dev/null +++ b/hw/i2c/i2c_mux_pca954x.c @@ -0,0 +1,290 @@ +/* + * I2C multiplexer for PCA954x series of I2C multiplexer/switch chips. + * + * Copyright 2021 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/i2c/i2c.h" +#include "hw/i2c/i2c_mux_pca954x.h" +#include "hw/i2c/smbus_slave.h" +#include "hw/qdev-core.h" +#include "hw/sysbus.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/queue.h" +#include "qom/object.h" +#include "trace.h" + +#define PCA9548_CHANNEL_COUNT 8 +#define PCA9546_CHANNEL_COUNT 4 + +/* + * struct Pca954xChannel - The i2c mux device will have N of these states + * that own the i2c channel bus. + * @bus: The owned channel bus. + * @enabled: Is this channel active? + */ +typedef struct Pca954xChannel { + SysBusDevice parent; + + I2CBus *bus; + + bool enabled; +} Pca954xChannel; + +#define TYPE_PCA954X_CHANNEL "pca954x-channel" +#define PCA954X_CHANNEL(obj) \ + OBJECT_CHECK(Pca954xChannel, (obj), TYPE_PCA954X_CHANNEL) + +/* + * struct Pca954xState - The pca954x state object. + * @control: The value written to the mux control. + * @channel: The set of i2c channel buses that act as channels which own the + * i2c children. + */ +typedef struct Pca954xState { + SMBusDevice parent; + + uint8_t control; + + /* The channel i2c buses. */ + Pca954xChannel channel[PCA9548_CHANNEL_COUNT]; +} Pca954xState; + +/* + * struct Pca954xClass - The pca954x class object. + * @nchans: The number of i2c channels this device has. + */ +typedef struct Pca954xClass { + SMBusDeviceClass parent; + + uint8_t nchans; +} Pca954xClass; + +#define TYPE_PCA954X "pca954x" +OBJECT_DECLARE_TYPE(Pca954xState, Pca954xClass, PCA954X) + +/* + * For each channel, if it's enabled, recursively call match on those children. + */ +static bool pca954x_match(I2CSlave *candidate, uint8_t address, + bool broadcast, + I2CNodeList *current_devs) +{ + Pca954xState *mux = PCA954X(candidate); + Pca954xClass *mc = PCA954X_GET_CLASS(mux); + int i; + + /* They are talking to the mux itself (or all devices enabled). */ + if ((candidate->address == address) || broadcast) { + I2CNode *node = g_malloc(sizeof(struct I2CNode)); + node->elt = candidate; + QLIST_INSERT_HEAD(current_devs, node, next); + if (!broadcast) { + return true; + } + } + + for (i = 0; i < mc->nchans; i++) { + if (!mux->channel[i].enabled) { + continue; + } + + if (i2c_scan_bus(mux->channel[i].bus, address, broadcast, + current_devs)) { + if (!broadcast) { + return true; + } + } + } + + /* If we arrived here we didn't find a match, return broadcast. */ + return broadcast; +} + +static void pca954x_enable_channel(Pca954xState *s, uint8_t enable_mask) +{ + Pca954xClass *mc = PCA954X_GET_CLASS(s); + int i; + + /* + * For each channel, check if their bit is set in enable_mask and if yes, + * enable it, otherwise disable, hide it. + */ + for (i = 0; i < mc->nchans; i++) { + if (enable_mask & (1 << i)) { + s->channel[i].enabled = true; + } else { + s->channel[i].enabled = false; + } + } +} + +static void pca954x_write(Pca954xState *s, uint8_t data) +{ + s->control = data; + pca954x_enable_channel(s, data); + + trace_pca954x_write_bytes(data); +} + +static int pca954x_write_data(SMBusDevice *d, uint8_t *buf, uint8_t len) +{ + Pca954xState *s = PCA954X(d); + + if (len == 0) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: writing empty data\n", __func__); + return -1; + } + + /* + * len should be 1, because they write one byte to enable/disable channels. + */ + if (len > 1) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: extra data after channel selection mask\n", + __func__); + return -1; + } + + pca954x_write(s, buf[0]); + return 0; +} + +static uint8_t pca954x_read_byte(SMBusDevice *d) +{ + Pca954xState *s = PCA954X(d); + uint8_t data = s->control; + trace_pca954x_read_data(data); + return data; +} + +static void pca954x_enter_reset(Object *obj, ResetType type) +{ + Pca954xState *s = PCA954X(obj); + /* Reset will disable all channels. */ + pca954x_write(s, 0); +} + +I2CBus *pca954x_i2c_get_bus(I2CSlave *mux, uint8_t channel) +{ + Pca954xClass *pc = PCA954X_GET_CLASS(mux); + Pca954xState *pca954x = PCA954X(mux); + + g_assert(channel < pc->nchans); + return I2C_BUS(qdev_get_child_bus(DEVICE(&pca954x->channel[channel]), + "i2c-bus")); +} + +static void pca954x_channel_init(Object *obj) +{ + Pca954xChannel *s = PCA954X_CHANNEL(obj); + s->bus = i2c_init_bus(DEVICE(s), "i2c-bus"); + + /* Start all channels as disabled. */ + s->enabled = false; +} + +static void pca954x_channel_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + dc->desc = "Pca954x Channel"; +} + +static void pca9546_class_init(ObjectClass *klass, void *data) +{ + Pca954xClass *s = PCA954X_CLASS(klass); + s->nchans = PCA9546_CHANNEL_COUNT; +} + +static void pca9548_class_init(ObjectClass *klass, void *data) +{ + Pca954xClass *s = PCA954X_CLASS(klass); + s->nchans = PCA9548_CHANNEL_COUNT; +} + +static void pca954x_realize(DeviceState *dev, Error **errp) +{ + Pca954xState *s = PCA954X(dev); + Pca954xClass *c = PCA954X_GET_CLASS(s); + int i; + + /* SMBus modules. Cannot fail. */ + for (i = 0; i < c->nchans; i++) { + sysbus_realize(SYS_BUS_DEVICE(&s->channel[i]), &error_abort); + } +} + +static void pca954x_init(Object *obj) +{ + Pca954xState *s = PCA954X(obj); + Pca954xClass *c = PCA954X_GET_CLASS(obj); + int i; + + /* Only initialize the children we expect. */ + for (i = 0; i < c->nchans; i++) { + object_initialize_child(obj, "channel[*]", &s->channel[i], + TYPE_PCA954X_CHANNEL); + } +} + +static void pca954x_class_init(ObjectClass *klass, void *data) +{ + I2CSlaveClass *sc = I2C_SLAVE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + SMBusDeviceClass *k = SMBUS_DEVICE_CLASS(klass); + + sc->match_and_add = pca954x_match; + + rc->phases.enter = pca954x_enter_reset; + + dc->desc = "Pca954x i2c-mux"; + dc->realize = pca954x_realize; + + k->write_data = pca954x_write_data; + k->receive_byte = pca954x_read_byte; +} + +static const TypeInfo pca954x_info[] = { + { + .name = TYPE_PCA954X, + .parent = TYPE_SMBUS_DEVICE, + .instance_size = sizeof(Pca954xState), + .instance_init = pca954x_init, + .class_size = sizeof(Pca954xClass), + .class_init = pca954x_class_init, + .abstract = true, + }, + { + .name = TYPE_PCA9546, + .parent = TYPE_PCA954X, + .class_init = pca9546_class_init, + }, + { + .name = TYPE_PCA9548, + .parent = TYPE_PCA954X, + .class_init = pca9548_class_init, + }, + { + .name = TYPE_PCA954X_CHANNEL, + .parent = TYPE_SYS_BUS_DEVICE, + .class_init = pca954x_channel_class_init, + .instance_size = sizeof(Pca954xChannel), + .instance_init = pca954x_channel_init, + } +}; + +DEFINE_TYPES(pca954x_info) diff --git a/hw/i2c/imx_i2c.c b/hw/i2c/imx_i2c.c index 2e02e1c4fa..9792583fea 100644 --- a/hw/i2c/imx_i2c.c +++ b/hw/i2c/imx_i2c.c @@ -171,7 +171,7 @@ static void imx_i2c_write(void *opaque, hwaddr offset, switch (offset) { case IADR_ADDR: s->iadr = value & IADR_MASK; - /* i2c_set_slave_address(s->bus, (uint8_t)s->iadr); */ + /* i2c_slave_set_address(s->bus, (uint8_t)s->iadr); */ break; case IFDR_ADDR: s->ifdr = value & IFDR_MASK; diff --git a/hw/i2c/meson.build b/hw/i2c/meson.build index cdcd694a7f..d3df273251 100644 --- a/hw/i2c/meson.build +++ b/hw/i2c/meson.build @@ -14,4 +14,6 @@ i2c_ss.add(when: 'CONFIG_SMBUS_EEPROM', if_true: files('smbus_eeprom.c')) i2c_ss.add(when: 'CONFIG_VERSATILE_I2C', if_true: files('versatile_i2c.c')) i2c_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_i2c.c')) i2c_ss.add(when: 'CONFIG_PPC4XX', if_true: files('ppc4xx_i2c.c')) +i2c_ss.add(when: 'CONFIG_PCA954X', if_true: files('i2c_mux_pca954x.c')) +i2c_ss.add(when: 'CONFIG_PMBUS', if_true: files('pmbus_device.c')) softmmu_ss.add_all(when: 'CONFIG_I2C', if_true: i2c_ss) diff --git a/hw/i2c/mpc_i2c.c b/hw/i2c/mpc_i2c.c index 720d2331e9..845392505f 100644 --- a/hw/i2c/mpc_i2c.c +++ b/hw/i2c/mpc_i2c.c @@ -20,7 +20,6 @@ #include "qemu/osdep.h" #include "hw/i2c/i2c.h" #include "hw/irq.h" -#include "qemu/log.h" #include "qemu/module.h" #include "hw/sysbus.h" #include "migration/vmstate.h" diff --git a/hw/i2c/pm_smbus.c b/hw/i2c/pm_smbus.c index 06e1e5321b..d7eae548cb 100644 --- a/hw/i2c/pm_smbus.c +++ b/hw/i2c/pm_smbus.c @@ -128,14 +128,14 @@ static void smb_transaction(PMSMBus *s) * So at least Linux may or may not set the read bit here. * So just ignore the read bit for this command. */ - if (i2c_start_transfer(bus, addr, 0)) { + if (i2c_start_send(bus, addr)) { goto error; } ret = i2c_send(bus, s->smb_data1); if (ret) { goto error; } - if (i2c_start_transfer(bus, addr, 1)) { + if (i2c_start_recv(bus, addr)) { goto error; } s->in_i2c_block_read = true; diff --git a/hw/i2c/pmbus_device.c b/hw/i2c/pmbus_device.c new file mode 100644 index 0000000000..24f8f522d9 --- /dev/null +++ b/hw/i2c/pmbus_device.c @@ -0,0 +1,1612 @@ +/* + * PMBus wrapper over SMBus + * + * Copyright 2021 Google LLC + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include +#include +#include "hw/i2c/pmbus_device.h" +#include "migration/vmstate.h" +#include "qemu/module.h" +#include "qemu/log.h" + +uint16_t pmbus_data2direct_mode(PMBusCoefficients c, uint32_t value) +{ + /* R is usually negative to fit large readings into 16 bits */ + uint16_t y = (c.m * value + c.b) * pow(10, c.R); + return y; +} + +uint32_t pmbus_direct_mode2data(PMBusCoefficients c, uint16_t value) +{ + /* X = (Y * 10^-R - b) / m */ + uint32_t x = (value / pow(10, c.R) - c.b) / c.m; + return x; +} + +void pmbus_send(PMBusDevice *pmdev, const uint8_t *data, uint16_t len) +{ + if (pmdev->out_buf_len + len > SMBUS_DATA_MAX_LEN) { + qemu_log_mask(LOG_GUEST_ERROR, + "PMBus device tried to send too much data"); + len = 0; + } + + for (int i = len - 1; i >= 0; i--) { + pmdev->out_buf[i + pmdev->out_buf_len] = data[len - i - 1]; + } + pmdev->out_buf_len += len; +} + +/* Internal only, convert unsigned ints to the little endian bus */ +static void pmbus_send_uint(PMBusDevice *pmdev, uint64_t data, uint8_t size) +{ + uint8_t bytes[8]; + g_assert(size <= 8); + + for (int i = 0; i < size; i++) { + bytes[i] = data & 0xFF; + data = data >> 8; + } + pmbus_send(pmdev, bytes, size); +} + +void pmbus_send8(PMBusDevice *pmdev, uint8_t data) +{ + pmbus_send_uint(pmdev, data, 1); +} + +void pmbus_send16(PMBusDevice *pmdev, uint16_t data) +{ + pmbus_send_uint(pmdev, data, 2); +} + +void pmbus_send32(PMBusDevice *pmdev, uint32_t data) +{ + pmbus_send_uint(pmdev, data, 4); +} + +void pmbus_send64(PMBusDevice *pmdev, uint64_t data) +{ + pmbus_send_uint(pmdev, data, 8); +} + +void pmbus_send_string(PMBusDevice *pmdev, const char *data) +{ + size_t len = strlen(data); + g_assert(len > 0); + g_assert(len + pmdev->out_buf_len < SMBUS_DATA_MAX_LEN); + pmdev->out_buf[len + pmdev->out_buf_len] = len; + + for (int i = len - 1; i >= 0; i--) { + pmdev->out_buf[i + pmdev->out_buf_len] = data[len - 1 - i]; + } + pmdev->out_buf_len += len + 1; +} + + +static uint64_t pmbus_receive_uint(const uint8_t *buf, uint8_t len) +{ + uint64_t ret = 0; + + /* Exclude command code from return value */ + buf++; + len--; + + for (int i = len - 1; i >= 0; i--) { + ret = ret << 8 | buf[i]; + } + return ret; +} + +uint8_t pmbus_receive8(PMBusDevice *pmdev) +{ + if (pmdev->in_buf_len - 1 != 1) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: length mismatch. Expected 1 byte, got %d bytes\n", + __func__, pmdev->in_buf_len - 1); + } + return pmbus_receive_uint(pmdev->in_buf, pmdev->in_buf_len); +} + +uint16_t pmbus_receive16(PMBusDevice *pmdev) +{ + if (pmdev->in_buf_len - 1 != 2) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: length mismatch. Expected 2 bytes, got %d bytes\n", + __func__, pmdev->in_buf_len - 1); + } + return pmbus_receive_uint(pmdev->in_buf, pmdev->in_buf_len); +} + +uint32_t pmbus_receive32(PMBusDevice *pmdev) +{ + if (pmdev->in_buf_len - 1 != 4) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: length mismatch. Expected 4 bytes, got %d bytes\n", + __func__, pmdev->in_buf_len - 1); + } + return pmbus_receive_uint(pmdev->in_buf, pmdev->in_buf_len); +} + +uint64_t pmbus_receive64(PMBusDevice *pmdev) +{ + if (pmdev->in_buf_len - 1 != 8) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: length mismatch. Expected 8 bytes, got %d bytes\n", + __func__, pmdev->in_buf_len - 1); + } + return pmbus_receive_uint(pmdev->in_buf, pmdev->in_buf_len); +} + +static uint8_t pmbus_out_buf_pop(PMBusDevice *pmdev) +{ + if (pmdev->out_buf_len == 0) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: tried to read from empty buffer", + __func__); + return 0xFF; + } + uint8_t data = pmdev->out_buf[pmdev->out_buf_len - 1]; + pmdev->out_buf_len--; + return data; +} + +static void pmbus_quick_cmd(SMBusDevice *smd, uint8_t read) +{ + PMBusDevice *pmdev = PMBUS_DEVICE(smd); + PMBusDeviceClass *pmdc = PMBUS_DEVICE_GET_CLASS(pmdev); + + if (pmdc->quick_cmd) { + pmdc->quick_cmd(pmdev, read); + } +} + +static void pmbus_pages_alloc(PMBusDevice *pmdev) +{ + /* some PMBus devices don't use the PAGE command, so they get 1 page */ + PMBusDeviceClass *k = PMBUS_DEVICE_GET_CLASS(pmdev); + if (k->device_num_pages == 0) { + k->device_num_pages = 1; + } + pmdev->num_pages = k->device_num_pages; + pmdev->pages = g_new0(PMBusPage, k->device_num_pages); +} + +void pmbus_check_limits(PMBusDevice *pmdev) +{ + for (int i = 0; i < pmdev->num_pages; i++) { + if ((pmdev->pages[i].operation & PB_OP_ON) == 0) { + continue; /* don't check powered off devices */ + } + + if (pmdev->pages[i].read_vout > pmdev->pages[i].vout_ov_fault_limit) { + pmdev->pages[i].status_word |= PB_STATUS_VOUT; + pmdev->pages[i].status_vout |= PB_STATUS_VOUT_OV_FAULT; + } + + if (pmdev->pages[i].read_vout > pmdev->pages[i].vout_ov_warn_limit) { + pmdev->pages[i].status_word |= PB_STATUS_VOUT; + pmdev->pages[i].status_vout |= PB_STATUS_VOUT_OV_WARN; + } + + if (pmdev->pages[i].read_vout < pmdev->pages[i].vout_uv_warn_limit) { + pmdev->pages[i].status_word |= PB_STATUS_VOUT; + pmdev->pages[i].status_vout |= PB_STATUS_VOUT_UV_WARN; + } + + if (pmdev->pages[i].read_vout < pmdev->pages[i].vout_uv_fault_limit) { + pmdev->pages[i].status_word |= PB_STATUS_VOUT; + pmdev->pages[i].status_vout |= PB_STATUS_VOUT_UV_FAULT; + } + + if (pmdev->pages[i].read_vin > pmdev->pages[i].vin_ov_warn_limit) { + pmdev->pages[i].status_word |= PB_STATUS_INPUT; + pmdev->pages[i].status_input |= PB_STATUS_INPUT_VIN_OV_WARN; + } + + if (pmdev->pages[i].read_vin < pmdev->pages[i].vin_uv_warn_limit) { + pmdev->pages[i].status_word |= PB_STATUS_INPUT; + pmdev->pages[i].status_input |= PB_STATUS_INPUT_VIN_UV_WARN; + } + + if (pmdev->pages[i].read_iout > pmdev->pages[i].iout_oc_warn_limit) { + pmdev->pages[i].status_word |= PB_STATUS_IOUT_POUT; + pmdev->pages[i].status_iout |= PB_STATUS_IOUT_OC_WARN; + } + + if (pmdev->pages[i].read_iout > pmdev->pages[i].iout_oc_fault_limit) { + pmdev->pages[i].status_word |= PB_STATUS_IOUT_POUT; + pmdev->pages[i].status_iout |= PB_STATUS_IOUT_OC_FAULT; + } + + if (pmdev->pages[i].read_pin > pmdev->pages[i].pin_op_warn_limit) { + pmdev->pages[i].status_word |= PB_STATUS_INPUT; + pmdev->pages[i].status_input |= PB_STATUS_INPUT_PIN_OP_WARN; + } + + if (pmdev->pages[i].read_temperature_1 + > pmdev->pages[i].ot_fault_limit) { + pmdev->pages[i].status_word |= PB_STATUS_TEMPERATURE; + pmdev->pages[i].status_temperature |= PB_STATUS_OT_FAULT; + } + + if (pmdev->pages[i].read_temperature_1 + > pmdev->pages[i].ot_warn_limit) { + pmdev->pages[i].status_word |= PB_STATUS_TEMPERATURE; + pmdev->pages[i].status_temperature |= PB_STATUS_OT_WARN; + } + } +} + +static uint8_t pmbus_receive_byte(SMBusDevice *smd) +{ + PMBusDevice *pmdev = PMBUS_DEVICE(smd); + PMBusDeviceClass *pmdc = PMBUS_DEVICE_GET_CLASS(pmdev); + uint8_t ret = 0xFF; + uint8_t index = pmdev->page; + + if (pmdev->out_buf_len != 0) { + ret = pmbus_out_buf_pop(pmdev); + return ret; + } + + switch (pmdev->code) { + case PMBUS_PAGE: + pmbus_send8(pmdev, pmdev->page); + break; + + case PMBUS_OPERATION: /* R/W byte */ + pmbus_send8(pmdev, pmdev->pages[index].operation); + break; + + case PMBUS_ON_OFF_CONFIG: /* R/W byte */ + pmbus_send8(pmdev, pmdev->pages[index].on_off_config); + break; + + case PMBUS_PHASE: /* R/W byte */ + pmbus_send8(pmdev, pmdev->pages[index].phase); + break; + + case PMBUS_WRITE_PROTECT: /* R/W byte */ + pmbus_send8(pmdev, pmdev->pages[index].write_protect); + break; + + case PMBUS_CAPABILITY: + pmbus_send8(pmdev, pmdev->capability); + break; + + case PMBUS_VOUT_MODE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT_MODE) { + pmbus_send8(pmdev, pmdev->pages[index].vout_mode); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_COMMAND: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_command); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_TRIM: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_trim); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_CAL_OFFSET: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_cal_offset); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_MAX: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_max); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_MARGIN_HIGH: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT_MARGIN) { + pmbus_send16(pmdev, pmdev->pages[index].vout_margin_high); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_MARGIN_LOW: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT_MARGIN) { + pmbus_send16(pmdev, pmdev->pages[index].vout_margin_low); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_TRANSITION_RATE: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_transition_rate); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_DROOP: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_droop); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_SCALE_LOOP: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_scale_loop); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_SCALE_MONITOR: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_scale_monitor); + } else { + goto passthough; + } + break; + + /* TODO: implement coefficients support */ + + case PMBUS_POUT_MAX: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_POUT) { + pmbus_send16(pmdev, pmdev->pages[index].pout_max); + } else { + goto passthough; + } + break; + + case PMBUS_VIN_ON: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmbus_send16(pmdev, pmdev->pages[index].vin_on); + } else { + goto passthough; + } + break; + + case PMBUS_VIN_OFF: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmbus_send16(pmdev, pmdev->pages[index].vin_off); + } else { + goto passthough; + } + break; + + case PMBUS_IOUT_CAL_GAIN: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT_GAIN) { + pmbus_send16(pmdev, pmdev->pages[index].iout_cal_gain); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_OV_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_ov_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_OV_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send8(pmdev, pmdev->pages[index].vout_ov_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_OV_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_ov_warn_limit); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_UV_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_uv_warn_limit); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_UV_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].vout_uv_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_VOUT_UV_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send8(pmdev, pmdev->pages[index].vout_uv_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_IOUT_OC_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmbus_send16(pmdev, pmdev->pages[index].iout_oc_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_IOUT_OC_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmbus_send8(pmdev, pmdev->pages[index].iout_oc_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_IOUT_OC_LV_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmbus_send16(pmdev, pmdev->pages[index].iout_oc_lv_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_IOUT_OC_LV_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmbus_send8(pmdev, pmdev->pages[index].iout_oc_lv_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_IOUT_OC_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmbus_send16(pmdev, pmdev->pages[index].iout_oc_warn_limit); + } else { + goto passthough; + } + break; + + case PMBUS_IOUT_UC_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmbus_send16(pmdev, pmdev->pages[index].iout_uc_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_IOUT_UC_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmbus_send8(pmdev, pmdev->pages[index].iout_uc_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_OT_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmbus_send16(pmdev, pmdev->pages[index].ot_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_OT_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmbus_send8(pmdev, pmdev->pages[index].ot_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_OT_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmbus_send16(pmdev, pmdev->pages[index].ot_warn_limit); + } else { + goto passthough; + } + break; + + case PMBUS_UT_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmbus_send16(pmdev, pmdev->pages[index].ut_warn_limit); + } else { + goto passthough; + } + break; + + case PMBUS_UT_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmbus_send16(pmdev, pmdev->pages[index].ut_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_UT_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmbus_send8(pmdev, pmdev->pages[index].ut_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_VIN_OV_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmbus_send16(pmdev, pmdev->pages[index].vin_ov_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_VIN_OV_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmbus_send8(pmdev, pmdev->pages[index].vin_ov_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_VIN_OV_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmbus_send16(pmdev, pmdev->pages[index].vin_ov_warn_limit); + } else { + goto passthough; + } + break; + + case PMBUS_VIN_UV_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmbus_send16(pmdev, pmdev->pages[index].vin_uv_warn_limit); + } else { + goto passthough; + } + break; + + case PMBUS_VIN_UV_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmbus_send16(pmdev, pmdev->pages[index].vin_uv_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_VIN_UV_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmbus_send8(pmdev, pmdev->pages[index].vin_uv_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_IIN_OC_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IIN) { + pmbus_send16(pmdev, pmdev->pages[index].iin_oc_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_IIN_OC_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_IIN) { + pmbus_send8(pmdev, pmdev->pages[index].iin_oc_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_IIN_OC_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IIN) { + pmbus_send16(pmdev, pmdev->pages[index].iin_oc_warn_limit); + } else { + goto passthough; + } + break; + + case PMBUS_POUT_OP_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_POUT) { + pmbus_send16(pmdev, pmdev->pages[index].pout_op_fault_limit); + } else { + goto passthough; + } + break; + + case PMBUS_POUT_OP_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_POUT) { + pmbus_send8(pmdev, pmdev->pages[index].pout_op_fault_response); + } else { + goto passthough; + } + break; + + case PMBUS_POUT_OP_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_POUT) { + pmbus_send16(pmdev, pmdev->pages[index].pout_op_warn_limit); + } else { + goto passthough; + } + break; + + case PMBUS_PIN_OP_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_PIN) { + pmbus_send16(pmdev, pmdev->pages[index].pin_op_warn_limit); + } else { + goto passthough; + } + break; + + case PMBUS_STATUS_BYTE: /* R/W byte */ + pmbus_send8(pmdev, pmdev->pages[index].status_word & 0xFF); + break; + + case PMBUS_STATUS_WORD: /* R/W word */ + pmbus_send16(pmdev, pmdev->pages[index].status_word); + break; + + case PMBUS_STATUS_VOUT: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send8(pmdev, pmdev->pages[index].status_vout); + } else { + goto passthough; + } + break; + + case PMBUS_STATUS_IOUT: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmbus_send8(pmdev, pmdev->pages[index].status_iout); + } else { + goto passthough; + } + break; + + case PMBUS_STATUS_INPUT: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN || + pmdev->pages[index].page_flags & PB_HAS_IIN || + pmdev->pages[index].page_flags & PB_HAS_PIN) { + pmbus_send8(pmdev, pmdev->pages[index].status_input); + } else { + goto passthough; + } + break; + + case PMBUS_STATUS_TEMPERATURE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmbus_send8(pmdev, pmdev->pages[index].status_temperature); + } else { + goto passthough; + } + break; + + case PMBUS_STATUS_CML: /* R/W byte */ + pmbus_send8(pmdev, pmdev->pages[index].status_cml); + break; + + case PMBUS_STATUS_OTHER: /* R/W byte */ + pmbus_send8(pmdev, pmdev->pages[index].status_other); + break; + + case PMBUS_READ_EIN: /* Read-Only block 5 bytes */ + if (pmdev->pages[index].page_flags & PB_HAS_EIN) { + pmbus_send(pmdev, pmdev->pages[index].read_ein, 5); + } else { + goto passthough; + } + break; + + case PMBUS_READ_EOUT: /* Read-Only block 5 bytes */ + if (pmdev->pages[index].page_flags & PB_HAS_EOUT) { + pmbus_send(pmdev, pmdev->pages[index].read_eout, 5); + } else { + goto passthough; + } + break; + + case PMBUS_READ_VIN: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmbus_send16(pmdev, pmdev->pages[index].read_vin); + } else { + goto passthough; + } + break; + + case PMBUS_READ_IIN: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_IIN) { + pmbus_send16(pmdev, pmdev->pages[index].read_iin); + } else { + goto passthough; + } + break; + + case PMBUS_READ_VOUT: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmbus_send16(pmdev, pmdev->pages[index].read_vout); + } else { + goto passthough; + } + break; + + case PMBUS_READ_IOUT: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmbus_send16(pmdev, pmdev->pages[index].read_iout); + } else { + goto passthough; + } + break; + + case PMBUS_READ_TEMPERATURE_1: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmbus_send16(pmdev, pmdev->pages[index].read_temperature_1); + } else { + goto passthough; + } + break; + + case PMBUS_READ_TEMPERATURE_2: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMP2) { + pmbus_send16(pmdev, pmdev->pages[index].read_temperature_2); + } else { + goto passthough; + } + break; + + case PMBUS_READ_TEMPERATURE_3: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMP3) { + pmbus_send16(pmdev, pmdev->pages[index].read_temperature_3); + } else { + goto passthough; + } + break; + + case PMBUS_READ_POUT: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_POUT) { + pmbus_send16(pmdev, pmdev->pages[index].read_pout); + } else { + goto passthough; + } + break; + + case PMBUS_READ_PIN: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_PIN) { + pmbus_send16(pmdev, pmdev->pages[index].read_pin); + } else { + goto passthough; + } + break; + + case PMBUS_REVISION: /* Read-Only byte */ + pmbus_send8(pmdev, pmdev->pages[index].revision); + break; + + case PMBUS_MFR_ID: /* R/W block */ + if (pmdev->pages[index].page_flags & PB_HAS_MFR_INFO) { + pmbus_send_string(pmdev, pmdev->pages[index].mfr_id); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_MODEL: /* R/W block */ + if (pmdev->pages[index].page_flags & PB_HAS_MFR_INFO) { + pmbus_send_string(pmdev, pmdev->pages[index].mfr_model); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_REVISION: /* R/W block */ + if (pmdev->pages[index].page_flags & PB_HAS_MFR_INFO) { + pmbus_send_string(pmdev, pmdev->pages[index].mfr_revision); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_LOCATION: /* R/W block */ + if (pmdev->pages[index].page_flags & PB_HAS_MFR_INFO) { + pmbus_send_string(pmdev, pmdev->pages[index].mfr_location); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_VIN_MIN: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_vin_min); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_VIN_MAX: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_vin_max); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_IIN_MAX: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_IIN_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_iin_max); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_PIN_MAX: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_PIN_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_pin_max); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_VOUT_MIN: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_vout_min); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_VOUT_MAX: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_vout_max); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_IOUT_MAX: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_iout_max); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_POUT_MAX: /* Read-Only word */ + if (pmdev->pages[index].page_flags & PB_HAS_POUT_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_pout_max); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_MAX_TEMP_1: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMP_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_max_temp_1); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_MAX_TEMP_2: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMP_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_max_temp_2); + } else { + goto passthough; + } + break; + + case PMBUS_MFR_MAX_TEMP_3: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMP_RATING) { + pmbus_send16(pmdev, pmdev->pages[index].mfr_max_temp_3); + } else { + goto passthough; + } + break; + + case PMBUS_CLEAR_FAULTS: /* Send Byte */ + case PMBUS_PAGE_PLUS_WRITE: /* Block Write-only */ + case PMBUS_STORE_DEFAULT_ALL: /* Send Byte */ + case PMBUS_RESTORE_DEFAULT_ALL: /* Send Byte */ + case PMBUS_STORE_DEFAULT_CODE: /* Write-only Byte */ + case PMBUS_RESTORE_DEFAULT_CODE: /* Write-only Byte */ + case PMBUS_STORE_USER_ALL: /* Send Byte */ + case PMBUS_RESTORE_USER_ALL: /* Send Byte */ + case PMBUS_STORE_USER_CODE: /* Write-only Byte */ + case PMBUS_RESTORE_USER_CODE: /* Write-only Byte */ + case PMBUS_QUERY: /* Write-Only */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: reading from write only register 0x%02x\n", + __func__, pmdev->code); + break; + +passthough: + default: + /* Pass through read request if not handled */ + if (pmdc->receive_byte) { + ret = pmdc->receive_byte(pmdev); + } + break; + } + + if (pmdev->out_buf_len != 0) { + ret = pmbus_out_buf_pop(pmdev); + return ret; + } + + return ret; +} + +/* + * PMBus clear faults command applies to all status registers, existing faults + * should separately get re-asserted. + */ +static void pmbus_clear_faults(PMBusDevice *pmdev) +{ + for (uint8_t i = 0; i < pmdev->num_pages; i++) { + pmdev->pages[i].status_word = 0; + pmdev->pages[i].status_vout = 0; + pmdev->pages[i].status_iout = 0; + pmdev->pages[i].status_input = 0; + pmdev->pages[i].status_temperature = 0; + pmdev->pages[i].status_cml = 0; + pmdev->pages[i].status_other = 0; + pmdev->pages[i].status_mfr_specific = 0; + pmdev->pages[i].status_fans_1_2 = 0; + pmdev->pages[i].status_fans_3_4 = 0; + } + +} + +/* + * PMBus operation is used to turn On and Off PSUs + * Therefore, default value for the Operation should be PB_OP_ON or 0x80 + */ +static void pmbus_operation(PMBusDevice *pmdev) +{ + uint8_t index = pmdev->page; + if ((pmdev->pages[index].operation & PB_OP_ON) == 0) { + pmdev->pages[index].read_vout = 0; + pmdev->pages[index].read_iout = 0; + pmdev->pages[index].read_pout = 0; + return; + } + + if (pmdev->pages[index].operation & (PB_OP_ON | PB_OP_MARGIN_HIGH)) { + pmdev->pages[index].read_vout = pmdev->pages[index].vout_margin_high; + } + + if (pmdev->pages[index].operation & (PB_OP_ON | PB_OP_MARGIN_LOW)) { + pmdev->pages[index].read_vout = pmdev->pages[index].vout_margin_low; + } + pmbus_check_limits(pmdev); +} + +static int pmbus_write_data(SMBusDevice *smd, uint8_t *buf, uint8_t len) +{ + PMBusDevice *pmdev = PMBUS_DEVICE(smd); + PMBusDeviceClass *pmdc = PMBUS_DEVICE_GET_CLASS(pmdev); + int ret = 0; + uint8_t index; + + if (len == 0) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: writing empty data\n", __func__); + return -1; + } + + if (!pmdev->pages) { /* allocate memory for pages on first use */ + pmbus_pages_alloc(pmdev); + } + + pmdev->in_buf_len = len; + pmdev->in_buf = buf; + + pmdev->code = buf[0]; /* PMBus command code */ + if (len == 1) { /* Single length writes are command codes only */ + return 0; + } + + if (pmdev->code == PMBUS_PAGE) { + pmdev->page = pmbus_receive8(pmdev); + return 0; + } + /* loop through all the pages when 0xFF is received */ + if (pmdev->page == PB_ALL_PAGES) { + for (int i = 0; i < pmdev->num_pages; i++) { + pmdev->page = i; + pmbus_write_data(smd, buf, len); + } + pmdev->page = PB_ALL_PAGES; + return 0; + } + + index = pmdev->page; + + switch (pmdev->code) { + case PMBUS_OPERATION: /* R/W byte */ + pmdev->pages[index].operation = pmbus_receive8(pmdev); + pmbus_operation(pmdev); + break; + + case PMBUS_ON_OFF_CONFIG: /* R/W byte */ + pmdev->pages[index].on_off_config = pmbus_receive8(pmdev); + break; + + case PMBUS_CLEAR_FAULTS: /* Send Byte */ + pmbus_clear_faults(pmdev); + break; + + case PMBUS_PHASE: /* R/W byte */ + pmdev->pages[index].phase = pmbus_receive8(pmdev); + break; + + case PMBUS_PAGE_PLUS_WRITE: /* Block Write-only */ + case PMBUS_WRITE_PROTECT: /* R/W byte */ + pmdev->pages[index].write_protect = pmbus_receive8(pmdev); + break; + + case PMBUS_VOUT_MODE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT_MODE) { + pmdev->pages[index].vout_mode = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_COMMAND: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_command = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_TRIM: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_trim = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_CAL_OFFSET: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_cal_offset = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_MAX: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_max = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_MARGIN_HIGH: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT_MARGIN) { + pmdev->pages[index].vout_margin_high = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_MARGIN_LOW: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT_MARGIN) { + pmdev->pages[index].vout_margin_low = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_TRANSITION_RATE: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_transition_rate = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_DROOP: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_droop = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_SCALE_LOOP: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_scale_loop = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_SCALE_MONITOR: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_scale_monitor = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_POUT_MAX: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].pout_max = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VIN_ON: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmdev->pages[index].vin_on = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VIN_OFF: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmdev->pages[index].vin_off = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IOUT_CAL_GAIN: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT_GAIN) { + pmdev->pages[index].iout_cal_gain = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_OV_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_ov_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_OV_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_ov_fault_response = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_OV_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_ov_warn_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_UV_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_uv_warn_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_UV_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_uv_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VOUT_UV_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].vout_uv_fault_response = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IOUT_OC_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmdev->pages[index].iout_oc_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IOUT_OC_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmdev->pages[index].iout_oc_fault_response = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IOUT_OC_LV_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmdev->pages[index].iout_oc_lv_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IOUT_OC_LV_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmdev->pages[index].iout_oc_lv_fault_response + = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IOUT_OC_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmdev->pages[index].iout_oc_warn_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IOUT_UC_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmdev->pages[index].iout_uc_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IOUT_UC_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmdev->pages[index].iout_uc_fault_response = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_OT_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmdev->pages[index].ot_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_OT_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmdev->pages[index].ot_fault_response = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_OT_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmdev->pages[index].ot_warn_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_UT_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmdev->pages[index].ut_warn_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_UT_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmdev->pages[index].ut_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_UT_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmdev->pages[index].ut_fault_response = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VIN_OV_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmdev->pages[index].vin_ov_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VIN_OV_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmdev->pages[index].vin_ov_fault_response = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VIN_OV_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmdev->pages[index].vin_ov_warn_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VIN_UV_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmdev->pages[index].vin_uv_warn_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VIN_UV_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmdev->pages[index].vin_uv_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_VIN_UV_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VIN) { + pmdev->pages[index].vin_uv_fault_response = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IIN_OC_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IIN) { + pmdev->pages[index].iin_oc_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IIN_OC_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_IIN) { + pmdev->pages[index].iin_oc_fault_response = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_IIN_OC_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_IIN) { + pmdev->pages[index].iin_oc_warn_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_POUT_OP_FAULT_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].pout_op_fault_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_POUT_OP_FAULT_RESPONSE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].pout_op_fault_response = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_POUT_OP_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].pout_op_warn_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_PIN_OP_WARN_LIMIT: /* R/W word */ + if (pmdev->pages[index].page_flags & PB_HAS_PIN) { + pmdev->pages[index].pin_op_warn_limit = pmbus_receive16(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_STATUS_BYTE: /* R/W byte */ + pmdev->pages[index].status_word = pmbus_receive8(pmdev); + break; + + case PMBUS_STATUS_WORD: /* R/W word */ + pmdev->pages[index].status_word = pmbus_receive16(pmdev); + break; + + case PMBUS_STATUS_VOUT: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_VOUT) { + pmdev->pages[index].status_vout = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_STATUS_IOUT: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_IOUT) { + pmdev->pages[index].status_iout = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_STATUS_INPUT: /* R/W byte */ + pmdev->pages[index].status_input = pmbus_receive8(pmdev); + break; + + case PMBUS_STATUS_TEMPERATURE: /* R/W byte */ + if (pmdev->pages[index].page_flags & PB_HAS_TEMPERATURE) { + pmdev->pages[index].status_temperature = pmbus_receive8(pmdev); + } else { + goto passthrough; + } + break; + + case PMBUS_STATUS_CML: /* R/W byte */ + pmdev->pages[index].status_cml = pmbus_receive8(pmdev); + break; + + case PMBUS_STATUS_OTHER: /* R/W byte */ + pmdev->pages[index].status_other = pmbus_receive8(pmdev); + break; + + case PMBUS_PAGE_PLUS_READ: /* Block Read-only */ + case PMBUS_CAPABILITY: /* Read-Only byte */ + case PMBUS_COEFFICIENTS: /* Read-only block 5 bytes */ + case PMBUS_READ_EIN: /* Read-Only block 5 bytes */ + case PMBUS_READ_EOUT: /* Read-Only block 5 bytes */ + case PMBUS_READ_VIN: /* Read-Only word */ + case PMBUS_READ_IIN: /* Read-Only word */ + case PMBUS_READ_VCAP: /* Read-Only word */ + case PMBUS_READ_VOUT: /* Read-Only word */ + case PMBUS_READ_IOUT: /* Read-Only word */ + case PMBUS_READ_TEMPERATURE_1: /* Read-Only word */ + case PMBUS_READ_TEMPERATURE_2: /* Read-Only word */ + case PMBUS_READ_TEMPERATURE_3: /* Read-Only word */ + case PMBUS_READ_FAN_SPEED_1: /* Read-Only word */ + case PMBUS_READ_FAN_SPEED_2: /* Read-Only word */ + case PMBUS_READ_FAN_SPEED_3: /* Read-Only word */ + case PMBUS_READ_FAN_SPEED_4: /* Read-Only word */ + case PMBUS_READ_DUTY_CYCLE: /* Read-Only word */ + case PMBUS_READ_FREQUENCY: /* Read-Only word */ + case PMBUS_READ_POUT: /* Read-Only word */ + case PMBUS_READ_PIN: /* Read-Only word */ + case PMBUS_REVISION: /* Read-Only byte */ + case PMBUS_APP_PROFILE_SUPPORT: /* Read-Only block-read */ + case PMBUS_MFR_VIN_MIN: /* Read-Only word */ + case PMBUS_MFR_VIN_MAX: /* Read-Only word */ + case PMBUS_MFR_IIN_MAX: /* Read-Only word */ + case PMBUS_MFR_PIN_MAX: /* Read-Only word */ + case PMBUS_MFR_VOUT_MIN: /* Read-Only word */ + case PMBUS_MFR_VOUT_MAX: /* Read-Only word */ + case PMBUS_MFR_IOUT_MAX: /* Read-Only word */ + case PMBUS_MFR_POUT_MAX: /* Read-Only word */ + case PMBUS_MFR_TAMBIENT_MAX: /* Read-Only word */ + case PMBUS_MFR_TAMBIENT_MIN: /* Read-Only word */ + case PMBUS_MFR_EFFICIENCY_LL: /* Read-Only block 14 bytes */ + case PMBUS_MFR_EFFICIENCY_HL: /* Read-Only block 14 bytes */ + case PMBUS_MFR_PIN_ACCURACY: /* Read-Only byte */ + case PMBUS_IC_DEVICE_ID: /* Read-Only block-read */ + case PMBUS_IC_DEVICE_REV: /* Read-Only block-read */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: writing to read-only register 0x%02x\n", + __func__, pmdev->code); + break; + +passthrough: + /* Unimplimented registers get passed to the device */ + default: + if (pmdc->write_data) { + ret = pmdc->write_data(pmdev, buf, len); + } + break; + } + pmbus_check_limits(pmdev); + pmdev->in_buf_len = 0; + return ret; +} + +int pmbus_page_config(PMBusDevice *pmdev, uint8_t index, uint64_t flags) +{ + if (!pmdev->pages) { /* allocate memory for pages on first use */ + pmbus_pages_alloc(pmdev); + } + + /* The 0xFF page is special for commands applying to all pages */ + if (index == PB_ALL_PAGES) { + for (int i = 0; i < pmdev->num_pages; i++) { + pmdev->pages[i].page_flags = flags; + } + return 0; + } + + if (index > pmdev->num_pages - 1) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: index %u is out of range\n", + __func__, index); + return -1; + } + + pmdev->pages[index].page_flags = flags; + + return 0; +} + +/* TODO: include pmbus page info in vmstate */ +const VMStateDescription vmstate_pmbus_device = { + .name = TYPE_PMBUS_DEVICE, + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_SMBUS_DEVICE(smb, PMBusDevice), + VMSTATE_UINT8(num_pages, PMBusDevice), + VMSTATE_UINT8(code, PMBusDevice), + VMSTATE_UINT8(page, PMBusDevice), + VMSTATE_UINT8(capability, PMBusDevice), + VMSTATE_END_OF_LIST() + } +}; + +static void pmbus_device_finalize(Object *obj) +{ + PMBusDevice *pmdev = PMBUS_DEVICE(obj); + g_free(pmdev->pages); +} + +static void pmbus_device_class_init(ObjectClass *klass, void *data) +{ + SMBusDeviceClass *k = SMBUS_DEVICE_CLASS(klass); + + k->quick_cmd = pmbus_quick_cmd; + k->write_data = pmbus_write_data; + k->receive_byte = pmbus_receive_byte; +} + +static const TypeInfo pmbus_device_type_info = { + .name = TYPE_PMBUS_DEVICE, + .parent = TYPE_SMBUS_DEVICE, + .instance_size = sizeof(PMBusDevice), + .instance_finalize = pmbus_device_finalize, + .abstract = true, + .class_size = sizeof(PMBusDeviceClass), + .class_init = pmbus_device_class_init, +}; + +static void pmbus_device_register_types(void) +{ + type_register_static(&pmbus_device_type_info); +} + +type_init(pmbus_device_register_types) diff --git a/hw/i2c/ppc4xx_i2c.c b/hw/i2c/ppc4xx_i2c.c index c0a8e04567..75d50f1515 100644 --- a/hw/i2c/ppc4xx_i2c.c +++ b/hw/i2c/ppc4xx_i2c.c @@ -1,6 +1,8 @@ /* * PPC4xx I2C controller emulation * + * Documentation: PPC405GP User's Manual, Chapter 22. IIC Bus Interface + * * Copyright (c) 2007 Jocelyn Mayer * Copyright (c) 2012 François Revol * Copyright (c) 2016-2018 BALATON Zoltan @@ -238,11 +240,14 @@ static void ppc4xx_i2c_writeb(void *opaque, hwaddr addr, uint64_t value, i2c->sts &= ~IIC_STS_ERR; } } - if (!(i2c->sts & IIC_STS_ERR) && - i2c_send_recv(i2c->bus, &i2c->mdata[i], !recv)) { - i2c->sts |= IIC_STS_ERR; - i2c->extsts |= IIC_EXTSTS_XFRA; - break; + if (!(i2c->sts & IIC_STS_ERR)) { + if (recv) { + i2c->mdata[i] = i2c_recv(i2c->bus); + } else if (i2c_send(i2c->bus, i2c->mdata[i]) < 0) { + i2c->sts |= IIC_STS_ERR; + i2c->extsts |= IIC_EXTSTS_XFRA; + break; + } } if (value & IIC_CNTL_RPST || !(value & IIC_CNTL_CHT)) { i2c_end_transfer(i2c->bus); diff --git a/hw/i2c/smbus_eeprom.c b/hw/i2c/smbus_eeprom.c index 4d2bf99207..12c5741f38 100644 --- a/hw/i2c/smbus_eeprom.c +++ b/hw/i2c/smbus_eeprom.c @@ -276,7 +276,7 @@ uint8_t *spd_data_generate(enum sdram_type type, ram_addr_t ram_size) spd[18] = 12; /* ~CAS latencies supported */ spd[19] = (type == DDR2 ? 0 : 1); /* reserved / ~CS latencies supported */ spd[20] = 2; /* DIMM type / ~WE latencies */ - /* module features */ + spd[21] = (type < DDR2 ? 0x20 : 0); /* module features */ /* memory chip features */ spd[23] = 0x12; /* clock cycle time @ medium CAS latency */ /* data access time */ diff --git a/hw/i2c/smbus_master.c b/hw/i2c/smbus_master.c index dc43b8637d..6a53c34e70 100644 --- a/hw/i2c/smbus_master.c +++ b/hw/i2c/smbus_master.c @@ -29,7 +29,7 @@ int smbus_receive_byte(I2CBus *bus, uint8_t addr) { uint8_t data; - if (i2c_start_transfer(bus, addr, 1)) { + if (i2c_start_recv(bus, addr)) { return -1; } data = i2c_recv(bus); @@ -40,7 +40,7 @@ int smbus_receive_byte(I2CBus *bus, uint8_t addr) int smbus_send_byte(I2CBus *bus, uint8_t addr, uint8_t data) { - if (i2c_start_transfer(bus, addr, 0)) { + if (i2c_start_send(bus, addr)) { return -1; } i2c_send(bus, data); @@ -51,11 +51,11 @@ int smbus_send_byte(I2CBus *bus, uint8_t addr, uint8_t data) int smbus_read_byte(I2CBus *bus, uint8_t addr, uint8_t command) { uint8_t data; - if (i2c_start_transfer(bus, addr, 0)) { + if (i2c_start_send(bus, addr)) { return -1; } i2c_send(bus, command); - if (i2c_start_transfer(bus, addr, 1)) { + if (i2c_start_recv(bus, addr)) { i2c_end_transfer(bus); return -1; } @@ -67,7 +67,7 @@ int smbus_read_byte(I2CBus *bus, uint8_t addr, uint8_t command) int smbus_write_byte(I2CBus *bus, uint8_t addr, uint8_t command, uint8_t data) { - if (i2c_start_transfer(bus, addr, 0)) { + if (i2c_start_send(bus, addr)) { return -1; } i2c_send(bus, command); @@ -79,11 +79,11 @@ int smbus_write_byte(I2CBus *bus, uint8_t addr, uint8_t command, uint8_t data) int smbus_read_word(I2CBus *bus, uint8_t addr, uint8_t command) { uint16_t data; - if (i2c_start_transfer(bus, addr, 0)) { + if (i2c_start_send(bus, addr)) { return -1; } i2c_send(bus, command); - if (i2c_start_transfer(bus, addr, 1)) { + if (i2c_start_recv(bus, addr)) { i2c_end_transfer(bus); return -1; } @@ -96,7 +96,7 @@ int smbus_read_word(I2CBus *bus, uint8_t addr, uint8_t command) int smbus_write_word(I2CBus *bus, uint8_t addr, uint8_t command, uint16_t data) { - if (i2c_start_transfer(bus, addr, 0)) { + if (i2c_start_send(bus, addr)) { return -1; } i2c_send(bus, command); @@ -113,12 +113,12 @@ int smbus_read_block(I2CBus *bus, uint8_t addr, uint8_t command, uint8_t *data, int i; if (send_cmd) { - if (i2c_start_transfer(bus, addr, 0)) { + if (i2c_start_send(bus, addr)) { return -1; } i2c_send(bus, command); } - if (i2c_start_transfer(bus, addr, 1)) { + if (i2c_start_recv(bus, addr)) { if (send_cmd) { i2c_end_transfer(bus); } @@ -149,7 +149,7 @@ int smbus_write_block(I2CBus *bus, uint8_t addr, uint8_t command, uint8_t *data, len = 32; } - if (i2c_start_transfer(bus, addr, 0)) { + if (i2c_start_send(bus, addr)) { return -1; } i2c_send(bus, command); diff --git a/hw/i2c/trace-events b/hw/i2c/trace-events index 82fe6f965f..7d8907c1ee 100644 --- a/hw/i2c/trace-events +++ b/hw/i2c/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # core.c @@ -26,3 +26,8 @@ npcm7xx_smbus_recv_byte(const char *id, uint8_t value) "%s recv byte: 0x%02x" npcm7xx_smbus_stop(const char *id) "%s stopping" npcm7xx_smbus_nack(const char *id) "%s nacking" npcm7xx_smbus_recv_fifo(const char *id, uint8_t received, uint8_t expected) "%s recv fifo: received %u, expected %u" + +# i2c-mux-pca954x.c + +pca954x_write_bytes(uint8_t value) "PCA954X write data: 0x%02x" +pca954x_read_data(uint8_t value) "PCA954X read data: 0x%02x" diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index 5706cd765c..dc9e2d2e54 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -1,5 +1,9 @@ +config X86_FW_OVMF + bool + config SEV bool + select X86_FW_OVMF depends on KVM config PC @@ -23,7 +27,8 @@ config PC imply TPM_TIS_ISA imply VGA_PCI imply VIRTIO_VGA - select FDC + imply NVDIMM + select FDC_ISA select I8259 select I8254 select PCKBD @@ -106,6 +111,7 @@ config MICROVM select ACPI_HW_REDUCED select PCI_EXPRESS_GENERIC_BRIDGE select USB_XHCI_SYSBUS + select I8254 config X86_IOMMU bool diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 012cbe72e4..689247cd0f 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -43,7 +43,6 @@ #include "sysemu/tpm.h" #include "hw/acpi/tpm.h" #include "hw/acpi/vmgenid.h" -#include "hw/boards.h" #include "sysemu/tpm_backend.h" #include "hw/rtc/mc146818rtc_regs.h" #include "migration/vmstate.h" @@ -108,7 +107,9 @@ typedef struct AcpiPmInfo { typedef struct AcpiMiscInfo { bool is_piix4; bool has_hpet; +#ifdef CONFIG_TPM TPMVersion tpm_version; +#endif const unsigned char *dsdt_code; unsigned dsdt_size; uint16_t pvpanic_port; @@ -221,10 +222,6 @@ static void acpi_get_pm_info(MachineState *machine, AcpiPmInfo *pm) /* w2k requires FADT(rev1) or it won't boot, keep PC compatible */ pm->fadt.rev = 1; pm->cpu_hp_io_base = PIIX4_CPU_HOTPLUG_IO_BASE; - pm->pcihp_io_base = - object_property_get_uint(obj, ACPI_PCIHP_IO_BASE_PROP, NULL); - pm->pcihp_io_len = - object_property_get_uint(obj, ACPI_PCIHP_IO_LEN_PROP, NULL); } if (lpc) { uint64_t smi_features = object_property_get_uint(lpc, @@ -240,6 +237,10 @@ static void acpi_get_pm_info(MachineState *machine, AcpiPmInfo *pm) pm->smi_on_cpu_unplug = !!(smi_features & BIT_ULL(ICH9_LPC_SMI_F_CPU_HOT_UNPLUG_BIT)); } + pm->pcihp_io_base = + object_property_get_uint(obj, ACPI_PCIHP_IO_BASE_PROP, NULL); + pm->pcihp_io_len = + object_property_get_uint(obj, ACPI_PCIHP_IO_LEN_PROP, NULL); /* The above need not be conditional on machine type because the reset port * happens to be the same on PIIX (pc) and ICH9 (q35). */ @@ -290,7 +291,9 @@ static void acpi_get_misc_info(AcpiMiscInfo *info) } info->has_hpet = hpet_find(); +#ifdef CONFIG_TPM info->tpm_version = tpm_get_version(tpm_find()); +#endif info->pvpanic_port = pvpanic_port(); info->applesmc_io_base = applesmc_port(); } @@ -299,7 +302,7 @@ static void acpi_get_misc_info(AcpiMiscInfo *info) * Because of the PXB hosts we cannot simply query TYPE_PCI_HOST_BRIDGE. * On i386 arch we only have two pci hosts, so we can look only for them. */ -static Object *acpi_get_i386_pci_host(void) +Object *acpi_get_i386_pci_host(void) { PCIHostState *host; @@ -320,7 +323,10 @@ static void acpi_get_pci_holes(Range *hole, Range *hole64) Object *pci_host; pci_host = acpi_get_i386_pci_host(); - g_assert(pci_host); + + if (!pci_host) { + return; + } range_set_bounds1(hole, object_property_get_uint(pci_host, @@ -371,7 +377,7 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus, Aml *dev, *notify_method = NULL, *method; QObject *bsel; PCIBus *sec; - int i; + int devfn; bsel = object_property_get_qobject(OBJECT(bus), ACPI_PCIHP_PROP_BSEL, NULL); if (bsel) { @@ -381,20 +387,31 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus, notify_method = aml_method("DVNT", 2, AML_NOTSERIALIZED); } - for (i = 0; i < ARRAY_SIZE(bus->devices); i += PCI_FUNC_MAX) { + for (devfn = 0; devfn < ARRAY_SIZE(bus->devices); devfn++) { DeviceClass *dc; PCIDeviceClass *pc; - PCIDevice *pdev = bus->devices[i]; - int slot = PCI_SLOT(i); + PCIDevice *pdev = bus->devices[devfn]; + int slot = PCI_SLOT(devfn); + int func = PCI_FUNC(devfn); + /* ACPI spec: 1.0b: Table 6-2 _ADR Object Bus Types, PCI type */ + int adr = slot << 16 | func; bool hotplug_enabled_dev; bool bridge_in_acpi; bool cold_plugged_bridge; if (!pdev) { - if (bsel) { /* add hotplug slots for non present devices */ - dev = aml_device("S%.02X", PCI_DEVFN(slot, 0)); + /* + * add hotplug slots for non present devices. + * hotplug is supported only for non-multifunction device + * so generate device description only for function 0 + */ + if (bsel && !func) { + if (pci_bus_is_express(bus) && slot > 0) { + break; + } + dev = aml_device("S%.02X", devfn); aml_append(dev, aml_name_decl("_SUN", aml_int(slot))); - aml_append(dev, aml_name_decl("_ADR", aml_int(slot << 16))); + aml_append(dev, aml_name_decl("_ADR", aml_int(adr))); method = aml_method("_EJ0", 1, AML_NOTSERIALIZED); aml_append(method, aml_call2("PCEJ", aml_name("BSEL"), aml_name("_SUN")) @@ -430,16 +447,29 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus, continue; } - /* start to compose PCI slot descriptor */ - dev = aml_device("S%.02X", PCI_DEVFN(slot, 0)); - aml_append(dev, aml_name_decl("_ADR", aml_int(slot << 16))); + /* + * allow describing coldplugged bridges in ACPI even if they are not + * on function 0, as they are not unpluggable, for all other devices + * generate description only for function 0 per slot + */ + if (func && !bridge_in_acpi) { + continue; + } + + /* start to compose PCI device descriptor */ + dev = aml_device("S%.02X", devfn); + aml_append(dev, aml_name_decl("_ADR", aml_int(adr))); if (bsel) { - aml_append(dev, aml_name_decl("_SUN", aml_int(slot))); + /* + * Can't declare _SUN here for every device as it changes 'slot' + * enumeration order in linux kernel, so use another variable for it + */ + aml_append(dev, aml_name_decl("ASUN", aml_int(slot))); method = aml_method("_DSM", 4, AML_SERIALIZED); aml_append(method, aml_return( aml_call6("PDSM", aml_arg(0), aml_arg(1), aml_arg(2), - aml_arg(3), aml_name("BSEL"), aml_name("_SUN")) + aml_arg(3), aml_name("BSEL"), aml_name("ASUN")) )); aml_append(dev, method); } @@ -466,6 +496,7 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus, aml_append(method, aml_return(aml_int(s3d))); aml_append(dev, method); } else if (hotplug_enabled_dev) { + aml_append(dev, aml_name_decl("_SUN", aml_int(slot))); /* add _EJ0 to make slot hotpluggable */ method = aml_method("_EJ0", 1, AML_NOTSERIALIZED); aml_append(method, @@ -485,7 +516,7 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus, build_append_pci_bus_devices(dev, sec_bus, pcihp_bridge_en); } - /* slot descriptor has been composed, add it into parent context */ + /* device descriptor has been composed, add it into parent context */ aml_append(parent_scope, dev); } @@ -514,13 +545,12 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus, /* Notify about child bus events in any case */ if (pcihp_bridge_en) { QLIST_FOREACH(sec, &bus->child, sibling) { - int32_t devfn = sec->parent_dev->devfn; - - if (pci_bus_is_root(sec) || pci_bus_is_express(sec)) { + if (pci_bus_is_root(sec)) { continue; } - aml_append(method, aml_name("^S%.02X.PCNT", devfn)); + aml_append(method, aml_name("^S%.02X.PCNT", + sec->parent_dev->devfn)); } } @@ -1246,7 +1276,7 @@ static void build_piix4_isa_bridge(Aml *table) aml_append(table, scope); } -static void build_piix4_pci_hotplug(Aml *table) +static void build_x86_acpi_pci_hotplug(Aml *table, uint64_t pcihp_addr) { Aml *scope; Aml *field; @@ -1255,20 +1285,22 @@ static void build_piix4_pci_hotplug(Aml *table) scope = aml_scope("_SB.PCI0"); aml_append(scope, - aml_operation_region("PCST", AML_SYSTEM_IO, aml_int(0xae00), 0x08)); + aml_operation_region("PCST", AML_SYSTEM_IO, aml_int(pcihp_addr), 0x08)); field = aml_field("PCST", AML_DWORD_ACC, AML_NOLOCK, AML_WRITE_AS_ZEROS); aml_append(field, aml_named_field("PCIU", 32)); aml_append(field, aml_named_field("PCID", 32)); aml_append(scope, field); aml_append(scope, - aml_operation_region("SEJ", AML_SYSTEM_IO, aml_int(0xae08), 0x04)); + aml_operation_region("SEJ", AML_SYSTEM_IO, + aml_int(pcihp_addr + ACPI_PCIHP_SEJ_BASE), 0x04)); field = aml_field("SEJ", AML_DWORD_ACC, AML_NOLOCK, AML_WRITE_AS_ZEROS); aml_append(field, aml_named_field("B0EJ", 32)); aml_append(scope, field); aml_append(scope, - aml_operation_region("BNMR", AML_SYSTEM_IO, aml_int(0xae10), 0x08)); + aml_operation_region("BNMR", AML_SYSTEM_IO, + aml_int(pcihp_addr + ACPI_PCIHP_BNMR_BASE), 0x08)); field = aml_field("BNMR", AML_DWORD_ACC, AML_NOLOCK, AML_WRITE_AS_ZEROS); aml_append(field, aml_named_field("BNUM", 32)); aml_append(field, aml_named_field("PIDX", 32)); @@ -1375,7 +1407,9 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, uint32_t nr_mem = machine->ram_slots; int root_bus_limit = 0xFF; PCIBus *bus = NULL; +#ifdef CONFIG_TPM TPMIf *tpm = tpm_find(); +#endif int i; VMBusBridge *vmbus_bridge = vmbus_bridge_find(); @@ -1400,7 +1434,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, build_piix4_isa_bridge(dsdt); build_isa_devices_aml(dsdt); if (pm->pcihp_bridge_en || pm->pcihp_root_en) { - build_piix4_pci_hotplug(dsdt); + build_x86_acpi_pci_hotplug(dsdt, pm->pcihp_io_base); } build_piix4_pci0_int(dsdt); } else { @@ -1448,6 +1482,9 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, } build_q35_isa_bridge(dsdt); build_isa_devices_aml(dsdt); + if (pm->pcihp_bridge_en) { + build_x86_acpi_pci_hotplug(dsdt, pm->pcihp_io_base); + } build_q35_pci0_int(dsdt); if (pcms->smbus && !pcmc->do_not_add_smb_acpi) { build_smb0(dsdt, pcms->smbus, ICH9_SMB_DEV, ICH9_SMB_FUNC); @@ -1482,7 +1519,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, { aml_append(scope, aml_name_decl("_HID", aml_string("ACPI0006"))); - if (misc->is_piix4 && (pm->pcihp_bridge_en || pm->pcihp_root_en)) { + if (pm->pcihp_bridge_en || pm->pcihp_root_en) { method = aml_method("_E01", 0, AML_NOTSERIALIZED); aml_append(method, aml_acquire(aml_name("\\_SB.PCI0.BLCK"), 0xFFFF)); @@ -1608,10 +1645,12 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, } } +#ifdef CONFIG_TPM if (TPM_IS_TIS_ISA(tpm_find())) { aml_append(crs, aml_memory32_fixed(TPM_TIS_ADDR_BASE, TPM_TIS_ADDR_SIZE, AML_READ_WRITE)); } +#endif aml_append(scope, aml_name_decl("_CRS", crs)); /* reserve GPE0 block resources */ @@ -1748,6 +1787,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, PCIBus *bus = NULL; pci_host = acpi_get_i386_pci_host(); + if (pci_host) { bus = PCI_HOST_BRIDGE(pci_host)->bus; } @@ -1757,6 +1797,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, /* Scan all PCI buses. Generate tables to support hotplug. */ build_append_pci_bus_devices(scope, bus, pm->pcihp_bridge_en); +#ifdef CONFIG_TPM if (TPM_IS_TIS_ISA(tpm)) { if (misc->tpm_version == TPM_VERSION_2_0) { dev = aml_device("TPM"); @@ -1784,11 +1825,13 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, aml_append(scope, dev); } +#endif aml_append(sb_scope, scope); } } +#ifdef CONFIG_TPM if (TPM_IS_CRB(tpm)) { dev = aml_device("TPM"); aml_append(dev, aml_name_decl("_HID", aml_string("MSFT0101"))); @@ -1803,6 +1846,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, aml_append(sb_scope, dev); } +#endif aml_append(dsdt, sb_scope); @@ -1819,6 +1863,7 @@ build_hpet(GArray *table_data, BIOSLinker *linker, const char *oem_id, const char *oem_table_id) { Acpi20Hpet *hpet; + int hpet_start = table_data->len; hpet = acpi_data_push(table_data, sizeof(*hpet)); /* Note timer_block_id value must be kept in sync with value advertised by @@ -1827,13 +1872,16 @@ build_hpet(GArray *table_data, BIOSLinker *linker, const char *oem_id, hpet->timer_block_id = cpu_to_le32(0x8086a201); hpet->addr.address = cpu_to_le64(HPET_BASE); build_header(linker, table_data, - (void *)hpet, "HPET", sizeof(*hpet), 1, oem_id, oem_table_id); + (void *)(table_data->data + hpet_start), + "HPET", sizeof(*hpet), 1, oem_id, oem_table_id); } +#ifdef CONFIG_TPM static void build_tpm_tcpa(GArray *table_data, BIOSLinker *linker, GArray *tcpalog, const char *oem_id, const char *oem_table_id) { + int tcpa_start = table_data->len; Acpi20Tcpa *tcpa = acpi_data_push(table_data, sizeof *tcpa); unsigned log_addr_size = sizeof(tcpa->log_area_start_address); unsigned log_addr_offset = @@ -1852,8 +1900,10 @@ build_tpm_tcpa(GArray *table_data, BIOSLinker *linker, GArray *tcpalog, ACPI_BUILD_TPMLOG_FILE, 0); build_header(linker, table_data, - (void *)tcpa, "TCPA", sizeof(*tcpa), 2, oem_id, oem_table_id); + (void *)(table_data->data + tcpa_start), + "TCPA", sizeof(*tcpa), 2, oem_id, oem_table_id); } +#endif #define HOLE_640K_START (640 * KiB) #define HOLE_640K_END (1 * MiB) @@ -1991,6 +2041,56 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) x86ms->oem_table_id); } +/* + * Insert DMAR scope for PCI bridges and endpoint devcie + */ +static void +insert_scope(PCIBus *bus, PCIDevice *dev, void *opaque) +{ + GArray *scope_blob = opaque; + AcpiDmarDeviceScope *scope = NULL; + + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) { + /* Dmar Scope Type: 0x02 for PCI Bridge */ + build_append_int_noprefix(scope_blob, 0x02, 1); + } else { + /* Dmar Scope Type: 0x01 for PCI Endpoint Device */ + build_append_int_noprefix(scope_blob, 0x01, 1); + } + + /* length */ + build_append_int_noprefix(scope_blob, + sizeof(*scope) + sizeof(scope->path[0]), 1); + /* reserved */ + build_append_int_noprefix(scope_blob, 0, 2); + /* enumeration_id */ + build_append_int_noprefix(scope_blob, 0, 1); + /* bus */ + build_append_int_noprefix(scope_blob, pci_bus_num(bus), 1); + /* device */ + build_append_int_noprefix(scope_blob, PCI_SLOT(dev->devfn), 1); + /* function */ + build_append_int_noprefix(scope_blob, PCI_FUNC(dev->devfn), 1); +} + +/* For a given PCI host bridge, walk and insert DMAR scope */ +static int +dmar_host_bridges(Object *obj, void *opaque) +{ + GArray *scope_blob = opaque; + + if (object_dynamic_cast(obj, TYPE_PCI_HOST_BRIDGE)) { + PCIBus *bus = PCI_HOST_BRIDGE(obj)->bus; + + if (bus && !pci_bus_bypass_iommu(bus)) { + pci_for_each_device(bus, pci_bus_num(bus), insert_scope, + scope_blob); + } + } + + return 0; +} + /* * VT-d spec 8.1 DMA Remapping Reporting Structure * (version Oct. 2014 or later) @@ -2010,6 +2110,15 @@ build_dmar_q35(GArray *table_data, BIOSLinker *linker, const char *oem_id, /* Root complex IOAPIC use one path[0] only */ size_t ioapic_scope_size = sizeof(*scope) + sizeof(scope->path[0]); IntelIOMMUState *intel_iommu = INTEL_IOMMU_DEVICE(iommu); + GArray *scope_blob = g_array_new(false, true, 1); + + /* + * A PCI bus walk, for each PCI host bridge. + * Insert scope for each PCI bridge and endpoint device which + * is attached to a bus with iommu enabled. + */ + object_child_foreach_recursive(object_get_root(), + dmar_host_bridges, scope_blob); assert(iommu); if (x86_iommu_ir_supported(iommu)) { @@ -2023,8 +2132,9 @@ build_dmar_q35(GArray *table_data, BIOSLinker *linker, const char *oem_id, /* DMAR Remapping Hardware Unit Definition structure */ drhd = acpi_data_push(table_data, sizeof(*drhd) + ioapic_scope_size); drhd->type = cpu_to_le16(ACPI_DMAR_TYPE_HARDWARE_UNIT); - drhd->length = cpu_to_le16(sizeof(*drhd) + ioapic_scope_size); - drhd->flags = ACPI_DMAR_INCLUDE_PCI_ALL; + drhd->length = + cpu_to_le16(sizeof(*drhd) + ioapic_scope_size + scope_blob->len); + drhd->flags = 0; /* Don't include all pci device */ drhd->pci_segment = cpu_to_le16(0); drhd->address = cpu_to_le64(Q35_HOST_BRIDGE_IOMMU_ADDR); @@ -2038,6 +2148,10 @@ build_dmar_q35(GArray *table_data, BIOSLinker *linker, const char *oem_id, scope->path[0].device = PCI_SLOT(Q35_PSEUDO_DEVFN_IOAPIC); scope->path[0].function = PCI_FUNC(Q35_PSEUDO_DEVFN_IOAPIC); + /* Add scope found above */ + g_array_append_vals(table_data, scope_blob->data, scope_blob->len); + g_array_free(scope_blob, true); + if (iommu->dt_supported) { atsr = acpi_data_push(table_data, sizeof(*atsr)); atsr->type = cpu_to_le16(ACPI_DMAR_TYPE_ATSR); @@ -2168,7 +2282,7 @@ ivrs_host_bridges(Object *obj, void *opaque) if (object_dynamic_cast(obj, TYPE_PCI_HOST_BRIDGE)) { PCIBus *bus = PCI_HOST_BRIDGE(obj)->bus; - if (bus) { + if (bus && !pci_bus_bypass_iommu(bus)) { pci_for_each_device(bus, pci_bus_num(bus), insert_ivhd, ivhd_blob); } } @@ -2294,7 +2408,9 @@ static bool acpi_get_mcfg(AcpiMcfgInfo *mcfg) QObject *o; pci_host = acpi_get_i386_pci_host(); - g_assert(pci_host); + if (!pci_host) { + return false; + } o = object_property_get_qobject(pci_host, PCIE_HOST_MCFG_BASE, NULL); if (!o) { @@ -2324,7 +2440,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) AcpiPmInfo pm; AcpiMiscInfo misc; AcpiMcfgInfo mcfg; - Range pci_hole, pci_hole64; + Range pci_hole = {}, pci_hole64 = {}; uint8_t *u; size_t aml_len = 0; GArray *tables_blob = tables->table_data; @@ -2403,6 +2519,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) build_hpet(tables_blob, tables->linker, x86ms->oem_id, x86ms->oem_table_id); } +#ifdef CONFIG_TPM if (misc.tpm_version != TPM_VERSION_UNSPEC) { if (misc.tpm_version == TPM_VERSION_1_2) { acpi_add_table(table_offsets, tables_blob); @@ -2414,6 +2531,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) x86ms->oem_id, x86ms->oem_table_id); } } +#endif if (pcms->numa_nodes) { acpi_add_table(table_offsets, tables_blob); build_srat(tables_blob, tables->linker, machine); @@ -2605,8 +2723,10 @@ void acpi_setup(void) AcpiBuildTables tables; AcpiBuildState *build_state; Object *vmgenid_dev; +#ifdef CONFIG_TPM TPMIf *tpm; static FwCfgTPMConfig tpm_config; +#endif if (!x86ms->fw_cfg) { ACPI_BUILD_DPRINTF("No fw cfg. Bailing out.\n"); @@ -2638,6 +2758,7 @@ void acpi_setup(void) acpi_add_rom_blob(acpi_build_update, build_state, tables.linker->cmd_blob, ACPI_BUILD_LOADER_FILE); +#ifdef CONFIG_TPM fw_cfg_add_file(x86ms->fw_cfg, ACPI_BUILD_TPMLOG_FILE, tables.tcpalog->data, acpi_data_len(tables.tcpalog)); @@ -2651,6 +2772,7 @@ void acpi_setup(void) fw_cfg_add_file(x86ms->fw_cfg, "etc/tpm/config", &tpm_config, sizeof tpm_config); } +#endif vmgenid_dev = find_vmgenid_dev(); if (vmgenid_dev) { diff --git a/hw/i386/acpi-build.h b/hw/i386/acpi-build.h index 74df5fc612..0dce155c8c 100644 --- a/hw/i386/acpi-build.h +++ b/hw/i386/acpi-build.h @@ -5,6 +5,11 @@ extern const struct AcpiGenericAddress x86_nvdimm_acpi_dsmio; +/* PCI Hot-plug registers bases. See docs/spec/acpi_pci_hotplug.txt */ +#define ACPI_PCIHP_SEJ_BASE 0x8 +#define ACPI_PCIHP_BNMR_BASE 0x10 + void acpi_setup(void); +Object *acpi_get_i386_pci_host(void); #endif diff --git a/hw/i386/acpi-common.h b/hw/i386/acpi-common.h index b12cd73ea5..a68825acf5 100644 --- a/hw/i386/acpi-common.h +++ b/hw/i386/acpi-common.h @@ -1,9 +1,9 @@ #ifndef HW_I386_ACPI_COMMON_H #define HW_I386_ACPI_COMMON_H -#include "include/hw/acpi/acpi_dev_interface.h" -#include "include/hw/acpi/bios-linker-loader.h" -#include "include/hw/i386/x86.h" +#include "hw/acpi/acpi_dev_interface.h" +#include "hw/acpi/bios-linker-loader.h" +#include "hw/i386/x86.h" /* Default IOAPIC ID */ #define ACPI_BUILD_IOAPIC_ID 0x0 diff --git a/hw/i386/acpi-microvm.c b/hw/i386/acpi-microvm.c index ccd3303aac..1a0f77b911 100644 --- a/hw/i386/acpi-microvm.c +++ b/hw/i386/acpi-microvm.c @@ -30,7 +30,6 @@ #include "hw/acpi/bios-linker-loader.h" #include "hw/acpi/generic_event_device.h" #include "hw/acpi/utils.h" -#include "hw/boards.h" #include "hw/i386/fw_cfg.h" #include "hw/i386/microvm.h" #include "hw/pci/pci.h" diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c index 74a93a5d93..2801dff97c 100644 --- a/hw/i386/amd_iommu.c +++ b/hw/i386/amd_iommu.c @@ -99,7 +99,7 @@ static uint64_t amdvi_readq(AMDVIState *s, hwaddr addr) } /* internal write */ -static void amdvi_writeq_raw(AMDVIState *s, uint64_t val, hwaddr addr) +static void amdvi_writeq_raw(AMDVIState *s, hwaddr addr, uint64_t val) { stq_le_p(&s->mmior[addr], val); } @@ -382,7 +382,7 @@ static void amdvi_completion_wait(AMDVIState *s, uint64_t *cmd) } /* set completion interrupt */ if (extract64(cmd[0], 1, 1)) { - amdvi_test_mask(s, AMDVI_MMIO_STATUS, AMDVI_MMIO_STATUS_COMP_INT); + amdvi_assign_orq(s, AMDVI_MMIO_STATUS, AMDVI_MMIO_STATUS_COMP_INT); /* generate interrupt */ amdvi_generate_msi_interrupt(s); } @@ -553,7 +553,7 @@ static void amdvi_cmdbuf_run(AMDVIState *s) trace_amdvi_command_exec(s->cmdbuf_head, s->cmdbuf_tail, s->cmdbuf); amdvi_cmdbuf_exec(s); s->cmdbuf_head += AMDVI_COMMAND_SIZE; - amdvi_writeq_raw(s, s->cmdbuf_head, AMDVI_MMIO_COMMAND_HEAD); + amdvi_writeq_raw(s, AMDVI_MMIO_COMMAND_HEAD, s->cmdbuf_head); /* wrap head pointer */ if (s->cmdbuf_head >= s->cmdbuf_len * AMDVI_COMMAND_SIZE) { @@ -860,8 +860,8 @@ static inline uint8_t get_pte_translation_mode(uint64_t pte) static inline uint64_t pte_override_page_mask(uint64_t pte) { - uint8_t page_mask = 12; - uint64_t addr = (pte & AMDVI_DEV_PT_ROOT_MASK) ^ AMDVI_DEV_PT_ROOT_MASK; + uint8_t page_mask = 13; + uint64_t addr = (pte & AMDVI_DEV_PT_ROOT_MASK) >> 12; /* find the first zero bit */ while (addr & 1) { page_mask++; diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c index e48a54fa36..4e68d5dea4 100644 --- a/hw/i386/fw_cfg.c +++ b/hw/i386/fw_cfg.c @@ -22,6 +22,7 @@ #include "hw/nvram/fw_cfg.h" #include "e820_memory_layout.h" #include "kvm/kvm_i386.h" +#include "qapi/error.h" #include CONFIG_DEVICES struct hpet_fw_config hpet_cfg = {.count = UINT8_MAX}; @@ -78,7 +79,8 @@ void fw_cfg_build_smbios(MachineState *ms, FWCfgState *fw_cfg) } smbios_get_tables(ms, mem_array, array_count, &smbios_tables, &smbios_tables_len, - &smbios_anchor, &smbios_anchor_len); + &smbios_anchor, &smbios_anchor_len, + &error_fatal); g_free(mem_array); if (smbios_anchor) { diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 6be8f32918..209b3f5553 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -24,14 +24,12 @@ #include "qemu/main-loop.h" #include "qapi/error.h" #include "hw/sysbus.h" -#include "exec/address-spaces.h" #include "intel_iommu_internal.h" #include "hw/pci/pci.h" #include "hw/pci/pci_bus.h" #include "hw/qdev-properties.h" #include "hw/i386/pc.h" #include "hw/i386/apic-msidef.h" -#include "hw/boards.h" #include "hw/i386/x86-iommu.h" #include "hw/pci-host/q35.h" #include "sysemu/kvm.h" diff --git a/hw/i386/kvm/apic.c b/hw/i386/kvm/apic.c index 3dbff2be2e..1e89ca0899 100644 --- a/hw/i386/kvm/apic.c +++ b/hw/i386/kvm/apic.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" #include "qemu/module.h" -#include "cpu.h" #include "hw/i386/apic_internal.h" #include "hw/pci/msi.h" #include "sysemu/hw_accel.h" @@ -146,7 +145,7 @@ static void kvm_apic_put(CPUState *cs, run_on_cpu_data data) ret = kvm_vcpu_ioctl(CPU(s->cpu), KVM_SET_LAPIC, &kapic); if (ret < 0) { - fprintf(stderr, "KVM_SET_LAPIC failed: %s\n", strerror(ret)); + fprintf(stderr, "KVM_SET_LAPIC failed: %s\n", strerror(-ret)); abort(); } } diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c index 51872dd84c..df70b4a033 100644 --- a/hw/i386/kvm/clock.c +++ b/hw/i386/kvm/clock.c @@ -14,7 +14,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "qemu/host-utils.h" #include "qemu/module.h" #include "sysemu/kvm.h" @@ -106,7 +105,7 @@ static void kvm_update_clock(KVMClockState *s) ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data); if (ret < 0) { - fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret)); + fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(-ret)); abort(); } s->clock = data.clock; @@ -190,7 +189,7 @@ static void kvmclock_vm_state_change(void *opaque, bool running, data.clock = s->clock; ret = kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data); if (ret < 0) { - fprintf(stderr, "KVM_SET_CLOCK failed: %s\n", strerror(ret)); + fprintf(stderr, "KVM_SET_CLOCK failed: %s\n", strerror(-ret)); abort(); } diff --git a/hw/i386/kvm/i8254.c b/hw/i386/kvm/i8254.c index c558893961..fa68669e8a 100644 --- a/hw/i386/kvm/i8254.c +++ b/hw/i386/kvm/i8254.c @@ -104,7 +104,7 @@ static void kvm_pit_get(PITCommonState *pit) if (kvm_has_pit_state2()) { ret = kvm_vm_ioctl(kvm_state, KVM_GET_PIT2, &kpit); if (ret < 0) { - fprintf(stderr, "KVM_GET_PIT2 failed: %s\n", strerror(ret)); + fprintf(stderr, "KVM_GET_PIT2 failed: %s\n", strerror(-ret)); abort(); } pit->channels[0].irq_disabled = kpit.flags & KVM_PIT_FLAGS_HPET_LEGACY; @@ -115,7 +115,7 @@ static void kvm_pit_get(PITCommonState *pit) */ ret = kvm_vm_ioctl(kvm_state, KVM_GET_PIT, &kpit); if (ret < 0) { - fprintf(stderr, "KVM_GET_PIT failed: %s\n", strerror(ret)); + fprintf(stderr, "KVM_GET_PIT failed: %s\n", strerror(-ret)); abort(); } } @@ -180,7 +180,7 @@ static void kvm_pit_put(PITCommonState *pit) if (ret < 0) { fprintf(stderr, "%s failed: %s\n", kvm_has_pit_state2() ? "KVM_SET_PIT2" : "KVM_SET_PIT", - strerror(ret)); + strerror(-ret)); abort(); } } @@ -272,7 +272,7 @@ static void kvm_pit_realizefn(DeviceState *dev, Error **errp) } if (ret < 0) { error_setg(errp, "Create kernel PIC irqchip failed: %s", - strerror(ret)); + strerror(-ret)); return; } switch (s->lost_tick_policy) { @@ -286,7 +286,7 @@ static void kvm_pit_realizefn(DeviceState *dev, Error **errp) if (ret < 0) { error_setg(errp, "Can't disable in-kernel PIT reinjection: %s", - strerror(ret)); + strerror(-ret)); return; } } diff --git a/hw/i386/kvm/i8259.c b/hw/i386/kvm/i8259.c index 3f8bf69e9c..d61bae4dc3 100644 --- a/hw/i386/kvm/i8259.c +++ b/hw/i386/kvm/i8259.c @@ -43,7 +43,7 @@ static void kvm_pic_get(PICCommonState *s) chip.chip_id = s->master ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE; ret = kvm_vm_ioctl(kvm_state, KVM_GET_IRQCHIP, &chip); if (ret < 0) { - fprintf(stderr, "KVM_GET_IRQCHIP failed: %s\n", strerror(ret)); + fprintf(stderr, "KVM_GET_IRQCHIP failed: %s\n", strerror(-ret)); abort(); } @@ -96,7 +96,7 @@ static void kvm_pic_put(PICCommonState *s) ret = kvm_vm_ioctl(kvm_state, KVM_SET_IRQCHIP, &chip); if (ret < 0) { - fprintf(stderr, "KVM_SET_IRQCHIP failed: %s\n", strerror(ret)); + fprintf(stderr, "KVM_SET_IRQCHIP failed: %s\n", strerror(-ret)); abort(); } } diff --git a/hw/i386/kvm/ioapic.c b/hw/i386/kvm/ioapic.c index dfc3c98005..ee7c8ef68b 100644 --- a/hw/i386/kvm/ioapic.c +++ b/hw/i386/kvm/ioapic.c @@ -13,7 +13,6 @@ #include "qemu/osdep.h" #include "monitor/monitor.h" #include "hw/i386/x86.h" -#include "hw/irq.h" #include "hw/qdev-properties.h" #include "hw/i386/ioapic_internal.h" #include "hw/i386/apic_internal.h" @@ -63,7 +62,7 @@ static void kvm_ioapic_get(IOAPICCommonState *s) chip.chip_id = KVM_IRQCHIP_IOAPIC; ret = kvm_vm_ioctl(kvm_state, KVM_GET_IRQCHIP, &chip); if (ret < 0) { - fprintf(stderr, "KVM_GET_IRQCHIP failed: %s\n", strerror(ret)); + fprintf(stderr, "KVM_GET_IRQCHIP failed: %s\n", strerror(-ret)); abort(); } @@ -96,7 +95,7 @@ static void kvm_ioapic_put(IOAPICCommonState *s) ret = kvm_vm_ioctl(kvm_state, KVM_SET_IRQCHIP, &chip); if (ret < 0) { - fprintf(stderr, "KVM_SET_IRQCHIP failed: %s\n", strerror(ret)); + fprintf(stderr, "KVM_SET_IRQCHIP failed: %s\n", strerror(-ret)); abort(); } } diff --git a/hw/i386/kvmvapic.c b/hw/i386/kvmvapic.c index 46315445d2..43f8a8f679 100644 --- a/hw/i386/kvmvapic.c +++ b/hw/i386/kvmvapic.c @@ -11,7 +11,6 @@ #include "qemu/osdep.h" #include "qemu/module.h" -#include "cpu.h" #include "sysemu/sysemu.h" #include "sysemu/cpus.h" #include "sysemu/hw_accel.h" diff --git a/hw/i386/meson.build b/hw/i386/meson.build index e5d109f5c6..80dad29f2b 100644 --- a/hw/i386/meson.build +++ b/hw/i386/meson.build @@ -24,6 +24,8 @@ i386_ss.add(when: 'CONFIG_PC', if_true: files( 'pc_sysfw.c', 'acpi-build.c', 'port92.c')) +i386_ss.add(when: 'CONFIG_X86_FW_OVMF', if_true: files('pc_sysfw_ovmf.c'), + if_false: files('pc_sysfw_ovmf-stubs.c')) subdir('kvm') subdir('xen') diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c index edf2b0f061..aba0c83219 100644 --- a/hw/i386/microvm.c +++ b/hw/i386/microvm.c @@ -49,7 +49,6 @@ #include "hw/pci-host/gpex.h" #include "hw/usb/xhci.h" -#include "cpu.h" #include "elf.h" #include "kvm/kvm_i386.h" #include "hw/xen/start_info.h" diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 8a84b25a03..c2b9d62a35 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -65,7 +65,6 @@ #include "hw/xen/start_info.h" #include "ui/qemu-spice.h" #include "exec/memory.h" -#include "exec/address-spaces.h" #include "sysemu/arch_init.h" #include "qemu/bitmap.h" #include "qemu/config-file.h" @@ -74,7 +73,6 @@ #include "qemu/cutils.h" #include "hw/acpi/acpi.h" #include "hw/acpi/cpu_hotplug.h" -#include "hw/boards.h" #include "acpi-build.h" #include "hw/mem/pc-dimm.h" #include "hw/mem/nvdimm.h" @@ -96,6 +94,15 @@ #include "trace.h" #include CONFIG_DEVICES +GlobalProperty pc_compat_6_0[] = { + { "qemu64" "-" TYPE_X86_CPU, "family", "6" }, + { "qemu64" "-" TYPE_X86_CPU, "model", "6" }, + { "qemu64" "-" TYPE_X86_CPU, "stepping", "3" }, + { TYPE_X86_CPU, "x-vendor-cpuid-only", "off" }, + { "ICH9-LPC", "acpi-pci-hotplug-with-bridge-support", "off" }, +}; +const size_t pc_compat_6_0_len = G_N_ELEMENTS(pc_compat_6_0); + GlobalProperty pc_compat_5_2[] = { { "ICH9-LPC", "x-smi-cpu-hotunplug", "off" }, }; @@ -705,73 +712,61 @@ void pc_acpi_smi_interrupt(void *opaque, int irq, int level) * This function is very similar to smp_parse() * in hw/core/machine.c but includes CPU die support. */ -void pc_smp_parse(MachineState *ms, QemuOpts *opts) +static void pc_smp_parse(MachineState *ms, SMPConfiguration *config, Error **errp) { - X86MachineState *x86ms = X86_MACHINE(ms); + unsigned cpus = config->has_cpus ? config->cpus : 0; + unsigned sockets = config->has_sockets ? config->sockets : 0; + unsigned dies = config->has_dies ? config->dies : 1; + unsigned cores = config->has_cores ? config->cores : 0; + unsigned threads = config->has_threads ? config->threads : 0; - if (opts) { - unsigned cpus = qemu_opt_get_number(opts, "cpus", 0); - unsigned sockets = qemu_opt_get_number(opts, "sockets", 0); - unsigned dies = qemu_opt_get_number(opts, "dies", 1); - unsigned cores = qemu_opt_get_number(opts, "cores", 0); - unsigned threads = qemu_opt_get_number(opts, "threads", 0); - - /* compute missing values, prefer sockets over cores over threads */ - if (cpus == 0 || sockets == 0) { - cores = cores > 0 ? cores : 1; - threads = threads > 0 ? threads : 1; - if (cpus == 0) { - sockets = sockets > 0 ? sockets : 1; - cpus = cores * threads * dies * sockets; - } else { - ms->smp.max_cpus = - qemu_opt_get_number(opts, "maxcpus", cpus); - sockets = ms->smp.max_cpus / (cores * threads * dies); - } - } else if (cores == 0) { - threads = threads > 0 ? threads : 1; - cores = cpus / (sockets * dies * threads); - cores = cores > 0 ? cores : 1; - } else if (threads == 0) { - threads = cpus / (cores * dies * sockets); - threads = threads > 0 ? threads : 1; - } else if (sockets * dies * cores * threads < cpus) { - error_report("cpu topology: " - "sockets (%u) * dies (%u) * cores (%u) * threads (%u) < " - "smp_cpus (%u)", - sockets, dies, cores, threads, cpus); - exit(1); + /* compute missing values, prefer sockets over cores over threads */ + if (cpus == 0 || sockets == 0) { + cores = cores > 0 ? cores : 1; + threads = threads > 0 ? threads : 1; + if (cpus == 0) { + sockets = sockets > 0 ? sockets : 1; + cpus = cores * threads * dies * sockets; + } else { + ms->smp.max_cpus = config->has_maxcpus ? config->maxcpus : cpus; + sockets = ms->smp.max_cpus / (cores * threads * dies); } - - ms->smp.max_cpus = - qemu_opt_get_number(opts, "maxcpus", cpus); - - if (ms->smp.max_cpus < cpus) { - error_report("maxcpus must be equal to or greater than smp"); - exit(1); - } - - if (sockets * dies * cores * threads != ms->smp.max_cpus) { - error_report("Invalid CPU topology deprecated: " - "sockets (%u) * dies (%u) * cores (%u) * threads (%u) " - "!= maxcpus (%u)", - sockets, dies, cores, threads, - ms->smp.max_cpus); - exit(1); - } - - ms->smp.cpus = cpus; - ms->smp.cores = cores; - ms->smp.threads = threads; - ms->smp.sockets = sockets; - x86ms->smp_dies = dies; + } else if (cores == 0) { + threads = threads > 0 ? threads : 1; + cores = cpus / (sockets * dies * threads); + cores = cores > 0 ? cores : 1; + } else if (threads == 0) { + threads = cpus / (cores * dies * sockets); + threads = threads > 0 ? threads : 1; + } else if (sockets * dies * cores * threads < cpus) { + error_setg(errp, "cpu topology: " + "sockets (%u) * dies (%u) * cores (%u) * threads (%u) < " + "smp_cpus (%u)", + sockets, dies, cores, threads, cpus); + return; } - if (ms->smp.cpus > 1) { - Error *blocker = NULL; - error_setg(&blocker, QERR_REPLAY_NOT_SUPPORTED, "smp"); - replay_add_blocker(blocker); + ms->smp.max_cpus = config->has_maxcpus ? config->maxcpus : cpus; + + if (ms->smp.max_cpus < cpus) { + error_setg(errp, "maxcpus must be equal to or greater than smp"); + return; } + + if (sockets * dies * cores * threads != ms->smp.max_cpus) { + error_setg(errp, "Invalid CPU topology deprecated: " + "sockets (%u) * dies (%u) * cores (%u) * threads (%u) " + "!= maxcpus (%u)", + sockets, dies, cores, threads, + ms->smp.max_cpus); + return; + } + + ms->smp.cpus = cpus; + ms->smp.cores = cores; + ms->smp.threads = threads; + ms->smp.sockets = sockets; + ms->smp.dies = dies; } static @@ -1529,6 +1524,21 @@ static void pc_machine_set_hpet(Object *obj, bool value, Error **errp) pcms->hpet_enabled = value; } +static bool pc_machine_get_default_bus_bypass_iommu(Object *obj, Error **errp) +{ + PCMachineState *pcms = PC_MACHINE(obj); + + return pcms->default_bus_bypass_iommu; +} + +static void pc_machine_set_default_bus_bypass_iommu(Object *obj, bool value, + Error **errp) +{ + PCMachineState *pcms = PC_MACHINE(obj); + + pcms->default_bus_bypass_iommu = value; +} + static void pc_machine_get_max_ram_below_4g(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) @@ -1628,6 +1638,7 @@ static void pc_machine_initfn(Object *obj) #ifdef CONFIG_HPET pcms->hpet_enabled = true; #endif + pcms->default_bus_bypass_iommu = false; pc_system_flash_create(pcms); pcms->pcspk = isa_new(TYPE_PC_SPEAKER); @@ -1752,6 +1763,10 @@ static void pc_machine_class_init(ObjectClass *oc, void *data) object_class_property_add_bool(oc, "hpet", pc_machine_get_hpet, pc_machine_set_hpet); + object_class_property_add_bool(oc, "default_bus_bypass_iommu", + pc_machine_get_default_bus_bypass_iommu, + pc_machine_set_default_bus_bypass_iommu); + object_class_property_add(oc, PC_MACHINE_MAX_FW_SIZE, "size", pc_machine_get_max_fw_size, pc_machine_set_max_fw_size, NULL, NULL); diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 46cc951073..30b8bd6ea9 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -42,15 +42,12 @@ #include "hw/irq.h" #include "sysemu/kvm.h" #include "hw/kvm/clock.h" -#include "sysemu/sysemu.h" #include "hw/sysbus.h" #include "sysemu/arch_init.h" #include "hw/i2c/smbus_eeprom.h" #include "hw/xen/xen-x86.h" #include "exec/memory.h" -#include "exec/address-spaces.h" #include "hw/acpi/acpi.h" -#include "cpu.h" #include "qapi/error.h" #include "qemu/error-report.h" #include "sysemu/xen.h" @@ -64,6 +61,7 @@ #include "hw/hyperv/vmbus-bridge.h" #include "hw/mem/nvdimm.h" #include "hw/i386/acpi-build.h" +#include "kvm/kvm-cpu.h" #define MAX_IDE_BUS 2 @@ -415,7 +413,7 @@ static void pc_i440fx_machine_options(MachineClass *m) machine_class_allow_dynamic_sysbus_dev(m, TYPE_VMBUS_BRIDGE); } -static void pc_i440fx_6_0_machine_options(MachineClass *m) +static void pc_i440fx_6_1_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_i440fx_machine_options(m); @@ -424,6 +422,18 @@ static void pc_i440fx_6_0_machine_options(MachineClass *m) pcmc->default_cpu_version = 1; } +DEFINE_I440FX_MACHINE(v6_1, "pc-i440fx-6.1", NULL, + pc_i440fx_6_1_machine_options); + +static void pc_i440fx_6_0_machine_options(MachineClass *m) +{ + pc_i440fx_6_1_machine_options(m); + m->alias = NULL; + m->is_default = false; + compat_props_add(m->compat_props, hw_compat_6_0, hw_compat_6_0_len); + compat_props_add(m->compat_props, pc_compat_6_0, pc_compat_6_0_len); +} + DEFINE_I440FX_MACHINE(v6_0, "pc-i440fx-6.0", NULL, pc_i440fx_6_0_machine_options); diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 53450190f5..04b4a4788d 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -37,8 +37,8 @@ #include "sysemu/kvm.h" #include "hw/kvm/clock.h" #include "hw/pci-host/q35.h" +#include "hw/pci/pcie_port.h" #include "hw/qdev-properties.h" -#include "exec/address-spaces.h" #include "hw/i386/x86.h" #include "hw/i386/pc.h" #include "hw/i386/ich9.h" @@ -137,6 +137,7 @@ static void pc_q35_init(MachineState *machine) ram_addr_t lowmem; DriveInfo *hd[MAX_SATA_PORTS]; MachineClass *mc = MACHINE_GET_CLASS(machine); + bool acpi_pcihp; /* Check whether RAM fits below 4G (leaving 1/2 GByte for IO memory * and 256 Mbytes for PCI Express Enhanced Configuration Access Mapping @@ -237,6 +238,15 @@ static void pc_q35_init(MachineState *machine) object_property_set_link(OBJECT(machine), PC_MACHINE_ACPI_DEVICE_PROP, OBJECT(lpc), &error_abort); + acpi_pcihp = object_property_get_bool(OBJECT(lpc), + "acpi-pci-hotplug-with-bridge-support", + NULL); + + if (acpi_pcihp) { + object_register_sugar_prop(TYPE_PCIE_SLOT, "native-hotplug", + "false", true); + } + /* irq lines */ gsi_state = pc_gsi_create(&x86ms->gsi, pcmc->pci_enabled); @@ -345,7 +355,7 @@ static void pc_q35_machine_options(MachineClass *m) m->max_cpus = 288; } -static void pc_q35_6_0_machine_options(MachineClass *m) +static void pc_q35_6_1_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_q35_machine_options(m); @@ -353,6 +363,17 @@ static void pc_q35_6_0_machine_options(MachineClass *m) pcmc->default_cpu_version = 1; } +DEFINE_Q35_MACHINE(v6_1, "pc-q35-6.1", NULL, + pc_q35_6_1_machine_options); + +static void pc_q35_6_0_machine_options(MachineClass *m) +{ + pc_q35_6_1_machine_options(m); + m->alias = NULL; + compat_props_add(m->compat_props, hw_compat_6_0, hw_compat_6_0_len); + compat_props_add(m->compat_props, pc_compat_6_0, pc_compat_6_0_len); +} + DEFINE_Q35_MACHINE(v6_0, "pc-q35-6.0", NULL, pc_q35_6_0_machine_options); diff --git a/hw/i386/pc_sysfw.c b/hw/i386/pc_sysfw.c index 9fe72b370e..68d6b1f783 100644 --- a/hw/i386/pc_sysfw.c +++ b/hw/i386/pc_sysfw.c @@ -35,7 +35,6 @@ #include "hw/i386/pc.h" #include "hw/loader.h" #include "hw/qdev-properties.h" -#include "sysemu/sysemu.h" #include "hw/block/flash.h" #include "sysemu/kvm.h" #include "sysemu/sev.h" @@ -125,113 +124,6 @@ void pc_system_flash_cleanup_unused(PCMachineState *pcms) } } -#define OVMF_TABLE_FOOTER_GUID "96b582de-1fb2-45f7-baea-a366c55a082d" - -static uint8_t *ovmf_table; -static int ovmf_table_len; - -static void pc_system_parse_ovmf_flash(uint8_t *flash_ptr, size_t flash_size) -{ - uint8_t *ptr; - QemuUUID guid; - int tot_len; - - /* should only be called once */ - if (ovmf_table) { - return; - } - - if (flash_size < TARGET_PAGE_SIZE) { - return; - } - - /* - * if this is OVMF there will be a table footer - * guid 48 bytes before the end of the flash file. If it's - * not found, silently abort the flash parsing. - */ - qemu_uuid_parse(OVMF_TABLE_FOOTER_GUID, &guid); - guid = qemu_uuid_bswap(guid); /* guids are LE */ - ptr = flash_ptr + flash_size - 48; - if (!qemu_uuid_is_equal((QemuUUID *)ptr, &guid)) { - return; - } - - /* if found, just before is two byte table length */ - ptr -= sizeof(uint16_t); - tot_len = le16_to_cpu(*(uint16_t *)ptr) - sizeof(guid) - sizeof(uint16_t); - - if (tot_len <= 0) { - return; - } - - ovmf_table = g_malloc(tot_len); - ovmf_table_len = tot_len; - - /* - * ptr is the foot of the table, so copy it all to the newly - * allocated ovmf_table and then set the ovmf_table pointer - * to the table foot - */ - memcpy(ovmf_table, ptr - tot_len, tot_len); - ovmf_table += tot_len; -} - -bool pc_system_ovmf_table_find(const char *entry, uint8_t **data, - int *data_len) -{ - uint8_t *ptr = ovmf_table; - int tot_len = ovmf_table_len; - QemuUUID entry_guid; - - if (qemu_uuid_parse(entry, &entry_guid) < 0) { - return false; - } - - if (!ptr) { - return false; - } - - entry_guid = qemu_uuid_bswap(entry_guid); /* guids are LE */ - while (tot_len >= sizeof(QemuUUID) + sizeof(uint16_t)) { - int len; - QemuUUID *guid; - - /* - * The data structure is - * arbitrary length data - * 2 byte length of entire entry - * 16 byte guid - */ - guid = (QemuUUID *)(ptr - sizeof(QemuUUID)); - len = le16_to_cpu(*(uint16_t *)(ptr - sizeof(QemuUUID) - - sizeof(uint16_t))); - - /* - * just in case the table is corrupt, wouldn't want to spin in - * the zero case - */ - if (len < sizeof(QemuUUID) + sizeof(uint16_t)) { - return false; - } else if (len > tot_len) { - return false; - } - - ptr -= len; - tot_len -= len; - if (qemu_uuid_is_equal(guid, &entry_guid)) { - if (data) { - *data = ptr; - } - if (data_len) { - *data_len = len - sizeof(QemuUUID) - sizeof(uint16_t); - } - return true; - } - } - return false; -} - /* * Map the pcms->flash[] from 4GiB downward, and realize. * Map them in descending order, i.e. pcms->flash[0] at the top, diff --git a/hw/i386/pc_sysfw_ovmf-stubs.c b/hw/i386/pc_sysfw_ovmf-stubs.c new file mode 100644 index 0000000000..aabe78b271 --- /dev/null +++ b/hw/i386/pc_sysfw_ovmf-stubs.c @@ -0,0 +1,26 @@ +/* + * QEMU PC System Firmware (OVMF stubs) + * + * Copyright (c) 2021 Red Hat, Inc. + * + * Author: + * Philippe Mathieu-Daudé + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/i386/pc.h" + +bool pc_system_ovmf_table_find(const char *entry, uint8_t **data, int *data_len) +{ + g_assert_not_reached(); +} + +void pc_system_parse_ovmf_flash(uint8_t *flash_ptr, size_t flash_size) +{ + g_assert_not_reached(); +} diff --git a/hw/i386/pc_sysfw_ovmf.c b/hw/i386/pc_sysfw_ovmf.c new file mode 100644 index 0000000000..f4dd92c588 --- /dev/null +++ b/hw/i386/pc_sysfw_ovmf.c @@ -0,0 +1,151 @@ +/* + * QEMU PC System Firmware (OVMF specific) + * + * Copyright (c) 2003-2004 Fabrice Bellard + * Copyright (c) 2011-2012 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "hw/i386/pc.h" +#include "cpu.h" + +#define OVMF_TABLE_FOOTER_GUID "96b582de-1fb2-45f7-baea-a366c55a082d" + +static bool ovmf_flash_parsed; +static uint8_t *ovmf_table; +static int ovmf_table_len; + +void pc_system_parse_ovmf_flash(uint8_t *flash_ptr, size_t flash_size) +{ + uint8_t *ptr; + QemuUUID guid; + int tot_len; + + /* should only be called once */ + if (ovmf_flash_parsed) { + return; + } + + ovmf_flash_parsed = true; + + if (flash_size < TARGET_PAGE_SIZE) { + return; + } + + /* + * if this is OVMF there will be a table footer + * guid 48 bytes before the end of the flash file. If it's + * not found, silently abort the flash parsing. + */ + qemu_uuid_parse(OVMF_TABLE_FOOTER_GUID, &guid); + guid = qemu_uuid_bswap(guid); /* guids are LE */ + ptr = flash_ptr + flash_size - 48; + if (!qemu_uuid_is_equal((QemuUUID *)ptr, &guid)) { + return; + } + + /* if found, just before is two byte table length */ + ptr -= sizeof(uint16_t); + tot_len = le16_to_cpu(*(uint16_t *)ptr) - sizeof(guid) - sizeof(uint16_t); + + if (tot_len <= 0) { + return; + } + + ovmf_table = g_malloc(tot_len); + ovmf_table_len = tot_len; + + /* + * ptr is the foot of the table, so copy it all to the newly + * allocated ovmf_table and then set the ovmf_table pointer + * to the table foot + */ + memcpy(ovmf_table, ptr - tot_len, tot_len); + ovmf_table += tot_len; +} + +/** + * pc_system_ovmf_table_find - Find the data associated with an entry in OVMF's + * reset vector GUIDed table. + * + * @entry: GUID string of the entry to lookup + * @data: Filled with a pointer to the entry's value (if not NULL) + * @data_len: Filled with the length of the entry's value (if not NULL). Pass + * NULL here if the length of data is known. + * + * Return: true if the entry was found in the OVMF table; false otherwise. + */ +bool pc_system_ovmf_table_find(const char *entry, uint8_t **data, + int *data_len) +{ + uint8_t *ptr = ovmf_table; + int tot_len = ovmf_table_len; + QemuUUID entry_guid; + + assert(ovmf_flash_parsed); + + if (qemu_uuid_parse(entry, &entry_guid) < 0) { + return false; + } + + if (!ptr) { + return false; + } + + entry_guid = qemu_uuid_bswap(entry_guid); /* guids are LE */ + while (tot_len >= sizeof(QemuUUID) + sizeof(uint16_t)) { + int len; + QemuUUID *guid; + + /* + * The data structure is + * arbitrary length data + * 2 byte length of entire entry + * 16 byte guid + */ + guid = (QemuUUID *)(ptr - sizeof(QemuUUID)); + len = le16_to_cpu(*(uint16_t *)(ptr - sizeof(QemuUUID) - + sizeof(uint16_t))); + + /* + * just in case the table is corrupt, wouldn't want to spin in + * the zero case + */ + if (len < sizeof(QemuUUID) + sizeof(uint16_t)) { + return false; + } else if (len > tot_len) { + return false; + } + + ptr -= len; + tot_len -= len; + if (qemu_uuid_is_equal(guid, &entry_guid)) { + if (data) { + *data = ptr; + } + if (data_len) { + *data_len = len - sizeof(QemuUUID) - sizeof(uint16_t); + } + return true; + } + } + return false; +} diff --git a/hw/i386/trace-events b/hw/i386/trace-events index e48bef2b0d..5bf7e52bf5 100644 --- a/hw/i386/trace-events +++ b/hw/i386/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # x86-iommu.c x86_iommu_iec_notify(bool global, uint32_t index, uint32_t mask) "Notify IEC invalidation: global=%d index=%" PRIu32 " mask=%" PRIu32 diff --git a/hw/i386/vmport.c b/hw/i386/vmport.c index 490a57f52c..7cc75dbc6d 100644 --- a/hw/i386/vmport.c +++ b/hw/i386/vmport.c @@ -37,7 +37,6 @@ #include "sysemu/hw_accel.h" #include "sysemu/qtest.h" #include "qemu/log.h" -#include "cpu.h" #include "trace.h" #include "qom/object.h" diff --git a/hw/i386/x86-iommu.c b/hw/i386/x86-iommu.c index 5f4301639c..86ad03972e 100644 --- a/hw/i386/x86-iommu.c +++ b/hw/i386/x86-iommu.c @@ -19,7 +19,6 @@ #include "qemu/osdep.h" #include "hw/sysbus.h" -#include "hw/boards.h" #include "hw/i386/x86-iommu.h" #include "hw/qdev-properties.h" #include "hw/i386/pc.h" diff --git a/hw/i386/x86.c b/hw/i386/x86.c index 3e2e53df38..02dd69b9c1 100644 --- a/hw/i386/x86.c +++ b/hw/i386/x86.c @@ -64,7 +64,7 @@ inline void init_topo_info(X86CPUTopoInfo *topo_info, { MachineState *ms = MACHINE(x86ms); - topo_info->dies_per_pkg = x86ms->smp_dies; + topo_info->dies_per_pkg = ms->smp.dies; topo_info->cores_per_die = ms->smp.cores; topo_info->threads_per_core = ms->smp.threads; } @@ -293,7 +293,7 @@ void x86_cpu_pre_plug(HotplugHandler *hotplug_dev, init_topo_info(&topo_info, x86ms); - env->nr_dies = x86ms->smp_dies; + env->nr_dies = ms->smp.dies; /* * If APIC ID is not set, @@ -301,13 +301,13 @@ void x86_cpu_pre_plug(HotplugHandler *hotplug_dev, */ if (cpu->apic_id == UNASSIGNED_APIC_ID) { int max_socket = (ms->smp.max_cpus - 1) / - smp_threads / smp_cores / x86ms->smp_dies; + smp_threads / smp_cores / ms->smp.dies; /* * die-id was optional in QEMU 4.0 and older, so keep it optional * if there's only one die per socket. */ - if (cpu->die_id < 0 && x86ms->smp_dies == 1) { + if (cpu->die_id < 0 && ms->smp.dies == 1) { cpu->die_id = 0; } @@ -322,9 +322,9 @@ void x86_cpu_pre_plug(HotplugHandler *hotplug_dev, if (cpu->die_id < 0) { error_setg(errp, "CPU die-id is not set"); return; - } else if (cpu->die_id > x86ms->smp_dies - 1) { + } else if (cpu->die_id > ms->smp.dies - 1) { error_setg(errp, "Invalid CPU die-id: %u must be in range 0:%u", - cpu->die_id, x86ms->smp_dies - 1); + cpu->die_id, ms->smp.dies - 1); return; } if (cpu->core_id < 0) { @@ -477,7 +477,7 @@ const CPUArchIdList *x86_possible_cpu_arch_ids(MachineState *ms) &topo_info, &topo_ids); ms->possible_cpus->cpus[i].props.has_socket_id = true; ms->possible_cpus->cpus[i].props.socket_id = topo_ids.pkg_id; - if (x86ms->smp_dies > 1) { + if (ms->smp.dies > 1) { ms->possible_cpus->cpus[i].props.has_die_id = true; ms->possible_cpus->cpus[i].props.die_id = topo_ids.die_id; } @@ -1251,16 +1251,33 @@ static void x86_machine_set_oem_table_id(Object *obj, const char *value, strncpy(x86ms->oem_table_id, value, 8); } +static void x86_machine_get_bus_lock_ratelimit(Object *obj, Visitor *v, + const char *name, void *opaque, Error **errp) +{ + X86MachineState *x86ms = X86_MACHINE(obj); + uint64_t bus_lock_ratelimit = x86ms->bus_lock_ratelimit; + + visit_type_uint64(v, name, &bus_lock_ratelimit, errp); +} + +static void x86_machine_set_bus_lock_ratelimit(Object *obj, Visitor *v, + const char *name, void *opaque, Error **errp) +{ + X86MachineState *x86ms = X86_MACHINE(obj); + + visit_type_uint64(v, name, &x86ms->bus_lock_ratelimit, errp); +} + static void x86_machine_initfn(Object *obj) { X86MachineState *x86ms = X86_MACHINE(obj); x86ms->smm = ON_OFF_AUTO_AUTO; x86ms->acpi = ON_OFF_AUTO_AUTO; - x86ms->smp_dies = 1; x86ms->pci_irq_mask = ACPI_BUILD_PCI_IRQS; x86ms->oem_id = g_strndup(ACPI_BUILD_APPNAME6, 6); x86ms->oem_table_id = g_strndup(ACPI_BUILD_APPNAME8, 8); + x86ms->bus_lock_ratelimit = 0; } static void x86_machine_class_init(ObjectClass *oc, void *data) @@ -1304,6 +1321,12 @@ static void x86_machine_class_init(ObjectClass *oc, void *data) "Override the default value of field OEM Table ID " "in ACPI table header." "The string may be up to 8 bytes in size"); + + object_class_property_add(oc, X86_MACHINE_BUS_LOCK_RATELIMIT, "uint64_t", + x86_machine_get_bus_lock_ratelimit, + x86_machine_set_bus_lock_ratelimit, NULL, NULL); + object_class_property_set_description(oc, X86_MACHINE_BUS_LOCK_RATELIMIT, + "Set the ratelimit for the bus locks acquired in VMs"); } static const TypeInfo x86_machine_info = { diff --git a/hw/i386/xen/trace-events b/hw/i386/xen/trace-events index ca3a4948ba..5d6be61090 100644 --- a/hw/i386/xen/trace-events +++ b/hw/i386/xen/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # xen_platform.c xen_platform_log(char *s) "xen platform: %s" diff --git a/hw/i386/xen/xen-hvm.c b/hw/i386/xen/xen-hvm.c index 7ce672e5a5..9b432773f0 100644 --- a/hw/i386/xen/xen-hvm.c +++ b/hw/i386/xen/xen-hvm.c @@ -33,7 +33,6 @@ #include "sysemu/xen.h" #include "sysemu/xen-mapcache.h" #include "trace.h" -#include "exec/address-spaces.h" #include #include @@ -109,6 +108,7 @@ typedef struct XenIOState { shared_iopage_t *shared_page; shared_vmport_iopage_t *shared_vmport_page; buffered_iopage_t *buffered_io_page; + xenforeignmemory_resource_handle *fres; QEMUTimer *buffered_io_timer; CPUState **cpu_by_vcpu_id; /* the evtchn port for polling the notification, */ @@ -1254,6 +1254,9 @@ static void xen_exit_notifier(Notifier *n, void *data) XenIOState *state = container_of(n, XenIOState, exit); xen_destroy_ioreq_server(xen_domid, state->ioservid); + if (state->fres != NULL) { + xenforeignmemory_unmap_resource(xen_fmem, state->fres); + } xenevtchn_close(state->xce_handle); xs_daemon_close(state->xenstore); @@ -1321,7 +1324,6 @@ static void xen_wakeup_notifier(Notifier *notifier, void *data) static int xen_map_ioreq_server(XenIOState *state) { void *addr = NULL; - xenforeignmemory_resource_handle *fres; xen_pfn_t ioreq_pfn; xen_pfn_t bufioreq_pfn; evtchn_port_t bufioreq_evtchn; @@ -1333,12 +1335,12 @@ static int xen_map_ioreq_server(XenIOState *state) */ QEMU_BUILD_BUG_ON(XENMEM_resource_ioreq_server_frame_bufioreq != 0); QEMU_BUILD_BUG_ON(XENMEM_resource_ioreq_server_frame_ioreq(0) != 1); - fres = xenforeignmemory_map_resource(xen_fmem, xen_domid, + state->fres = xenforeignmemory_map_resource(xen_fmem, xen_domid, XENMEM_resource_ioreq_server, state->ioservid, 0, 2, &addr, PROT_READ | PROT_WRITE, 0); - if (fres != NULL) { + if (state->fres != NULL) { trace_xen_map_resource_ioreq(state->ioservid, addr); state->buffered_io_page = addr; state->shared_page = addr + TARGET_PAGE_SIZE; diff --git a/hw/i386/xen/xen-mapcache.c b/hw/i386/xen/xen-mapcache.c index 5b120ed44b..bd47c3d672 100644 --- a/hw/i386/xen/xen-mapcache.c +++ b/hw/i386/xen/xen-mapcache.c @@ -169,9 +169,23 @@ static void xen_remap_bucket(MapCacheEntry *entry, if (entry->vaddr_base != NULL) { if (!(entry->flags & XEN_MAPCACHE_ENTRY_DUMMY)) { - ram_block_notify_remove(entry->vaddr_base, entry->size); + ram_block_notify_remove(entry->vaddr_base, entry->size, + entry->size); } - if (munmap(entry->vaddr_base, entry->size) != 0) { + + /* + * If an entry is being replaced by another mapping and we're using + * MAP_FIXED flag for it - there is possibility of a race for vaddr + * address with another thread doing an mmap call itself + * (see man 2 mmap). To avoid that we skip explicit unmapping here + * and allow the kernel to destroy the previous mappings by replacing + * them in mmap call later. + * + * Non-identical replacements are not allowed therefore. + */ + assert(!vaddr || (entry->vaddr_base == vaddr && entry->size == size)); + + if (!vaddr && munmap(entry->vaddr_base, entry->size) != 0) { perror("unmap fails"); exit(-1); } @@ -211,7 +225,7 @@ static void xen_remap_bucket(MapCacheEntry *entry, } if (!(entry->flags & XEN_MAPCACHE_ENTRY_DUMMY)) { - ram_block_notify_add(vaddr_base, size); + ram_block_notify_add(vaddr_base, size, size); } entry->vaddr_base = vaddr_base; @@ -452,7 +466,7 @@ static void xen_invalidate_map_cache_entry_unlocked(uint8_t *buffer) } pentry->next = entry->next; - ram_block_notify_remove(entry->vaddr_base, entry->size); + ram_block_notify_remove(entry->vaddr_base, entry->size, entry->size); if (munmap(entry->vaddr_base, entry->size) != 0) { perror("unmap fails"); exit(-1); diff --git a/hw/i386/xen/xen_platform.c b/hw/i386/xen/xen_platform.c index 01ae1fb161..72028449ba 100644 --- a/hw/i386/xen/xen_platform.c +++ b/hw/i386/xen/xen_platform.c @@ -27,12 +27,10 @@ #include "qapi/error.h" #include "hw/ide.h" #include "hw/pci/pci.h" -#include "hw/irq.h" #include "hw/xen/xen_common.h" #include "migration/vmstate.h" #include "hw/xen/xen-legacy-backend.h" #include "trace.h" -#include "exec/address-spaces.h" #include "sysemu/xen.h" #include "sysemu/block-backend.h" #include "qemu/error-report.h" diff --git a/hw/ide/Kconfig b/hw/ide/Kconfig index 5d9106b1ac..dd85fa3619 100644 --- a/hw/ide/Kconfig +++ b/hw/ide/Kconfig @@ -8,7 +8,7 @@ config IDE_QDEV config IDE_PCI bool depends on PCI - select IDE_CORE + select IDE_QDEV config IDE_ISA bool @@ -41,6 +41,7 @@ config IDE_VIA config MICRODRIVE bool select IDE_QDEV + depends on PCMCIA config AHCI bool diff --git a/hw/ide/ahci_internal.h b/hw/ide/ahci_internal.h index 7f32e87731..109de9e2d1 100644 --- a/hw/ide/ahci_internal.h +++ b/hw/ide/ahci_internal.h @@ -26,7 +26,6 @@ #include "hw/ide/ahci.h" #include "hw/ide/internal.h" -#include "hw/sysbus.h" #include "hw/pci/pci.h" #define AHCI_MEM_BAR_SIZE 0x1000 diff --git a/hw/ide/ioport.c b/hw/ide/ioport.c index b613ff3bba..e6caa537fa 100644 --- a/hw/ide/ioport.c +++ b/hw/ide/ioport.c @@ -50,15 +50,19 @@ static const MemoryRegionPortio ide_portio2_list[] = { PORTIO_END_OF_LIST(), }; -void ide_init_ioport(IDEBus *bus, ISADevice *dev, int iobase, int iobase2) +int ide_init_ioport(IDEBus *bus, ISADevice *dev, int iobase, int iobase2) { + int ret; + /* ??? Assume only ISA and PCI configurations, and that the PCI-ISA bridge has been setup properly to always register with ISA. */ - isa_register_portio_list(dev, &bus->portio_list, - iobase, ide_portio_list, bus, "ide"); + ret = isa_register_portio_list(dev, &bus->portio_list, + iobase, ide_portio_list, bus, "ide"); - if (iobase2) { - isa_register_portio_list(dev, &bus->portio2_list, - iobase2, ide_portio2_list, bus, "ide"); + if (ret == 0 && iobase2) { + ret = isa_register_portio_list(dev, &bus->portio2_list, + iobase2, ide_portio2_list, bus, "ide"); } + + return ret; } diff --git a/hw/ide/piix.c b/hw/ide/piix.c index b9860e35a5..d3e738320b 100644 --- a/hw/ide/piix.c +++ b/hw/ide/piix.c @@ -26,6 +26,7 @@ #include "qemu/osdep.h" #include "hw/pci/pci.h" #include "migration/vmstate.h" +#include "qapi/error.h" #include "qemu/module.h" #include "sysemu/block-backend.h" #include "sysemu/blockdev.h" @@ -123,7 +124,8 @@ static void piix_ide_reset(DeviceState *dev) pci_conf[0x20] = 0x01; /* BMIBA: 20-23h */ } -static void pci_piix_init_ports(PCIIDEState *d) { +static int pci_piix_init_ports(PCIIDEState *d) +{ static const struct { int iobase; int iobase2; @@ -132,24 +134,30 @@ static void pci_piix_init_ports(PCIIDEState *d) { {0x1f0, 0x3f6, 14}, {0x170, 0x376, 15}, }; - int i; + int i, ret; for (i = 0; i < 2; i++) { ide_bus_new(&d->bus[i], sizeof(d->bus[i]), DEVICE(d), i, 2); - ide_init_ioport(&d->bus[i], NULL, port_info[i].iobase, - port_info[i].iobase2); + ret = ide_init_ioport(&d->bus[i], NULL, port_info[i].iobase, + port_info[i].iobase2); + if (ret) { + return ret; + } ide_init2(&d->bus[i], isa_get_irq(NULL, port_info[i].isairq)); bmdma_init(&d->bus[i], &d->bmdma[i], d); d->bmdma[i].bus = &d->bus[i]; ide_register_restart_cb(&d->bus[i]); } + + return 0; } static void pci_piix_ide_realize(PCIDevice *dev, Error **errp) { PCIIDEState *d = PCI_IDE(dev); uint8_t *pci_conf = dev->config; + int rc; pci_conf[PCI_CLASS_PROG] = 0x80; // legacy ATA mode @@ -158,7 +166,11 @@ static void pci_piix_ide_realize(PCIDevice *dev, Error **errp) vmstate_register(VMSTATE_IF(dev), 0, &vmstate_ide_pci, d); - pci_piix_init_ports(d); + rc = pci_piix_init_ports(d); + if (rc) { + error_setg_errno(errp, -rc, "Failed to realize %s", + object_get_typename(OBJECT(dev))); + } } int pci_piix3_xen_ide_unplug(DeviceState *dev, bool aux) diff --git a/hw/ide/trace-events b/hw/ide/trace-events index 6e357685f9..15d7921f15 100644 --- a/hw/ide/trace-events +++ b/hw/ide/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # core.c # portio diff --git a/hw/input/hid.c b/hw/input/hid.c index e1d2e46083..8aab0521f4 100644 --- a/hw/input/hid.c +++ b/hw/input/hid.c @@ -51,8 +51,8 @@ static const uint8_t hid_usage_keys[0x100] = { 0x45, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0xe8, 0xe9, 0x71, 0x72, 0x73, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, 0x00, 0xe3, 0xe7, 0x65, + 0x88, 0x00, 0x00, 0x87, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x8a, 0x00, 0x8b, 0x00, 0x89, 0xe7, 0x65, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, diff --git a/hw/input/lasips2.c b/hw/input/lasips2.c index 0786e57338..e7faf24058 100644 --- a/hw/input/lasips2.c +++ b/hw/input/lasips2.c @@ -24,12 +24,9 @@ #include "qemu/osdep.h" #include "qemu/log.h" #include "hw/qdev-properties.h" -#include "hw/hw.h" #include "hw/input/ps2.h" #include "hw/input/lasips2.h" -#include "hw/sysbus.h" #include "exec/hwaddr.h" -#include "sysemu/sysemu.h" #include "trace.h" #include "exec/address-spaces.h" #include "migration/vmstate.h" diff --git a/hw/input/lm832x.c b/hw/input/lm832x.c index 4cb1e9de01..19a646d9bb 100644 --- a/hw/input/lm832x.c +++ b/hw/input/lm832x.c @@ -19,6 +19,7 @@ */ #include "qemu/osdep.h" +#include "hw/input/lm832x.h" #include "hw/i2c/i2c.h" #include "hw/irq.h" #include "migration/vmstate.h" @@ -27,7 +28,6 @@ #include "ui/console.h" #include "qom/object.h" -#define TYPE_LM8323 "lm8323" OBJECT_DECLARE_SIMPLE_TYPE(LM823KbdState, LM8323) struct LM823KbdState { diff --git a/hw/input/meson.build b/hw/input/meson.build index 0042c3f0dc..8deb011d4a 100644 --- a/hw/input/meson.build +++ b/hw/input/meson.build @@ -13,7 +13,6 @@ softmmu_ss.add(when: 'CONFIG_VIRTIO_INPUT', if_true: files('virtio-input-hid.c') softmmu_ss.add(when: 'CONFIG_VIRTIO_INPUT_HOST', if_true: files('virtio-input-host.c')) softmmu_ss.add(when: 'CONFIG_VHOST_USER_INPUT', if_true: files('vhost-user-input.c')) -softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-softusb.c')) softmmu_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_keypad.c')) softmmu_ss.add(when: 'CONFIG_TSC210X', if_true: files('tsc210x.c')) softmmu_ss.add(when: 'CONFIG_LASIPS2', if_true: files('lasips2.c')) diff --git a/hw/input/milkymist-softusb.c b/hw/input/milkymist-softusb.c deleted file mode 100644 index d885c708d7..0000000000 --- a/hw/input/milkymist-softusb.c +++ /dev/null @@ -1,319 +0,0 @@ -/* - * QEMU model of the Milkymist SoftUSB block. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * not available yet - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "ui/console.h" -#include "hw/input/hid.h" -#include "hw/irq.h" -#include "hw/qdev-properties.h" -#include "qemu/error-report.h" -#include "qemu/module.h" -#include "qom/object.h" - -enum { - R_CTRL = 0, - R_MAX -}; - -enum { - CTRL_RESET = (1<<0), -}; - -#define COMLOC_DEBUG_PRODUCE 0x1000 -#define COMLOC_DEBUG_BASE 0x1001 -#define COMLOC_MEVT_PRODUCE 0x1101 -#define COMLOC_MEVT_BASE 0x1102 -#define COMLOC_KEVT_PRODUCE 0x1142 -#define COMLOC_KEVT_BASE 0x1143 - -#define TYPE_MILKYMIST_SOFTUSB "milkymist-softusb" -OBJECT_DECLARE_SIMPLE_TYPE(MilkymistSoftUsbState, MILKYMIST_SOFTUSB) - -struct MilkymistSoftUsbState { - SysBusDevice parent_obj; - - HIDState hid_kbd; - HIDState hid_mouse; - - MemoryRegion regs_region; - MemoryRegion pmem; - MemoryRegion dmem; - qemu_irq irq; - - void *pmem_ptr; - void *dmem_ptr; - - /* device properties */ - uint32_t pmem_size; - uint32_t dmem_size; - - /* device registers */ - uint32_t regs[R_MAX]; - - /* mouse state */ - uint8_t mouse_hid_buffer[4]; - - /* keyboard state */ - uint8_t kbd_hid_buffer[8]; -}; - -static uint64_t softusb_read(void *opaque, hwaddr addr, - unsigned size) -{ - MilkymistSoftUsbState *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_CTRL: - r = s->regs[addr]; - break; - - default: - error_report("milkymist_softusb: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - trace_milkymist_softusb_memory_read(addr << 2, r); - - return r; -} - -static void -softusb_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - MilkymistSoftUsbState *s = opaque; - - trace_milkymist_softusb_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_CTRL: - s->regs[addr] = value; - break; - - default: - error_report("milkymist_softusb: write access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } -} - -static const MemoryRegionOps softusb_mmio_ops = { - .read = softusb_read, - .write = softusb_write, - .endianness = DEVICE_NATIVE_ENDIAN, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, -}; - -static inline void softusb_read_dmem(MilkymistSoftUsbState *s, - uint32_t offset, uint8_t *buf, uint32_t len) -{ - if (offset + len >= s->dmem_size) { - error_report("milkymist_softusb: read dmem out of bounds " - "at offset 0x%x, len %d", offset, len); - memset(buf, 0, len); - return; - } - - memcpy(buf, s->dmem_ptr + offset, len); -} - -static inline void softusb_write_dmem(MilkymistSoftUsbState *s, - uint32_t offset, uint8_t *buf, uint32_t len) -{ - if (offset + len >= s->dmem_size) { - error_report("milkymist_softusb: write dmem out of bounds " - "at offset 0x%x, len %d", offset, len); - return; - } - - memcpy(s->dmem_ptr + offset, buf, len); -} - -static void softusb_mouse_changed(MilkymistSoftUsbState *s) -{ - uint8_t m; - - softusb_read_dmem(s, COMLOC_MEVT_PRODUCE, &m, 1); - trace_milkymist_softusb_mevt(m); - softusb_write_dmem(s, COMLOC_MEVT_BASE + 4 * m, s->mouse_hid_buffer, 4); - m = (m + 1) & 0xf; - softusb_write_dmem(s, COMLOC_MEVT_PRODUCE, &m, 1); - - trace_milkymist_softusb_pulse_irq(); - qemu_irq_pulse(s->irq); -} - -static void softusb_kbd_changed(MilkymistSoftUsbState *s) -{ - uint8_t m; - - softusb_read_dmem(s, COMLOC_KEVT_PRODUCE, &m, 1); - trace_milkymist_softusb_kevt(m); - softusb_write_dmem(s, COMLOC_KEVT_BASE + 8 * m, s->kbd_hid_buffer, 8); - m = (m + 1) & 0x7; - softusb_write_dmem(s, COMLOC_KEVT_PRODUCE, &m, 1); - - trace_milkymist_softusb_pulse_irq(); - qemu_irq_pulse(s->irq); -} - -static void softusb_kbd_hid_datain(HIDState *hs) -{ - MilkymistSoftUsbState *s = container_of(hs, MilkymistSoftUsbState, hid_kbd); - int len; - - /* if device is in reset, do nothing */ - if (s->regs[R_CTRL] & CTRL_RESET) { - return; - } - - while (hid_has_events(hs)) { - len = hid_keyboard_poll(hs, s->kbd_hid_buffer, - sizeof(s->kbd_hid_buffer)); - - if (len == 8) { - softusb_kbd_changed(s); - } - } -} - -static void softusb_mouse_hid_datain(HIDState *hs) -{ - MilkymistSoftUsbState *s = - container_of(hs, MilkymistSoftUsbState, hid_mouse); - int len; - - /* if device is in reset, do nothing */ - if (s->regs[R_CTRL] & CTRL_RESET) { - return; - } - - while (hid_has_events(hs)) { - len = hid_pointer_poll(hs, s->mouse_hid_buffer, - sizeof(s->mouse_hid_buffer)); - - if (len == 4) { - softusb_mouse_changed(s); - } - } -} - -static void milkymist_softusb_reset(DeviceState *d) -{ - MilkymistSoftUsbState *s = MILKYMIST_SOFTUSB(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } - memset(s->kbd_hid_buffer, 0, sizeof(s->kbd_hid_buffer)); - memset(s->mouse_hid_buffer, 0, sizeof(s->mouse_hid_buffer)); - - hid_reset(&s->hid_kbd); - hid_reset(&s->hid_mouse); - - /* defaults */ - s->regs[R_CTRL] = CTRL_RESET; -} - -static void milkymist_softusb_realize(DeviceState *dev, Error **errp) -{ - MilkymistSoftUsbState *s = MILKYMIST_SOFTUSB(dev); - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - - sysbus_init_irq(sbd, &s->irq); - - memory_region_init_io(&s->regs_region, OBJECT(s), &softusb_mmio_ops, s, - "milkymist-softusb", R_MAX * 4); - sysbus_init_mmio(sbd, &s->regs_region); - - /* register pmem and dmem */ - memory_region_init_ram_nomigrate(&s->pmem, OBJECT(s), "milkymist-softusb.pmem", - s->pmem_size, &error_fatal); - vmstate_register_ram_global(&s->pmem); - s->pmem_ptr = memory_region_get_ram_ptr(&s->pmem); - sysbus_init_mmio(sbd, &s->pmem); - memory_region_init_ram_nomigrate(&s->dmem, OBJECT(s), "milkymist-softusb.dmem", - s->dmem_size, &error_fatal); - vmstate_register_ram_global(&s->dmem); - s->dmem_ptr = memory_region_get_ram_ptr(&s->dmem); - sysbus_init_mmio(sbd, &s->dmem); - - hid_init(&s->hid_kbd, HID_KEYBOARD, softusb_kbd_hid_datain); - hid_init(&s->hid_mouse, HID_MOUSE, softusb_mouse_hid_datain); -} - -static const VMStateDescription vmstate_milkymist_softusb = { - .name = "milkymist-softusb", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, MilkymistSoftUsbState, R_MAX), - VMSTATE_HID_KEYBOARD_DEVICE(hid_kbd, MilkymistSoftUsbState), - VMSTATE_HID_POINTER_DEVICE(hid_mouse, MilkymistSoftUsbState), - VMSTATE_BUFFER(kbd_hid_buffer, MilkymistSoftUsbState), - VMSTATE_BUFFER(mouse_hid_buffer, MilkymistSoftUsbState), - VMSTATE_END_OF_LIST() - } -}; - -static Property milkymist_softusb_properties[] = { - DEFINE_PROP_UINT32("pmem_size", MilkymistSoftUsbState, pmem_size, 0x00001000), - DEFINE_PROP_UINT32("dmem_size", MilkymistSoftUsbState, dmem_size, 0x00002000), - DEFINE_PROP_END_OF_LIST(), -}; - -static void milkymist_softusb_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = milkymist_softusb_realize; - dc->reset = milkymist_softusb_reset; - dc->vmsd = &vmstate_milkymist_softusb; - device_class_set_props(dc, milkymist_softusb_properties); -} - -static const TypeInfo milkymist_softusb_info = { - .name = TYPE_MILKYMIST_SOFTUSB, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(MilkymistSoftUsbState), - .class_init = milkymist_softusb_class_init, -}; - -static void milkymist_softusb_register_types(void) -{ - type_register_static(&milkymist_softusb_info); -} - -type_init(milkymist_softusb_register_types) diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c index dde85ba6c6..baba62f357 100644 --- a/hw/input/pckbd.c +++ b/hw/input/pckbd.c @@ -23,13 +23,16 @@ */ #include "qemu/osdep.h" +#include "qemu/error-report.h" #include "qemu/log.h" +#include "qemu/timer.h" #include "hw/isa/isa.h" #include "migration/vmstate.h" #include "hw/acpi/aml-build.h" #include "hw/input/ps2.h" #include "hw/irq.h" #include "hw/input/i8042.h" +#include "hw/qdev-properties.h" #include "sysemu/reset.h" #include "sysemu/runstate.h" @@ -59,21 +62,6 @@ #define KBD_CCMD_RESET 0xFE /* Pulse bit 0 of the output port P2 = CPU reset. */ #define KBD_CCMD_NO_OP 0xFF /* Pulse no bits of the output port P2. */ -/* Keyboard Commands */ -#define KBD_CMD_SET_LEDS 0xED /* Set keyboard leds */ -#define KBD_CMD_ECHO 0xEE -#define KBD_CMD_GET_ID 0xF2 /* get keyboard ID */ -#define KBD_CMD_SET_RATE 0xF3 /* Set typematic rate */ -#define KBD_CMD_ENABLE 0xF4 /* Enable scanning */ -#define KBD_CMD_RESET_DISABLE 0xF5 /* reset and disable scanning */ -#define KBD_CMD_RESET_ENABLE 0xF6 /* reset and enable scanning */ -#define KBD_CMD_RESET 0xFF /* Reset */ - -/* Keyboard Replies */ -#define KBD_REPLY_POR 0xAA /* Power on reset */ -#define KBD_REPLY_ACK 0xFA /* Command ACK */ -#define KBD_REPLY_RESEND 0xFE /* Command NACK, send the cmd again */ - /* Status Register Bits */ #define KBD_STAT_OBF 0x01 /* Keyboard output buffer full */ #define KBD_STAT_IBF 0x02 /* Keyboard input buffer full */ @@ -106,41 +94,37 @@ */ #define KBD_OUT_ONES 0xcc -/* Mouse Commands */ -#define AUX_SET_SCALE11 0xE6 /* Set 1:1 scaling */ -#define AUX_SET_SCALE21 0xE7 /* Set 2:1 scaling */ -#define AUX_SET_RES 0xE8 /* Set resolution */ -#define AUX_GET_SCALE 0xE9 /* Get scaling factor */ -#define AUX_SET_STREAM 0xEA /* Set stream mode */ -#define AUX_POLL 0xEB /* Poll */ -#define AUX_RESET_WRAP 0xEC /* Reset wrap mode */ -#define AUX_SET_WRAP 0xEE /* Set wrap mode */ -#define AUX_SET_REMOTE 0xF0 /* Set remote mode */ -#define AUX_GET_TYPE 0xF2 /* Get type */ -#define AUX_SET_SAMPLE 0xF3 /* Set sample rate */ -#define AUX_ENABLE_DEV 0xF4 /* Enable aux device */ -#define AUX_DISABLE_DEV 0xF5 /* Disable aux device */ -#define AUX_SET_DEFAULT 0xF6 -#define AUX_RESET 0xFF /* Reset aux device */ -#define AUX_ACK 0xFA /* Command byte ACK. */ +#define KBD_PENDING_KBD_COMPAT 0x01 +#define KBD_PENDING_AUX_COMPAT 0x02 +#define KBD_PENDING_CTRL_KBD 0x04 +#define KBD_PENDING_CTRL_AUX 0x08 +#define KBD_PENDING_KBD KBD_MODE_DISABLE_KBD /* 0x10 */ +#define KBD_PENDING_AUX KBD_MODE_DISABLE_MOUSE /* 0x20 */ -#define MOUSE_STATUS_REMOTE 0x40 -#define MOUSE_STATUS_ENABLED 0x20 -#define MOUSE_STATUS_SCALE21 0x10 +#define KBD_MIGR_TIMER_PENDING 0x1 -#define KBD_PENDING_KBD 1 -#define KBD_PENDING_AUX 2 +#define KBD_OBSRC_KBD 0x01 +#define KBD_OBSRC_MOUSE 0x02 +#define KBD_OBSRC_CTRL 0x04 typedef struct KBDState { uint8_t write_cmd; /* if non zero, write data to port 60 is expected */ uint8_t status; uint8_t mode; uint8_t outport; + uint32_t migration_flags; + uint32_t obsrc; bool outport_present; + bool extended_state; + bool extended_state_loaded; /* Bitmask of devices with data available. */ uint8_t pending; + uint8_t obdata; + uint8_t cbdata; + uint8_t pending_tmp; void *kbd; void *mouse; + QEMUTimer *throttle_timer; qemu_irq irq_kbd; qemu_irq irq_mouse; @@ -148,56 +132,123 @@ typedef struct KBDState { hwaddr mask; } KBDState; -/* update irq and KBD_STAT_[MOUSE_]OBF */ /* XXX: not generating the irqs if KBD_MODE_DISABLE_KBD is set may be incorrect, but it avoids having to simulate exact delays */ -static void kbd_update_irq(KBDState *s) +static void kbd_update_irq_lines(KBDState *s) { int irq_kbd_level, irq_mouse_level; irq_kbd_level = 0; irq_mouse_level = 0; - s->status &= ~(KBD_STAT_OBF | KBD_STAT_MOUSE_OBF); - s->outport &= ~(KBD_OUT_OBF | KBD_OUT_MOUSE_OBF); - if (s->pending) { - s->status |= KBD_STAT_OBF; - s->outport |= KBD_OUT_OBF; - /* kbd data takes priority over aux data. */ - if (s->pending == KBD_PENDING_AUX) { - s->status |= KBD_STAT_MOUSE_OBF; - s->outport |= KBD_OUT_MOUSE_OBF; - if (s->mode & KBD_MODE_MOUSE_INT) + + if (s->status & KBD_STAT_OBF) { + if (s->status & KBD_STAT_MOUSE_OBF) { + if (s->mode & KBD_MODE_MOUSE_INT) { irq_mouse_level = 1; + } } else { if ((s->mode & KBD_MODE_KBD_INT) && - !(s->mode & KBD_MODE_DISABLE_KBD)) + !(s->mode & KBD_MODE_DISABLE_KBD)) { irq_kbd_level = 1; + } } } qemu_set_irq(s->irq_kbd, irq_kbd_level); qemu_set_irq(s->irq_mouse, irq_mouse_level); } +static void kbd_deassert_irq(KBDState *s) +{ + s->status &= ~(KBD_STAT_OBF | KBD_STAT_MOUSE_OBF); + s->outport &= ~(KBD_OUT_OBF | KBD_OUT_MOUSE_OBF); + kbd_update_irq_lines(s); +} + +static uint8_t kbd_pending(KBDState *s) +{ + if (s->extended_state) { + return s->pending & (~s->mode | ~(KBD_PENDING_KBD | KBD_PENDING_AUX)); + } else { + return s->pending; + } +} + +/* update irq and KBD_STAT_[MOUSE_]OBF */ +static void kbd_update_irq(KBDState *s) +{ + uint8_t pending = kbd_pending(s); + + s->status &= ~(KBD_STAT_OBF | KBD_STAT_MOUSE_OBF); + s->outport &= ~(KBD_OUT_OBF | KBD_OUT_MOUSE_OBF); + if (pending) { + s->status |= KBD_STAT_OBF; + s->outport |= KBD_OUT_OBF; + if (pending & KBD_PENDING_CTRL_KBD) { + s->obsrc = KBD_OBSRC_CTRL; + } else if (pending & KBD_PENDING_CTRL_AUX) { + s->status |= KBD_STAT_MOUSE_OBF; + s->outport |= KBD_OUT_MOUSE_OBF; + s->obsrc = KBD_OBSRC_CTRL; + } else if (pending & KBD_PENDING_KBD) { + s->obsrc = KBD_OBSRC_KBD; + } else { + s->status |= KBD_STAT_MOUSE_OBF; + s->outport |= KBD_OUT_MOUSE_OBF; + s->obsrc = KBD_OBSRC_MOUSE; + } + } + kbd_update_irq_lines(s); +} + +static void kbd_safe_update_irq(KBDState *s) +{ + /* + * with KBD_STAT_OBF set, a call to kbd_read_data() will eventually call + * kbd_update_irq() + */ + if (s->status & KBD_STAT_OBF) { + return; + } + /* the throttle timer is pending and will call kbd_update_irq() */ + if (s->throttle_timer && timer_pending(s->throttle_timer)) { + return; + } + if (kbd_pending(s)) { + kbd_update_irq(s); + } +} + static void kbd_update_kbd_irq(void *opaque, int level) { - KBDState *s = (KBDState *)opaque; + KBDState *s = opaque; - if (level) + if (level) { s->pending |= KBD_PENDING_KBD; - else + } else { s->pending &= ~KBD_PENDING_KBD; - kbd_update_irq(s); + } + kbd_safe_update_irq(s); } static void kbd_update_aux_irq(void *opaque, int level) { - KBDState *s = (KBDState *)opaque; + KBDState *s = opaque; - if (level) + if (level) { s->pending |= KBD_PENDING_AUX; - else + } else { s->pending &= ~KBD_PENDING_AUX; - kbd_update_irq(s); + } + kbd_safe_update_irq(s); +} + +static void kbd_throttle_timeout(void *opaque) +{ + KBDState *s = opaque; + + if (kbd_pending(s)) { + kbd_update_irq(s); + } } static uint64_t kbd_read_status(void *opaque, hwaddr addr, @@ -212,10 +263,25 @@ static uint64_t kbd_read_status(void *opaque, hwaddr addr, static void kbd_queue(KBDState *s, int b, int aux) { - if (aux) - ps2_queue(s->mouse, b); - else - ps2_queue(s->kbd, b); + if (s->extended_state) { + s->cbdata = b; + s->pending &= ~KBD_PENDING_CTRL_KBD & ~KBD_PENDING_CTRL_AUX; + s->pending |= aux ? KBD_PENDING_CTRL_AUX : KBD_PENDING_CTRL_KBD; + kbd_safe_update_irq(s); + } else { + ps2_queue(aux ? s->mouse : s->kbd, b); + } +} + +static uint8_t kbd_dequeue(KBDState *s) +{ + uint8_t b = s->cbdata; + + s->pending &= ~KBD_PENDING_CTRL_KBD & ~KBD_PENDING_CTRL_AUX; + if (kbd_pending(s)) { + kbd_update_irq(s); + } + return b; } static void outport_write(KBDState *s, uint32_t val) @@ -265,6 +331,7 @@ static void kbd_write_command(void *opaque, hwaddr addr, break; case KBD_CCMD_MOUSE_ENABLE: s->mode &= ~KBD_MODE_DISABLE_MOUSE; + kbd_safe_update_irq(s); break; case KBD_CCMD_TEST_MOUSE: kbd_queue(s, 0x00, 0); @@ -278,11 +345,10 @@ static void kbd_write_command(void *opaque, hwaddr addr, break; case KBD_CCMD_KBD_DISABLE: s->mode |= KBD_MODE_DISABLE_KBD; - kbd_update_irq(s); break; case KBD_CCMD_KBD_ENABLE: s->mode &= ~KBD_MODE_DISABLE_KBD; - kbd_update_irq(s); + kbd_safe_update_irq(s); break; case KBD_CCMD_READ_INPORT: kbd_queue(s, 0x80, 0); @@ -315,15 +381,24 @@ static uint64_t kbd_read_data(void *opaque, hwaddr addr, unsigned size) { KBDState *s = opaque; - uint32_t val; - if (s->pending == KBD_PENDING_AUX) - val = ps2_read_data(s->mouse); - else - val = ps2_read_data(s->kbd); + if (s->status & KBD_STAT_OBF) { + kbd_deassert_irq(s); + if (s->obsrc & KBD_OBSRC_KBD) { + if (s->throttle_timer) { + timer_mod(s->throttle_timer, + qemu_clock_get_us(QEMU_CLOCK_VIRTUAL) + 1000); + } + s->obdata = ps2_read_data(s->kbd); + } else if (s->obsrc & KBD_OBSRC_MOUSE) { + s->obdata = ps2_read_data(s->mouse); + } else if (s->obsrc & KBD_OBSRC_CTRL) { + s->obdata = kbd_dequeue(s); + } + } - trace_pckbd_kbd_read_data(val); - return val; + trace_pckbd_kbd_read_data(s->obdata); + return s->obdata; } static void kbd_write_data(void *opaque, hwaddr addr, @@ -336,12 +411,23 @@ static void kbd_write_data(void *opaque, hwaddr addr, switch(s->write_cmd) { case 0: ps2_write_keyboard(s->kbd, val); + /* sending data to the keyboard reenables PS/2 communication */ + s->mode &= ~KBD_MODE_DISABLE_KBD; + kbd_safe_update_irq(s); break; case KBD_CCMD_WRITE_MODE: s->mode = val; ps2_keyboard_set_translation(s->kbd, (s->mode & KBD_MODE_KCC) != 0); - /* ??? */ - kbd_update_irq(s); + /* + * a write to the mode byte interrupt enable flags directly updates + * the irq lines + */ + kbd_update_irq_lines(s); + /* + * a write to the mode byte disable interface flags may raise + * an irq if there is pending data in the PS/2 queues. + */ + kbd_safe_update_irq(s); break; case KBD_CCMD_WRITE_OBUF: kbd_queue(s, val, 0); @@ -354,6 +440,9 @@ static void kbd_write_data(void *opaque, hwaddr addr, break; case KBD_CCMD_WRITE_MOUSE: ps2_write_mouse(s->mouse, val); + /* sending data to the mouse reenables PS/2 communication */ + s->mode &= ~KBD_MODE_DISABLE_MOUSE; + kbd_safe_update_irq(s); break; default: break; @@ -368,7 +457,11 @@ static void kbd_reset(void *opaque) s->mode = KBD_MODE_KBD_INT | KBD_MODE_MOUSE_INT; s->status = KBD_STAT_CMD | KBD_STAT_UNLOCKED; s->outport = KBD_OUT_RESET | KBD_OUT_A20 | KBD_OUT_ONES; - s->outport_present = false; + s->pending = 0; + kbd_deassert_irq(s); + if (s->throttle_timer) { + timer_del(s->throttle_timer); + } } static uint8_t kbd_outport_default(KBDState *s) @@ -403,13 +496,99 @@ static const VMStateDescription vmstate_kbd_outport = { } }; +static int kbd_extended_state_pre_save(void *opaque) +{ + KBDState *s = opaque; + + s->migration_flags = 0; + if (s->throttle_timer && timer_pending(s->throttle_timer)) { + s->migration_flags |= KBD_MIGR_TIMER_PENDING; + } + + return 0; +} + +static int kbd_extended_state_post_load(void *opaque, int version_id) +{ + KBDState *s = opaque; + + if (s->migration_flags & KBD_MIGR_TIMER_PENDING) { + kbd_throttle_timeout(s); + } + s->extended_state_loaded = true; + + return 0; +} + +static bool kbd_extended_state_needed(void *opaque) +{ + KBDState *s = opaque; + + return s->extended_state; +} + +static const VMStateDescription vmstate_kbd_extended_state = { + .name = "pckbd/extended_state", + .post_load = kbd_extended_state_post_load, + .pre_save = kbd_extended_state_pre_save, + .needed = kbd_extended_state_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT32(migration_flags, KBDState), + VMSTATE_UINT32(obsrc, KBDState), + VMSTATE_UINT8(obdata, KBDState), + VMSTATE_UINT8(cbdata, KBDState), + VMSTATE_END_OF_LIST() + } +}; + +static int kbd_pre_save(void *opaque) +{ + KBDState *s = opaque; + + if (s->extended_state) { + s->pending_tmp = s->pending; + } else { + s->pending_tmp = 0; + if (s->pending & KBD_PENDING_KBD) { + s->pending_tmp |= KBD_PENDING_KBD_COMPAT; + } + if (s->pending & KBD_PENDING_AUX) { + s->pending_tmp |= KBD_PENDING_AUX_COMPAT; + } + } + return 0; +} + +static int kbd_pre_load(void *opaque) +{ + KBDState *s = opaque; + + s->outport_present = false; + s->extended_state_loaded = false; + return 0; +} + static int kbd_post_load(void *opaque, int version_id) { KBDState *s = opaque; if (!s->outport_present) { s->outport = kbd_outport_default(s); } - s->outport_present = false; + s->pending = s->pending_tmp; + if (!s->extended_state_loaded) { + s->obsrc = s->status & KBD_STAT_OBF ? + (s->status & KBD_STAT_MOUSE_OBF ? KBD_OBSRC_MOUSE : KBD_OBSRC_KBD) : + 0; + if (s->pending & KBD_PENDING_KBD_COMPAT) { + s->pending |= KBD_PENDING_KBD; + } + if (s->pending & KBD_PENDING_AUX_COMPAT) { + s->pending |= KBD_PENDING_AUX; + } + } + /* clear all unused flags */ + s->pending &= KBD_PENDING_CTRL_KBD | KBD_PENDING_CTRL_AUX | + KBD_PENDING_KBD | KBD_PENDING_AUX; return 0; } @@ -417,16 +596,19 @@ static const VMStateDescription vmstate_kbd = { .name = "pckbd", .version_id = 3, .minimum_version_id = 3, + .pre_load = kbd_pre_load, .post_load = kbd_post_load, + .pre_save = kbd_pre_save, .fields = (VMStateField[]) { VMSTATE_UINT8(write_cmd, KBDState), VMSTATE_UINT8(status, KBDState), VMSTATE_UINT8(mode, KBDState), - VMSTATE_UINT8(pending, KBDState), + VMSTATE_UINT8(pending_tmp, KBDState), VMSTATE_END_OF_LIST() }, .subsections = (const VMStateDescription*[]) { &vmstate_kbd_outport, + &vmstate_kbd_extended_state, NULL } }; @@ -472,6 +654,8 @@ void i8042_mm_init(qemu_irq kbd_irq, qemu_irq mouse_irq, s->irq_mouse = mouse_irq; s->mask = mask; + s->extended_state = true; + vmstate_register(NULL, 0, &vmstate_kbd, s); memory_region_init_io(region, NULL, &i8042_mmio_ops, s, "i8042", size); @@ -485,6 +669,7 @@ struct ISAKBDState { ISADevice parent_obj; KBDState kbd; + bool kbd_throttle; MemoryRegion io[2]; }; @@ -557,6 +742,13 @@ static void i8042_realizefn(DeviceState *dev, Error **errp) s->kbd = ps2_kbd_init(kbd_update_kbd_irq, s); s->mouse = ps2_mouse_init(kbd_update_aux_irq, s); + if (isa_s->kbd_throttle && !isa_s->kbd.extended_state) { + warn_report(TYPE_I8042 ": can't enable kbd-throttle without" + " extended-state, disabling kbd-throttle"); + } else if (isa_s->kbd_throttle) { + s->throttle_timer = timer_new_us(QEMU_CLOCK_VIRTUAL, + kbd_throttle_timeout, s); + } qemu_register_reset(kbd_reset, s); } @@ -588,11 +780,18 @@ static void i8042_build_aml(ISADevice *isadev, Aml *scope) aml_append(scope, mou); } +static Property i8042_properties[] = { + DEFINE_PROP_BOOL("extended-state", ISAKBDState, kbd.extended_state, true), + DEFINE_PROP_BOOL("kbd-throttle", ISAKBDState, kbd_throttle, false), + DEFINE_PROP_END_OF_LIST(), +}; + static void i8042_class_initfn(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); ISADeviceClass *isa = ISA_DEVICE_CLASS(klass); + device_class_set_props(dc, i8042_properties); dc->realize = i8042_realizefn; dc->vmsd = &vmstate_kbd_isa; isa->build_aml = i8042_build_aml; diff --git a/hw/input/ps2.c b/hw/input/ps2.c index 72cdb80ae1..8dd482c1f6 100644 --- a/hw/input/ps2.c +++ b/hw/input/ps2.c @@ -212,8 +212,12 @@ void ps2_raise_irq(PS2State *s) void ps2_queue(PS2State *s, int b) { + if (PS2_QUEUE_SIZE - s->queue.count < 1) { + return; + } + ps2_queue_noirq(s, b); - s->update_irq(s->update_arg, 1); + ps2_raise_irq(s); } void ps2_queue_2(PS2State *s, int b1, int b2) @@ -224,7 +228,7 @@ void ps2_queue_2(PS2State *s, int b1, int b2) ps2_queue_noirq(s, b1); ps2_queue_noirq(s, b2); - s->update_irq(s->update_arg, 1); + ps2_raise_irq(s); } void ps2_queue_3(PS2State *s, int b1, int b2, int b3) @@ -236,7 +240,7 @@ void ps2_queue_3(PS2State *s, int b1, int b2, int b3) ps2_queue_noirq(s, b1); ps2_queue_noirq(s, b2); ps2_queue_noirq(s, b3); - s->update_irq(s->update_arg, 1); + ps2_raise_irq(s); } void ps2_queue_4(PS2State *s, int b1, int b2, int b3, int b4) @@ -249,7 +253,7 @@ void ps2_queue_4(PS2State *s, int b1, int b2, int b3, int b4) ps2_queue_noirq(s, b2); ps2_queue_noirq(s, b3); ps2_queue_noirq(s, b4); - s->update_irq(s->update_arg, 1); + ps2_raise_irq(s); } /* keycode is the untranslated scancode in the current scancode set. */ @@ -293,7 +297,8 @@ static void ps2_keyboard_event(DeviceState *dev, QemuConsole *src, qcode = qemu_input_key_value_to_qcode(key->key); mod = ps2_modifier_bit(qcode); - trace_ps2_keyboard_event(s, qcode, key->down, mod, s->modifiers); + trace_ps2_keyboard_event(s, qcode, key->down, mod, + s->modifiers, s->scancode_set, s->translate); if (key->down) { s->modifiers |= mod; } else { @@ -515,7 +520,9 @@ uint32_t ps2_read_data(PS2State *s) /* reading deasserts IRQ */ s->update_irq(s->update_arg, 0); /* reassert IRQs if data left */ - s->update_irq(s->update_arg, q->count != 0); + if (q->count) { + s->update_irq(s->update_arg, 1); + } } return val; } @@ -645,7 +652,8 @@ void ps2_keyboard_set_translation(void *opaque, int mode) static int ps2_mouse_send_packet(PS2MouseState *s) { - const int needed = 3 + (s->mouse_type - 2); + /* IMPS/2 and IMEX send 4 bytes, PS2 sends 3 bytes */ + const int needed = s->mouse_type ? 4 : 3; unsigned int b; int dx1, dy1, dz1; diff --git a/hw/input/trace-events b/hw/input/trace-events index 1dd8ad6018..e0bfe7f3ee 100644 --- a/hw/input/trace-events +++ b/hw/input/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # adb-kbd.c adb_device_kbd_no_key(void) "Ignoring NO_KEY" @@ -30,7 +30,7 @@ pckbd_kbd_write_data(uint64_t val) "0x%02"PRIx64 # ps2.c ps2_put_keycode(void *opaque, int keycode) "%p keycode 0x%02x" -ps2_keyboard_event(void *opaque, int qcode, int down, unsigned int modifier, unsigned int modifiers) "%p qcode %d down %d modifier 0x%x modifiers 0x%x" +ps2_keyboard_event(void *opaque, int qcode, int down, unsigned int modifier, unsigned int modifiers, int set, int xlate) "%p qcode %d down %d modifier 0x%x modifiers 0x%x set %d xlate %d" ps2_read_data(void *opaque) "%p" ps2_set_ledstate(void *s, int ledstate) "%p ledstate %d" ps2_reset_keyboard(void *s) "%p" @@ -44,13 +44,6 @@ ps2_mouse_reset(void *opaque) "%p" ps2_kbd_init(void *s) "%p" ps2_mouse_init(void *s) "%p" -# milkymist-softusb.c -milkymist_softusb_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_softusb_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_softusb_mevt(uint8_t m) "m %d" -milkymist_softusb_kevt(uint8_t m) "m %d" -milkymist_softusb_pulse_irq(void) "Pulse IRQ" - # hid.c hid_kbd_queue_full(void) "queue full" hid_kbd_queue_empty(void) "queue empty" diff --git a/hw/input/vhost-user-input.c b/hw/input/vhost-user-input.c index 63984a8ba7..273e96a7b1 100644 --- a/hw/input/vhost-user-input.c +++ b/hw/input/vhost-user-input.c @@ -49,13 +49,15 @@ static void vhost_input_get_config(VirtIODevice *vdev, uint8_t *config_data) { VirtIOInput *vinput = VIRTIO_INPUT(vdev); VHostUserInput *vhi = VHOST_USER_INPUT(vdev); + Error *local_err = NULL; int ret; memset(config_data, 0, vinput->cfg_size); - ret = vhost_dev_get_config(&vhi->vhost->dev, config_data, vinput->cfg_size); + ret = vhost_dev_get_config(&vhi->vhost->dev, config_data, vinput->cfg_size, + &local_err); if (ret) { - error_report("vhost-user-input: get device config space failed"); + error_report_err(local_err); return; } } diff --git a/hw/input/virtio-input-host.c b/hw/input/virtio-input-host.c index 85daf73f1a..137efba57b 100644 --- a/hw/input/virtio-input-host.c +++ b/hw/input/virtio-input-host.c @@ -193,13 +193,16 @@ static void virtio_input_host_handle_status(VirtIOInput *vinput, { VirtIOInputHost *vih = VIRTIO_INPUT_HOST(vinput); struct input_event evdev; + struct timeval tval; int rc; - if (gettimeofday(&evdev.time, NULL)) { + if (gettimeofday(&tval, NULL)) { perror("virtio_input_host_handle_status: gettimeofday"); return; } + evdev.input_event_sec = tval.tv_sec; + evdev.input_event_usec = tval.tv_usec; evdev.type = le16_to_cpu(event->type); evdev.code = le16_to_cpu(event->code); evdev.value = le32_to_cpu(event->value); diff --git a/hw/intc/apic.c b/hw/intc/apic.c index f4f50f974e..3df11c34d6 100644 --- a/hw/intc/apic.c +++ b/hw/intc/apic.c @@ -17,7 +17,6 @@ * License along with this library; if not, see */ #include "qemu/osdep.h" -#include "cpu.h" #include "qemu/thread.h" #include "hw/i386/apic_internal.h" #include "hw/i386/apic.h" diff --git a/hw/intc/apic_common.c b/hw/intc/apic_common.c index 6c86932870..7ebd165c4e 100644 --- a/hw/intc/apic_common.c +++ b/hw/intc/apic_common.c @@ -22,7 +22,6 @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "qapi/error.h" -#include "cpu.h" #include "qapi/visitor.h" #include "hw/i386/apic.h" #include "hw/i386/apic_internal.h" diff --git a/hw/intc/arm_gic_kvm.c b/hw/intc/arm_gic_kvm.c index 9494185cf4..7d2a13273a 100644 --- a/hw/intc/arm_gic_kvm.c +++ b/hw/intc/arm_gic_kvm.c @@ -22,8 +22,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu/module.h" -#include "cpu.h" -#include "hw/sysbus.h" #include "migration/blocker.h" #include "sysemu/kvm.h" #include "kvm_arm.h" diff --git a/hw/intc/arm_gicv3.c b/hw/intc/arm_gicv3.c index 66eaa97198..d63f8af604 100644 --- a/hw/intc/arm_gicv3.c +++ b/hw/intc/arm_gicv3.c @@ -18,7 +18,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu/module.h" -#include "hw/sysbus.h" #include "hw/intc/arm_gicv3.h" #include "gicv3_internal.h" diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index 43ef1d7a84..a032d505f5 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -14,6 +14,7 @@ #include "qemu/osdep.h" #include "qemu/bitops.h" +#include "qemu/log.h" #include "qemu/main-loop.h" #include "trace.h" #include "gicv3_internal.h" @@ -1226,7 +1227,7 @@ static void icv_dir_write(CPUARMState *env, const ARMCPRegInfo *ri, trace_gicv3_icv_dir_write(gicv3_redist_affid(cs), value); - if (irq >= cs->gic->num_irq) { + if (irq >= GICV3_MAXIRQ) { /* Also catches special interrupt numbers and LPIs */ return; } @@ -1261,7 +1262,7 @@ static void icv_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, trace_gicv3_icv_eoir_write(ri->crm == 8 ? 0 : 1, gicv3_redist_affid(cs), value); - if (irq >= cs->gic->num_irq) { + if (irq >= GICV3_MAXIRQ) { /* Also catches special interrupt numbers and LPIs */ return; } @@ -1307,27 +1308,16 @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, GICv3CPUState *cs = icc_cs_from_env(env); int irq = value & 0xffffff; int grp; + bool is_eoir0 = ri->crm == 8; - if (icv_access(env, ri->crm == 8 ? HCR_FMO : HCR_IMO)) { + if (icv_access(env, is_eoir0 ? HCR_FMO : HCR_IMO)) { icv_eoir_write(env, ri, value); return; } - trace_gicv3_icc_eoir_write(ri->crm == 8 ? 0 : 1, + trace_gicv3_icc_eoir_write(is_eoir0 ? 0 : 1, gicv3_redist_affid(cs), value); - if (ri->crm == 8) { - /* EOIR0 */ - grp = GICV3_G0; - } else { - /* EOIR1 */ - if (arm_is_secure(env)) { - grp = GICV3_G1; - } else { - grp = GICV3_G1NS; - } - } - if (irq >= cs->gic->num_irq) { /* This handles two cases: * 1. If software writes the ID of a spurious interrupt [ie 1020-1023] @@ -1340,7 +1330,36 @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, return; } - if (icc_highest_active_group(cs) != grp) { + grp = icc_highest_active_group(cs); + switch (grp) { + case GICV3_G0: + if (!is_eoir0) { + return; + } + if (!(cs->gic->gicd_ctlr & GICD_CTLR_DS) + && arm_feature(env, ARM_FEATURE_EL3) && !arm_is_secure(env)) { + return; + } + break; + case GICV3_G1: + if (is_eoir0) { + return; + } + if (!arm_is_secure(env)) { + return; + } + break; + case GICV3_G1NS: + if (is_eoir0) { + return; + } + if (!arm_is_el3_or_mon(env) && arm_is_secure(env)) { + return; + } + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: IRQ %d isn't active\n", __func__, irq); return; } diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index 65a4c880a3..5c09f00dec 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -22,7 +22,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/intc/arm_gicv3_common.h" -#include "hw/sysbus.h" #include "qemu/error-report.h" #include "qemu/module.h" #include "sysemu/kvm.h" diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index 8645220d61..53da703ed8 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -453,7 +453,7 @@ MemTxResult gicv3_redist_read(void *opaque, hwaddr offset, uint64_t *data, if (r == MEMTX_ERROR) { qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid guest read at offset " TARGET_FMT_plx - "size %u\n", __func__, offset, size); + " size %u\n", __func__, offset, size); trace_gicv3_redist_badread(gicv3_redist_affid(cs), offset, size, attrs.secure); /* The spec requires that reserved registers are RAZ/WI; @@ -510,7 +510,7 @@ MemTxResult gicv3_redist_write(void *opaque, hwaddr offset, uint64_t data, if (r == MEMTX_ERROR) { qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid guest write at offset " TARGET_FMT_plx - "size %u\n", __func__, offset, size); + " size %u\n", __func__, offset, size); trace_gicv3_redist_badwrite(gicv3_redist_affid(cs), offset, data, size, attrs.secure); /* The spec requires that reserved registers are RAZ/WI; diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index 0d8426dafc..1e7ddcb94c 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/sysbus.h" #include "migration/vmstate.h" #include "qemu/timer.h" @@ -128,15 +127,14 @@ static bool nvic_isrpending(NVICState *s) { int irq; - /* We can shortcut if the highest priority pending interrupt - * happens to be external or if there is nothing pending. + /* + * We can shortcut if the highest priority pending interrupt + * happens to be external; if not we need to check the whole + * vectors[] array. */ if (s->vectpending > NVIC_FIRST_IRQ) { return true; } - if (s->vectpending == 0) { - return false; - } for (irq = NVIC_FIRST_IRQ; irq < s->num_irq; irq++) { if (s->vectors[irq].pending) { @@ -806,6 +804,16 @@ void armv7m_nvic_acknowledge_irq(void *opaque) nvic_irq_update(s); } +static bool vectpending_targets_secure(NVICState *s) +{ + /* Return true if s->vectpending targets Secure state */ + if (s->vectpending_is_s_banked) { + return true; + } + return !exc_is_banked(s->vectpending) && + exc_targets_secure(s, s->vectpending); +} + void armv7m_nvic_get_pending_irq_info(void *opaque, int *pirq, bool *ptargets_secure) { @@ -815,12 +823,7 @@ void armv7m_nvic_get_pending_irq_info(void *opaque, assert(pending > ARMV7M_EXCP_RESET && pending < s->num_irq); - if (s->vectpending_is_s_banked) { - targets_secure = true; - } else { - targets_secure = !exc_is_banked(pending) && - exc_targets_secure(s, pending); - } + targets_secure = vectpending_targets_secure(s); trace_nvic_get_pending_irq_info(pending, targets_secure); @@ -1041,7 +1044,19 @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) /* VECTACTIVE */ val = cpu->env.v7m.exception; /* VECTPENDING */ - val |= (s->vectpending & 0xff) << 12; + if (s->vectpending) { + /* + * From v8.1M VECTPENDING must read as 1 if accessed as + * NonSecure and the highest priority pending and enabled + * exception targets Secure. + */ + int vp = s->vectpending; + if (!attrs.secure && arm_feature(&cpu->env, ARM_FEATURE_V8_1M) && + vectpending_targets_secure(s)) { + vp = 1; + } + val |= (vp & 0x1ff) << 12; + } /* ISRPENDING - set if any external IRQ is pending */ if (nvic_isrpending(s)) { val |= (1 << 22); @@ -2942,12 +2957,6 @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) static void armv7m_nvic_instance_init(Object *obj) { - /* We have a different default value for the num-irq property - * than our superclass. This function runs after qdev init - * has set the defaults from the Property array and before - * any user-specified property setting, so just modify the - * value in the GICState struct. - */ DeviceState *dev = DEVICE(obj); NVICState *nvic = NVIC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); diff --git a/hw/intc/grlib_irqmp.c b/hw/intc/grlib_irqmp.c index 984334fa7b..3bfe2544b7 100644 --- a/hw/intc/grlib_irqmp.c +++ b/hw/intc/grlib_irqmp.c @@ -27,7 +27,6 @@ #include "qemu/osdep.h" #include "hw/irq.h" #include "hw/sysbus.h" -#include "cpu.h" #include "hw/qdev-properties.h" #include "hw/sparc/grlib.h" diff --git a/hw/intc/ibex_plic.c b/hw/intc/ibex_plic.c index c1b72fcab0..edf76e4f61 100644 --- a/hw/intc/ibex_plic.c +++ b/hw/intc/ibex_plic.c @@ -225,23 +225,23 @@ static void ibex_plic_irq_request(void *opaque, int irq, int level) static Property ibex_plic_properties[] = { DEFINE_PROP_UINT32("num-cpus", IbexPlicState, num_cpus, 1), - DEFINE_PROP_UINT32("num-sources", IbexPlicState, num_sources, 80), + DEFINE_PROP_UINT32("num-sources", IbexPlicState, num_sources, 176), DEFINE_PROP_UINT32("pending-base", IbexPlicState, pending_base, 0), - DEFINE_PROP_UINT32("pending-num", IbexPlicState, pending_num, 3), + DEFINE_PROP_UINT32("pending-num", IbexPlicState, pending_num, 6), - DEFINE_PROP_UINT32("source-base", IbexPlicState, source_base, 0x0c), - DEFINE_PROP_UINT32("source-num", IbexPlicState, source_num, 3), + DEFINE_PROP_UINT32("source-base", IbexPlicState, source_base, 0x18), + DEFINE_PROP_UINT32("source-num", IbexPlicState, source_num, 6), - DEFINE_PROP_UINT32("priority-base", IbexPlicState, priority_base, 0x18), - DEFINE_PROP_UINT32("priority-num", IbexPlicState, priority_num, 80), + DEFINE_PROP_UINT32("priority-base", IbexPlicState, priority_base, 0x30), + DEFINE_PROP_UINT32("priority-num", IbexPlicState, priority_num, 177), - DEFINE_PROP_UINT32("enable-base", IbexPlicState, enable_base, 0x200), - DEFINE_PROP_UINT32("enable-num", IbexPlicState, enable_num, 3), + DEFINE_PROP_UINT32("enable-base", IbexPlicState, enable_base, 0x300), + DEFINE_PROP_UINT32("enable-num", IbexPlicState, enable_num, 6), - DEFINE_PROP_UINT32("threshold-base", IbexPlicState, threshold_base, 0x20c), + DEFINE_PROP_UINT32("threshold-base", IbexPlicState, threshold_base, 0x318), - DEFINE_PROP_UINT32("claim-base", IbexPlicState, claim_base, 0x210), + DEFINE_PROP_UINT32("claim-base", IbexPlicState, claim_base, 0x31c), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/intc/imx_gpcv2.c b/hw/intc/imx_gpcv2.c index 17007a4078..237d5f97eb 100644 --- a/hw/intc/imx_gpcv2.c +++ b/hw/intc/imx_gpcv2.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" #include "hw/intc/imx_gpcv2.h" #include "migration/vmstate.h" -#include "qemu/log.h" #include "qemu/module.h" #define GPC_PU_PGC_SW_PUP_REQ 0x0f8 diff --git a/hw/intc/lm32_pic.c b/hw/intc/lm32_pic.c deleted file mode 100644 index 991a90bc99..0000000000 --- a/hw/intc/lm32_pic.c +++ /dev/null @@ -1,195 +0,0 @@ -/* - * LatticeMico32 CPU interrupt controller logic. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - */ - -#include "qemu/osdep.h" - -#include "migration/vmstate.h" -#include "monitor/monitor.h" -#include "qemu/module.h" -#include "hw/sysbus.h" -#include "trace.h" -#include "hw/lm32/lm32_pic.h" -#include "hw/intc/intc.h" -#include "hw/irq.h" -#include "qom/object.h" - -#define TYPE_LM32_PIC "lm32-pic" -OBJECT_DECLARE_SIMPLE_TYPE(LM32PicState, LM32_PIC) - -struct LM32PicState { - SysBusDevice parent_obj; - - qemu_irq parent_irq; - uint32_t im; /* interrupt mask */ - uint32_t ip; /* interrupt pending */ - uint32_t irq_state; - - /* statistics */ - uint64_t stats_irq_count[32]; -}; - -static void update_irq(LM32PicState *s) -{ - s->ip |= s->irq_state; - - if (s->ip & s->im) { - trace_lm32_pic_raise_irq(); - qemu_irq_raise(s->parent_irq); - } else { - trace_lm32_pic_lower_irq(); - qemu_irq_lower(s->parent_irq); - } -} - -static void irq_handler(void *opaque, int irq, int level) -{ - LM32PicState *s = opaque; - - assert(irq < 32); - trace_lm32_pic_interrupt(irq, level); - - if (level) { - s->irq_state |= (1 << irq); - s->stats_irq_count[irq]++; - } else { - s->irq_state &= ~(1 << irq); - } - - update_irq(s); -} - -void lm32_pic_set_im(DeviceState *d, uint32_t im) -{ - LM32PicState *s = LM32_PIC(d); - - trace_lm32_pic_set_im(im); - s->im = im; - - update_irq(s); -} - -void lm32_pic_set_ip(DeviceState *d, uint32_t ip) -{ - LM32PicState *s = LM32_PIC(d); - - trace_lm32_pic_set_ip(ip); - - /* ack interrupt */ - s->ip &= ~ip; - - update_irq(s); -} - -uint32_t lm32_pic_get_im(DeviceState *d) -{ - LM32PicState *s = LM32_PIC(d); - - trace_lm32_pic_get_im(s->im); - return s->im; -} - -uint32_t lm32_pic_get_ip(DeviceState *d) -{ - LM32PicState *s = LM32_PIC(d); - - trace_lm32_pic_get_ip(s->ip); - return s->ip; -} - -static void pic_reset(DeviceState *d) -{ - LM32PicState *s = LM32_PIC(d); - int i; - - s->im = 0; - s->ip = 0; - s->irq_state = 0; - for (i = 0; i < 32; i++) { - s->stats_irq_count[i] = 0; - } -} - -static bool lm32_get_statistics(InterruptStatsProvider *obj, - uint64_t **irq_counts, unsigned int *nb_irqs) -{ - LM32PicState *s = LM32_PIC(obj); - *irq_counts = s->stats_irq_count; - *nb_irqs = ARRAY_SIZE(s->stats_irq_count); - return true; -} - -static void lm32_print_info(InterruptStatsProvider *obj, Monitor *mon) -{ - LM32PicState *s = LM32_PIC(obj); - monitor_printf(mon, "lm32-pic: im=%08x ip=%08x irq_state=%08x\n", - s->im, s->ip, s->irq_state); -} - -static void lm32_pic_init(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - LM32PicState *s = LM32_PIC(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - - qdev_init_gpio_in(dev, irq_handler, 32); - sysbus_init_irq(sbd, &s->parent_irq); -} - -static const VMStateDescription vmstate_lm32_pic = { - .name = "lm32-pic", - .version_id = 2, - .minimum_version_id = 2, - .fields = (VMStateField[]) { - VMSTATE_UINT32(im, LM32PicState), - VMSTATE_UINT32(ip, LM32PicState), - VMSTATE_UINT32(irq_state, LM32PicState), - VMSTATE_UINT64_ARRAY(stats_irq_count, LM32PicState, 32), - VMSTATE_END_OF_LIST() - } -}; - -static void lm32_pic_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - InterruptStatsProviderClass *ic = INTERRUPT_STATS_PROVIDER_CLASS(klass); - - dc->reset = pic_reset; - dc->vmsd = &vmstate_lm32_pic; - ic->get_statistics = lm32_get_statistics; - ic->print_info = lm32_print_info; -} - -static const TypeInfo lm32_pic_info = { - .name = TYPE_LM32_PIC, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(LM32PicState), - .instance_init = lm32_pic_init, - .class_init = lm32_pic_class_init, - .interfaces = (InterfaceInfo[]) { - { TYPE_INTERRUPT_STATS_PROVIDER }, - { } - }, -}; - -static void lm32_pic_register_types(void) -{ - type_register_static(&lm32_pic_info); -} - -type_init(lm32_pic_register_types) diff --git a/hw/intc/meson.build b/hw/intc/meson.build index 1c299039f6..6e52a166e3 100644 --- a/hw/intc/meson.build +++ b/hw/intc/meson.build @@ -14,10 +14,8 @@ softmmu_ss.add(when: 'CONFIG_HEATHROW_PIC', if_true: files('heathrow_pic.c')) softmmu_ss.add(when: 'CONFIG_I8259', if_true: files('i8259_common.c', 'i8259.c')) softmmu_ss.add(when: 'CONFIG_IMX', if_true: files('imx_avic.c', 'imx_gpcv2.c')) softmmu_ss.add(when: 'CONFIG_IOAPIC', if_true: files('ioapic_common.c')) -softmmu_ss.add(when: 'CONFIG_LM32_DEVICES', if_true: files('lm32_pic.c')) softmmu_ss.add(when: 'CONFIG_OPENPIC', if_true: files('openpic.c')) softmmu_ss.add(when: 'CONFIG_PL190', if_true: files('pl190.c')) -softmmu_ss.add(when: 'CONFIG_PUV3', if_true: files('puv3_intc.c')) softmmu_ss.add(when: 'CONFIG_REALVIEW', if_true: files('realview_gic.c')) softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_intctl.c')) softmmu_ss.add(when: 'CONFIG_XILINX', if_true: files('xilinx_intc.c')) diff --git a/hw/intc/ompic.c b/hw/intc/ompic.c index 1731a10683..1f10314807 100644 --- a/hw/intc/ompic.c +++ b/hw/intc/ompic.c @@ -7,7 +7,6 @@ */ #include "qemu/osdep.h" -#include "qemu/log.h" #include "qemu/module.h" #include "qapi/error.h" #include "hw/irq.h" diff --git a/hw/intc/openpic.c b/hw/intc/openpic.c index 65970e1b37..9b4c17854d 100644 --- a/hw/intc/openpic.c +++ b/hw/intc/openpic.c @@ -47,7 +47,6 @@ #include "qapi/error.h" #include "qemu/bitops.h" #include "qapi/qmp/qerror.h" -#include "qemu/log.h" #include "qemu/module.h" #include "qemu/timer.h" #include "qemu/error-report.h" diff --git a/hw/intc/openpic_kvm.c b/hw/intc/openpic_kvm.c index e1a39e33cb..21da680389 100644 --- a/hw/intc/openpic_kvm.c +++ b/hw/intc/openpic_kvm.c @@ -24,9 +24,7 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include -#include "exec/address-spaces.h" #include "hw/ppc/openpic.h" #include "hw/ppc/openpic_kvm.h" #include "hw/pci/msi.h" diff --git a/hw/intc/ppc-uic.c b/hw/intc/ppc-uic.c index 7171de7b35..60013f2dde 100644 --- a/hw/intc/ppc-uic.c +++ b/hw/intc/ppc-uic.c @@ -23,7 +23,7 @@ */ #include "qemu/osdep.h" -#include "include/hw/intc/ppc-uic.h" +#include "hw/intc/ppc-uic.h" #include "hw/irq.h" #include "cpu.h" #include "hw/ppc/ppc.h" diff --git a/hw/intc/puv3_intc.c b/hw/intc/puv3_intc.c deleted file mode 100644 index 65226f5e7c..0000000000 --- a/hw/intc/puv3_intc.c +++ /dev/null @@ -1,147 +0,0 @@ -/* - * INTC device simulation in PKUnity SoC - * - * Copyright (C) 2010-2012 Guan Xuetao - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation, or any later version. - * See the COPYING file in the top-level directory. - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "qom/object.h" - -#undef DEBUG_PUV3 -#include "hw/unicore32/puv3.h" -#include "qemu/module.h" -#include "qemu/log.h" - -#define TYPE_PUV3_INTC "puv3_intc" -OBJECT_DECLARE_SIMPLE_TYPE(PUV3INTCState, PUV3_INTC) - -struct PUV3INTCState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - qemu_irq parent_irq; - - uint32_t reg_ICMR; - uint32_t reg_ICPR; -}; - -/* Update interrupt status after enabled or pending bits have been changed. */ -static void puv3_intc_update(PUV3INTCState *s) -{ - if (s->reg_ICMR & s->reg_ICPR) { - qemu_irq_raise(s->parent_irq); - } else { - qemu_irq_lower(s->parent_irq); - } -} - -/* Process a change in an external INTC input. */ -static void puv3_intc_handler(void *opaque, int irq, int level) -{ - PUV3INTCState *s = opaque; - - DPRINTF("irq 0x%x, level 0x%x\n", irq, level); - if (level) { - s->reg_ICPR |= (1 << irq); - } else { - s->reg_ICPR &= ~(1 << irq); - } - puv3_intc_update(s); -} - -static uint64_t puv3_intc_read(void *opaque, hwaddr offset, - unsigned size) -{ - PUV3INTCState *s = opaque; - uint32_t ret = 0; - - switch (offset) { - case 0x04: /* INTC_ICMR */ - ret = s->reg_ICMR; - break; - case 0x0c: /* INTC_ICIP */ - ret = s->reg_ICPR; /* the same value with ICPR */ - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } - DPRINTF("offset 0x%x, value 0x%x\n", offset, ret); - return ret; -} - -static void puv3_intc_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PUV3INTCState *s = opaque; - - DPRINTF("offset 0x%x, value 0x%x\n", offset, value); - switch (offset) { - case 0x00: /* INTC_ICLR */ - case 0x14: /* INTC_ICCR */ - break; - case 0x04: /* INTC_ICMR */ - s->reg_ICMR = value; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - return; - } - puv3_intc_update(s); -} - -static const MemoryRegionOps puv3_intc_ops = { - .read = puv3_intc_read, - .write = puv3_intc_write, - .impl = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void puv3_intc_realize(DeviceState *dev, Error **errp) -{ - PUV3INTCState *s = PUV3_INTC(dev); - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - - qdev_init_gpio_in(dev, puv3_intc_handler, PUV3_IRQS_NR); - sysbus_init_irq(sbd, &s->parent_irq); - - s->reg_ICMR = 0; - s->reg_ICPR = 0; - - memory_region_init_io(&s->iomem, OBJECT(s), &puv3_intc_ops, s, "puv3_intc", - PUV3_REGS_OFFSET); - sysbus_init_mmio(sbd, &s->iomem); -} - -static void puv3_intc_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - dc->realize = puv3_intc_realize; -} - -static const TypeInfo puv3_intc_info = { - .name = TYPE_PUV3_INTC, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PUV3INTCState), - .class_init = puv3_intc_class_init, -}; - -static void puv3_intc_register_type(void) -{ - type_register_static(&puv3_intc_info); -} - -type_init(puv3_intc_register_type) diff --git a/hw/intc/s390_flic.c b/hw/intc/s390_flic.c index aacdb1bbc2..74e02858d4 100644 --- a/hw/intc/s390_flic.c +++ b/hw/intc/s390_flic.c @@ -20,7 +20,6 @@ #include "hw/qdev-properties.h" #include "hw/s390x/css.h" #include "trace.h" -#include "cpu.h" #include "qapi/error.h" #include "hw/s390x/s390-virtio-ccw.h" diff --git a/hw/intc/s390_flic_kvm.c b/hw/intc/s390_flic_kvm.c index b3fb9f8395..efe5054182 100644 --- a/hw/intc/s390_flic_kvm.c +++ b/hw/intc/s390_flic_kvm.c @@ -11,13 +11,11 @@ */ #include "qemu/osdep.h" -#include "cpu.h" -#include "kvm_s390x.h" +#include "kvm/kvm_s390x.h" #include #include "qemu/error-report.h" #include "qemu/module.h" #include "qapi/error.h" -#include "hw/sysbus.h" #include "sysemu/kvm.h" #include "hw/s390x/s390_flic.h" #include "hw/s390x/adapter.h" diff --git a/hw/intc/sifive_plic.c b/hw/intc/sifive_plic.c index 97a1a27a9a..78903beb06 100644 --- a/hw/intc/sifive_plic.c +++ b/hw/intc/sifive_plic.c @@ -25,11 +25,9 @@ #include "qemu/error-report.h" #include "hw/sysbus.h" #include "hw/pci/msi.h" -#include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/intc/sifive_plic.h" #include "target/riscv/cpu.h" -#include "sysemu/sysemu.h" #include "migration/vmstate.h" #define RISCV_DEBUG_PLIC 0 diff --git a/hw/intc/spapr_xive.c b/hw/intc/spapr_xive.c index 801bc19341..89cfa018f5 100644 --- a/hw/intc/spapr_xive.c +++ b/hw/intc/spapr_xive.c @@ -1798,7 +1798,7 @@ static target_ulong h_int_reset(PowerPCCPU *cpu, return H_PARAMETER; } - device_legacy_reset(DEVICE(xive)); + device_cold_reset(DEVICE(xive)); if (spapr_xive_in_kernel(xive)) { Error *local_err = NULL; diff --git a/hw/intc/trace-events b/hw/intc/trace-events index c9ab17234b..e56e7dd3b6 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # i8259.c pic_update_irq(bool master, uint8_t imr, uint8_t irr, uint8_t padd) "master %d imr %"PRIu8" irr %"PRIu8" padd %"PRIu8 @@ -51,15 +51,6 @@ grlib_irqmp_set_irq(int irq) "Raise CPU IRQ %d" grlib_irqmp_readl_unknown(uint64_t addr) "addr 0x%"PRIx64 grlib_irqmp_writel_unknown(uint64_t addr, uint32_t value) "addr 0x%"PRIx64" value 0x%x" -# lm32_pic.c -lm32_pic_raise_irq(void) "Raise CPU interrupt" -lm32_pic_lower_irq(void) "Lower CPU interrupt" -lm32_pic_interrupt(int irq, int level) "Set IRQ%d %d" -lm32_pic_set_im(uint32_t im) "im 0x%08x" -lm32_pic_set_ip(uint32_t ip) "ip 0x%08x" -lm32_pic_get_im(uint32_t im) "im 0x%08x" -lm32_pic_get_ip(uint32_t ip) "ip 0x%08x" - # xics.c xics_icp_check_ipi(int server, uint8_t mfrr) "CPU %d can take IPI mfrr=0x%x" xics_icp_accept(uint32_t old_xirr, uint32_t new_xirr) "icp_accept: XIRR 0x%"PRIx32"->0x%"PRIx32 diff --git a/hw/intc/xics.c b/hw/intc/xics.c index 68f9d44feb..48a835eab7 100644 --- a/hw/intc/xics.c +++ b/hw/intc/xics.c @@ -27,7 +27,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "trace.h" #include "qemu/timer.h" #include "hw/ppc/xics.h" diff --git a/hw/intc/xics_kvm.c b/hw/intc/xics_kvm.c index 570d635bcc..f5bfc501bc 100644 --- a/hw/intc/xics_kvm.c +++ b/hw/intc/xics_kvm.c @@ -28,7 +28,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu-common.h" -#include "cpu.h" #include "trace.h" #include "sysemu/kvm.h" #include "hw/ppc/spapr.h" diff --git a/hw/intc/xics_spapr.c b/hw/intc/xics_spapr.c index 8ae4f41459..37b2d99977 100644 --- a/hw/intc/xics_spapr.c +++ b/hw/intc/xics_spapr.c @@ -26,7 +26,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "trace.h" #include "qemu/timer.h" #include "hw/ppc/spapr.h" diff --git a/hw/ipmi/ipmi_bmc_sim.c b/hw/ipmi/ipmi_bmc_sim.c index 55fb81fa5a..905e091094 100644 --- a/hw/ipmi/ipmi_bmc_sim.c +++ b/hw/ipmi/ipmi_bmc_sim.c @@ -189,7 +189,7 @@ struct IPMIBmcSim { uint8_t watchdog_use; uint8_t watchdog_action; uint8_t watchdog_pretimeout; /* In seconds */ - bool watchdog_expired; + uint8_t watchdog_expired; uint16_t watchdog_timeout; /* in 100's of milliseconds */ bool watchdog_running; @@ -2110,7 +2110,7 @@ static const VMStateDescription vmstate_ipmi_sim = { VMSTATE_UINT8(watchdog_use, IPMIBmcSim), VMSTATE_UINT8(watchdog_action, IPMIBmcSim), VMSTATE_UINT8(watchdog_pretimeout, IPMIBmcSim), - VMSTATE_BOOL(watchdog_expired, IPMIBmcSim), + VMSTATE_UINT8(watchdog_expired, IPMIBmcSim), VMSTATE_UINT16(watchdog_timeout, IPMIBmcSim), VMSTATE_BOOL(watchdog_running, IPMIBmcSim), VMSTATE_BOOL(watchdog_preaction_ran, IPMIBmcSim), diff --git a/hw/ipmi/isa_ipmi_bt.c b/hw/ipmi/isa_ipmi_bt.c index b7c2ad557b..02625eb94e 100644 --- a/hw/ipmi/isa_ipmi_bt.c +++ b/hw/ipmi/isa_ipmi_bt.c @@ -23,7 +23,6 @@ */ #include "qemu/osdep.h" -#include "qemu/log.h" #include "qemu/module.h" #include "qapi/error.h" #include "hw/irq.h" diff --git a/hw/ipmi/isa_ipmi_kcs.c b/hw/ipmi/isa_ipmi_kcs.c index 7dd6bf0040..3b23ad08b3 100644 --- a/hw/ipmi/isa_ipmi_kcs.c +++ b/hw/ipmi/isa_ipmi_kcs.c @@ -23,7 +23,6 @@ */ #include "qemu/osdep.h" -#include "qemu/log.h" #include "qemu/module.h" #include "qapi/error.h" #include "hw/irq.h" diff --git a/hw/isa/Kconfig b/hw/isa/Kconfig index 55e0003ce4..d42143a991 100644 --- a/hw/isa/Kconfig +++ b/hw/isa/Kconfig @@ -17,6 +17,7 @@ config ISA_SUPERIO bool select ISA_BUS select PCKBD + select FDC_ISA config PC87312 bool @@ -27,7 +28,7 @@ config PC87312 select MC146818RTC select SERIAL_ISA select PARALLEL - select FDC + select FDC_ISA select IDE_ISA config PIIX3 @@ -46,16 +47,21 @@ config VT82C686 select ISA_SUPERIO select ACPI_SMBUS select SERIAL_ISA - select FDC + select FDC_ISA select USB_UHCI select APM + select I8254 + select I8257 + select I8259 + select MC146818RTC + select PARALLEL config SMC37C669 bool select ISA_SUPERIO select SERIAL_ISA select PARALLEL - select FDC + select FDC_ISA config LPC_ICH9 bool diff --git a/hw/isa/isa-bus.c b/hw/isa/isa-bus.c index d27a3c171f..f4576b8e09 100644 --- a/hw/isa/isa-bus.c +++ b/hw/isa/isa-bus.c @@ -139,13 +139,17 @@ void isa_unregister_ioport(ISADevice *dev, MemoryRegion *io) memory_region_del_subregion(isabus->address_space_io, io); } -void isa_register_portio_list(ISADevice *dev, - PortioList *piolist, uint16_t start, - const MemoryRegionPortio *pio_start, - void *opaque, const char *name) +int isa_register_portio_list(ISADevice *dev, + PortioList *piolist, uint16_t start, + const MemoryRegionPortio *pio_start, + void *opaque, const char *name) { assert(piolist && !piolist->owner); + if (!isabus) { + return -ENODEV; + } + /* START is how we should treat DEV, regardless of the actual contents of the portio array. This is how the old code actually handled e.g. the FDC device. */ @@ -153,6 +157,8 @@ void isa_register_portio_list(ISADevice *dev, portio_list_init(piolist, OBJECT(dev), pio_start, opaque, name); portio_list_add(piolist, isabus->address_space_io, start); + + return 0; } static void isa_device_init(Object *obj) diff --git a/hw/isa/isa-superio.c b/hw/isa/isa-superio.c index 179c185695..c81bfe58ef 100644 --- a/hw/isa/isa-superio.c +++ b/hw/isa/isa-superio.c @@ -14,7 +14,6 @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "qapi/error.h" -#include "sysemu/sysemu.h" #include "sysemu/blockdev.h" #include "chardev/char.h" #include "hw/block/fdc.h" diff --git a/hw/isa/lpc_ich9.c b/hw/isa/lpc_ich9.c index 3963b73520..5f9de0239c 100644 --- a/hw/isa/lpc_ich9.c +++ b/hw/isa/lpc_ich9.c @@ -34,7 +34,6 @@ #include "qapi/visitor.h" #include "qemu/range.h" #include "hw/isa/isa.h" -#include "hw/sysbus.h" #include "migration/vmstate.h" #include "hw/irq.h" #include "hw/isa/apm.h" @@ -45,7 +44,6 @@ #include "hw/acpi/ich9.h" #include "hw/pci/pci_bus.h" #include "hw/qdev-properties.h" -#include "exec/address-spaces.h" #include "sysemu/runstate.h" #include "sysemu/sysemu.h" #include "hw/core/cpu.h" diff --git a/hw/isa/piix3.c b/hw/isa/piix3.c index f46ccae25c..dab901c9ad 100644 --- a/hw/isa/piix3.c +++ b/hw/isa/piix3.c @@ -29,7 +29,6 @@ #include "hw/isa/isa.h" #include "hw/xen/xen.h" #include "sysemu/xen.h" -#include "sysemu/sysemu.h" #include "sysemu/reset.h" #include "sysemu/runstate.h" #include "migration/vmstate.h" diff --git a/hw/isa/piix4.c b/hw/isa/piix4.c index b3b6a4378a..0fe7b69bc4 100644 --- a/hw/isa/piix4.c +++ b/hw/isa/piix4.c @@ -29,7 +29,6 @@ #include "hw/southbridge/piix.h" #include "hw/pci/pci.h" #include "hw/isa/isa.h" -#include "hw/sysbus.h" #include "hw/intc/i8259.h" #include "hw/dma/i8257.h" #include "hw/timer/i8254.h" @@ -268,8 +267,9 @@ DeviceState *piix4_create(PCIBus *pci_bus, ISABus **isa_bus, I2CBus **smbus) pci_create_simple(pci_bus, devfn + 2, "piix4-usb-uhci"); if (smbus) { *smbus = piix4_pm_init(pci_bus, devfn + 3, 0x1100, - isa_get_irq(NULL, 9), NULL, 0, NULL); - } + qdev_get_gpio_in_named(dev, "isa", 9), + NULL, 0, NULL); + } return dev; } diff --git a/hw/isa/trace-events b/hw/isa/trace-events index 641d69eedf..b8f877e1ed 100644 --- a/hw/isa/trace-events +++ b/hw/isa/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # isa-superio.c superio_create_parallel(int id, uint16_t base, unsigned int irq) "id=%d, base 0x%03x, irq %u" diff --git a/hw/isa/vt82c686.c b/hw/isa/vt82c686.c index 98325bb32b..f57f3e7067 100644 --- a/hw/isa/vt82c686.c +++ b/hw/isa/vt82c686.c @@ -8,6 +8,9 @@ * * Contributions after 2012-01-13 are licensed under the terms of the * GNU GPL, version 2 or (at your option) any later version. + * + * VT8231 south bridge support and general clean up to allow it + * Copyright (c) 2018-2020 BALATON Zoltan */ #include "qemu/osdep.h" @@ -30,7 +33,6 @@ #include "qemu/module.h" #include "qemu/range.h" #include "qemu/timer.h" -#include "exec/address-spaces.h" #include "trace.h" #define TYPE_VIA_PM "via-pm" @@ -265,15 +267,80 @@ static const TypeInfo vt8231_pm_info = { }; -typedef struct SuperIOConfig { - uint8_t regs[0x100]; - MemoryRegion io; -} SuperIOConfig; +#define TYPE_VIA_SUPERIO "via-superio" +OBJECT_DECLARE_SIMPLE_TYPE(ViaSuperIOState, VIA_SUPERIO) -static void superio_cfg_write(void *opaque, hwaddr addr, uint64_t data, - unsigned size) +struct ViaSuperIOState { + ISASuperIODevice superio; + uint8_t regs[0x100]; + const MemoryRegionOps *io_ops; + MemoryRegion io; +}; + +static inline void via_superio_io_enable(ViaSuperIOState *s, bool enable) { - SuperIOConfig *sc = opaque; + memory_region_set_enabled(&s->io, enable); +} + +static void via_superio_realize(DeviceState *d, Error **errp) +{ + ViaSuperIOState *s = VIA_SUPERIO(d); + ISASuperIOClass *ic = ISA_SUPERIO_GET_CLASS(s); + Error *local_err = NULL; + + assert(s->io_ops); + ic->parent_realize(d, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + memory_region_init_io(&s->io, OBJECT(d), s->io_ops, s, "via-superio", 2); + memory_region_set_enabled(&s->io, false); + /* The floppy also uses 0x3f0 and 0x3f1 but this seems to work anyway */ + memory_region_add_subregion(isa_address_space_io(ISA_DEVICE(s)), 0x3f0, + &s->io); +} + +static uint64_t via_superio_cfg_read(void *opaque, hwaddr addr, unsigned size) +{ + ViaSuperIOState *sc = opaque; + uint8_t idx = sc->regs[0]; + uint8_t val = sc->regs[idx]; + + if (addr == 0) { + return idx; + } + if (addr == 1 && idx == 0) { + val = 0; /* reading reg 0 where we store index value */ + } + trace_via_superio_read(idx, val); + return val; +} + +static void via_superio_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ISASuperIOClass *sc = ISA_SUPERIO_CLASS(klass); + + sc->parent_realize = dc->realize; + dc->realize = via_superio_realize; +} + +static const TypeInfo via_superio_info = { + .name = TYPE_VIA_SUPERIO, + .parent = TYPE_ISA_SUPERIO, + .instance_size = sizeof(ViaSuperIOState), + .class_size = sizeof(ISASuperIOClass), + .class_init = via_superio_class_init, + .abstract = true, +}; + +#define TYPE_VT82C686B_SUPERIO "vt82c686b-superio" + +static void vt82c686b_superio_cfg_write(void *opaque, hwaddr addr, + uint64_t data, unsigned size) +{ + ViaSuperIOState *sc = opaque; uint8_t idx = sc->regs[0]; if (addr == 0) { /* config index register */ @@ -304,25 +371,9 @@ static void superio_cfg_write(void *opaque, hwaddr addr, uint64_t data, sc->regs[idx] = data; } -static uint64_t superio_cfg_read(void *opaque, hwaddr addr, unsigned size) -{ - SuperIOConfig *sc = opaque; - uint8_t idx = sc->regs[0]; - uint8_t val = sc->regs[idx]; - - if (addr == 0) { - return idx; - } - if (addr == 1 && idx == 0) { - val = 0; /* reading reg 0 where we store index value */ - } - trace_via_superio_read(idx, val); - return val; -} - -static const MemoryRegionOps superio_cfg_ops = { - .read = superio_cfg_read, - .write = superio_cfg_write, +static const MemoryRegionOps vt82c686b_superio_cfg_ops = { + .read = via_superio_cfg_read, + .write = vt82c686b_superio_cfg_write, .endianness = DEVICE_NATIVE_ENDIAN, .impl = { .min_access_size = 1, @@ -330,47 +381,215 @@ static const MemoryRegionOps superio_cfg_ops = { }, }; +static void vt82c686b_superio_reset(DeviceState *dev) +{ + ViaSuperIOState *s = VIA_SUPERIO(dev); -OBJECT_DECLARE_SIMPLE_TYPE(VT82C686BISAState, VT82C686B_ISA) + memset(s->regs, 0, sizeof(s->regs)); + /* Device ID */ + vt82c686b_superio_cfg_write(s, 0, 0xe0, 1); + vt82c686b_superio_cfg_write(s, 1, 0x3c, 1); + /* Function select - all disabled */ + vt82c686b_superio_cfg_write(s, 0, 0xe2, 1); + vt82c686b_superio_cfg_write(s, 1, 0x03, 1); + /* Floppy ctrl base addr 0x3f0-7 */ + vt82c686b_superio_cfg_write(s, 0, 0xe3, 1); + vt82c686b_superio_cfg_write(s, 1, 0xfc, 1); + /* Parallel port base addr 0x378-f */ + vt82c686b_superio_cfg_write(s, 0, 0xe6, 1); + vt82c686b_superio_cfg_write(s, 1, 0xde, 1); + /* Serial port 1 base addr 0x3f8-f */ + vt82c686b_superio_cfg_write(s, 0, 0xe7, 1); + vt82c686b_superio_cfg_write(s, 1, 0xfe, 1); + /* Serial port 2 base addr 0x2f8-f */ + vt82c686b_superio_cfg_write(s, 0, 0xe8, 1); + vt82c686b_superio_cfg_write(s, 1, 0xbe, 1); -struct VT82C686BISAState { + vt82c686b_superio_cfg_write(s, 0, 0, 1); +} + +static void vt82c686b_superio_init(Object *obj) +{ + VIA_SUPERIO(obj)->io_ops = &vt82c686b_superio_cfg_ops; +} + +static void vt82c686b_superio_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ISASuperIOClass *sc = ISA_SUPERIO_CLASS(klass); + + dc->reset = vt82c686b_superio_reset; + sc->serial.count = 2; + sc->parallel.count = 1; + sc->ide.count = 0; /* emulated by via-ide */ + sc->floppy.count = 1; +} + +static const TypeInfo vt82c686b_superio_info = { + .name = TYPE_VT82C686B_SUPERIO, + .parent = TYPE_VIA_SUPERIO, + .instance_size = sizeof(ViaSuperIOState), + .instance_init = vt82c686b_superio_init, + .class_size = sizeof(ISASuperIOClass), + .class_init = vt82c686b_superio_class_init, +}; + + +#define TYPE_VT8231_SUPERIO "vt8231-superio" + +static void vt8231_superio_cfg_write(void *opaque, hwaddr addr, + uint64_t data, unsigned size) +{ + ViaSuperIOState *sc = opaque; + uint8_t idx = sc->regs[0]; + + if (addr == 0) { /* config index register */ + sc->regs[0] = data; + return; + } + + /* config data register */ + trace_via_superio_write(idx, data); + switch (idx) { + case 0x00 ... 0xdf: + case 0xe7 ... 0xef: + case 0xf0 ... 0xf1: + case 0xf5: + case 0xf8: + case 0xfd: + /* ignore write to read only registers */ + return; + default: + qemu_log_mask(LOG_UNIMP, + "via_superio_cfg: unimplemented register 0x%x\n", idx); + break; + } + sc->regs[idx] = data; +} + +static const MemoryRegionOps vt8231_superio_cfg_ops = { + .read = via_superio_cfg_read, + .write = vt8231_superio_cfg_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + .min_access_size = 1, + .max_access_size = 1, + }, +}; + +static void vt8231_superio_reset(DeviceState *dev) +{ + ViaSuperIOState *s = VIA_SUPERIO(dev); + + memset(s->regs, 0, sizeof(s->regs)); + /* Device ID */ + s->regs[0xf0] = 0x3c; + /* Device revision */ + s->regs[0xf1] = 0x01; + /* Function select - all disabled */ + vt8231_superio_cfg_write(s, 0, 0xf2, 1); + vt8231_superio_cfg_write(s, 1, 0x03, 1); + /* Serial port base addr */ + vt8231_superio_cfg_write(s, 0, 0xf4, 1); + vt8231_superio_cfg_write(s, 1, 0xfe, 1); + /* Parallel port base addr */ + vt8231_superio_cfg_write(s, 0, 0xf6, 1); + vt8231_superio_cfg_write(s, 1, 0xde, 1); + /* Floppy ctrl base addr */ + vt8231_superio_cfg_write(s, 0, 0xf7, 1); + vt8231_superio_cfg_write(s, 1, 0xfc, 1); + + vt8231_superio_cfg_write(s, 0, 0, 1); +} + +static void vt8231_superio_init(Object *obj) +{ + VIA_SUPERIO(obj)->io_ops = &vt8231_superio_cfg_ops; +} + +static uint16_t vt8231_superio_serial_iobase(ISASuperIODevice *sio, + uint8_t index) +{ + return 0x2f8; /* FIXME: This should be settable via registers f2-f4 */ +} + +static void vt8231_superio_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ISASuperIOClass *sc = ISA_SUPERIO_CLASS(klass); + + dc->reset = vt8231_superio_reset; + sc->serial.count = 1; + sc->serial.get_iobase = vt8231_superio_serial_iobase; + sc->parallel.count = 1; + sc->ide.count = 0; /* emulated by via-ide */ + sc->floppy.count = 1; +} + +static const TypeInfo vt8231_superio_info = { + .name = TYPE_VT8231_SUPERIO, + .parent = TYPE_VIA_SUPERIO, + .instance_size = sizeof(ViaSuperIOState), + .instance_init = vt8231_superio_init, + .class_size = sizeof(ISASuperIOClass), + .class_init = vt8231_superio_class_init, +}; + + +#define TYPE_VIA_ISA "via-isa" +OBJECT_DECLARE_SIMPLE_TYPE(ViaISAState, VIA_ISA) + +struct ViaISAState { PCIDevice dev; qemu_irq cpu_intr; - SuperIOConfig superio_cfg; + ViaSuperIOState *via_sio; +}; + +static const VMStateDescription vmstate_via = { + .name = "via-isa", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_PCI_DEVICE(dev, ViaISAState), + VMSTATE_END_OF_LIST() + } +}; + +static const TypeInfo via_isa_info = { + .name = TYPE_VIA_ISA, + .parent = TYPE_PCI_DEVICE, + .instance_size = sizeof(ViaISAState), + .abstract = true, + .interfaces = (InterfaceInfo[]) { + { INTERFACE_CONVENTIONAL_PCI_DEVICE }, + { }, + }, }; static void via_isa_request_i8259_irq(void *opaque, int irq, int level) { - VT82C686BISAState *s = opaque; + ViaISAState *s = opaque; qemu_set_irq(s->cpu_intr, level); } +/* TYPE_VT82C686B_ISA */ + static void vt82c686b_write_config(PCIDevice *d, uint32_t addr, uint32_t val, int len) { - VT82C686BISAState *s = VT82C686B_ISA(d); + ViaISAState *s = VIA_ISA(d); trace_via_isa_write(addr, val, len); pci_default_write_config(d, addr, val, len); if (addr == 0x85) { /* BIT(1): enable or disable superio config io ports */ - memory_region_set_enabled(&s->superio_cfg.io, val & BIT(1)); + via_superio_io_enable(s->via_sio, val & BIT(1)); } } -static const VMStateDescription vmstate_via = { - .name = "vt82c686b", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_PCI_DEVICE(dev, VT82C686BISAState), - VMSTATE_END_OF_LIST() - } -}; - static void vt82c686b_isa_reset(DeviceState *dev) { - VT82C686BISAState *s = VT82C686B_ISA(dev); + ViaISAState *s = VIA_ISA(dev); uint8_t *pci_conf = s->dev.config; pci_set_long(pci_conf + PCI_CAPABILITY_LIST, 0x000000c0); @@ -386,18 +605,11 @@ static void vt82c686b_isa_reset(DeviceState *dev) pci_conf[0x5a] = 0x04; /* KBC/RTC Control*/ pci_conf[0x5f] = 0x04; pci_conf[0x77] = 0x10; /* GPIO Control 1/2/3/4 */ - - s->superio_cfg.regs[0xe0] = 0x3c; /* Device ID */ - s->superio_cfg.regs[0xe2] = 0x03; /* Function select */ - s->superio_cfg.regs[0xe3] = 0xfc; /* Floppy ctrl base addr */ - s->superio_cfg.regs[0xe6] = 0xde; /* Parallel port base addr */ - s->superio_cfg.regs[0xe7] = 0xfe; /* Serial port 1 base addr */ - s->superio_cfg.regs[0xe8] = 0xbe; /* Serial port 2 base addr */ } static void vt82c686b_realize(PCIDevice *d, Error **errp) { - VT82C686BISAState *s = VT82C686B_ISA(d); + ViaISAState *s = VIA_ISA(d); DeviceState *dev = DEVICE(d); ISABus *isa_bus; qemu_irq *isa_irq; @@ -410,7 +622,8 @@ static void vt82c686b_realize(PCIDevice *d, Error **errp) isa_bus_irqs(isa_bus, i8259_init(isa_bus, *isa_irq)); i8254_pit_init(isa_bus, 0x40, 0, NULL); i8257_dma_init(isa_bus, 0); - isa_create_simple(isa_bus, TYPE_VT82C686B_SUPERIO); + s->via_sio = VIA_SUPERIO(isa_create_simple(isa_bus, + TYPE_VT82C686B_SUPERIO)); mc146818_rtc_init(isa_bus, 2000, NULL); for (i = 0; i < PCI_CONFIG_HEADER_SIZE; i++) { @@ -418,19 +631,9 @@ static void vt82c686b_realize(PCIDevice *d, Error **errp) d->wmask[i] = 0; } } - - memory_region_init_io(&s->superio_cfg.io, OBJECT(d), &superio_cfg_ops, - &s->superio_cfg, "superio_cfg", 2); - memory_region_set_enabled(&s->superio_cfg.io, false); - /* - * The floppy also uses 0x3f0 and 0x3f1. - * But we do not emulate a floppy, so just set it here. - */ - memory_region_add_subregion(isa_bus->address_space_io, 0x3f0, - &s->superio_cfg.io); } -static void via_class_init(ObjectClass *klass, void *data) +static void vt82c686b_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); @@ -438,47 +641,101 @@ static void via_class_init(ObjectClass *klass, void *data) k->realize = vt82c686b_realize; k->config_write = vt82c686b_write_config; k->vendor_id = PCI_VENDOR_ID_VIA; - k->device_id = PCI_DEVICE_ID_VIA_ISA_BRIDGE; + k->device_id = PCI_DEVICE_ID_VIA_82C686B_ISA; k->class_id = PCI_CLASS_BRIDGE_ISA; k->revision = 0x40; dc->reset = vt82c686b_isa_reset; dc->desc = "ISA bridge"; dc->vmsd = &vmstate_via; - /* - * Reason: part of VIA VT82C686 southbridge, needs to be wired up, - * e.g. by mips_fuloong2e_init() - */ + /* Reason: part of VIA VT82C686 southbridge, needs to be wired up */ dc->user_creatable = false; } -static const TypeInfo via_info = { +static const TypeInfo vt82c686b_isa_info = { .name = TYPE_VT82C686B_ISA, - .parent = TYPE_PCI_DEVICE, - .instance_size = sizeof(VT82C686BISAState), - .class_init = via_class_init, - .interfaces = (InterfaceInfo[]) { - { INTERFACE_CONVENTIONAL_PCI_DEVICE }, - { }, - }, + .parent = TYPE_VIA_ISA, + .instance_size = sizeof(ViaISAState), + .class_init = vt82c686b_class_init, }; +/* TYPE_VT8231_ISA */ -static void vt82c686b_superio_class_init(ObjectClass *klass, void *data) +static void vt8231_write_config(PCIDevice *d, uint32_t addr, + uint32_t val, int len) { - ISASuperIOClass *sc = ISA_SUPERIO_CLASS(klass); + ViaISAState *s = VIA_ISA(d); - sc->serial.count = 2; - sc->parallel.count = 1; - sc->ide.count = 0; - sc->floppy.count = 1; + trace_via_isa_write(addr, val, len); + pci_default_write_config(d, addr, val, len); + if (addr == 0x50) { + /* BIT(2): enable or disable superio config io ports */ + via_superio_io_enable(s->via_sio, val & BIT(2)); + } } -static const TypeInfo via_superio_info = { - .name = TYPE_VT82C686B_SUPERIO, - .parent = TYPE_ISA_SUPERIO, - .instance_size = sizeof(ISASuperIODevice), - .class_size = sizeof(ISASuperIOClass), - .class_init = vt82c686b_superio_class_init, +static void vt8231_isa_reset(DeviceState *dev) +{ + ViaISAState *s = VIA_ISA(dev); + uint8_t *pci_conf = s->dev.config; + + pci_set_long(pci_conf + PCI_CAPABILITY_LIST, 0x000000c0); + pci_set_word(pci_conf + PCI_COMMAND, PCI_COMMAND_IO | PCI_COMMAND_MEMORY | + PCI_COMMAND_MASTER | PCI_COMMAND_SPECIAL); + pci_set_word(pci_conf + PCI_STATUS, PCI_STATUS_DEVSEL_MEDIUM); + + pci_conf[0x58] = 0x40; /* Miscellaneous Control 0 */ + pci_conf[0x67] = 0x08; /* Fast IR Config */ + pci_conf[0x6b] = 0x01; /* Fast IR I/O Base */ +} + +static void vt8231_realize(PCIDevice *d, Error **errp) +{ + ViaISAState *s = VIA_ISA(d); + DeviceState *dev = DEVICE(d); + ISABus *isa_bus; + qemu_irq *isa_irq; + int i; + + qdev_init_gpio_out(dev, &s->cpu_intr, 1); + isa_irq = qemu_allocate_irqs(via_isa_request_i8259_irq, s, 1); + isa_bus = isa_bus_new(dev, get_system_memory(), pci_address_space_io(d), + &error_fatal); + isa_bus_irqs(isa_bus, i8259_init(isa_bus, *isa_irq)); + i8254_pit_init(isa_bus, 0x40, 0, NULL); + i8257_dma_init(isa_bus, 0); + s->via_sio = VIA_SUPERIO(isa_create_simple(isa_bus, TYPE_VT8231_SUPERIO)); + mc146818_rtc_init(isa_bus, 2000, NULL); + + for (i = 0; i < PCI_CONFIG_HEADER_SIZE; i++) { + if (i < PCI_COMMAND || i >= PCI_REVISION_ID) { + d->wmask[i] = 0; + } + } +} + +static void vt8231_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); + + k->realize = vt8231_realize; + k->config_write = vt8231_write_config; + k->vendor_id = PCI_VENDOR_ID_VIA; + k->device_id = PCI_DEVICE_ID_VIA_8231_ISA; + k->class_id = PCI_CLASS_BRIDGE_ISA; + k->revision = 0x10; + dc->reset = vt8231_isa_reset; + dc->desc = "ISA bridge"; + dc->vmsd = &vmstate_via; + /* Reason: part of VIA VT8231 southbridge, needs to be wired up */ + dc->user_creatable = false; +} + +static const TypeInfo vt8231_isa_info = { + .name = TYPE_VT8231_ISA, + .parent = TYPE_VIA_ISA, + .instance_size = sizeof(ViaISAState), + .class_init = vt8231_class_init, }; @@ -487,8 +744,12 @@ static void vt82c686b_register_types(void) type_register_static(&via_pm_info); type_register_static(&vt82c686b_pm_info); type_register_static(&vt8231_pm_info); - type_register_static(&via_info); type_register_static(&via_superio_info); + type_register_static(&vt82c686b_superio_info); + type_register_static(&vt8231_superio_info); + type_register_static(&via_isa_info); + type_register_static(&vt82c686b_isa_info); + type_register_static(&vt8231_isa_info); } type_init(vt82c686b_register_types) diff --git a/hw/lm32/Kconfig b/hw/lm32/Kconfig deleted file mode 100644 index 8ac94205d7..0000000000 --- a/hw/lm32/Kconfig +++ /dev/null @@ -1,18 +0,0 @@ -config LM32_DEVICES - bool - select PTIMER - -config MILKYMIST - bool - # FIXME: disabling it results in compile-time errors - select MILKYMIST_TMU2 if OPENGL && X11 - select PFLASH_CFI01 - select FRAMEBUFFER - select SD - select USB_OHCI - select LM32_DEVICES - -config LM32_EVR - bool - select LM32_DEVICES - select PFLASH_CFI02 diff --git a/hw/lm32/lm32.h b/hw/lm32/lm32.h deleted file mode 100644 index 7b4f6255b9..0000000000 --- a/hw/lm32/lm32.h +++ /dev/null @@ -1,48 +0,0 @@ -#ifndef HW_LM32_H -#define HW_LM32_H - -#include "hw/char/lm32_juart.h" -#include "hw/qdev-properties.h" -#include "qapi/error.h" - -static inline DeviceState *lm32_pic_init(qemu_irq cpu_irq) -{ - DeviceState *dev; - SysBusDevice *d; - - dev = qdev_new("lm32-pic"); - d = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(d, &error_fatal); - sysbus_connect_irq(d, 0, cpu_irq); - - return dev; -} - -static inline DeviceState *lm32_juart_init(Chardev *chr) -{ - DeviceState *dev; - - dev = qdev_new(TYPE_LM32_JUART); - qdev_prop_set_chr(dev, "chardev", chr); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - - return dev; -} - -static inline DeviceState *lm32_uart_create(hwaddr addr, - qemu_irq irq, - Chardev *chr) -{ - DeviceState *dev; - SysBusDevice *s; - - dev = qdev_new("lm32-uart"); - s = SYS_BUS_DEVICE(dev); - qdev_prop_set_chr(dev, "chardev", chr); - sysbus_realize_and_unref(s, &error_fatal); - sysbus_mmio_map(s, 0, addr); - sysbus_connect_irq(s, 0, irq); - return dev; -} - -#endif diff --git a/hw/lm32/lm32_boards.c b/hw/lm32/lm32_boards.c deleted file mode 100644 index b5d97dd53e..0000000000 --- a/hw/lm32/lm32_boards.c +++ /dev/null @@ -1,333 +0,0 @@ -/* - * QEMU models for LatticeMico32 uclinux and evr32 boards. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - */ - -#include "qemu/osdep.h" -#include "qemu/units.h" -#include "qemu/cutils.h" -#include "qemu/error-report.h" -#include "cpu.h" -#include "hw/sysbus.h" -#include "hw/irq.h" -#include "hw/block/flash.h" -#include "hw/boards.h" -#include "hw/loader.h" -#include "elf.h" -#include "lm32_hwsetup.h" -#include "lm32.h" -#include "exec/address-spaces.h" -#include "sysemu/reset.h" -#include "sysemu/sysemu.h" - -typedef struct { - LM32CPU *cpu; - hwaddr bootstrap_pc; - hwaddr flash_base; - hwaddr hwsetup_base; - hwaddr initrd_base; - size_t initrd_size; - hwaddr cmdline_base; -} ResetInfo; - -static void cpu_irq_handler(void *opaque, int irq, int level) -{ - LM32CPU *cpu = opaque; - CPUState *cs = CPU(cpu); - - if (level) { - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } else { - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } -} - -static void main_cpu_reset(void *opaque) -{ - ResetInfo *reset_info = opaque; - CPULM32State *env = &reset_info->cpu->env; - - cpu_reset(CPU(reset_info->cpu)); - - /* init defaults */ - env->pc = (uint32_t)reset_info->bootstrap_pc; - env->regs[R_R1] = (uint32_t)reset_info->hwsetup_base; - env->regs[R_R2] = (uint32_t)reset_info->cmdline_base; - env->regs[R_R3] = (uint32_t)reset_info->initrd_base; - env->regs[R_R4] = (uint32_t)(reset_info->initrd_base + - reset_info->initrd_size); - env->eba = reset_info->flash_base; - env->deba = reset_info->flash_base; -} - -static void lm32_evr_init(MachineState *machine) -{ - MachineClass *mc = MACHINE_GET_CLASS(machine); - const char *kernel_filename = machine->kernel_filename; - LM32CPU *cpu; - CPULM32State *env; - DriveInfo *dinfo; - MemoryRegion *address_space_mem = get_system_memory(); - qemu_irq irq[32]; - ResetInfo *reset_info; - int i; - - if (machine->ram_size != mc->default_ram_size) { - char *sz = size_to_str(mc->default_ram_size); - error_report("Invalid RAM size, should be %s", sz); - g_free(sz); - exit(EXIT_FAILURE); - } - - /* memory map */ - hwaddr flash_base = 0x04000000; - size_t flash_sector_size = 256 * KiB; - size_t flash_size = 32 * MiB; - hwaddr ram_base = 0x08000000; - hwaddr timer0_base = 0x80002000; - hwaddr uart0_base = 0x80006000; - hwaddr timer1_base = 0x8000a000; - int uart0_irq = 0; - int timer0_irq = 1; - int timer1_irq = 3; - - reset_info = g_malloc0(sizeof(ResetInfo)); - - cpu = LM32_CPU(cpu_create(machine->cpu_type)); - - env = &cpu->env; - reset_info->cpu = cpu; - - reset_info->flash_base = flash_base; - - memory_region_add_subregion(address_space_mem, ram_base, machine->ram); - - dinfo = drive_get(IF_PFLASH, 0, 0); - /* Spansion S29NS128P */ - pflash_cfi02_register(flash_base, "lm32_evr.flash", flash_size, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - flash_sector_size, - 1, 2, 0x01, 0x7e, 0x43, 0x00, 0x555, 0x2aa, 1); - - /* create irq lines */ - env->pic_state = lm32_pic_init(qemu_allocate_irq(cpu_irq_handler, cpu, 0)); - for (i = 0; i < 32; i++) { - irq[i] = qdev_get_gpio_in(env->pic_state, i); - } - - lm32_uart_create(uart0_base, irq[uart0_irq], serial_hd(0)); - sysbus_create_simple("lm32-timer", timer0_base, irq[timer0_irq]); - sysbus_create_simple("lm32-timer", timer1_base, irq[timer1_irq]); - - /* make sure juart isn't the first chardev */ - env->juart_state = lm32_juart_init(serial_hd(1)); - - reset_info->bootstrap_pc = flash_base; - - if (kernel_filename) { - uint64_t entry; - int kernel_size; - - kernel_size = load_elf(kernel_filename, NULL, NULL, NULL, - &entry, NULL, NULL, NULL, - 1, EM_LATTICEMICO32, 0, 0); - reset_info->bootstrap_pc = entry; - - if (kernel_size < 0) { - kernel_size = load_image_targphys(kernel_filename, ram_base, - machine->ram_size); - reset_info->bootstrap_pc = ram_base; - } - - if (kernel_size < 0) { - error_report("could not load kernel '%s'", kernel_filename); - exit(1); - } - } - - qemu_register_reset(main_cpu_reset, reset_info); -} - -static void lm32_uclinux_init(MachineState *machine) -{ - MachineClass *mc = MACHINE_GET_CLASS(machine); - const char *kernel_filename = machine->kernel_filename; - const char *kernel_cmdline = machine->kernel_cmdline; - const char *initrd_filename = machine->initrd_filename; - LM32CPU *cpu; - CPULM32State *env; - DriveInfo *dinfo; - MemoryRegion *address_space_mem = get_system_memory(); - qemu_irq irq[32]; - HWSetup *hw; - ResetInfo *reset_info; - int i; - - if (machine->ram_size != mc->default_ram_size) { - char *sz = size_to_str(mc->default_ram_size); - error_report("Invalid RAM size, should be %s", sz); - g_free(sz); - exit(EXIT_FAILURE); - } - - /* memory map */ - hwaddr flash_base = 0x04000000; - size_t flash_sector_size = 256 * KiB; - size_t flash_size = 32 * MiB; - hwaddr ram_base = 0x08000000; - hwaddr uart0_base = 0x80000000; - hwaddr timer0_base = 0x80002000; - hwaddr timer1_base = 0x80010000; - hwaddr timer2_base = 0x80012000; - int uart0_irq = 0; - int timer0_irq = 1; - int timer1_irq = 20; - int timer2_irq = 21; - hwaddr hwsetup_base = 0x0bffe000; - hwaddr cmdline_base = 0x0bfff000; - hwaddr initrd_base = 0x08400000; - size_t initrd_max = 0x01000000; - - reset_info = g_malloc0(sizeof(ResetInfo)); - - cpu = LM32_CPU(cpu_create(machine->cpu_type)); - - env = &cpu->env; - reset_info->cpu = cpu; - - reset_info->flash_base = flash_base; - - memory_region_add_subregion(address_space_mem, ram_base, machine->ram); - - dinfo = drive_get(IF_PFLASH, 0, 0); - /* Spansion S29NS128P */ - pflash_cfi02_register(flash_base, "lm32_uclinux.flash", flash_size, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - flash_sector_size, - 1, 2, 0x01, 0x7e, 0x43, 0x00, 0x555, 0x2aa, 1); - - /* create irq lines */ - env->pic_state = lm32_pic_init(qemu_allocate_irq(cpu_irq_handler, env, 0)); - for (i = 0; i < 32; i++) { - irq[i] = qdev_get_gpio_in(env->pic_state, i); - } - - lm32_uart_create(uart0_base, irq[uart0_irq], serial_hd(0)); - sysbus_create_simple("lm32-timer", timer0_base, irq[timer0_irq]); - sysbus_create_simple("lm32-timer", timer1_base, irq[timer1_irq]); - sysbus_create_simple("lm32-timer", timer2_base, irq[timer2_irq]); - - /* make sure juart isn't the first chardev */ - env->juart_state = lm32_juart_init(serial_hd(1)); - - reset_info->bootstrap_pc = flash_base; - - if (kernel_filename) { - uint64_t entry; - int kernel_size; - - kernel_size = load_elf(kernel_filename, NULL, NULL, NULL, - &entry, NULL, NULL, NULL, - 1, EM_LATTICEMICO32, 0, 0); - reset_info->bootstrap_pc = entry; - - if (kernel_size < 0) { - kernel_size = load_image_targphys(kernel_filename, ram_base, - machine->ram_size); - reset_info->bootstrap_pc = ram_base; - } - - if (kernel_size < 0) { - error_report("could not load kernel '%s'", kernel_filename); - exit(1); - } - } - - /* generate a rom with the hardware description */ - hw = hwsetup_init(); - hwsetup_add_cpu(hw, "LM32", 75000000); - hwsetup_add_flash(hw, "flash", flash_base, flash_size); - hwsetup_add_ddr_sdram(hw, "ddr_sdram", ram_base, machine->ram_size); - hwsetup_add_timer(hw, "timer0", timer0_base, timer0_irq); - hwsetup_add_timer(hw, "timer1_dev_only", timer1_base, timer1_irq); - hwsetup_add_timer(hw, "timer2_dev_only", timer2_base, timer2_irq); - hwsetup_add_uart(hw, "uart", uart0_base, uart0_irq); - hwsetup_add_trailer(hw); - hwsetup_create_rom(hw, hwsetup_base); - hwsetup_free(hw); - - reset_info->hwsetup_base = hwsetup_base; - - if (kernel_cmdline && strlen(kernel_cmdline)) { - pstrcpy_targphys("cmdline", cmdline_base, TARGET_PAGE_SIZE, - kernel_cmdline); - reset_info->cmdline_base = cmdline_base; - } - - if (initrd_filename) { - size_t initrd_size; - initrd_size = load_image_targphys(initrd_filename, initrd_base, - initrd_max); - reset_info->initrd_base = initrd_base; - reset_info->initrd_size = initrd_size; - } - - qemu_register_reset(main_cpu_reset, reset_info); -} - -static void lm32_evr_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "LatticeMico32 EVR32 eval system"; - mc->init = lm32_evr_init; - mc->is_default = true; - mc->default_cpu_type = LM32_CPU_TYPE_NAME("lm32-full"); - mc->default_ram_size = 64 * MiB; - mc->default_ram_id = "lm32_evr.sdram"; -} - -static const TypeInfo lm32_evr_type = { - .name = MACHINE_TYPE_NAME("lm32-evr"), - .parent = TYPE_MACHINE, - .class_init = lm32_evr_class_init, -}; - -static void lm32_uclinux_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "lm32 platform for uClinux and u-boot by Theobroma Systems"; - mc->init = lm32_uclinux_init; - mc->default_cpu_type = LM32_CPU_TYPE_NAME("lm32-full"); - mc->default_ram_size = 64 * MiB; - mc->default_ram_id = "lm32_uclinux.sdram"; -} - -static const TypeInfo lm32_uclinux_type = { - .name = MACHINE_TYPE_NAME("lm32-uclinux"), - .parent = TYPE_MACHINE, - .class_init = lm32_uclinux_class_init, -}; - -static void lm32_machine_init(void) -{ - type_register_static(&lm32_evr_type); - type_register_static(&lm32_uclinux_type); -} - -type_init(lm32_machine_init) diff --git a/hw/lm32/lm32_hwsetup.h b/hw/lm32/lm32_hwsetup.h deleted file mode 100644 index e6cd30ad68..0000000000 --- a/hw/lm32/lm32_hwsetup.h +++ /dev/null @@ -1,179 +0,0 @@ -/* - * LatticeMico32 hwsetup helper functions. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - */ - -/* - * These are helper functions for creating the hardware description blob used - * in the Theobroma's uClinux port. - */ - -#ifndef QEMU_HW_LM32_HWSETUP_H -#define QEMU_HW_LM32_HWSETUP_H - -#include "qemu/cutils.h" -#include "hw/loader.h" - -typedef struct { - void *data; - void *ptr; -} HWSetup; - -enum hwsetup_tag { - HWSETUP_TAG_EOL = 0, - HWSETUP_TAG_CPU = 1, - HWSETUP_TAG_ASRAM = 2, - HWSETUP_TAG_FLASH = 3, - HWSETUP_TAG_SDRAM = 4, - HWSETUP_TAG_OCM = 5, - HWSETUP_TAG_DDR_SDRAM = 6, - HWSETUP_TAG_DDR2_SDRAM = 7, - HWSETUP_TAG_TIMER = 8, - HWSETUP_TAG_UART = 9, - HWSETUP_TAG_GPIO = 10, - HWSETUP_TAG_TRISPEEDMAC = 11, - HWSETUP_TAG_I2CM = 12, - HWSETUP_TAG_LEDS = 13, - HWSETUP_TAG_7SEG = 14, - HWSETUP_TAG_SPI_S = 15, - HWSETUP_TAG_SPI_M = 16, -}; - -static inline HWSetup *hwsetup_init(void) -{ - HWSetup *hw; - - hw = g_malloc(sizeof(HWSetup)); - hw->data = g_malloc0(TARGET_PAGE_SIZE); - hw->ptr = hw->data; - - return hw; -} - -static inline void hwsetup_free(HWSetup *hw) -{ - g_free(hw->data); - g_free(hw); -} - -static inline void hwsetup_create_rom(HWSetup *hw, - hwaddr base) -{ - rom_add_blob("hwsetup", hw->data, TARGET_PAGE_SIZE, - TARGET_PAGE_SIZE, base, NULL, NULL, NULL, NULL, true); -} - -static inline void hwsetup_add_u8(HWSetup *hw, uint8_t u) -{ - stb_p(hw->ptr, u); - hw->ptr += 1; -} - -static inline void hwsetup_add_u32(HWSetup *hw, uint32_t u) -{ - stl_p(hw->ptr, u); - hw->ptr += 4; -} - -static inline void hwsetup_add_tag(HWSetup *hw, enum hwsetup_tag t) -{ - stl_p(hw->ptr, t); - hw->ptr += 4; -} - -static inline void hwsetup_add_str(HWSetup *hw, const char *str) -{ - pstrcpy(hw->ptr, 32, str); - hw->ptr += 32; -} - -static inline void hwsetup_add_trailer(HWSetup *hw) -{ - hwsetup_add_u32(hw, 8); /* size */ - hwsetup_add_tag(hw, HWSETUP_TAG_EOL); -} - -static inline void hwsetup_add_cpu(HWSetup *hw, - const char *name, uint32_t frequency) -{ - hwsetup_add_u32(hw, 44); /* size */ - hwsetup_add_tag(hw, HWSETUP_TAG_CPU); - hwsetup_add_str(hw, name); - hwsetup_add_u32(hw, frequency); -} - -static inline void hwsetup_add_flash(HWSetup *hw, - const char *name, uint32_t base, uint32_t size) -{ - hwsetup_add_u32(hw, 52); /* size */ - hwsetup_add_tag(hw, HWSETUP_TAG_FLASH); - hwsetup_add_str(hw, name); - hwsetup_add_u32(hw, base); - hwsetup_add_u32(hw, size); - hwsetup_add_u8(hw, 8); /* read latency */ - hwsetup_add_u8(hw, 8); /* write latency */ - hwsetup_add_u8(hw, 25); /* address width */ - hwsetup_add_u8(hw, 32); /* data width */ -} - -static inline void hwsetup_add_ddr_sdram(HWSetup *hw, - const char *name, uint32_t base, uint32_t size) -{ - hwsetup_add_u32(hw, 48); /* size */ - hwsetup_add_tag(hw, HWSETUP_TAG_DDR_SDRAM); - hwsetup_add_str(hw, name); - hwsetup_add_u32(hw, base); - hwsetup_add_u32(hw, size); -} - -static inline void hwsetup_add_timer(HWSetup *hw, - const char *name, uint32_t base, uint32_t irq) -{ - hwsetup_add_u32(hw, 56); /* size */ - hwsetup_add_tag(hw, HWSETUP_TAG_TIMER); - hwsetup_add_str(hw, name); - hwsetup_add_u32(hw, base); - hwsetup_add_u8(hw, 1); /* wr_tickcount */ - hwsetup_add_u8(hw, 1); /* rd_tickcount */ - hwsetup_add_u8(hw, 1); /* start_stop_control */ - hwsetup_add_u8(hw, 32); /* counter_width */ - hwsetup_add_u32(hw, 20); /* reload_ticks */ - hwsetup_add_u8(hw, irq); - hwsetup_add_u8(hw, 0); /* padding */ - hwsetup_add_u8(hw, 0); /* padding */ - hwsetup_add_u8(hw, 0); /* padding */ -} - -static inline void hwsetup_add_uart(HWSetup *hw, - const char *name, uint32_t base, uint32_t irq) -{ - hwsetup_add_u32(hw, 56); /* size */ - hwsetup_add_tag(hw, HWSETUP_TAG_UART); - hwsetup_add_str(hw, name); - hwsetup_add_u32(hw, base); - hwsetup_add_u32(hw, 115200); /* baudrate */ - hwsetup_add_u8(hw, 8); /* databits */ - hwsetup_add_u8(hw, 1); /* stopbits */ - hwsetup_add_u8(hw, 1); /* use_interrupt */ - hwsetup_add_u8(hw, 1); /* block_on_transmit */ - hwsetup_add_u8(hw, 1); /* block_on_receive */ - hwsetup_add_u8(hw, 4); /* rx_buffer_size */ - hwsetup_add_u8(hw, 4); /* tx_buffer_size */ - hwsetup_add_u8(hw, irq); -} - -#endif /* QEMU_HW_LM32_HWSETUP_H */ diff --git a/hw/lm32/meson.build b/hw/lm32/meson.build deleted file mode 100644 index 42d6f8db3d..0000000000 --- a/hw/lm32/meson.build +++ /dev/null @@ -1,6 +0,0 @@ -lm32_ss = ss.source_set() -# LM32 boards -lm32_ss.add(when: 'CONFIG_LM32_EVR', if_true: files('lm32_boards.c')) -lm32_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist.c')) - -hw_arch += {'lm32': lm32_ss} diff --git a/hw/lm32/milkymist-hw.h b/hw/lm32/milkymist-hw.h deleted file mode 100644 index 5dca5d52f5..0000000000 --- a/hw/lm32/milkymist-hw.h +++ /dev/null @@ -1,133 +0,0 @@ -#ifndef QEMU_HW_MILKYMIST_HW_H -#define QEMU_HW_MILKYMIST_HW_H - -#include "hw/qdev-core.h" -#include "net/net.h" -#include "qapi/error.h" - -static inline DeviceState *milkymist_uart_create(hwaddr base, - qemu_irq irq, - Chardev *chr) -{ - DeviceState *dev; - - dev = qdev_new("milkymist-uart"); - qdev_prop_set_chr(dev, "chardev", chr); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq); - - return dev; -} - -static inline DeviceState *milkymist_hpdmc_create(hwaddr base) -{ - DeviceState *dev; - - dev = qdev_new("milkymist-hpdmc"); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - - return dev; -} - -static inline DeviceState *milkymist_vgafb_create(hwaddr base, - uint32_t fb_offset, uint32_t fb_mask) -{ - DeviceState *dev; - - dev = qdev_new("milkymist-vgafb"); - qdev_prop_set_uint32(dev, "fb_offset", fb_offset); - qdev_prop_set_uint32(dev, "fb_mask", fb_mask); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - - return dev; -} - -static inline DeviceState *milkymist_sysctl_create(hwaddr base, - qemu_irq gpio_irq, qemu_irq timer0_irq, qemu_irq timer1_irq, - uint32_t freq_hz, uint32_t system_id, uint32_t capabilities, - uint32_t gpio_strappings) -{ - DeviceState *dev; - - dev = qdev_new("milkymist-sysctl"); - qdev_prop_set_uint32(dev, "frequency", freq_hz); - qdev_prop_set_uint32(dev, "systemid", system_id); - qdev_prop_set_uint32(dev, "capabilities", capabilities); - qdev_prop_set_uint32(dev, "gpio_strappings", gpio_strappings); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, gpio_irq); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 1, timer0_irq); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 2, timer1_irq); - - return dev; -} - -static inline DeviceState *milkymist_pfpu_create(hwaddr base, - qemu_irq irq) -{ - DeviceState *dev; - - dev = qdev_new("milkymist-pfpu"); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq); - return dev; -} - -static inline DeviceState *milkymist_ac97_create(hwaddr base, - qemu_irq crrequest_irq, qemu_irq crreply_irq, qemu_irq dmar_irq, - qemu_irq dmaw_irq) -{ - DeviceState *dev; - - dev = qdev_new("milkymist-ac97"); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, crrequest_irq); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 1, crreply_irq); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 2, dmar_irq); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 3, dmaw_irq); - - return dev; -} - -static inline DeviceState *milkymist_minimac2_create(hwaddr base, - hwaddr buffers_base, qemu_irq rx_irq, qemu_irq tx_irq) -{ - DeviceState *dev; - - qemu_check_nic_model(&nd_table[0], "minimac2"); - dev = qdev_new("milkymist-minimac2"); - qdev_set_nic_properties(dev, &nd_table[0]); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 1, buffers_base); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, rx_irq); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 1, tx_irq); - - return dev; -} - -static inline DeviceState *milkymist_softusb_create(hwaddr base, - qemu_irq irq, uint32_t pmem_base, uint32_t pmem_size, - uint32_t dmem_base, uint32_t dmem_size) -{ - DeviceState *dev; - - dev = qdev_new("milkymist-softusb"); - qdev_prop_set_uint32(dev, "pmem_size", pmem_size); - qdev_prop_set_uint32(dev, "dmem_size", dmem_size); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 1, pmem_base); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 2, dmem_base); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq); - - return dev; -} - -#endif /* QEMU_HW_MILKYMIST_HW_H */ diff --git a/hw/lm32/milkymist.c b/hw/lm32/milkymist.c deleted file mode 100644 index 72d1326531..0000000000 --- a/hw/lm32/milkymist.c +++ /dev/null @@ -1,250 +0,0 @@ -/* - * QEMU model for the Milkymist board. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - */ - -#include "qemu/osdep.h" -#include "qemu/units.h" -#include "qemu/error-report.h" -#include "qemu-common.h" -#include "qemu/datadir.h" -#include "cpu.h" -#include "hw/sysbus.h" -#include "hw/irq.h" -#include "hw/block/flash.h" -#include "sysemu/sysemu.h" -#include "sysemu/qtest.h" -#include "sysemu/reset.h" -#include "hw/boards.h" -#include "hw/loader.h" -#include "hw/qdev-properties.h" -#include "elf.h" -#include "milkymist-hw.h" -#include "hw/display/milkymist_tmu2.h" -#include "hw/sd/sd.h" -#include "lm32.h" -#include "exec/address-spaces.h" -#include "qemu/cutils.h" - -#define BIOS_FILENAME "mmone-bios.bin" -#define BIOS_OFFSET 0x00860000 -#define BIOS_SIZE (512 * KiB) -#define KERNEL_LOAD_ADDR 0x40000000 - -typedef struct { - LM32CPU *cpu; - hwaddr bootstrap_pc; - hwaddr flash_base; - hwaddr initrd_base; - size_t initrd_size; - hwaddr cmdline_base; -} ResetInfo; - -static void cpu_irq_handler(void *opaque, int irq, int level) -{ - LM32CPU *cpu = opaque; - CPUState *cs = CPU(cpu); - - if (level) { - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } else { - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } -} - -static void main_cpu_reset(void *opaque) -{ - ResetInfo *reset_info = opaque; - CPULM32State *env = &reset_info->cpu->env; - - cpu_reset(CPU(reset_info->cpu)); - - /* init defaults */ - env->pc = reset_info->bootstrap_pc; - env->regs[R_R1] = reset_info->cmdline_base; - env->regs[R_R2] = reset_info->initrd_base; - env->regs[R_R3] = reset_info->initrd_base + reset_info->initrd_size; - env->eba = reset_info->flash_base; - env->deba = reset_info->flash_base; -} - -static DeviceState *milkymist_memcard_create(hwaddr base) -{ - DeviceState *dev; - DriveInfo *dinfo; - - dev = qdev_new("milkymist-memcard"); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - - dinfo = drive_get_next(IF_SD); - if (dinfo) { - DeviceState *card; - - card = qdev_new(TYPE_SD_CARD); - qdev_prop_set_drive_err(card, "drive", blk_by_legacy_dinfo(dinfo), - &error_fatal); - qdev_realize_and_unref(card, qdev_get_child_bus(dev, "sd-bus"), - &error_fatal); - } - - return dev; -} - -static void -milkymist_init(MachineState *machine) -{ - MachineClass *mc = MACHINE_GET_CLASS(machine); - const char *bios_name = machine->firmware ?: BIOS_FILENAME; - const char *kernel_filename = machine->kernel_filename; - const char *kernel_cmdline = machine->kernel_cmdline; - const char *initrd_filename = machine->initrd_filename; - LM32CPU *cpu; - CPULM32State *env; - int kernel_size; - DriveInfo *dinfo; - MemoryRegion *address_space_mem = get_system_memory(); - qemu_irq irq[32]; - int i; - char *bios_filename; - ResetInfo *reset_info; - - if (machine->ram_size != mc->default_ram_size) { - char *sz = size_to_str(mc->default_ram_size); - error_report("Invalid RAM size, should be %s", sz); - g_free(sz); - exit(EXIT_FAILURE); - } - - /* memory map */ - hwaddr flash_base = 0x00000000; - size_t flash_sector_size = 128 * KiB; - size_t flash_size = 32 * MiB; - hwaddr sdram_base = 0x40000000; - - hwaddr initrd_base = sdram_base + 0x1002000; - hwaddr cmdline_base = sdram_base + 0x1000000; - size_t initrd_max = machine->ram_size - 0x1002000; - - reset_info = g_malloc0(sizeof(ResetInfo)); - - cpu = LM32_CPU(cpu_create(machine->cpu_type)); - - env = &cpu->env; - reset_info->cpu = cpu; - - cpu_lm32_set_phys_msb_ignore(env, 1); - - memory_region_add_subregion(address_space_mem, sdram_base, machine->ram); - - dinfo = drive_get(IF_PFLASH, 0, 0); - /* Numonyx JS28F256J3F105 */ - pflash_cfi01_register(flash_base, "milkymist.flash", flash_size, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - flash_sector_size, 2, 0x00, 0x89, 0x00, 0x1d, 1); - - /* create irq lines */ - env->pic_state = lm32_pic_init(qemu_allocate_irq(cpu_irq_handler, cpu, 0)); - for (i = 0; i < 32; i++) { - irq[i] = qdev_get_gpio_in(env->pic_state, i); - } - - /* load bios rom */ - bios_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name); - - if (bios_filename) { - if (load_image_targphys(bios_filename, BIOS_OFFSET, BIOS_SIZE) < 0) { - error_report("could not load bios '%s'", bios_filename); - exit(1); - } - } - - reset_info->bootstrap_pc = BIOS_OFFSET; - - /* if no kernel is given no valid bios rom is a fatal error */ - if (!kernel_filename && !dinfo && !bios_filename && !qtest_enabled()) { - error_report("could not load Milkymist One bios '%s'", bios_name); - exit(1); - } - g_free(bios_filename); - - milkymist_uart_create(0x60000000, irq[0], serial_hd(0)); - milkymist_sysctl_create(0x60001000, irq[1], irq[2], irq[3], - 80000000, 0x10014d31, 0x0000041f, 0x00000001); - milkymist_hpdmc_create(0x60002000); - milkymist_vgafb_create(0x60003000, 0x40000000, 0x0fffffff); - milkymist_memcard_create(0x60004000); - milkymist_ac97_create(0x60005000, irq[4], irq[5], irq[6], irq[7]); - milkymist_pfpu_create(0x60006000, irq[8]); - if (machine->enable_graphics) { - milkymist_tmu2_create(0x60007000, irq[9]); - } - milkymist_minimac2_create(0x60008000, 0x30000000, irq[10], irq[11]); - milkymist_softusb_create(0x6000f000, irq[15], - 0x20000000, 0x1000, 0x20020000, 0x2000); - - /* make sure juart isn't the first chardev */ - env->juart_state = lm32_juart_init(serial_hd(1)); - - if (kernel_filename) { - uint64_t entry; - - /* Boots a kernel elf binary. */ - kernel_size = load_elf(kernel_filename, NULL, NULL, NULL, - &entry, NULL, NULL, NULL, - 1, EM_LATTICEMICO32, 0, 0); - reset_info->bootstrap_pc = entry; - - if (kernel_size < 0) { - kernel_size = load_image_targphys(kernel_filename, sdram_base, - machine->ram_size); - reset_info->bootstrap_pc = sdram_base; - } - - if (kernel_size < 0) { - error_report("could not load kernel '%s'", kernel_filename); - exit(1); - } - } - - if (kernel_cmdline && strlen(kernel_cmdline)) { - pstrcpy_targphys("cmdline", cmdline_base, TARGET_PAGE_SIZE, - kernel_cmdline); - reset_info->cmdline_base = (uint32_t)cmdline_base; - } - - if (initrd_filename) { - size_t initrd_size; - initrd_size = load_image_targphys(initrd_filename, initrd_base, - initrd_max); - reset_info->initrd_base = (uint32_t)initrd_base; - reset_info->initrd_size = (uint32_t)initrd_size; - } - - qemu_register_reset(main_cpu_reset, reset_info); -} - -static void milkymist_machine_init(MachineClass *mc) -{ - mc->desc = "Milkymist One"; - mc->init = milkymist_init; - mc->default_cpu_type = LM32_CPU_TYPE_NAME("lm32-full"); - mc->default_ram_size = 128 * MiB; - mc->default_ram_id = "milkymist.sdram"; -} - -DEFINE_MACHINE("milkymist", milkymist_machine_init) diff --git a/hw/m68k/an5206.c b/hw/m68k/an5206.c index 673898b0ea..11ae4c9795 100644 --- a/hw/m68k/an5206.c +++ b/hw/m68k/an5206.c @@ -13,7 +13,6 @@ #include "hw/boards.h" #include "hw/loader.h" #include "elf.h" -#include "exec/address-spaces.h" #include "qemu/error-report.h" #include "sysemu/qtest.h" diff --git a/hw/m68k/mcf5208.c b/hw/m68k/mcf5208.c index 7a03c71059..93812ee206 100644 --- a/hw/m68k/mcf5208.c +++ b/hw/m68k/mcf5208.c @@ -26,7 +26,6 @@ #include "hw/loader.h" #include "hw/sysbus.h" #include "elf.h" -#include "exec/address-spaces.h" #define SYS_FREQ 166666666 diff --git a/hw/m68k/mcf_intc.c b/hw/m68k/mcf_intc.c index cf02f57a71..4cd30188c0 100644 --- a/hw/m68k/mcf_intc.c +++ b/hw/m68k/mcf_intc.c @@ -11,7 +11,6 @@ #include "qemu/module.h" #include "qemu/log.h" #include "cpu.h" -#include "hw/hw.h" #include "hw/irq.h" #include "hw/sysbus.h" #include "hw/m68k/mcf.h" diff --git a/hw/m68k/next-cube.c b/hw/m68k/next-cube.c index 92b45d760f..e0d4a94f9d 100644 --- a/hw/m68k/next-cube.c +++ b/hw/m68k/next-cube.c @@ -10,9 +10,7 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "exec/hwaddr.h" -#include "exec/address-spaces.h" #include "sysemu/sysemu.h" #include "sysemu/qtest.h" #include "hw/irq.h" @@ -986,8 +984,8 @@ static void next_cube_init(MachineState *machine) sysbus_mmio_map(SYS_BUS_DEVICE(pcdev), 1, 0x02100000); /* BMAP memory */ - memory_region_init_ram_shared_nomigrate(bmapm1, NULL, "next.bmapmem", 64, - true, &error_fatal); + memory_region_init_ram_flags_nomigrate(bmapm1, NULL, "next.bmapmem", 64, + RAM_SHARED, &error_fatal); memory_region_add_subregion(sysmem, 0x020c0000, bmapm1); /* The Rev_2.5_v66.bin firmware accesses it at 0x820c0020, too */ memory_region_init_alias(bmapm2, NULL, "next.bmapmem2", bmapm1, 0x0, 64); diff --git a/hw/m68k/next-kbd.c b/hw/m68k/next-kbd.c index c11b5281f1..0544160e91 100644 --- a/hw/m68k/next-kbd.c +++ b/hw/m68k/next-kbd.c @@ -29,12 +29,9 @@ #include "qemu/osdep.h" #include "qemu/log.h" -#include "exec/address-spaces.h" -#include "hw/hw.h" #include "hw/sysbus.h" #include "hw/m68k/next-cube.h" #include "ui/console.h" -#include "sysemu/sysemu.h" #include "migration/vmstate.h" #include "qom/object.h" diff --git a/hw/m68k/q800.c b/hw/m68k/q800.c index 4d2e866eec..ac0a13060b 100644 --- a/hw/m68k/q800.c +++ b/hw/m68k/q800.c @@ -26,14 +26,11 @@ #include "qemu/datadir.h" #include "sysemu/sysemu.h" #include "cpu.h" -#include "hw/hw.h" #include "hw/boards.h" -#include "hw/irq.h" #include "hw/or-irq.h" #include "elf.h" #include "hw/loader.h" #include "ui/console.h" -#include "exec/address-spaces.h" #include "hw/char/escc.h" #include "hw/sysbus.h" #include "hw/scsi/esp.h" @@ -73,6 +70,8 @@ #define NUBUS_SUPER_SLOT_BASE 0x60000000 #define NUBUS_SLOT_BASE 0xf0000000 +#define SONIC_PROM_SIZE 0x1000 + /* * the video base, whereas it a Nubus address, * is needed by the kernel to have early display and @@ -214,8 +213,10 @@ static void q800_init(MachineState *machine) int32_t initrd_size; MemoryRegion *rom; MemoryRegion *io; + MemoryRegion *dp8393x_prom = g_new(MemoryRegion, 1); + uint8_t *prom; const int io_slice_nb = (IO_SIZE / IO_SLICE) - 1; - int i; + int i, checksum; ram_addr_t ram_size = machine->ram_size; const char *kernel_filename = machine->kernel_filename; const char *initrd_filename = machine->initrd_filename; @@ -322,9 +323,22 @@ static void q800_init(MachineState *machine) sysbus = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(sysbus, &error_fatal); sysbus_mmio_map(sysbus, 0, SONIC_BASE); - sysbus_mmio_map(sysbus, 1, SONIC_PROM_BASE); sysbus_connect_irq(sysbus, 0, qdev_get_gpio_in(glue, 2)); + memory_region_init_rom(dp8393x_prom, NULL, "dp8393x-q800.prom", + SONIC_PROM_SIZE, &error_fatal); + memory_region_add_subregion(get_system_memory(), SONIC_PROM_BASE, + dp8393x_prom); + + /* Add MAC address with valid checksum to PROM */ + prom = memory_region_get_ram_ptr(dp8393x_prom); + checksum = 0; + for (i = 0; i < 6; i++) { + prom[i] = revbit8(nd_table[0].macaddr.a[i]); + checksum ^= prom[i]; + } + prom[7] = 0xff - checksum; + /* SCC */ dev = qdev_new(TYPE_ESCC); diff --git a/hw/m68k/virt.c b/hw/m68k/virt.c index e9a5d4c69b..4e8bce5aa6 100644 --- a/hw/m68k/virt.c +++ b/hw/m68k/virt.c @@ -12,14 +12,11 @@ #include "qemu-common.h" #include "sysemu/sysemu.h" #include "cpu.h" -#include "hw/hw.h" #include "hw/boards.h" -#include "hw/irq.h" #include "hw/qdev-properties.h" #include "elf.h" #include "hw/loader.h" #include "ui/console.h" -#include "exec/address-spaces.h" #include "hw/sysbus.h" #include "standard-headers/asm-m68k/bootinfo.h" #include "standard-headers/asm-m68k/bootinfo-virt.h" diff --git a/hw/mem/Kconfig b/hw/mem/Kconfig index a0ef2cf648..8b19fdc49f 100644 --- a/hw/mem/Kconfig +++ b/hw/mem/Kconfig @@ -7,6 +7,4 @@ config MEM_DEVICE config NVDIMM bool - default y - depends on (PC || PSERIES || ARM_VIRT) select MEM_DEVICE diff --git a/hw/mem/meson.build b/hw/mem/meson.build index ef79e04678..3c8fdef9f9 100644 --- a/hw/mem/meson.build +++ b/hw/mem/meson.build @@ -1,8 +1,9 @@ mem_ss = ss.source_set() mem_ss.add(files('memory-device.c')) -mem_ss.add(when: 'CONFIG_FUZZ', if_true: files('sparse-mem.c')) mem_ss.add(when: 'CONFIG_DIMM', if_true: files('pc-dimm.c')) mem_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_mc.c')) mem_ss.add(when: 'CONFIG_NVDIMM', if_true: files('nvdimm.c')) softmmu_ss.add_all(when: 'CONFIG_MEM_DEVICE', if_true: mem_ss) + +softmmu_ss.add(when: 'CONFIG_FUZZ', if_true: files('sparse-mem.c')) diff --git a/hw/mem/pc-dimm.c b/hw/mem/pc-dimm.c index 12b655eda8..a3a2560301 100644 --- a/hw/mem/pc-dimm.c +++ b/hw/mem/pc-dimm.c @@ -34,6 +34,16 @@ static int pc_dimm_get_free_slot(const int *hint, int max_slots, Error **errp); +static MemoryRegion *pc_dimm_get_memory_region(PCDIMMDevice *dimm, Error **errp) +{ + if (!dimm->hostmem) { + error_setg(errp, "'" PC_DIMM_MEMDEV_PROP "' property must be set"); + return NULL; + } + + return host_memory_backend_get_memory(dimm->hostmem); +} + void pc_dimm_pre_plug(PCDIMMDevice *dimm, MachineState *machine, const uint64_t *legacy_align, Error **errp) { @@ -66,9 +76,8 @@ void pc_dimm_pre_plug(PCDIMMDevice *dimm, MachineState *machine, void pc_dimm_plug(PCDIMMDevice *dimm, MachineState *machine) { - PCDIMMDeviceClass *ddc = PC_DIMM_GET_CLASS(dimm); - MemoryRegion *vmstate_mr = ddc->get_vmstate_memory_region(dimm, - &error_abort); + MemoryRegion *vmstate_mr = pc_dimm_get_memory_region(dimm, + &error_abort); memory_device_plug(MEMORY_DEVICE(dimm), machine); vmstate_register_ram(vmstate_mr, DEVICE(dimm)); @@ -76,9 +85,8 @@ void pc_dimm_plug(PCDIMMDevice *dimm, MachineState *machine) void pc_dimm_unplug(PCDIMMDevice *dimm, MachineState *machine) { - PCDIMMDeviceClass *ddc = PC_DIMM_GET_CLASS(dimm); - MemoryRegion *vmstate_mr = ddc->get_vmstate_memory_region(dimm, - &error_abort); + MemoryRegion *vmstate_mr = pc_dimm_get_memory_region(dimm, + &error_abort); memory_device_unplug(MEMORY_DEVICE(dimm), machine); vmstate_unregister_ram(vmstate_mr, DEVICE(dimm)); @@ -205,16 +213,6 @@ static void pc_dimm_unrealize(DeviceState *dev) host_memory_backend_set_mapped(dimm->hostmem, false); } -static MemoryRegion *pc_dimm_get_memory_region(PCDIMMDevice *dimm, Error **errp) -{ - if (!dimm->hostmem) { - error_setg(errp, "'" PC_DIMM_MEMDEV_PROP "' property must be set"); - return NULL; - } - - return host_memory_backend_get_memory(dimm->hostmem); -} - static uint64_t pc_dimm_md_get_addr(const MemoryDeviceState *md) { return object_property_get_uint(OBJECT(md), PC_DIMM_ADDR_PROP, @@ -266,7 +264,6 @@ static void pc_dimm_md_fill_device_info(const MemoryDeviceState *md, static void pc_dimm_class_init(ObjectClass *oc, void *data) { DeviceClass *dc = DEVICE_CLASS(oc); - PCDIMMDeviceClass *ddc = PC_DIMM_CLASS(oc); MemoryDeviceClass *mdc = MEMORY_DEVICE_CLASS(oc); dc->realize = pc_dimm_realize; @@ -274,8 +271,6 @@ static void pc_dimm_class_init(ObjectClass *oc, void *data) device_class_set_props(dc, pc_dimm_properties); dc->desc = "DIMM memory module"; - ddc->get_vmstate_memory_region = pc_dimm_get_memory_region; - mdc->get_addr = pc_dimm_md_get_addr; mdc->set_addr = pc_dimm_md_set_addr; /* for a dimm plugged_size == region_size */ diff --git a/hw/mem/sparse-mem.c b/hw/mem/sparse-mem.c index a13ac74dd9..e6640eb8e7 100644 --- a/hw/mem/sparse-mem.c +++ b/hw/mem/sparse-mem.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" -#include "exec/address-spaces.h" #include "hw/qdev-properties.h" #include "hw/sysbus.h" #include "qapi/error.h" diff --git a/hw/mem/trace-events b/hw/mem/trace-events index 9f6b52acd7..8b6b02b5bf 100644 --- a/hw/mem/trace-events +++ b/hw/mem/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pc-dimm.c mhp_pc_dimm_assigned_slot(int slot) "%d" diff --git a/hw/meson.build b/hw/meson.build index 1aa7ffbf9a..00b49848c7 100644 --- a/hw/meson.build +++ b/hw/meson.build @@ -21,6 +21,7 @@ subdir('mem') subdir('misc') subdir('net') subdir('nubus') +subdir('nvme') subdir('nvram') subdir('pci') subdir('pci-bridge') @@ -30,6 +31,7 @@ subdir('rdma') subdir('rtc') subdir('scsi') subdir('sd') +subdir('sensor') subdir('smbios') subdir('ssi') subdir('timer') @@ -48,11 +50,9 @@ subdir('avr') subdir('cris') subdir('hppa') subdir('i386') -subdir('lm32') subdir('m68k') subdir('microblaze') subdir('mips') -subdir('moxie') subdir('nios2') subdir('openrisc') subdir('ppc') @@ -64,5 +64,4 @@ subdir('sh4') subdir('sparc') subdir('sparc64') subdir('tricore') -subdir('unicore32') subdir('xtensa') diff --git a/hw/microblaze/boot.c b/hw/microblaze/boot.c index caaba1aa4c..8821d009f1 100644 --- a/hw/microblaze/boot.c +++ b/hw/microblaze/boot.c @@ -33,7 +33,6 @@ #include "qemu/error-report.h" #include "sysemu/device_tree.h" #include "sysemu/reset.h" -#include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/loader.h" #include "elf.h" diff --git a/hw/mips/Kconfig b/hw/mips/Kconfig index aadd436bf4..b4c5549ce8 100644 --- a/hw/mips/Kconfig +++ b/hw/mips/Kconfig @@ -20,7 +20,7 @@ config JAZZ select G364FB select DP8393X select ESP - select FDC + select FDC_SYSBUS select MC146818RTC select PCKBD select SERIAL @@ -47,9 +47,15 @@ config LOONGSON3V config MIPS_CPS bool select PTIMER + select MIPS_ITU config MIPS_BOSTON bool + select FITLOADER + select MIPS_CPS + select PCI_EXPRESS_XILINX + select AHCI_ICH9 + select SERIAL config FW_CFG_MIPS bool diff --git a/hw/mips/boston.c b/hw/mips/boston.c index ac2e93a05a..20b06865b2 100644 --- a/hw/mips/boston.c +++ b/hw/mips/boston.c @@ -20,7 +20,6 @@ #include "qemu/osdep.h" #include "qemu/units.h" -#include "exec/address-spaces.h" #include "hw/boards.h" #include "hw/char/serial.h" #include "hw/ide/pci.h" diff --git a/hw/mips/fuloong2e.c b/hw/mips/fuloong2e.c index 4f61f2c873..c1b8066a13 100644 --- a/hw/mips/fuloong2e.c +++ b/hw/mips/fuloong2e.c @@ -33,13 +33,11 @@ #include "hw/mips/bootloader.h" #include "hw/mips/cpudevs.h" #include "hw/pci/pci.h" -#include "qemu/log.h" #include "hw/loader.h" #include "hw/ide/pci.h" #include "hw/qdev-properties.h" #include "elf.h" #include "hw/isa/vt82c686.h" -#include "exec/address-spaces.h" #include "sysemu/qtest.h" #include "sysemu/reset.h" #include "sysemu/sysemu.h" diff --git a/hw/mips/gt64xxx_pci.c b/hw/mips/gt64xxx_pci.c index 43349d6837..c7480bd019 100644 --- a/hw/mips/gt64xxx_pci.c +++ b/hw/mips/gt64xxx_pci.c @@ -33,7 +33,6 @@ #include "migration/vmstate.h" #include "hw/intc/i8259.h" #include "hw/irq.h" -#include "exec/address-spaces.h" #include "trace.h" #include "qom/object.h" diff --git a/hw/mips/jazz.c b/hw/mips/jazz.c index 1a0888a0fd..d6183e1882 100644 --- a/hw/mips/jazz.c +++ b/hw/mips/jazz.c @@ -47,7 +47,6 @@ #include "hw/audio/pcspk.h" #include "hw/input/i8042.h" #include "hw/sysbus.h" -#include "exec/address-spaces.h" #include "sysemu/qtest.h" #include "sysemu/reset.h" #include "qapi/error.h" @@ -120,39 +119,17 @@ static const MemoryRegionOps dma_dummy_ops = { #define MAGNUM_BIOS_SIZE \ (BIOS_SIZE < MAGNUM_BIOS_SIZE_MAX ? BIOS_SIZE : MAGNUM_BIOS_SIZE_MAX) -#if defined(CONFIG_TCG) && !defined(CONFIG_USER_ONLY) -static void (*real_do_transaction_failed)(CPUState *cpu, hwaddr physaddr, - vaddr addr, unsigned size, - MMUAccessType access_type, - int mmu_idx, MemTxAttrs attrs, - MemTxResult response, - uintptr_t retaddr); - -static void mips_jazz_do_transaction_failed(CPUState *cs, hwaddr physaddr, - vaddr addr, unsigned size, - MMUAccessType access_type, - int mmu_idx, MemTxAttrs attrs, - MemTxResult response, - uintptr_t retaddr) -{ - if (access_type != MMU_INST_FETCH) { - /* ignore invalid access (ie do not raise exception) */ - return; - } - (*real_do_transaction_failed)(cs, physaddr, addr, size, access_type, - mmu_idx, attrs, response, retaddr); -} -#endif /* CONFIG_TCG && !CONFIG_USER_ONLY */ +#define SONIC_PROM_SIZE 0x1000 static void mips_jazz_init(MachineState *machine, enum jazz_model_e jazz_model) { MemoryRegion *address_space = get_system_memory(); char *filename; - int bios_size, n; + int bios_size, n, big_endian; Clock *cpuclk; MIPSCPU *cpu; - CPUClass *cc; + MIPSCPUClass *mcc; CPUMIPSState *env; qemu_irq *i8259; rc4030_dma *dmas; @@ -162,6 +139,7 @@ static void mips_jazz_init(MachineState *machine, MemoryRegion *rtc = g_new(MemoryRegion, 1); MemoryRegion *i8042 = g_new(MemoryRegion, 1); MemoryRegion *dma_dummy = g_new(MemoryRegion, 1); + MemoryRegion *dp8393x_prom = g_new(MemoryRegion, 1); NICInfo *nd; DeviceState *dev, *rc4030; SysBusDevice *sysbus; @@ -180,6 +158,12 @@ static void mips_jazz_init(MachineState *machine, [JAZZ_PICA61] = {33333333, 4}, }; +#ifdef TARGET_WORDS_BIGENDIAN + big_endian = 1; +#else + big_endian = 0; +#endif + if (machine->ram_size > 256 * MiB) { error_report("RAM size more than 256Mb is not supported"); exit(EXIT_FAILURE); @@ -199,8 +183,6 @@ static void mips_jazz_init(MachineState *machine, * However, we can't simply add a global memory region to catch * everything, as this would make all accesses including instruction * accesses be ignored and not raise exceptions. - * So instead we hijack the do_transaction_failed method on the CPU, and - * do not raise exceptions for data access. * * NOTE: this behaviour of raising exceptions for bad instruction * fetches but not bad data accesses was added in commit 54e755588cf1e9 @@ -210,11 +192,8 @@ static void mips_jazz_init(MachineState *machine, * we could replace this hijacking of CPU methods with a simple global * memory region that catches all memory accesses, as we do on Malta. */ - cc = CPU_GET_CLASS(cpu); -#if defined(CONFIG_TCG) && !defined(CONFIG_USER_ONLY) - real_do_transaction_failed = cc->tcg_ops->do_transaction_failed; - cc->tcg_ops->do_transaction_failed = mips_jazz_do_transaction_failed; -#endif /* CONFIG_TCG && !CONFIG_USER_ONLY */ + mcc = MIPS_CPU_GET_CLASS(cpu); + mcc->no_data_aborts = true; /* allocate RAM */ memory_region_add_subregion(address_space, 0, machine->ram); @@ -258,6 +237,10 @@ static void mips_jazz_init(MachineState *machine, NULL, "dummy_dma", 0x1000); memory_region_add_subregion(address_space, 0x8000d000, dma_dummy); + memory_region_init_rom(dp8393x_prom, NULL, "dp8393x-jazz.prom", + SONIC_PROM_SIZE, &error_fatal); + memory_region_add_subregion(address_space, 0x8000b000, dp8393x_prom); + /* ISA bus: IO space at 0x90000000, mem space at 0x91000000 */ memory_region_init(isa_io, NULL, "isa-io", 0x00010000); memory_region_init(isa_mem, NULL, "isa-mem", 0x01000000); @@ -305,18 +288,33 @@ static void mips_jazz_init(MachineState *machine, nd->model = g_strdup("dp83932"); } if (strcmp(nd->model, "dp83932") == 0) { + int checksum, i; + uint8_t *prom; + qemu_check_nic_model(nd, "dp83932"); dev = qdev_new("dp8393x"); qdev_set_nic_properties(dev, nd); qdev_prop_set_uint8(dev, "it_shift", 2); + qdev_prop_set_bit(dev, "big_endian", big_endian > 0); object_property_set_link(OBJECT(dev), "dma_mr", OBJECT(rc4030_dma_mr), &error_abort); sysbus = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(sysbus, &error_fatal); sysbus_mmio_map(sysbus, 0, 0x80001000); - sysbus_mmio_map(sysbus, 1, 0x8000b000); sysbus_connect_irq(sysbus, 0, qdev_get_gpio_in(rc4030, 4)); + + /* Add MAC address with valid checksum to PROM */ + prom = memory_region_get_ram_ptr(dp8393x_prom); + checksum = 0; + for (i = 0; i < 6; i++) { + prom[i] = nd->macaddr.a[i]; + checksum += prom[i]; + if (checksum > 0xff) { + checksum = (checksum + 1) & 0xff; + } + } + prom[7] = 0xff - checksum; break; } else if (is_help_option(nd->model)) { error_report("Supported NICs: dp83932"); @@ -363,16 +361,12 @@ static void mips_jazz_init(MachineState *machine, memory_region_add_subregion(address_space, 0x80005000, i8042); /* Serial ports */ - if (serial_hd(0)) { - serial_mm_init(address_space, 0x80006000, 0, - qdev_get_gpio_in(rc4030, 8), 8000000 / 16, - serial_hd(0), DEVICE_NATIVE_ENDIAN); - } - if (serial_hd(1)) { - serial_mm_init(address_space, 0x80007000, 0, - qdev_get_gpio_in(rc4030, 9), 8000000 / 16, - serial_hd(1), DEVICE_NATIVE_ENDIAN); - } + serial_mm_init(address_space, 0x80006000, 0, + qdev_get_gpio_in(rc4030, 8), 8000000 / 16, + serial_hd(0), DEVICE_NATIVE_ENDIAN); + serial_mm_init(address_space, 0x80007000, 0, + qdev_get_gpio_in(rc4030, 9), 8000000 / 16, + serial_hd(1), DEVICE_NATIVE_ENDIAN); /* Parallel port */ if (parallel_hds[0]) diff --git a/hw/mips/loongson3_virt.c b/hw/mips/loongson3_virt.c index b15071defc..ae192db0c8 100644 --- a/hw/mips/loongson3_virt.c +++ b/hw/mips/loongson3_virt.c @@ -29,10 +29,8 @@ #include "qemu/cutils.h" #include "qemu/datadir.h" #include "qapi/error.h" -#include "cpu.h" #include "elf.h" #include "kvm_mips.h" -#include "hw/boards.h" #include "hw/char/serial.h" #include "hw/intc/loongson_liointc.h" #include "hw/mips/mips.h" @@ -49,12 +47,10 @@ #include "hw/pci-host/gpex.h" #include "hw/usb.h" #include "net/net.h" -#include "exec/address-spaces.h" #include "sysemu/kvm.h" #include "sysemu/qtest.h" #include "sysemu/reset.h" #include "sysemu/runstate.h" -#include "qemu/log.h" #include "qemu/error-report.h" #define PM_CNTL_MODE 0x10 diff --git a/hw/mips/malta.c b/hw/mips/malta.c index 26e7b1bd9f..7dcf175d72 100644 --- a/hw/mips/malta.c +++ b/hw/mips/malta.c @@ -27,7 +27,6 @@ #include "qemu/bitops.h" #include "qemu-common.h" #include "qemu/datadir.h" -#include "cpu.h" #include "hw/clock.h" #include "hw/southbridge/piix.h" #include "hw/isa/superio.h" @@ -39,7 +38,6 @@ #include "hw/mips/mips.h" #include "hw/mips/cpudevs.h" #include "hw/pci/pci.h" -#include "sysemu/sysemu.h" #include "sysemu/arch_init.h" #include "qemu/log.h" #include "hw/mips/bios.h" @@ -47,7 +45,6 @@ #include "hw/irq.h" #include "hw/loader.h" #include "elf.h" -#include "exec/address-spaces.h" #include "qom/object.h" #include "hw/sysbus.h" /* SysBusDevice */ #include "qemu/host-utils.h" diff --git a/hw/mips/meson.build b/hw/mips/meson.build index 1195716dc7..dd0101ad4d 100644 --- a/hw/mips/meson.build +++ b/hw/mips/meson.build @@ -1,12 +1,15 @@ mips_ss = ss.source_set() mips_ss.add(files('bootloader.c', 'mips_int.c')) mips_ss.add(when: 'CONFIG_FW_CFG_MIPS', if_true: files('fw_cfg.c')) -mips_ss.add(when: 'CONFIG_FULOONG', if_true: files('fuloong2e.c')) mips_ss.add(when: 'CONFIG_LOONGSON3V', if_true: files('loongson3_bootp.c', 'loongson3_virt.c')) -mips_ss.add(when: 'CONFIG_JAZZ', if_true: files('jazz.c')) mips_ss.add(when: 'CONFIG_MALTA', if_true: files('gt64xxx_pci.c', 'malta.c')) -mips_ss.add(when: 'CONFIG_MIPSSIM', if_true: files('mipssim.c')) -mips_ss.add(when: 'CONFIG_MIPS_BOSTON', if_true: [files('boston.c'), fdt]) mips_ss.add(when: 'CONFIG_MIPS_CPS', if_true: files('cps.c')) +if 'CONFIG_TCG' in config_all +mips_ss.add(when: 'CONFIG_JAZZ', if_true: files('jazz.c')) +mips_ss.add(when: 'CONFIG_MIPSSIM', if_true: files('mipssim.c')) +mips_ss.add(when: 'CONFIG_FULOONG', if_true: files('fuloong2e.c')) +mips_ss.add(when: 'CONFIG_MIPS_BOSTON', if_true: [files('boston.c'), fdt]) +endif + hw_arch += {'mips': mips_ss} diff --git a/hw/mips/mips_int.c b/hw/mips/mips_int.c index 0f9c6f07c1..2db5e10fe0 100644 --- a/hw/mips/mips_int.c +++ b/hw/mips/mips_int.c @@ -24,7 +24,6 @@ #include "qemu/main-loop.h" #include "hw/irq.h" #include "hw/mips/cpudevs.h" -#include "cpu.h" #include "sysemu/kvm.h" #include "kvm_mips.h" diff --git a/hw/mips/mipssim.c b/hw/mips/mipssim.c index f5d0da05aa..2325e7e05a 100644 --- a/hw/mips/mipssim.c +++ b/hw/mips/mipssim.c @@ -29,7 +29,6 @@ #include "qapi/error.h" #include "qemu-common.h" #include "qemu/datadir.h" -#include "cpu.h" #include "hw/clock.h" #include "hw/mips/mips.h" #include "hw/mips/cpudevs.h" @@ -43,7 +42,6 @@ #include "elf.h" #include "hw/sysbus.h" #include "hw/qdev-properties.h" -#include "exec/address-spaces.h" #include "qemu/error-report.h" #include "sysemu/qtest.h" #include "sysemu/reset.h" diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index c71ed25820..507058d8bf 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -11,21 +11,6 @@ config ARMSSE_MHU config ARMSSE_CPU_PWRCTRL bool -config MAX111X - bool - -config TMP105 - bool - depends on I2C - -config TMP421 - bool - depends on I2C - -config EMC141X - bool - depends on I2C - config ISA_DEBUG bool depends on ISA_BUS diff --git a/hw/misc/aspeed_hace.c b/hw/misc/aspeed_hace.c new file mode 100644 index 0000000000..10f00e65f4 --- /dev/null +++ b/hw/misc/aspeed_hace.c @@ -0,0 +1,389 @@ +/* + * ASPEED Hash and Crypto Engine + * + * Copyright (C) 2021 IBM Corp. + * + * Joel Stanley + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/error-report.h" +#include "hw/misc/aspeed_hace.h" +#include "qapi/error.h" +#include "migration/vmstate.h" +#include "crypto/hash.h" +#include "hw/qdev-properties.h" +#include "hw/irq.h" + +#define R_CRYPT_CMD (0x10 / 4) + +#define R_STATUS (0x1c / 4) +#define HASH_IRQ BIT(9) +#define CRYPT_IRQ BIT(12) +#define TAG_IRQ BIT(15) + +#define R_HASH_SRC (0x20 / 4) +#define R_HASH_DEST (0x24 / 4) +#define R_HASH_SRC_LEN (0x2c / 4) + +#define R_HASH_CMD (0x30 / 4) +/* Hash algorithm selection */ +#define HASH_ALGO_MASK (BIT(4) | BIT(5) | BIT(6)) +#define HASH_ALGO_MD5 0 +#define HASH_ALGO_SHA1 BIT(5) +#define HASH_ALGO_SHA224 BIT(6) +#define HASH_ALGO_SHA256 (BIT(4) | BIT(6)) +#define HASH_ALGO_SHA512_SERIES (BIT(5) | BIT(6)) +/* SHA512 algorithm selection */ +#define SHA512_HASH_ALGO_MASK (BIT(10) | BIT(11) | BIT(12)) +#define HASH_ALGO_SHA512_SHA512 0 +#define HASH_ALGO_SHA512_SHA384 BIT(10) +#define HASH_ALGO_SHA512_SHA256 BIT(11) +#define HASH_ALGO_SHA512_SHA224 (BIT(10) | BIT(11)) +/* HMAC modes */ +#define HASH_HMAC_MASK (BIT(7) | BIT(8)) +#define HASH_DIGEST 0 +#define HASH_DIGEST_HMAC BIT(7) +#define HASH_DIGEST_ACCUM BIT(8) +#define HASH_HMAC_KEY (BIT(7) | BIT(8)) +/* Cascaded operation modes */ +#define HASH_ONLY 0 +#define HASH_ONLY2 BIT(0) +#define HASH_CRYPT_THEN_HASH BIT(1) +#define HASH_HASH_THEN_CRYPT (BIT(0) | BIT(1)) +/* Other cmd bits */ +#define HASH_IRQ_EN BIT(9) +#define HASH_SG_EN BIT(18) +/* Scatter-gather data list */ +#define SG_LIST_LEN_SIZE 4 +#define SG_LIST_LEN_MASK 0x0FFFFFFF +#define SG_LIST_LEN_LAST BIT(31) +#define SG_LIST_ADDR_SIZE 4 +#define SG_LIST_ADDR_MASK 0x7FFFFFFF +#define SG_LIST_ENTRY_SIZE (SG_LIST_LEN_SIZE + SG_LIST_ADDR_SIZE) +#define ASPEED_HACE_MAX_SG 256 /* max number of entries */ + +static const struct { + uint32_t mask; + QCryptoHashAlgorithm algo; +} hash_algo_map[] = { + { HASH_ALGO_MD5, QCRYPTO_HASH_ALG_MD5 }, + { HASH_ALGO_SHA1, QCRYPTO_HASH_ALG_SHA1 }, + { HASH_ALGO_SHA224, QCRYPTO_HASH_ALG_SHA224 }, + { HASH_ALGO_SHA256, QCRYPTO_HASH_ALG_SHA256 }, + { HASH_ALGO_SHA512_SERIES | HASH_ALGO_SHA512_SHA512, QCRYPTO_HASH_ALG_SHA512 }, + { HASH_ALGO_SHA512_SERIES | HASH_ALGO_SHA512_SHA384, QCRYPTO_HASH_ALG_SHA384 }, + { HASH_ALGO_SHA512_SERIES | HASH_ALGO_SHA512_SHA256, QCRYPTO_HASH_ALG_SHA256 }, +}; + +static int hash_algo_lookup(uint32_t reg) +{ + int i; + + reg &= HASH_ALGO_MASK | SHA512_HASH_ALGO_MASK; + + for (i = 0; i < ARRAY_SIZE(hash_algo_map); i++) { + if (reg == hash_algo_map[i].mask) { + return hash_algo_map[i].algo; + } + } + + return -1; +} + +static void do_hash_operation(AspeedHACEState *s, int algo, bool sg_mode) +{ + struct iovec iov[ASPEED_HACE_MAX_SG]; + g_autofree uint8_t *digest_buf; + size_t digest_len = 0; + int i; + + if (sg_mode) { + uint32_t len = 0; + + for (i = 0; !(len & SG_LIST_LEN_LAST); i++) { + uint32_t addr, src; + hwaddr plen; + + if (i == ASPEED_HACE_MAX_SG) { + qemu_log_mask(LOG_GUEST_ERROR, + "aspeed_hace: guest failed to set end of sg list marker\n"); + break; + } + + src = s->regs[R_HASH_SRC] + (i * SG_LIST_ENTRY_SIZE); + + len = address_space_ldl_le(&s->dram_as, src, + MEMTXATTRS_UNSPECIFIED, NULL); + + addr = address_space_ldl_le(&s->dram_as, src + SG_LIST_LEN_SIZE, + MEMTXATTRS_UNSPECIFIED, NULL); + addr &= SG_LIST_ADDR_MASK; + + iov[i].iov_len = len & SG_LIST_LEN_MASK; + plen = iov[i].iov_len; + iov[i].iov_base = address_space_map(&s->dram_as, addr, &plen, false, + MEMTXATTRS_UNSPECIFIED); + } + } else { + hwaddr len = s->regs[R_HASH_SRC_LEN]; + + iov[0].iov_len = len; + iov[0].iov_base = address_space_map(&s->dram_as, s->regs[R_HASH_SRC], + &len, false, + MEMTXATTRS_UNSPECIFIED); + i = 1; + } + + if (qcrypto_hash_bytesv(algo, iov, i, &digest_buf, &digest_len, NULL) < 0) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: qcrypto failed\n", __func__); + return; + } + + if (address_space_write(&s->dram_as, s->regs[R_HASH_DEST], + MEMTXATTRS_UNSPECIFIED, + digest_buf, digest_len)) { + qemu_log_mask(LOG_GUEST_ERROR, + "aspeed_hace: address space write failed\n"); + } + + for (; i > 0; i--) { + address_space_unmap(&s->dram_as, iov[i - 1].iov_base, + iov[i - 1].iov_len, false, + iov[i - 1].iov_len); + } + + /* + * Set status bits to indicate completion. Testing shows hardware sets + * these irrespective of HASH_IRQ_EN. + */ + s->regs[R_STATUS] |= HASH_IRQ; +} + +static uint64_t aspeed_hace_read(void *opaque, hwaddr addr, unsigned int size) +{ + AspeedHACEState *s = ASPEED_HACE(opaque); + + addr >>= 2; + + if (addr >= ASPEED_HACE_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Out-of-bounds read at offset 0x%" HWADDR_PRIx "\n", + __func__, addr << 2); + return 0; + } + + return s->regs[addr]; +} + +static void aspeed_hace_write(void *opaque, hwaddr addr, uint64_t data, + unsigned int size) +{ + AspeedHACEState *s = ASPEED_HACE(opaque); + AspeedHACEClass *ahc = ASPEED_HACE_GET_CLASS(s); + + addr >>= 2; + + if (addr >= ASPEED_HACE_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Out-of-bounds write at offset 0x%" HWADDR_PRIx "\n", + __func__, addr << 2); + return; + } + + switch (addr) { + case R_STATUS: + if (data & HASH_IRQ) { + data &= ~HASH_IRQ; + + if (s->regs[addr] & HASH_IRQ) { + qemu_irq_lower(s->irq); + } + } + break; + case R_HASH_SRC: + data &= ahc->src_mask; + break; + case R_HASH_DEST: + data &= ahc->dest_mask; + break; + case R_HASH_SRC_LEN: + data &= 0x0FFFFFFF; + break; + case R_HASH_CMD: { + int algo; + data &= ahc->hash_mask; + + if ((data & HASH_HMAC_MASK)) { + qemu_log_mask(LOG_UNIMP, + "%s: HMAC engine command mode %"PRIx64" not implemented", + __func__, (data & HASH_HMAC_MASK) >> 8); + } + if (data & BIT(1)) { + qemu_log_mask(LOG_UNIMP, + "%s: Cascaded mode not implemented", + __func__); + } + algo = hash_algo_lookup(data); + if (algo < 0) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Invalid hash algorithm selection 0x%"PRIx64"\n", + __func__, data & ahc->hash_mask); + break; + } + do_hash_operation(s, algo, data & HASH_SG_EN); + + if (data & HASH_IRQ_EN) { + qemu_irq_raise(s->irq); + } + break; + } + case R_CRYPT_CMD: + qemu_log_mask(LOG_UNIMP, "%s: Crypt commands not implemented\n", + __func__); + break; + default: + break; + } + + s->regs[addr] = data; +} + +static const MemoryRegionOps aspeed_hace_ops = { + .read = aspeed_hace_read, + .write = aspeed_hace_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 4, + }, +}; + +static void aspeed_hace_reset(DeviceState *dev) +{ + struct AspeedHACEState *s = ASPEED_HACE(dev); + + memset(s->regs, 0, sizeof(s->regs)); +} + +static void aspeed_hace_realize(DeviceState *dev, Error **errp) +{ + AspeedHACEState *s = ASPEED_HACE(dev); + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + + sysbus_init_irq(sbd, &s->irq); + + memory_region_init_io(&s->iomem, OBJECT(s), &aspeed_hace_ops, s, + TYPE_ASPEED_HACE, 0x1000); + + if (!s->dram_mr) { + error_setg(errp, TYPE_ASPEED_HACE ": 'dram' link not set"); + return; + } + + address_space_init(&s->dram_as, s->dram_mr, "dram"); + + sysbus_init_mmio(sbd, &s->iomem); +} + +static Property aspeed_hace_properties[] = { + DEFINE_PROP_LINK("dram", AspeedHACEState, dram_mr, + TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_PROP_END_OF_LIST(), +}; + + +static const VMStateDescription vmstate_aspeed_hace = { + .name = TYPE_ASPEED_HACE, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AspeedHACEState, ASPEED_HACE_NR_REGS), + VMSTATE_END_OF_LIST(), + } +}; + +static void aspeed_hace_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = aspeed_hace_realize; + dc->reset = aspeed_hace_reset; + device_class_set_props(dc, aspeed_hace_properties); + dc->vmsd = &vmstate_aspeed_hace; +} + +static const TypeInfo aspeed_hace_info = { + .name = TYPE_ASPEED_HACE, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AspeedHACEState), + .class_init = aspeed_hace_class_init, + .class_size = sizeof(AspeedHACEClass) +}; + +static void aspeed_ast2400_hace_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + AspeedHACEClass *ahc = ASPEED_HACE_CLASS(klass); + + dc->desc = "AST2400 Hash and Crypto Engine"; + + ahc->src_mask = 0x0FFFFFFF; + ahc->dest_mask = 0x0FFFFFF8; + ahc->hash_mask = 0x000003ff; /* No SG or SHA512 modes */ +} + +static const TypeInfo aspeed_ast2400_hace_info = { + .name = TYPE_ASPEED_AST2400_HACE, + .parent = TYPE_ASPEED_HACE, + .class_init = aspeed_ast2400_hace_class_init, +}; + +static void aspeed_ast2500_hace_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + AspeedHACEClass *ahc = ASPEED_HACE_CLASS(klass); + + dc->desc = "AST2500 Hash and Crypto Engine"; + + ahc->src_mask = 0x3fffffff; + ahc->dest_mask = 0x3ffffff8; + ahc->hash_mask = 0x000003ff; /* No SG or SHA512 modes */ +} + +static const TypeInfo aspeed_ast2500_hace_info = { + .name = TYPE_ASPEED_AST2500_HACE, + .parent = TYPE_ASPEED_HACE, + .class_init = aspeed_ast2500_hace_class_init, +}; + +static void aspeed_ast2600_hace_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + AspeedHACEClass *ahc = ASPEED_HACE_CLASS(klass); + + dc->desc = "AST2600 Hash and Crypto Engine"; + + ahc->src_mask = 0x7FFFFFFF; + ahc->dest_mask = 0x7FFFFFF8; + ahc->hash_mask = 0x00147FFF; +} + +static const TypeInfo aspeed_ast2600_hace_info = { + .name = TYPE_ASPEED_AST2600_HACE, + .parent = TYPE_ASPEED_HACE, + .class_init = aspeed_ast2600_hace_class_init, +}; + +static void aspeed_hace_register_types(void) +{ + type_register_static(&aspeed_ast2400_hace_info); + type_register_static(&aspeed_ast2500_hace_info); + type_register_static(&aspeed_ast2600_hace_info); + type_register_static(&aspeed_hace_info); +} + +type_init(aspeed_hace_register_types); diff --git a/hw/misc/aspeed_xdma.c b/hw/misc/aspeed_xdma.c index 533d237e3c..1c21577c98 100644 --- a/hw/misc/aspeed_xdma.c +++ b/hw/misc/aspeed_xdma.c @@ -30,6 +30,19 @@ #define XDMA_IRQ_ENG_STAT_US_COMP BIT(4) #define XDMA_IRQ_ENG_STAT_DS_COMP BIT(5) #define XDMA_IRQ_ENG_STAT_RESET 0xF8000000 + +#define XDMA_AST2600_BMC_CMDQ_ADDR 0x14 +#define XDMA_AST2600_BMC_CMDQ_ENDP 0x18 +#define XDMA_AST2600_BMC_CMDQ_WRP 0x1c +#define XDMA_AST2600_BMC_CMDQ_RDP 0x20 +#define XDMA_AST2600_IRQ_CTRL 0x38 +#define XDMA_AST2600_IRQ_CTRL_US_COMP BIT(16) +#define XDMA_AST2600_IRQ_CTRL_DS_COMP BIT(17) +#define XDMA_AST2600_IRQ_CTRL_W_MASK 0x017003FF +#define XDMA_AST2600_IRQ_STATUS 0x3c +#define XDMA_AST2600_IRQ_STATUS_US_COMP BIT(16) +#define XDMA_AST2600_IRQ_STATUS_DS_COMP BIT(17) + #define XDMA_MEM_SIZE 0x1000 #define TO_REG(addr) ((addr) / sizeof(uint32_t)) @@ -52,56 +65,48 @@ static void aspeed_xdma_write(void *opaque, hwaddr addr, uint64_t val, unsigned int idx; uint32_t val32 = (uint32_t)val; AspeedXDMAState *xdma = opaque; + AspeedXDMAClass *axc = ASPEED_XDMA_GET_CLASS(xdma); if (addr >= ASPEED_XDMA_REG_SIZE) { return; } - switch (addr) { - case XDMA_BMC_CMDQ_ENDP: + if (addr == axc->cmdq_endp) { xdma->regs[TO_REG(addr)] = val32 & XDMA_BMC_CMDQ_W_MASK; - break; - case XDMA_BMC_CMDQ_WRP: + } else if (addr == axc->cmdq_wrp) { idx = TO_REG(addr); xdma->regs[idx] = val32 & XDMA_BMC_CMDQ_W_MASK; - xdma->regs[TO_REG(XDMA_BMC_CMDQ_RDP)] = xdma->regs[idx]; + xdma->regs[TO_REG(axc->cmdq_rdp)] = xdma->regs[idx]; trace_aspeed_xdma_write(addr, val); if (xdma->bmc_cmdq_readp_set) { xdma->bmc_cmdq_readp_set = 0; } else { - xdma->regs[TO_REG(XDMA_IRQ_ENG_STAT)] |= - XDMA_IRQ_ENG_STAT_US_COMP | XDMA_IRQ_ENG_STAT_DS_COMP; + xdma->regs[TO_REG(axc->intr_status)] |= axc->intr_complete; - if (xdma->regs[TO_REG(XDMA_IRQ_ENG_CTRL)] & - (XDMA_IRQ_ENG_CTRL_US_COMP | XDMA_IRQ_ENG_CTRL_DS_COMP)) + if (xdma->regs[TO_REG(axc->intr_ctrl)] & axc->intr_complete) { qemu_irq_raise(xdma->irq); + } } - break; - case XDMA_BMC_CMDQ_RDP: + } else if (addr == axc->cmdq_rdp) { trace_aspeed_xdma_write(addr, val); if (val32 == XDMA_BMC_CMDQ_RDP_MAGIC) { xdma->bmc_cmdq_readp_set = 1; } - break; - case XDMA_IRQ_ENG_CTRL: - xdma->regs[TO_REG(addr)] = val32 & XDMA_IRQ_ENG_CTRL_W_MASK; - break; - case XDMA_IRQ_ENG_STAT: + } else if (addr == axc->intr_ctrl) { + xdma->regs[TO_REG(addr)] = val32 & axc->intr_ctrl_mask; + } else if (addr == axc->intr_status) { trace_aspeed_xdma_write(addr, val); idx = TO_REG(addr); - if (val32 & (XDMA_IRQ_ENG_STAT_US_COMP | XDMA_IRQ_ENG_STAT_DS_COMP)) { - xdma->regs[idx] &= - ~(XDMA_IRQ_ENG_STAT_US_COMP | XDMA_IRQ_ENG_STAT_DS_COMP); + if (val32 & axc->intr_complete) { + xdma->regs[idx] &= ~axc->intr_complete; qemu_irq_lower(xdma->irq); } - break; - default: + } else { xdma->regs[TO_REG(addr)] = val32; - break; } } @@ -127,10 +132,11 @@ static void aspeed_xdma_realize(DeviceState *dev, Error **errp) static void aspeed_xdma_reset(DeviceState *dev) { AspeedXDMAState *xdma = ASPEED_XDMA(dev); + AspeedXDMAClass *axc = ASPEED_XDMA_GET_CLASS(xdma); xdma->bmc_cmdq_readp_set = 0; memset(xdma->regs, 0, ASPEED_XDMA_REG_SIZE); - xdma->regs[TO_REG(XDMA_IRQ_ENG_STAT)] = XDMA_IRQ_ENG_STAT_RESET; + xdma->regs[TO_REG(axc->intr_status)] = XDMA_IRQ_ENG_STAT_RESET; qemu_irq_lower(xdma->irq); } @@ -144,6 +150,73 @@ static const VMStateDescription aspeed_xdma_vmstate = { }, }; +static void aspeed_2600_xdma_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + AspeedXDMAClass *axc = ASPEED_XDMA_CLASS(klass); + + dc->desc = "ASPEED 2600 XDMA Controller"; + + axc->cmdq_endp = XDMA_AST2600_BMC_CMDQ_ENDP; + axc->cmdq_wrp = XDMA_AST2600_BMC_CMDQ_WRP; + axc->cmdq_rdp = XDMA_AST2600_BMC_CMDQ_RDP; + axc->intr_ctrl = XDMA_AST2600_IRQ_CTRL; + axc->intr_ctrl_mask = XDMA_AST2600_IRQ_CTRL_W_MASK; + axc->intr_status = XDMA_AST2600_IRQ_STATUS; + axc->intr_complete = XDMA_AST2600_IRQ_STATUS_US_COMP | + XDMA_AST2600_IRQ_STATUS_DS_COMP; +} + +static const TypeInfo aspeed_2600_xdma_info = { + .name = TYPE_ASPEED_2600_XDMA, + .parent = TYPE_ASPEED_XDMA, + .class_init = aspeed_2600_xdma_class_init, +}; + +static void aspeed_2500_xdma_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + AspeedXDMAClass *axc = ASPEED_XDMA_CLASS(klass); + + dc->desc = "ASPEED 2500 XDMA Controller"; + + axc->cmdq_endp = XDMA_BMC_CMDQ_ENDP; + axc->cmdq_wrp = XDMA_BMC_CMDQ_WRP; + axc->cmdq_rdp = XDMA_BMC_CMDQ_RDP; + axc->intr_ctrl = XDMA_IRQ_ENG_CTRL; + axc->intr_ctrl_mask = XDMA_IRQ_ENG_CTRL_W_MASK; + axc->intr_status = XDMA_IRQ_ENG_STAT; + axc->intr_complete = XDMA_IRQ_ENG_STAT_US_COMP | XDMA_IRQ_ENG_STAT_DS_COMP; +}; + +static const TypeInfo aspeed_2500_xdma_info = { + .name = TYPE_ASPEED_2500_XDMA, + .parent = TYPE_ASPEED_XDMA, + .class_init = aspeed_2500_xdma_class_init, +}; + +static void aspeed_2400_xdma_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + AspeedXDMAClass *axc = ASPEED_XDMA_CLASS(klass); + + dc->desc = "ASPEED 2400 XDMA Controller"; + + axc->cmdq_endp = XDMA_BMC_CMDQ_ENDP; + axc->cmdq_wrp = XDMA_BMC_CMDQ_WRP; + axc->cmdq_rdp = XDMA_BMC_CMDQ_RDP; + axc->intr_ctrl = XDMA_IRQ_ENG_CTRL; + axc->intr_ctrl_mask = XDMA_IRQ_ENG_CTRL_W_MASK; + axc->intr_status = XDMA_IRQ_ENG_STAT; + axc->intr_complete = XDMA_IRQ_ENG_STAT_US_COMP | XDMA_IRQ_ENG_STAT_DS_COMP; +}; + +static const TypeInfo aspeed_2400_xdma_info = { + .name = TYPE_ASPEED_2400_XDMA, + .parent = TYPE_ASPEED_XDMA, + .class_init = aspeed_2400_xdma_class_init, +}; + static void aspeed_xdma_class_init(ObjectClass *classp, void *data) { DeviceClass *dc = DEVICE_CLASS(classp); @@ -158,10 +231,15 @@ static const TypeInfo aspeed_xdma_info = { .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(AspeedXDMAState), .class_init = aspeed_xdma_class_init, + .class_size = sizeof(AspeedXDMAClass), + .abstract = true, }; static void aspeed_xdma_register_type(void) { type_register_static(&aspeed_xdma_info); + type_register_static(&aspeed_2400_xdma_info); + type_register_static(&aspeed_2500_xdma_info); + type_register_static(&aspeed_2600_xdma_info); } type_init(aspeed_xdma_register_type); diff --git a/hw/misc/auxbus.c b/hw/misc/auxbus.c index 6c099ae2a2..434ff8d910 100644 --- a/hw/misc/auxbus.c +++ b/hw/misc/auxbus.c @@ -106,7 +106,6 @@ AUXReply aux_request(AUXBus *bus, AUXCommand cmd, uint32_t address, AUXReply ret = AUX_NACK; I2CBus *i2c_bus = aux_get_i2c_bus(bus); size_t i; - bool is_write = false; DPRINTF("request at address 0x%" PRIX32 ", command %u, len %u\n", address, cmd, len); @@ -117,11 +116,10 @@ AUXReply aux_request(AUXBus *bus, AUXCommand cmd, uint32_t address, */ case WRITE_AUX: case READ_AUX: - is_write = cmd == READ_AUX ? false : true; for (i = 0; i < len; i++) { if (!address_space_rw(&bus->aux_addr_space, address++, MEMTXATTRS_UNSPECIFIED, data++, 1, - is_write)) { + cmd == WRITE_AUX)) { ret = AUX_I2C_ACK; } else { ret = AUX_NACK; @@ -133,24 +131,37 @@ AUXReply aux_request(AUXBus *bus, AUXCommand cmd, uint32_t address, * Classic I2C transactions.. */ case READ_I2C: - case WRITE_I2C: - is_write = cmd == READ_I2C ? false : true; if (i2c_bus_busy(i2c_bus)) { i2c_end_transfer(i2c_bus); } - if (i2c_start_transfer(i2c_bus, address, is_write)) { + if (i2c_start_recv(i2c_bus, address)) { ret = AUX_I2C_NACK; break; } ret = AUX_I2C_ACK; - while (len > 0) { - if (i2c_send_recv(i2c_bus, data++, is_write) < 0) { + for (i = 0; i < len; i++) { + data[i] = i2c_recv(i2c_bus); + } + i2c_end_transfer(i2c_bus); + break; + case WRITE_I2C: + if (i2c_bus_busy(i2c_bus)) { + i2c_end_transfer(i2c_bus); + } + + if (i2c_start_send(i2c_bus, address)) { + ret = AUX_I2C_NACK; + break; + } + + ret = AUX_I2C_ACK; + for (i = 0; i < len; i++) { + if (i2c_send(i2c_bus, data[i]) < 0) { ret = AUX_I2C_NACK; break; } - len--; } i2c_end_transfer(i2c_bus); break; @@ -163,14 +174,12 @@ AUXReply aux_request(AUXBus *bus, AUXCommand cmd, uint32_t address, * - We changed the address. */ case WRITE_I2C_MOT: - case READ_I2C_MOT: - is_write = cmd == READ_I2C_MOT ? false : true; ret = AUX_I2C_NACK; if (!i2c_bus_busy(i2c_bus)) { /* * No transactions started.. */ - if (i2c_start_transfer(i2c_bus, address, is_write)) { + if (i2c_start_send(i2c_bus, address)) { break; } } else if ((address != bus->last_i2c_address) || @@ -179,23 +188,48 @@ AUXReply aux_request(AUXBus *bus, AUXCommand cmd, uint32_t address, * Transaction started but we need to restart.. */ i2c_end_transfer(i2c_bus); - if (i2c_start_transfer(i2c_bus, address, is_write)) { + if (i2c_start_send(i2c_bus, address)) { break; } } bus->last_transaction = cmd; bus->last_i2c_address = address; - while (len > 0) { - if (i2c_send_recv(i2c_bus, data++, is_write) < 0) { + ret = AUX_I2C_ACK; + for (i = 0; i < len; i++) { + if (i2c_send(i2c_bus, data[i]) < 0) { i2c_end_transfer(i2c_bus); + ret = AUX_I2C_NACK; break; } - len--; } - if (len == 0) { - ret = AUX_I2C_ACK; + break; + case READ_I2C_MOT: + ret = AUX_I2C_NACK; + if (!i2c_bus_busy(i2c_bus)) { + /* + * No transactions started.. + */ + if (i2c_start_recv(i2c_bus, address)) { + break; + } + } else if ((address != bus->last_i2c_address) || + (bus->last_transaction != cmd)) { + /* + * Transaction started but we need to restart.. + */ + i2c_end_transfer(i2c_bus); + if (i2c_start_recv(i2c_bus, address)) { + break; + } } + + bus->last_transaction = cmd; + bus->last_i2c_address = address; + for (i = 0; i < len; i++) { + data[i] = i2c_recv(i2c_bus); + } + ret = AUX_I2C_ACK; break; default: qemu_log_mask(LOG_UNIMP, "AUX cmd=%u not implemented\n", cmd); diff --git a/hw/misc/bcm2835_powermgt.c b/hw/misc/bcm2835_powermgt.c new file mode 100644 index 0000000000..25fa804cbd --- /dev/null +++ b/hw/misc/bcm2835_powermgt.c @@ -0,0 +1,160 @@ +/* + * BCM2835 Power Management emulation + * + * Copyright (C) 2017 Marcin Chojnacki + * Copyright (C) 2021 Nolan Leake + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/bcm2835_powermgt.h" +#include "migration/vmstate.h" +#include "sysemu/runstate.h" + +#define PASSWORD 0x5a000000 +#define PASSWORD_MASK 0xff000000 + +#define R_RSTC 0x1c +#define V_RSTC_RESET 0x20 +#define R_RSTS 0x20 +#define V_RSTS_POWEROFF 0x555 /* Linux uses partition 63 to indicate halt. */ +#define R_WDOG 0x24 + +static uint64_t bcm2835_powermgt_read(void *opaque, hwaddr offset, + unsigned size) +{ + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; + uint32_t res = 0; + + switch (offset) { + case R_RSTC: + res = s->rstc; + break; + case R_RSTS: + res = s->rsts; + break; + case R_WDOG: + res = s->wdog; + break; + + default: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_read: Unknown offset 0x%08"HWADDR_PRIx + "\n", offset); + res = 0; + break; + } + + return res; +} + +static void bcm2835_powermgt_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; + + if ((value & PASSWORD_MASK) != PASSWORD) { + qemu_log_mask(LOG_GUEST_ERROR, + "bcm2835_powermgt_write: Bad password 0x%"PRIx64 + " at offset 0x%08"HWADDR_PRIx"\n", + value, offset); + return; + } + + value = value & ~PASSWORD_MASK; + + switch (offset) { + case R_RSTC: + s->rstc = value; + if (value & V_RSTC_RESET) { + if ((s->rsts & 0xfff) == V_RSTS_POWEROFF) { + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + } else { + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); + } + } + break; + case R_RSTS: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_write: RSTS\n"); + s->rsts = value; + break; + case R_WDOG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_write: WDOG\n"); + s->wdog = value; + break; + + default: + qemu_log_mask(LOG_UNIMP, + "bcm2835_powermgt_write: Unknown offset 0x%08"HWADDR_PRIx + "\n", offset); + break; + } +} + +static const MemoryRegionOps bcm2835_powermgt_ops = { + .read = bcm2835_powermgt_read, + .write = bcm2835_powermgt_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl.min_access_size = 4, + .impl.max_access_size = 4, +}; + +static const VMStateDescription vmstate_bcm2835_powermgt = { + .name = TYPE_BCM2835_POWERMGT, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(rstc, BCM2835PowerMgtState), + VMSTATE_UINT32(rsts, BCM2835PowerMgtState), + VMSTATE_UINT32(wdog, BCM2835PowerMgtState), + VMSTATE_END_OF_LIST() + } +}; + +static void bcm2835_powermgt_init(Object *obj) +{ + BCM2835PowerMgtState *s = BCM2835_POWERMGT(obj); + + memory_region_init_io(&s->iomem, obj, &bcm2835_powermgt_ops, s, + TYPE_BCM2835_POWERMGT, 0x200); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); +} + +static void bcm2835_powermgt_reset(DeviceState *dev) +{ + BCM2835PowerMgtState *s = BCM2835_POWERMGT(dev); + + /* https://elinux.org/BCM2835_registers#PM */ + s->rstc = 0x00000102; + s->rsts = 0x00001000; + s->wdog = 0x00000000; +} + +static void bcm2835_powermgt_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = bcm2835_powermgt_reset; + dc->vmsd = &vmstate_bcm2835_powermgt; +} + +static TypeInfo bcm2835_powermgt_info = { + .name = TYPE_BCM2835_POWERMGT, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(BCM2835PowerMgtState), + .class_init = bcm2835_powermgt_class_init, + .instance_init = bcm2835_powermgt_init, +}; + +static void bcm2835_powermgt_register_types(void) +{ + type_register_static(&bcm2835_powermgt_info); +} + +type_init(bcm2835_powermgt_register_types) diff --git a/hw/misc/imx7_snvs.c b/hw/misc/imx7_snvs.c index 45972a5920..ee7698bd9c 100644 --- a/hw/misc/imx7_snvs.c +++ b/hw/misc/imx7_snvs.c @@ -14,7 +14,6 @@ #include "qemu/osdep.h" #include "hw/misc/imx7_snvs.h" -#include "qemu/log.h" #include "qemu/module.h" #include "sysemu/runstate.h" diff --git a/hw/misc/imx_ccm.c b/hw/misc/imx_ccm.c index 08a50ee4c8..9403c5daa3 100644 --- a/hw/misc/imx_ccm.c +++ b/hw/misc/imx_ccm.c @@ -13,7 +13,6 @@ #include "qemu/osdep.h" #include "hw/misc/imx_ccm.h" -#include "qemu/log.h" #include "qemu/module.h" #ifndef DEBUG_IMX_CCM diff --git a/hw/misc/imx_rngc.c b/hw/misc/imx_rngc.c index 4c270df2db..632c03779c 100644 --- a/hw/misc/imx_rngc.c +++ b/hw/misc/imx_rngc.c @@ -14,7 +14,6 @@ #include "qemu/osdep.h" #include "qemu/main-loop.h" #include "qemu/module.h" -#include "qemu/log.h" #include "qemu/guest-random.h" #include "hw/irq.h" #include "hw/misc/imx_rngc.h" diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c index a1fa4878be..1ba4a98377 100644 --- a/hw/misc/ivshmem.c +++ b/hw/misc/ivshmem.c @@ -493,9 +493,8 @@ static void process_msg_shmem(IVShmemState *s, int fd, Error **errp) size = buf.st_size; /* mmap the region and map into the BAR2 */ - memory_region_init_ram_from_fd(&s->server_bar2, OBJECT(s), - "ivshmem.bar2", size, true, fd, 0, - &local_err); + memory_region_init_ram_from_fd(&s->server_bar2, OBJECT(s), "ivshmem.bar2", + size, RAM_SHARED, fd, 0, &local_err); if (local_err) { error_propagate(errp, local_err); return; diff --git a/hw/misc/led.c b/hw/misc/led.c index f552b8b648..f6d6d68bce 100644 --- a/hw/misc/led.c +++ b/hw/misc/led.c @@ -10,7 +10,6 @@ #include "migration/vmstate.h" #include "hw/qdev-properties.h" #include "hw/misc/led.h" -#include "hw/irq.h" #include "trace.h" #define LED_INTENSITY_PERCENT_MAX 100 diff --git a/hw/misc/macio/macio.c b/hw/misc/macio/macio.c index e6eeb575d5..4515296e66 100644 --- a/hw/misc/macio/macio.c +++ b/hw/misc/macio/macio.c @@ -35,7 +35,6 @@ #include "hw/char/escc.h" #include "hw/misc/macio/macio.h" #include "hw/intc/heathrow_pic.h" -#include "sysemu/sysemu.h" #include "trace.h" /* Note: this code is strongly inspirated from the corresponding code diff --git a/hw/misc/macio/trace-events b/hw/misc/macio/trace-events index e4a1cc0d24..ad4b9d1c08 100644 --- a/hw/misc/macio/trace-events +++ b/hw/misc/macio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # cuda.c cuda_delay_set_sr_int(void) "" diff --git a/hw/misc/mchp_pfsoc_dmc.c b/hw/misc/mchp_pfsoc_dmc.c index 15cf3d7725..43d8e970ab 100644 --- a/hw/misc/mchp_pfsoc_dmc.c +++ b/hw/misc/mchp_pfsoc_dmc.c @@ -24,7 +24,6 @@ #include "qemu/bitops.h" #include "qemu/log.h" #include "qapi/error.h" -#include "hw/hw.h" #include "hw/sysbus.h" #include "hw/misc/mchp_pfsoc_dmc.h" diff --git a/hw/misc/mchp_pfsoc_ioscb.c b/hw/misc/mchp_pfsoc_ioscb.c index 8b0d1cacd7..f4fd55a0e5 100644 --- a/hw/misc/mchp_pfsoc_ioscb.c +++ b/hw/misc/mchp_pfsoc_ioscb.c @@ -24,7 +24,6 @@ #include "qemu/bitops.h" #include "qemu/log.h" #include "qapi/error.h" -#include "hw/hw.h" #include "hw/sysbus.h" #include "hw/misc/mchp_pfsoc_ioscb.h" diff --git a/hw/misc/mchp_pfsoc_sysreg.c b/hw/misc/mchp_pfsoc_sysreg.c index 248a313345..89571eded5 100644 --- a/hw/misc/mchp_pfsoc_sysreg.c +++ b/hw/misc/mchp_pfsoc_sysreg.c @@ -24,7 +24,6 @@ #include "qemu/bitops.h" #include "qemu/log.h" #include "qapi/error.h" -#include "hw/hw.h" #include "hw/sysbus.h" #include "hw/misc/mchp_pfsoc_sysreg.h" diff --git a/hw/misc/meson.build b/hw/misc/meson.build index 21034dc60a..a53b849a5a 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -3,13 +3,9 @@ softmmu_ss.add(when: 'CONFIG_EDU', if_true: files('edu.c')) softmmu_ss.add(when: 'CONFIG_FW_CFG_DMA', if_true: files('vmcoreinfo.c')) softmmu_ss.add(when: 'CONFIG_ISA_DEBUG', if_true: files('debugexit.c')) softmmu_ss.add(when: 'CONFIG_ISA_TESTDEV', if_true: files('pc-testdev.c')) -softmmu_ss.add(when: 'CONFIG_MAX111X', if_true: files('max111x.c')) softmmu_ss.add(when: 'CONFIG_PCA9552', if_true: files('pca9552.c')) softmmu_ss.add(when: 'CONFIG_PCI_TESTDEV', if_true: files('pci-testdev.c')) softmmu_ss.add(when: 'CONFIG_SGA', if_true: files('sga.c')) -softmmu_ss.add(when: 'CONFIG_TMP105', if_true: files('tmp105.c')) -softmmu_ss.add(when: 'CONFIG_TMP421', if_true: files('tmp421.c')) -softmmu_ss.add(when: 'CONFIG_EMC141X', if_true: files('emc141x.c')) softmmu_ss.add(when: 'CONFIG_UNIMP', if_true: files('unimp.c')) softmmu_ss.add(when: 'CONFIG_EMPTY_SLOT', if_true: files('empty_slot.c')) softmmu_ss.add(when: 'CONFIG_LED', if_true: files('led.c')) @@ -36,9 +32,6 @@ softmmu_ss.add(when: 'CONFIG_SIFIVE_E_PRCI', if_true: files('sifive_e_prci.c')) softmmu_ss.add(when: 'CONFIG_SIFIVE_U_OTP', if_true: files('sifive_u_otp.c')) softmmu_ss.add(when: 'CONFIG_SIFIVE_U_PRCI', if_true: files('sifive_u_prci.c')) -# PKUnity SoC devices -softmmu_ss.add(when: 'CONFIG_PUV3', if_true: files('puv3_pm.c')) - subdir('macio') softmmu_ss.add(when: 'CONFIG_IVSHMEM_DEVICE', if_true: files('ivshmem.c')) @@ -63,7 +56,6 @@ softmmu_ss.add(when: 'CONFIG_IMX', if_true: files( 'imx_ccm.c', 'imx_rngc.c', )) -softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-hpdmc.c', 'milkymist-pfpu.c')) softmmu_ss.add(when: 'CONFIG_MAINSTONE', if_true: files('mst_fpga.c')) softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( 'npcm7xx_clk.c', @@ -86,9 +78,10 @@ softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files( 'bcm2835_rng.c', 'bcm2835_thermal.c', 'bcm2835_cprman.c', + 'bcm2835_powermgt.c', )) softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c')) -softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c', 'zynq-xadc.c')) +softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c')) softmmu_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files('xlnx-versal-xramc.c')) softmmu_ss.add(when: 'CONFIG_STM32F2XX_SYSCFG', if_true: files('stm32f2xx_syscfg.c')) softmmu_ss.add(when: 'CONFIG_STM32F4XX_SYSCFG', if_true: files('stm32f4xx_syscfg.c')) @@ -109,6 +102,7 @@ softmmu_ss.add(when: 'CONFIG_PVPANIC_ISA', if_true: files('pvpanic-isa.c')) softmmu_ss.add(when: 'CONFIG_PVPANIC_PCI', if_true: files('pvpanic-pci.c')) softmmu_ss.add(when: 'CONFIG_AUX', if_true: files('auxbus.c')) softmmu_ss.add(when: 'CONFIG_ASPEED_SOC', if_true: files( + 'aspeed_hace.c', 'aspeed_lpc.c', 'aspeed_scu.c', 'aspeed_sdmc.c', diff --git a/hw/misc/milkymist-hpdmc.c b/hw/misc/milkymist-hpdmc.c deleted file mode 100644 index 09a3875f02..0000000000 --- a/hw/misc/milkymist-hpdmc.c +++ /dev/null @@ -1,172 +0,0 @@ -/* - * QEMU model of the Milkymist High Performance Dynamic Memory Controller. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://milkymist.walle.cc/socdoc/hpdmc.pdf - */ - -#include "qemu/osdep.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "qemu/error-report.h" -#include "qemu/module.h" -#include "qom/object.h" - -enum { - R_SYSTEM = 0, - R_BYPASS, - R_TIMING, - R_IODELAY, - R_MAX -}; - -enum { - IODELAY_DQSDELAY_RDY = (1<<5), - IODELAY_PLL1_LOCKED = (1<<6), - IODELAY_PLL2_LOCKED = (1<<7), -}; - -#define TYPE_MILKYMIST_HPDMC "milkymist-hpdmc" -OBJECT_DECLARE_SIMPLE_TYPE(MilkymistHpdmcState, MILKYMIST_HPDMC) - -struct MilkymistHpdmcState { - SysBusDevice parent_obj; - - MemoryRegion regs_region; - - uint32_t regs[R_MAX]; -}; - -static uint64_t hpdmc_read(void *opaque, hwaddr addr, - unsigned size) -{ - MilkymistHpdmcState *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_SYSTEM: - case R_BYPASS: - case R_TIMING: - case R_IODELAY: - r = s->regs[addr]; - break; - - default: - error_report("milkymist_hpdmc: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - trace_milkymist_hpdmc_memory_read(addr << 2, r); - - return r; -} - -static void hpdmc_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - MilkymistHpdmcState *s = opaque; - - trace_milkymist_hpdmc_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_SYSTEM: - case R_BYPASS: - case R_TIMING: - s->regs[addr] = value; - break; - case R_IODELAY: - /* ignore writes */ - break; - - default: - error_report("milkymist_hpdmc: write access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } -} - -static const MemoryRegionOps hpdmc_mmio_ops = { - .read = hpdmc_read, - .write = hpdmc_write, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void milkymist_hpdmc_reset(DeviceState *d) -{ - MilkymistHpdmcState *s = MILKYMIST_HPDMC(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } - - /* defaults */ - s->regs[R_IODELAY] = IODELAY_DQSDELAY_RDY | IODELAY_PLL1_LOCKED - | IODELAY_PLL2_LOCKED; -} - -static void milkymist_hpdmc_realize(DeviceState *dev, Error **errp) -{ - MilkymistHpdmcState *s = MILKYMIST_HPDMC(dev); - - memory_region_init_io(&s->regs_region, OBJECT(dev), &hpdmc_mmio_ops, s, - "milkymist-hpdmc", R_MAX * 4); - sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->regs_region); -} - -static const VMStateDescription vmstate_milkymist_hpdmc = { - .name = "milkymist-hpdmc", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, MilkymistHpdmcState, R_MAX), - VMSTATE_END_OF_LIST() - } -}; - -static void milkymist_hpdmc_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = milkymist_hpdmc_realize; - dc->reset = milkymist_hpdmc_reset; - dc->vmsd = &vmstate_milkymist_hpdmc; -} - -static const TypeInfo milkymist_hpdmc_info = { - .name = TYPE_MILKYMIST_HPDMC, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(MilkymistHpdmcState), - .class_init = milkymist_hpdmc_class_init, -}; - -static void milkymist_hpdmc_register_types(void) -{ - type_register_static(&milkymist_hpdmc_info); -} - -type_init(milkymist_hpdmc_register_types) diff --git a/hw/misc/milkymist-pfpu.c b/hw/misc/milkymist-pfpu.c deleted file mode 100644 index e4ee209c10..0000000000 --- a/hw/misc/milkymist-pfpu.c +++ /dev/null @@ -1,548 +0,0 @@ -/* - * QEMU model of the Milkymist programmable FPU. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://milkymist.walle.cc/socdoc/pfpu.pdf - * - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "qemu/log.h" -#include "qemu/module.h" -#include "qemu/error-report.h" -#include -#include "qom/object.h" - -/* #define TRACE_EXEC */ - -#ifdef TRACE_EXEC -# define D_EXEC(x) x -#else -# define D_EXEC(x) -#endif - -enum { - R_CTL = 0, - R_MESHBASE, - R_HMESHLAST, - R_VMESHLAST, - R_CODEPAGE, - R_VERTICES, - R_COLLISIONS, - R_STRAYWRITES, - R_LASTDMA, - R_PC, - R_DREGBASE, - R_CODEBASE, - R_MAX -}; - -enum { - CTL_START_BUSY = (1<<0), -}; - -enum { - OP_NOP = 0, - OP_FADD, - OP_FSUB, - OP_FMUL, - OP_FABS, - OP_F2I, - OP_I2F, - OP_VECTOUT, - OP_SIN, - OP_COS, - OP_ABOVE, - OP_EQUAL, - OP_COPY, - OP_IF, - OP_TSIGN, - OP_QUAKE, -}; - -enum { - GPR_X = 0, - GPR_Y = 1, - GPR_FLAGS = 2, -}; - -enum { - LATENCY_FADD = 5, - LATENCY_FSUB = 5, - LATENCY_FMUL = 7, - LATENCY_FABS = 2, - LATENCY_F2I = 2, - LATENCY_I2F = 3, - LATENCY_VECTOUT = 0, - LATENCY_SIN = 4, - LATENCY_COS = 4, - LATENCY_ABOVE = 2, - LATENCY_EQUAL = 2, - LATENCY_COPY = 2, - LATENCY_IF = 2, - LATENCY_TSIGN = 2, - LATENCY_QUAKE = 2, - MAX_LATENCY = 7 -}; - -#define GPR_BEGIN 0x100 -#define GPR_END 0x17f -#define MICROCODE_BEGIN 0x200 -#define MICROCODE_END 0x3ff -#define MICROCODE_WORDS 2048 - -#define REINTERPRET_CAST(type, val) (*((type *)&(val))) - -#ifdef TRACE_EXEC -static const char *opcode_to_str[] = { - "NOP", "FADD", "FSUB", "FMUL", "FABS", "F2I", "I2F", "VECTOUT", - "SIN", "COS", "ABOVE", "EQUAL", "COPY", "IF", "TSIGN", "QUAKE", -}; -#endif - -#define TYPE_MILKYMIST_PFPU "milkymist-pfpu" -OBJECT_DECLARE_SIMPLE_TYPE(MilkymistPFPUState, MILKYMIST_PFPU) - -struct MilkymistPFPUState { - SysBusDevice parent_obj; - - MemoryRegion regs_region; - Chardev *chr; - qemu_irq irq; - - uint32_t regs[R_MAX]; - uint32_t gp_regs[128]; - uint32_t microcode[MICROCODE_WORDS]; - - int output_queue_pos; - uint32_t output_queue[MAX_LATENCY]; -}; - -static inline uint32_t -get_dma_address(uint32_t base, uint32_t x, uint32_t y) -{ - return base + 8 * (128 * y + x); -} - -static inline void -output_queue_insert(MilkymistPFPUState *s, uint32_t val, int pos) -{ - s->output_queue[(s->output_queue_pos + pos) % MAX_LATENCY] = val; -} - -static inline uint32_t -output_queue_remove(MilkymistPFPUState *s) -{ - return s->output_queue[s->output_queue_pos]; -} - -static inline void -output_queue_advance(MilkymistPFPUState *s) -{ - s->output_queue[s->output_queue_pos] = 0; - s->output_queue_pos = (s->output_queue_pos + 1) % MAX_LATENCY; -} - -static int pfpu_decode_insn(MilkymistPFPUState *s) -{ - uint32_t pc = s->regs[R_PC]; - uint32_t insn = s->microcode[pc]; - uint32_t reg_a = (insn >> 18) & 0x7f; - uint32_t reg_b = (insn >> 11) & 0x7f; - uint32_t op = (insn >> 7) & 0xf; - uint32_t reg_d = insn & 0x7f; - uint32_t r = 0; - int latency = 0; - - switch (op) { - case OP_NOP: - break; - case OP_FADD: - { - float a = REINTERPRET_CAST(float, s->gp_regs[reg_a]); - float b = REINTERPRET_CAST(float, s->gp_regs[reg_b]); - float t = a + b; - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_FADD; - D_EXEC(qemu_log("ADD a=%f b=%f t=%f, r=%08x\n", a, b, t, r)); - } break; - case OP_FSUB: - { - float a = REINTERPRET_CAST(float, s->gp_regs[reg_a]); - float b = REINTERPRET_CAST(float, s->gp_regs[reg_b]); - float t = a - b; - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_FSUB; - D_EXEC(qemu_log("SUB a=%f b=%f t=%f, r=%08x\n", a, b, t, r)); - } break; - case OP_FMUL: - { - float a = REINTERPRET_CAST(float, s->gp_regs[reg_a]); - float b = REINTERPRET_CAST(float, s->gp_regs[reg_b]); - float t = a * b; - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_FMUL; - D_EXEC(qemu_log("MUL a=%f b=%f t=%f, r=%08x\n", a, b, t, r)); - } break; - case OP_FABS: - { - float a = REINTERPRET_CAST(float, s->gp_regs[reg_a]); - float t = fabsf(a); - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_FABS; - D_EXEC(qemu_log("ABS a=%f t=%f, r=%08x\n", a, t, r)); - } break; - case OP_F2I: - { - float a = REINTERPRET_CAST(float, s->gp_regs[reg_a]); - int32_t t = a; - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_F2I; - D_EXEC(qemu_log("F2I a=%f t=%d, r=%08x\n", a, t, r)); - } break; - case OP_I2F: - { - int32_t a = REINTERPRET_CAST(int32_t, s->gp_regs[reg_a]); - float t = a; - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_I2F; - D_EXEC(qemu_log("I2F a=%08x t=%f, r=%08x\n", a, t, r)); - } break; - case OP_VECTOUT: - { - uint32_t a = cpu_to_be32(s->gp_regs[reg_a]); - uint32_t b = cpu_to_be32(s->gp_regs[reg_b]); - hwaddr dma_ptr = - get_dma_address(s->regs[R_MESHBASE], - s->gp_regs[GPR_X], s->gp_regs[GPR_Y]); - cpu_physical_memory_write(dma_ptr, &a, 4); - cpu_physical_memory_write(dma_ptr + 4, &b, 4); - s->regs[R_LASTDMA] = dma_ptr + 4; - D_EXEC(qemu_log("VECTOUT a=%08x b=%08x dma=%08x\n", a, b, dma_ptr)); - trace_milkymist_pfpu_vectout(a, b, dma_ptr); - } break; - case OP_SIN: - { - int32_t a = REINTERPRET_CAST(int32_t, s->gp_regs[reg_a]); - float t = sinf(a * (1.0f / (M_PI * 4096.0f))); - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_SIN; - D_EXEC(qemu_log("SIN a=%d t=%f, r=%08x\n", a, t, r)); - } break; - case OP_COS: - { - int32_t a = REINTERPRET_CAST(int32_t, s->gp_regs[reg_a]); - float t = cosf(a * (1.0f / (M_PI * 4096.0f))); - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_COS; - D_EXEC(qemu_log("COS a=%d t=%f, r=%08x\n", a, t, r)); - } break; - case OP_ABOVE: - { - float a = REINTERPRET_CAST(float, s->gp_regs[reg_a]); - float b = REINTERPRET_CAST(float, s->gp_regs[reg_b]); - float t = (a > b) ? 1.0f : 0.0f; - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_ABOVE; - D_EXEC(qemu_log("ABOVE a=%f b=%f t=%f, r=%08x\n", a, b, t, r)); - } break; - case OP_EQUAL: - { - float a = REINTERPRET_CAST(float, s->gp_regs[reg_a]); - float b = REINTERPRET_CAST(float, s->gp_regs[reg_b]); - float t = (a == b) ? 1.0f : 0.0f; - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_EQUAL; - D_EXEC(qemu_log("EQUAL a=%f b=%f t=%f, r=%08x\n", a, b, t, r)); - } break; - case OP_COPY: - { - r = s->gp_regs[reg_a]; - latency = LATENCY_COPY; - D_EXEC(qemu_log("COPY")); - } break; - case OP_IF: - { - float a = REINTERPRET_CAST(float, s->gp_regs[reg_a]); - float b = REINTERPRET_CAST(float, s->gp_regs[reg_b]); - uint32_t f = s->gp_regs[GPR_FLAGS]; - float t = (f != 0) ? a : b; - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_IF; - D_EXEC(qemu_log("IF f=%u a=%f b=%f t=%f, r=%08x\n", f, a, b, t, r)); - } break; - case OP_TSIGN: - { - float a = REINTERPRET_CAST(float, s->gp_regs[reg_a]); - float b = REINTERPRET_CAST(float, s->gp_regs[reg_b]); - float t = (b < 0) ? -a : a; - r = REINTERPRET_CAST(uint32_t, t); - latency = LATENCY_TSIGN; - D_EXEC(qemu_log("TSIGN a=%f b=%f t=%f, r=%08x\n", a, b, t, r)); - } break; - case OP_QUAKE: - { - uint32_t a = s->gp_regs[reg_a]; - r = 0x5f3759df - (a >> 1); - latency = LATENCY_QUAKE; - D_EXEC(qemu_log("QUAKE a=%d r=%08x\n", a, r)); - } break; - - default: - error_report("milkymist_pfpu: unknown opcode %d", op); - break; - } - - if (!reg_d) { - D_EXEC(qemu_log("%04d %8s R%03d, R%03d \n", - s->regs[R_PC], opcode_to_str[op], reg_a, reg_b, latency, - s->regs[R_PC] + latency)); - } else { - D_EXEC(qemu_log("%04d %8s R%03d, R%03d -> R%03d\n", - s->regs[R_PC], opcode_to_str[op], reg_a, reg_b, latency, - s->regs[R_PC] + latency, reg_d)); - } - - if (op == OP_VECTOUT) { - return 0; - } - - /* store output for this cycle */ - if (reg_d) { - uint32_t val = output_queue_remove(s); - D_EXEC(qemu_log("R%03d <- 0x%08x\n", reg_d, val)); - s->gp_regs[reg_d] = val; - } - - output_queue_advance(s); - - /* store op output */ - if (op != OP_NOP) { - output_queue_insert(s, r, latency-1); - } - - /* advance PC */ - s->regs[R_PC]++; - - return 1; -}; - -static void pfpu_start(MilkymistPFPUState *s) -{ - int x, y; - int i; - - for (y = 0; y <= s->regs[R_VMESHLAST]; y++) { - for (x = 0; x <= s->regs[R_HMESHLAST]; x++) { - D_EXEC(qemu_log("\nprocessing x=%d y=%d\n", x, y)); - - /* set current position */ - s->gp_regs[GPR_X] = x; - s->gp_regs[GPR_Y] = y; - - /* run microcode on this position */ - i = 0; - while (pfpu_decode_insn(s)) { - /* decode at most MICROCODE_WORDS instructions */ - if (++i >= MICROCODE_WORDS) { - error_report("milkymist_pfpu: too many instructions " - "executed in microcode. No VECTOUT?"); - break; - } - } - - /* reset pc for next run */ - s->regs[R_PC] = 0; - } - } - - s->regs[R_VERTICES] = x * y; - - trace_milkymist_pfpu_pulse_irq(); - qemu_irq_pulse(s->irq); -} - -static inline int get_microcode_address(MilkymistPFPUState *s, uint32_t addr) -{ - return (512 * s->regs[R_CODEPAGE]) + addr - MICROCODE_BEGIN; -} - -static uint64_t pfpu_read(void *opaque, hwaddr addr, - unsigned size) -{ - MilkymistPFPUState *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_CTL: - case R_MESHBASE: - case R_HMESHLAST: - case R_VMESHLAST: - case R_CODEPAGE: - case R_VERTICES: - case R_COLLISIONS: - case R_STRAYWRITES: - case R_LASTDMA: - case R_PC: - case R_DREGBASE: - case R_CODEBASE: - r = s->regs[addr]; - break; - case GPR_BEGIN ... GPR_END: - r = s->gp_regs[addr - GPR_BEGIN]; - break; - case MICROCODE_BEGIN ... MICROCODE_END: - r = s->microcode[get_microcode_address(s, addr)]; - break; - - default: - error_report("milkymist_pfpu: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - trace_milkymist_pfpu_memory_read(addr << 2, r); - - return r; -} - -static void pfpu_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - MilkymistPFPUState *s = opaque; - - trace_milkymist_pfpu_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_CTL: - if (value & CTL_START_BUSY) { - pfpu_start(s); - } - break; - case R_MESHBASE: - case R_HMESHLAST: - case R_VMESHLAST: - case R_CODEPAGE: - case R_VERTICES: - case R_COLLISIONS: - case R_STRAYWRITES: - case R_LASTDMA: - case R_PC: - case R_DREGBASE: - case R_CODEBASE: - s->regs[addr] = value; - break; - case GPR_BEGIN ... GPR_END: - s->gp_regs[addr - GPR_BEGIN] = value; - break; - case MICROCODE_BEGIN ... MICROCODE_END: - s->microcode[get_microcode_address(s, addr)] = value; - break; - - default: - error_report("milkymist_pfpu: write access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } -} - -static const MemoryRegionOps pfpu_mmio_ops = { - .read = pfpu_read, - .write = pfpu_write, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void milkymist_pfpu_reset(DeviceState *d) -{ - MilkymistPFPUState *s = MILKYMIST_PFPU(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } - for (i = 0; i < 128; i++) { - s->gp_regs[i] = 0; - } - for (i = 0; i < MICROCODE_WORDS; i++) { - s->microcode[i] = 0; - } - s->output_queue_pos = 0; - for (i = 0; i < MAX_LATENCY; i++) { - s->output_queue[i] = 0; - } -} - -static void milkymist_pfpu_realize(DeviceState *dev, Error **errp) -{ - MilkymistPFPUState *s = MILKYMIST_PFPU(dev); - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - - sysbus_init_irq(sbd, &s->irq); - - memory_region_init_io(&s->regs_region, OBJECT(dev), &pfpu_mmio_ops, s, - "milkymist-pfpu", MICROCODE_END * 4); - sysbus_init_mmio(sbd, &s->regs_region); -} - -static const VMStateDescription vmstate_milkymist_pfpu = { - .name = "milkymist-pfpu", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, MilkymistPFPUState, R_MAX), - VMSTATE_UINT32_ARRAY(gp_regs, MilkymistPFPUState, 128), - VMSTATE_UINT32_ARRAY(microcode, MilkymistPFPUState, MICROCODE_WORDS), - VMSTATE_INT32(output_queue_pos, MilkymistPFPUState), - VMSTATE_UINT32_ARRAY(output_queue, MilkymistPFPUState, MAX_LATENCY), - VMSTATE_END_OF_LIST() - } -}; - -static void milkymist_pfpu_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = milkymist_pfpu_realize; - dc->reset = milkymist_pfpu_reset; - dc->vmsd = &vmstate_milkymist_pfpu; -} - -static const TypeInfo milkymist_pfpu_info = { - .name = TYPE_MILKYMIST_PFPU, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(MilkymistPFPUState), - .class_init = milkymist_pfpu_class_init, -}; - -static void milkymist_pfpu_register_types(void) -{ - type_register_static(&milkymist_pfpu_info); -} - -type_init(milkymist_pfpu_register_types) diff --git a/hw/misc/mips_itu.c b/hw/misc/mips_itu.c index 133399598f..80683fed31 100644 --- a/hw/misc/mips_itu.c +++ b/hw/misc/mips_itu.c @@ -22,7 +22,6 @@ #include "qemu/log.h" #include "qemu/module.h" #include "qapi/error.h" -#include "cpu.h" #include "exec/exec-all.h" #include "hw/misc/mips_itu.h" #include "hw/qdev-properties.h" diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c index c56aca86ad..b3b42a792c 100644 --- a/hw/misc/mps2-scc.c +++ b/hw/misc/mps2-scc.c @@ -23,6 +23,7 @@ #include "qemu/bitops.h" #include "trace.h" #include "hw/sysbus.h" +#include "hw/irq.h" #include "migration/vmstate.h" #include "hw/registerfields.h" #include "hw/misc/mps2-scc.h" @@ -186,10 +187,13 @@ static void mps2_scc_write(void *opaque, hwaddr offset, uint64_t value, switch (offset) { case A_CFG0: /* - * TODO on some boards bit 0 controls RAM remapping; - * on others bit 1 is CPU_WAIT. + * On some boards bit 0 controls board-specific remapping; + * we always reflect bit 0 in the 'remap' GPIO output line, + * and let the board wire it up or not as it chooses. + * TODO on some boards bit 1 is CPU_WAIT. */ s->cfg0 = value; + qemu_set_irq(s->remap, s->cfg0 & 1); break; case A_CFG1: s->cfg1 = value; @@ -283,7 +287,7 @@ static void mps2_scc_reset(DeviceState *dev) int i; trace_mps2_scc_reset(); - s->cfg0 = 0; + s->cfg0 = s->cfg0_reset; s->cfg1 = 0; s->cfg2 = 0; s->cfg5 = 0; @@ -308,6 +312,7 @@ static void mps2_scc_init(Object *obj) memory_region_init_io(&s->iomem, obj, &mps2_scc_ops, s, "mps2-scc", 0x1000); sysbus_init_mmio(sbd, &s->iomem); + qdev_init_gpio_out_named(DEVICE(obj), &s->remap, "remap", 1); } static void mps2_scc_realize(DeviceState *dev, Error **errp) @@ -353,6 +358,8 @@ static Property mps2_scc_properties[] = { DEFINE_PROP_UINT32("scc-cfg4", MPS2SCC, cfg4, 0), DEFINE_PROP_UINT32("scc-aid", MPS2SCC, aid, 0), DEFINE_PROP_UINT32("scc-id", MPS2SCC, id, 0), + /* Reset value for CFG0 register */ + DEFINE_PROP_UINT32("scc-cfg0", MPS2SCC, cfg0_reset, 0), /* * These are the initial settings for the source clocks on the board. * In hardware they can be configured via a config file read by the diff --git a/hw/misc/mst_fpga.c b/hw/misc/mst_fpga.c index edfc35d5f0..2aaadfa966 100644 --- a/hw/misc/mst_fpga.c +++ b/hw/misc/mst_fpga.c @@ -222,7 +222,7 @@ static void mst_fpga_init(Object *obj) sysbus_init_mmio(sbd, &s->iomem); } -static VMStateDescription vmstate_mst_fpga_regs = { +static const VMStateDescription vmstate_mst_fpga_regs = { .name = "mainstone_fpga", .version_id = 0, .minimum_version_id = 0, diff --git a/hw/misc/npcm7xx_clk.c b/hw/misc/npcm7xx_clk.c index a1ee67dc9a..0b61070c52 100644 --- a/hw/misc/npcm7xx_clk.c +++ b/hw/misc/npcm7xx_clk.c @@ -35,7 +35,7 @@ #define NPCM7XX_CLOCK_REF_HZ (25000000) /* Register Field Definitions */ -#define NPCM7XX_CLK_WDRCR_CA9C BIT(0) /* Cortex A9 Cores */ +#define NPCM7XX_CLK_WDRCR_CA9C BIT(0) /* Cortex-A9 Cores */ #define PLLCON_LOKI BIT(31) #define PLLCON_LOKS BIT(30) diff --git a/hw/misc/puv3_pm.c b/hw/misc/puv3_pm.c deleted file mode 100644 index 676c23f7db..0000000000 --- a/hw/misc/puv3_pm.c +++ /dev/null @@ -1,159 +0,0 @@ -/* - * Power Management device simulation in PKUnity SoC - * - * Copyright (C) 2010-2012 Guan Xuetao - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation, or any later version. - * See the COPYING file in the top-level directory. - */ - -#include "qemu/osdep.h" -#include "hw/sysbus.h" -#include "qom/object.h" - -#undef DEBUG_PUV3 -#include "hw/unicore32/puv3.h" -#include "qemu/module.h" -#include "qemu/log.h" - -#define TYPE_PUV3_PM "puv3_pm" -OBJECT_DECLARE_SIMPLE_TYPE(PUV3PMState, PUV3_PM) - -struct PUV3PMState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - - uint32_t reg_PMCR; - uint32_t reg_PCGR; - uint32_t reg_PLL_SYS_CFG; - uint32_t reg_PLL_DDR_CFG; - uint32_t reg_PLL_VGA_CFG; - uint32_t reg_DIVCFG; -}; - -static uint64_t puv3_pm_read(void *opaque, hwaddr offset, - unsigned size) -{ - PUV3PMState *s = opaque; - uint32_t ret = 0; - - switch (offset) { - case 0x14: - ret = s->reg_PCGR; - break; - case 0x18: - ret = s->reg_PLL_SYS_CFG; - break; - case 0x1c: - ret = s->reg_PLL_DDR_CFG; - break; - case 0x20: - ret = s->reg_PLL_VGA_CFG; - break; - case 0x24: - ret = s->reg_DIVCFG; - break; - case 0x28: /* PLL SYS STATUS */ - ret = 0x00002401; - break; - case 0x2c: /* PLL DDR STATUS */ - ret = 0x00100c00; - break; - case 0x30: /* PLL VGA STATUS */ - ret = 0x00003801; - break; - case 0x34: /* DIV STATUS */ - ret = 0x22f52015; - break; - case 0x38: /* SW RESET */ - ret = 0x0; - break; - case 0x44: /* PLL DFC DONE */ - ret = 0x7; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } - DPRINTF("offset 0x%x, value 0x%x\n", offset, ret); - - return ret; -} - -static void puv3_pm_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PUV3PMState *s = opaque; - - switch (offset) { - case 0x0: - s->reg_PMCR = value; - break; - case 0x14: - s->reg_PCGR = value; - break; - case 0x18: - s->reg_PLL_SYS_CFG = value; - break; - case 0x1c: - s->reg_PLL_DDR_CFG = value; - break; - case 0x20: - s->reg_PLL_VGA_CFG = value; - break; - case 0x24: - case 0x38: - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } - DPRINTF("offset 0x%x, value 0x%x\n", offset, value); -} - -static const MemoryRegionOps puv3_pm_ops = { - .read = puv3_pm_read, - .write = puv3_pm_write, - .impl = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void puv3_pm_realize(DeviceState *dev, Error **errp) -{ - PUV3PMState *s = PUV3_PM(dev); - - s->reg_PCGR = 0x0; - - memory_region_init_io(&s->iomem, OBJECT(s), &puv3_pm_ops, s, "puv3_pm", - PUV3_REGS_OFFSET); - sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); -} - -static void puv3_pm_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = puv3_pm_realize; -} - -static const TypeInfo puv3_pm_info = { - .name = TYPE_PUV3_PM, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PUV3PMState), - .class_init = puv3_pm_class_init, -}; - -static void puv3_pm_register_type(void) -{ - type_register_static(&puv3_pm_info); -} - -type_init(puv3_pm_register_type) diff --git a/hw/misc/pvpanic-isa.c b/hw/misc/pvpanic-isa.c index 27113abd6c..7b66d58acc 100644 --- a/hw/misc/pvpanic-isa.c +++ b/hw/misc/pvpanic-isa.c @@ -13,7 +13,6 @@ */ #include "qemu/osdep.h" -#include "qemu/log.h" #include "qemu/module.h" #include "sysemu/runstate.h" diff --git a/hw/misc/pvpanic-pci.c b/hw/misc/pvpanic-pci.c index d629639d8f..af8cbe2830 100644 --- a/hw/misc/pvpanic-pci.c +++ b/hw/misc/pvpanic-pci.c @@ -12,7 +12,6 @@ */ #include "qemu/osdep.h" -#include "qemu/log.h" #include "qemu/module.h" #include "sysemu/runstate.h" diff --git a/hw/misc/sifive_e_prci.c b/hw/misc/sifive_e_prci.c index 8ec4ee4b41..a8702c6a5d 100644 --- a/hw/misc/sifive_e_prci.c +++ b/hw/misc/sifive_e_prci.c @@ -23,7 +23,6 @@ #include "qapi/error.h" #include "qemu/log.h" #include "qemu/module.h" -#include "hw/hw.h" #include "hw/misc/sifive_e_prci.h" static uint64_t sifive_e_prci_read(void *opaque, hwaddr addr, unsigned int size) diff --git a/hw/misc/sifive_test.c b/hw/misc/sifive_test.c index 2deb2072cc..56df45bfe5 100644 --- a/hw/misc/sifive_test.c +++ b/hw/misc/sifive_test.c @@ -24,7 +24,6 @@ #include "qemu/log.h" #include "qemu/module.h" #include "sysemu/runstate.h" -#include "hw/hw.h" #include "hw/misc/sifive_test.h" static uint64_t sifive_test_read(void *opaque, hwaddr addr, unsigned int size) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index d0a89eb059..ede413965b 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # allwinner-cpucfg.c allwinner_cpucfg_cpu_reset(uint8_t cpu_id, uint32_t reset_addr) "id %u, reset_addr 0x%" PRIu32 @@ -67,16 +67,6 @@ slavio_sysctrl_mem_readl(uint32_t ret) "Read system control 0x%08x" slavio_led_mem_writew(uint32_t val) "Write diagnostic LED 0x%04x" slavio_led_mem_readw(uint32_t ret) "Read diagnostic LED 0x%04x" -# milkymist-hpdmc.c -milkymist_hpdmc_memory_read(uint32_t addr, uint32_t value) "addr=0x%08x value=0x%08x" -milkymist_hpdmc_memory_write(uint32_t addr, uint32_t value) "addr=0x%08x value=0x%08x" - -# milkymist-pfpu.c -milkymist_pfpu_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_pfpu_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_pfpu_vectout(uint32_t a, uint32_t b, uint32_t dma_ptr) "a 0x%08x b 0x%08x dma_ptr 0x%08x" -milkymist_pfpu_pulse_irq(void) "Pulse IRQ" - # aspeed_scu.c aspeed_scu_write(uint64_t offset, unsigned size, uint32_t data) "To 0x%" PRIx64 " of size %u: 0x%" PRIx32 diff --git a/hw/misc/virt_ctrl.c b/hw/misc/virt_ctrl.c index 2ea01bd7a1..3552d7a09a 100644 --- a/hw/misc/virt_ctrl.c +++ b/hw/misc/virt_ctrl.c @@ -5,7 +5,6 @@ */ #include "qemu/osdep.h" -#include "hw/irq.h" #include "hw/qdev-properties.h" #include "hw/sysbus.h" #include "migration/vmstate.h" diff --git a/hw/moxie/Kconfig b/hw/moxie/Kconfig deleted file mode 100644 index 3793ef0372..0000000000 --- a/hw/moxie/Kconfig +++ /dev/null @@ -1,3 +0,0 @@ -config MOXIESIM - bool - select SERIAL diff --git a/hw/moxie/meson.build b/hw/moxie/meson.build deleted file mode 100644 index 05a7c2e00f..0000000000 --- a/hw/moxie/meson.build +++ /dev/null @@ -1,4 +0,0 @@ -moxie_ss = ss.source_set() -moxie_ss.add(when: 'CONFIG_MOXIESIM', if_true: files('moxiesim.c')) - -hw_arch += {'moxie': moxie_ss} diff --git a/hw/moxie/moxiesim.c b/hw/moxie/moxiesim.c deleted file mode 100644 index f7b57fcae1..0000000000 --- a/hw/moxie/moxiesim.c +++ /dev/null @@ -1,157 +0,0 @@ -/* - * QEMU/moxiesim emulation - * - * Emulates a very simple machine model similar to the one used by the - * GDB moxie simulator. - * - * Copyright (c) 2008, 2009, 2010, 2013 Anthony Green - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to deal - * in the Software without restriction, including without limitation the rights - * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell - * copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN - * THE SOFTWARE. - */ - -#include "qemu/osdep.h" -#include "qemu/error-report.h" -#include "qapi/error.h" -#include "cpu.h" -#include "hw/sysbus.h" -#include "net/net.h" -#include "sysemu/reset.h" -#include "sysemu/sysemu.h" -#include "hw/boards.h" -#include "hw/loader.h" -#include "hw/char/serial.h" -#include "exec/address-spaces.h" -#include "elf.h" - -#define PHYS_MEM_BASE 0x80000000 -#define FIRMWARE_BASE 0x1000 -#define FIRMWARE_SIZE (128 * 0x1000) - -typedef struct { - uint64_t ram_size; - const char *kernel_filename; - const char *kernel_cmdline; - const char *initrd_filename; -} LoaderParams; - -static void load_kernel(MoxieCPU *cpu, LoaderParams *loader_params) -{ - uint64_t entry, kernel_high; - int64_t initrd_size; - long kernel_size; - ram_addr_t initrd_offset; - - kernel_size = load_elf(loader_params->kernel_filename, NULL, NULL, NULL, - &entry, NULL, &kernel_high, NULL, 1, EM_MOXIE, - 0, 0); - - if (kernel_size <= 0) { - error_report("could not load kernel '%s'", - loader_params->kernel_filename); - exit(1); - } - - /* load initrd */ - initrd_size = 0; - initrd_offset = 0; - if (loader_params->initrd_filename) { - initrd_size = get_image_size(loader_params->initrd_filename); - if (initrd_size > 0) { - initrd_offset = (kernel_high + ~TARGET_PAGE_MASK) - & TARGET_PAGE_MASK; - if (initrd_offset + initrd_size > loader_params->ram_size) { - error_report("memory too small for initial ram disk '%s'", - loader_params->initrd_filename); - exit(1); - } - initrd_size = load_image_targphys(loader_params->initrd_filename, - initrd_offset, - loader_params->ram_size); - } - if (initrd_size == (target_ulong)-1) { - error_report("could not load initial ram disk '%s'", - loader_params->initrd_filename); - exit(1); - } - } -} - -static void main_cpu_reset(void *opaque) -{ - MoxieCPU *cpu = opaque; - - cpu_reset(CPU(cpu)); -} - -static void moxiesim_init(MachineState *machine) -{ - MoxieCPU *cpu = NULL; - ram_addr_t ram_size = machine->ram_size; - const char *kernel_filename = machine->kernel_filename; - const char *kernel_cmdline = machine->kernel_cmdline; - const char *initrd_filename = machine->initrd_filename; - CPUMoxieState *env; - MemoryRegion *address_space_mem = get_system_memory(); - MemoryRegion *ram = g_new(MemoryRegion, 1); - MemoryRegion *rom = g_new(MemoryRegion, 1); - hwaddr ram_base = 0x200000; - LoaderParams loader_params; - - /* Init CPUs. */ - cpu = MOXIE_CPU(cpu_create(machine->cpu_type)); - env = &cpu->env; - - qemu_register_reset(main_cpu_reset, cpu); - - /* Allocate RAM. */ - memory_region_init_ram(ram, NULL, "moxiesim.ram", ram_size, &error_fatal); - memory_region_add_subregion(address_space_mem, ram_base, ram); - - memory_region_init_ram(rom, NULL, "moxie.rom", FIRMWARE_SIZE, &error_fatal); - memory_region_add_subregion(get_system_memory(), FIRMWARE_BASE, rom); - - if (kernel_filename) { - loader_params.ram_size = ram_size; - loader_params.kernel_filename = kernel_filename; - loader_params.kernel_cmdline = kernel_cmdline; - loader_params.initrd_filename = initrd_filename; - load_kernel(cpu, &loader_params); - } - if (machine->firmware) { - if (load_image_targphys(machine->firmware, FIRMWARE_BASE, FIRMWARE_SIZE) < 0) { - error_report("Failed to load firmware '%s'", machine->firmware); - } - } - - /* A single 16450 sits at offset 0x3f8. */ - if (serial_hd(0)) { - serial_mm_init(address_space_mem, 0x3f8, 0, env->irq[4], - 8000000/16, serial_hd(0), DEVICE_LITTLE_ENDIAN); - } -} - -static void moxiesim_machine_init(MachineClass *mc) -{ - mc->desc = "Moxie simulator platform"; - mc->init = moxiesim_init; - mc->is_default = true; - mc->default_cpu_type = MOXIE_CPU_TYPE_NAME("MoxieLite"); -} - -DEFINE_MACHINE("moxiesim", moxiesim_machine_init) diff --git a/hw/net/can/can_sja1000.c b/hw/net/can/can_sja1000.c index 42d2f99dfb..34eea684ce 100644 --- a/hw/net/can/can_sja1000.c +++ b/hw/net/can/can_sja1000.c @@ -275,6 +275,10 @@ static void buff2frame_pel(const uint8_t *buff, qemu_can_frame *frame) } frame->can_dlc = buff[0] & 0x0f; + if (frame->can_dlc > 8) { + frame->can_dlc = 8; + } + if (buff[0] & 0x80) { /* Extended */ frame->can_id |= QEMU_CAN_EFF_FLAG; frame->can_id |= buff[1] << 21; /* ID.28~ID.21 */ @@ -311,6 +315,10 @@ static void buff2frame_bas(const uint8_t *buff, qemu_can_frame *frame) } frame->can_dlc = buff[1] & 0x0f; + if (frame->can_dlc > 8) { + frame->can_dlc = 8; + } + for (i = 0; i < frame->can_dlc; i++) { frame->data[i] = buff[2 + i]; } diff --git a/hw/net/can/xlnx-zynqmp-can.c b/hw/net/can/xlnx-zynqmp-can.c index affa21a5ed..22bb8910fa 100644 --- a/hw/net/can/xlnx-zynqmp-can.c +++ b/hw/net/can/xlnx-zynqmp-can.c @@ -37,7 +37,6 @@ #include "qemu/bitops.h" #include "qemu/log.h" #include "qemu/cutils.h" -#include "sysemu/sysemu.h" #include "migration/vmstate.h" #include "hw/qdev-properties.h" #include "net/can_emu.h" diff --git a/hw/net/dp8393x.c b/hw/net/dp8393x.c index 533a8304d0..45b954e46c 100644 --- a/hw/net/dp8393x.c +++ b/hw/net/dp8393x.c @@ -28,15 +28,9 @@ #include "qemu/timer.h" #include #include "qom/object.h" +#include "trace.h" -//#define DEBUG_SONIC - -#define SONIC_PROM_SIZE 0x1000 - -#ifdef DEBUG_SONIC -#define DPRINTF(fmt, ...) \ -do { printf("sonic: " fmt , ## __VA_ARGS__); } while (0) -static const char* reg_names[] = { +static const char *reg_names[] = { "CR", "DCR", "RCR", "TCR", "IMR", "ISR", "UTDA", "CTDA", "TPS", "TFC", "TSA0", "TSA1", "TFS", "URDA", "CRDA", "CRBA0", "CRBA1", "RBWC0", "RBWC1", "EOBC", "URRA", "RSA", "REA", "RRP", @@ -45,12 +39,6 @@ static const char* reg_names[] = { "SR", "WT0", "WT1", "RSC", "CRCT", "FAET", "MPT", "MDT", "0x30", "0x31", "0x32", "0x33", "0x34", "0x35", "0x36", "0x37", "0x38", "0x39", "0x3a", "0x3b", "0x3c", "0x3d", "0x3e", "DCR2" }; -#else -#define DPRINTF(fmt, ...) do {} while (0) -#endif - -#define SONIC_ERROR(fmt, ...) \ -do { printf("sonic ERROR: %s: " fmt, __func__ , ## __VA_ARGS__); } while (0) #define SONIC_CR 0x00 #define SONIC_DCR 0x01 @@ -97,6 +85,7 @@ do { printf("sonic ERROR: %s: " fmt, __func__ , ## __VA_ARGS__); } while (0) #define SONIC_MPT 0x2e #define SONIC_MDT 0x2f #define SONIC_DCR2 0x3f +#define SONIC_REG_COUNT 0x40 #define SONIC_CR_HTX 0x0001 #define SONIC_CR_TXP 0x0002 @@ -161,23 +150,19 @@ struct dp8393xState { bool big_endian; bool last_rba_is_full; qemu_irq irq; -#ifdef DEBUG_SONIC int irq_level; -#endif QEMUTimer *watchdog; int64_t wt_last_update; NICConf conf; NICState *nic; MemoryRegion mmio; - MemoryRegion prom; /* Registers */ - uint8_t cam[16][6]; - uint16_t regs[0x40]; + uint16_t cam[16][3]; + uint16_t regs[SONIC_REG_COUNT]; /* Temporaries */ uint8_t tx_buffer[0x10000]; - uint16_t data[12]; int loopback_packet; /* Memory access */ @@ -185,7 +170,8 @@ struct dp8393xState { AddressSpace as; }; -/* Accessor functions for values which are formed by +/* + * Accessor functions for values which are formed by * concatenating two 16 bit device registers. By putting these * in their own functions with a uint32_t return type we avoid the * pitfall of implicit sign extension where ((x << 16) | y) is a @@ -233,34 +219,48 @@ static uint32_t dp8393x_wt(dp8393xState *s) return s->regs[SONIC_WT1] << 16 | s->regs[SONIC_WT0]; } -static uint16_t dp8393x_get(dp8393xState *s, int width, int offset) +static uint16_t dp8393x_get(dp8393xState *s, hwaddr addr, int offset) { + const MemTxAttrs attrs = MEMTXATTRS_UNSPECIFIED; uint16_t val; - if (s->big_endian) { - val = be16_to_cpu(s->data[offset * width + width - 1]); + if (s->regs[SONIC_DCR] & SONIC_DCR_DW) { + addr += offset << 2; + if (s->big_endian) { + val = address_space_ldl_be(&s->as, addr, attrs, NULL); + } else { + val = address_space_ldl_le(&s->as, addr, attrs, NULL); + } } else { - val = le16_to_cpu(s->data[offset * width]); + addr += offset << 1; + if (s->big_endian) { + val = address_space_lduw_be(&s->as, addr, attrs, NULL); + } else { + val = address_space_lduw_le(&s->as, addr, attrs, NULL); + } } + return val; } -static void dp8393x_put(dp8393xState *s, int width, int offset, - uint16_t val) +static void dp8393x_put(dp8393xState *s, + hwaddr addr, int offset, uint16_t val) { - if (s->big_endian) { - if (width == 2) { - s->data[offset * 2] = 0; - s->data[offset * 2 + 1] = cpu_to_be16(val); + const MemTxAttrs attrs = MEMTXATTRS_UNSPECIFIED; + + if (s->regs[SONIC_DCR] & SONIC_DCR_DW) { + addr += offset << 2; + if (s->big_endian) { + address_space_stl_be(&s->as, addr, val, attrs, NULL); } else { - s->data[offset] = cpu_to_be16(val); + address_space_stl_le(&s->as, addr, val, attrs, NULL); } } else { - if (width == 2) { - s->data[offset * 2] = cpu_to_le16(val); - s->data[offset * 2 + 1] = 0; + addr += offset << 1; + if (s->big_endian) { + address_space_stw_be(&s->as, addr, val, attrs, NULL); } else { - s->data[offset] = cpu_to_le16(val); + address_space_stw_le(&s->as, addr, val, attrs, NULL); } } } @@ -269,16 +269,14 @@ static void dp8393x_update_irq(dp8393xState *s) { int level = (s->regs[SONIC_IMR] & s->regs[SONIC_ISR]) ? 1 : 0; -#ifdef DEBUG_SONIC if (level != s->irq_level) { s->irq_level = level; if (level) { - DPRINTF("raise irq, isr is 0x%04x\n", s->regs[SONIC_ISR]); + trace_dp8393x_raise_irq(s->regs[SONIC_ISR]); } else { - DPRINTF("lower irq\n"); + trace_dp8393x_lower_irq(); } } -#endif qemu_set_irq(s->irq, level); } @@ -286,35 +284,29 @@ static void dp8393x_update_irq(dp8393xState *s) static void dp8393x_do_load_cam(dp8393xState *s) { int width, size; - uint16_t index = 0; + uint16_t index; width = (s->regs[SONIC_DCR] & SONIC_DCR_DW) ? 2 : 1; size = sizeof(uint16_t) * 4 * width; while (s->regs[SONIC_CDC] & 0x1f) { /* Fill current entry */ - address_space_read(&s->as, dp8393x_cdp(s), - MEMTXATTRS_UNSPECIFIED, s->data, size); - s->cam[index][0] = dp8393x_get(s, width, 1) & 0xff; - s->cam[index][1] = dp8393x_get(s, width, 1) >> 8; - s->cam[index][2] = dp8393x_get(s, width, 2) & 0xff; - s->cam[index][3] = dp8393x_get(s, width, 2) >> 8; - s->cam[index][4] = dp8393x_get(s, width, 3) & 0xff; - s->cam[index][5] = dp8393x_get(s, width, 3) >> 8; - DPRINTF("load cam[%d] with %02x%02x%02x%02x%02x%02x\n", index, - s->cam[index][0], s->cam[index][1], s->cam[index][2], - s->cam[index][3], s->cam[index][4], s->cam[index][5]); + index = dp8393x_get(s, dp8393x_cdp(s), 0) & 0xf; + s->cam[index][0] = dp8393x_get(s, dp8393x_cdp(s), 1); + s->cam[index][1] = dp8393x_get(s, dp8393x_cdp(s), 2); + s->cam[index][2] = dp8393x_get(s, dp8393x_cdp(s), 3); + trace_dp8393x_load_cam(index, + s->cam[index][0] >> 8, s->cam[index][0] & 0xff, + s->cam[index][1] >> 8, s->cam[index][1] & 0xff, + s->cam[index][2] >> 8, s->cam[index][2] & 0xff); /* Move to next entry */ s->regs[SONIC_CDC]--; s->regs[SONIC_CDP] += size; - index++; } /* Read CAM enable */ - address_space_read(&s->as, dp8393x_cdp(s), - MEMTXATTRS_UNSPECIFIED, s->data, size); - s->regs[SONIC_CE] = dp8393x_get(s, width, 0); - DPRINTF("load cam done. cam enable mask 0x%04x\n", s->regs[SONIC_CE]); + s->regs[SONIC_CE] = dp8393x_get(s, dp8393x_cdp(s), 0); + trace_dp8393x_load_cam_done(s->regs[SONIC_CE]); /* Done */ s->regs[SONIC_CR] &= ~SONIC_CR_LCAM; @@ -329,17 +321,14 @@ static void dp8393x_do_read_rra(dp8393xState *s) /* Read memory */ width = (s->regs[SONIC_DCR] & SONIC_DCR_DW) ? 2 : 1; size = sizeof(uint16_t) * 4 * width; - address_space_read(&s->as, dp8393x_rrp(s), - MEMTXATTRS_UNSPECIFIED, s->data, size); /* Update SONIC registers */ - s->regs[SONIC_CRBA0] = dp8393x_get(s, width, 0); - s->regs[SONIC_CRBA1] = dp8393x_get(s, width, 1); - s->regs[SONIC_RBWC0] = dp8393x_get(s, width, 2); - s->regs[SONIC_RBWC1] = dp8393x_get(s, width, 3); - DPRINTF("CRBA0/1: 0x%04x/0x%04x, RBWC0/1: 0x%04x/0x%04x\n", - s->regs[SONIC_CRBA0], s->regs[SONIC_CRBA1], - s->regs[SONIC_RBWC0], s->regs[SONIC_RBWC1]); + s->regs[SONIC_CRBA0] = dp8393x_get(s, dp8393x_rrp(s), 0); + s->regs[SONIC_CRBA1] = dp8393x_get(s, dp8393x_rrp(s), 1); + s->regs[SONIC_RBWC0] = dp8393x_get(s, dp8393x_rrp(s), 2); + s->regs[SONIC_RBWC1] = dp8393x_get(s, dp8393x_rrp(s), 3); + trace_dp8393x_read_rra_regs(s->regs[SONIC_CRBA0], s->regs[SONIC_CRBA1], + s->regs[SONIC_RBWC0], s->regs[SONIC_RBWC1]); /* Go to next entry */ s->regs[SONIC_RRP] += size; @@ -350,8 +339,7 @@ static void dp8393x_do_read_rra(dp8393xState *s) } /* Warn the host if CRBA now has the last available resource */ - if (s->regs[SONIC_RRP] == s->regs[SONIC_RWP]) - { + if (s->regs[SONIC_RRP] == s->regs[SONIC_RWP]) { s->regs[SONIC_ISR] |= SONIC_ISR_RBE; dp8393x_update_irq(s); } @@ -364,7 +352,8 @@ static void dp8393x_do_software_reset(dp8393xState *s) { timer_del(s->watchdog); - s->regs[SONIC_CR] &= ~(SONIC_CR_LCAM | SONIC_CR_RRRA | SONIC_CR_TXP | SONIC_CR_HTX); + s->regs[SONIC_CR] &= ~(SONIC_CR_LCAM | SONIC_CR_RRRA | SONIC_CR_TXP | + SONIC_CR_HTX); s->regs[SONIC_CR] |= SONIC_CR_RST | SONIC_CR_RXDIS; } @@ -433,28 +422,22 @@ static void dp8393x_do_receiver_disable(dp8393xState *s) static void dp8393x_do_transmit_packets(dp8393xState *s) { NetClientState *nc = qemu_get_queue(s->nic); - int width, size; int tx_len, len; uint16_t i; - width = (s->regs[SONIC_DCR] & SONIC_DCR_DW) ? 2 : 1; - while (1) { /* Read memory */ - size = sizeof(uint16_t) * 6 * width; s->regs[SONIC_TTDA] = s->regs[SONIC_CTDA]; - DPRINTF("Transmit packet at %08x\n", dp8393x_ttda(s)); - address_space_read(&s->as, dp8393x_ttda(s) + sizeof(uint16_t) * width, - MEMTXATTRS_UNSPECIFIED, s->data, size); + trace_dp8393x_transmit_packet(dp8393x_ttda(s)); tx_len = 0; /* Update registers */ - s->regs[SONIC_TCR] = dp8393x_get(s, width, 0) & 0xf000; - s->regs[SONIC_TPS] = dp8393x_get(s, width, 1); - s->regs[SONIC_TFC] = dp8393x_get(s, width, 2); - s->regs[SONIC_TSA0] = dp8393x_get(s, width, 3); - s->regs[SONIC_TSA1] = dp8393x_get(s, width, 4); - s->regs[SONIC_TFS] = dp8393x_get(s, width, 5); + s->regs[SONIC_TCR] = dp8393x_get(s, dp8393x_ttda(s), 1) & 0xf000; + s->regs[SONIC_TPS] = dp8393x_get(s, dp8393x_ttda(s), 2); + s->regs[SONIC_TFC] = dp8393x_get(s, dp8393x_ttda(s), 3); + s->regs[SONIC_TSA0] = dp8393x_get(s, dp8393x_ttda(s), 4); + s->regs[SONIC_TSA1] = dp8393x_get(s, dp8393x_ttda(s), 5); + s->regs[SONIC_TFS] = dp8393x_get(s, dp8393x_ttda(s), 6); /* Handle programmable interrupt */ if (s->regs[SONIC_TCR] & SONIC_TCR_PINT) { @@ -476,27 +459,26 @@ static void dp8393x_do_transmit_packets(dp8393xState *s) i++; if (i != s->regs[SONIC_TFC]) { /* Read next fragment details */ - size = sizeof(uint16_t) * 3 * width; - address_space_read(&s->as, - dp8393x_ttda(s) - + sizeof(uint16_t) * width * (4 + 3 * i), - MEMTXATTRS_UNSPECIFIED, s->data, - size); - s->regs[SONIC_TSA0] = dp8393x_get(s, width, 0); - s->regs[SONIC_TSA1] = dp8393x_get(s, width, 1); - s->regs[SONIC_TFS] = dp8393x_get(s, width, 2); + s->regs[SONIC_TSA0] = dp8393x_get(s, dp8393x_ttda(s), + 4 + 3 * i); + s->regs[SONIC_TSA1] = dp8393x_get(s, dp8393x_ttda(s), + 5 + 3 * i); + s->regs[SONIC_TFS] = dp8393x_get(s, dp8393x_ttda(s), + 6 + 3 * i); } } /* Handle Ethernet checksum */ if (!(s->regs[SONIC_TCR] & SONIC_TCR_CRCI)) { - /* Don't append FCS there, to look like slirp packets - * which don't have one */ + /* + * Don't append FCS there, to look like slirp packets + * which don't have one + */ } else { /* Remove existing FCS */ tx_len -= 4; if (tx_len < 0) { - SONIC_ERROR("tx_len is %d\n", tx_len); + trace_dp8393x_transmit_txlen_error(tx_len); break; } } @@ -515,22 +497,12 @@ static void dp8393x_do_transmit_packets(dp8393xState *s) s->regs[SONIC_TCR] |= SONIC_TCR_PTX; /* Write status */ - dp8393x_put(s, width, 0, - s->regs[SONIC_TCR] & 0x0fff); /* status */ - size = sizeof(uint16_t) * width; - address_space_write(&s->as, dp8393x_ttda(s), - MEMTXATTRS_UNSPECIFIED, s->data, size); + dp8393x_put(s, dp8393x_ttda(s), 0, s->regs[SONIC_TCR] & 0x0fff); if (!(s->regs[SONIC_CR] & SONIC_CR_HTX)) { /* Read footer of packet */ - size = sizeof(uint16_t) * width; - address_space_read(&s->as, - dp8393x_ttda(s) - + sizeof(uint16_t) * width - * (4 + 3 * s->regs[SONIC_TFC]), - MEMTXATTRS_UNSPECIFIED, s->data, - size); - s->regs[SONIC_CTDA] = dp8393x_get(s, width, 0); + s->regs[SONIC_CTDA] = dp8393x_get(s, dp8393x_ttda(s), + 4 + 3 * s->regs[SONIC_TFC]); if (s->regs[SONIC_CTDA] & SONIC_DESC_EOL) { /* EOL detected */ break; @@ -558,26 +530,34 @@ static void dp8393x_do_command(dp8393xState *s, uint16_t command) s->regs[SONIC_CR] |= (command & SONIC_CR_MASK); - if (command & SONIC_CR_HTX) + if (command & SONIC_CR_HTX) { dp8393x_do_halt_transmission(s); - if (command & SONIC_CR_TXP) + } + if (command & SONIC_CR_TXP) { dp8393x_do_transmit_packets(s); - if (command & SONIC_CR_RXDIS) + } + if (command & SONIC_CR_RXDIS) { dp8393x_do_receiver_disable(s); - if (command & SONIC_CR_RXEN) + } + if (command & SONIC_CR_RXEN) { dp8393x_do_receiver_enable(s); - if (command & SONIC_CR_STP) + } + if (command & SONIC_CR_STP) { dp8393x_do_stop_timer(s); - if (command & SONIC_CR_ST) + } + if (command & SONIC_CR_ST) { dp8393x_do_start_timer(s); - if (command & SONIC_CR_RST) + } + if (command & SONIC_CR_RST) { dp8393x_do_software_reset(s); + } if (command & SONIC_CR_RRRA) { dp8393x_do_read_rra(s); s->regs[SONIC_CR] &= ~SONIC_CR_RRRA; } - if (command & SONIC_CR_LCAM) + if (command & SONIC_CR_LCAM) { dp8393x_do_load_cam(s); + } } static uint64_t dp8393x_read(void *opaque, hwaddr addr, unsigned int size) @@ -587,110 +567,108 @@ static uint64_t dp8393x_read(void *opaque, hwaddr addr, unsigned int size) uint16_t val = 0; switch (reg) { - /* Update data before reading it */ - case SONIC_WT0: - case SONIC_WT1: - dp8393x_update_wt_regs(s); - val = s->regs[reg]; - break; - /* Accept read to some registers only when in reset mode */ - case SONIC_CAP2: - case SONIC_CAP1: - case SONIC_CAP0: - if (s->regs[SONIC_CR] & SONIC_CR_RST) { - val = s->cam[s->regs[SONIC_CEP] & 0xf][2* (SONIC_CAP0 - reg) + 1] << 8; - val |= s->cam[s->regs[SONIC_CEP] & 0xf][2* (SONIC_CAP0 - reg)]; - } - break; - /* All other registers have no special contrainst */ - default: - val = s->regs[reg]; + /* Update data before reading it */ + case SONIC_WT0: + case SONIC_WT1: + dp8393x_update_wt_regs(s); + val = s->regs[reg]; + break; + /* Accept read to some registers only when in reset mode */ + case SONIC_CAP2: + case SONIC_CAP1: + case SONIC_CAP0: + if (s->regs[SONIC_CR] & SONIC_CR_RST) { + val = s->cam[s->regs[SONIC_CEP] & 0xf][SONIC_CAP0 - reg]; + } + break; + /* All other registers have no special contraints */ + default: + val = s->regs[reg]; } - DPRINTF("read 0x%04x from reg %s\n", val, reg_names[reg]); + trace_dp8393x_read(reg, reg_names[reg], val, size); - return s->big_endian ? val << 16 : val; + return val; } -static void dp8393x_write(void *opaque, hwaddr addr, uint64_t data, +static void dp8393x_write(void *opaque, hwaddr addr, uint64_t val, unsigned int size) { dp8393xState *s = opaque; int reg = addr >> s->it_shift; - uint32_t val = s->big_endian ? data >> 16 : data; - DPRINTF("write 0x%04x to reg %s\n", (uint16_t)val, reg_names[reg]); + trace_dp8393x_write(reg, reg_names[reg], val, size); switch (reg) { - /* Command register */ - case SONIC_CR: - dp8393x_do_command(s, val); - break; - /* Prevent write to read-only registers */ - case SONIC_CAP2: - case SONIC_CAP1: - case SONIC_CAP0: - case SONIC_SR: - case SONIC_MDT: - DPRINTF("writing to reg %d invalid\n", reg); - break; - /* Accept write to some registers only when in reset mode */ - case SONIC_DCR: - if (s->regs[SONIC_CR] & SONIC_CR_RST) { - s->regs[reg] = val & 0xbfff; - } else { - DPRINTF("writing to DCR invalid\n"); - } - break; - case SONIC_DCR2: - if (s->regs[SONIC_CR] & SONIC_CR_RST) { - s->regs[reg] = val & 0xf017; - } else { - DPRINTF("writing to DCR2 invalid\n"); - } - break; - /* 12 lower bytes are Read Only */ - case SONIC_TCR: - s->regs[reg] = val & 0xf000; - break; - /* 9 lower bytes are Read Only */ - case SONIC_RCR: - s->regs[reg] = val & 0xffe0; - break; - /* Ignore most significant bit */ - case SONIC_IMR: - s->regs[reg] = val & 0x7fff; - dp8393x_update_irq(s); - break; - /* Clear bits by writing 1 to them */ - case SONIC_ISR: - val &= s->regs[reg]; - s->regs[reg] &= ~val; - if (val & SONIC_ISR_RBE) { - dp8393x_do_read_rra(s); - } - dp8393x_update_irq(s); - break; - /* The guest is required to store aligned pointers here */ - case SONIC_RSA: - case SONIC_REA: - case SONIC_RRP: - case SONIC_RWP: - if (s->regs[SONIC_DCR] & SONIC_DCR_DW) { - s->regs[reg] = val & 0xfffc; - } else { - s->regs[reg] = val & 0xfffe; - } - break; - /* Invert written value for some registers */ - case SONIC_CRCT: - case SONIC_FAET: - case SONIC_MPT: - s->regs[reg] = val ^ 0xffff; - break; - /* All other registers have no special contrainst */ - default: - s->regs[reg] = val; + /* Command register */ + case SONIC_CR: + dp8393x_do_command(s, val); + break; + /* Prevent write to read-only registers */ + case SONIC_CAP2: + case SONIC_CAP1: + case SONIC_CAP0: + case SONIC_SR: + case SONIC_MDT: + trace_dp8393x_write_invalid(reg); + break; + /* Accept write to some registers only when in reset mode */ + case SONIC_DCR: + if (s->regs[SONIC_CR] & SONIC_CR_RST) { + s->regs[reg] = val & 0xbfff; + } else { + trace_dp8393x_write_invalid_dcr("DCR"); + } + break; + case SONIC_DCR2: + if (s->regs[SONIC_CR] & SONIC_CR_RST) { + s->regs[reg] = val & 0xf017; + } else { + trace_dp8393x_write_invalid_dcr("DCR2"); + } + break; + /* 12 lower bytes are Read Only */ + case SONIC_TCR: + s->regs[reg] = val & 0xf000; + break; + /* 9 lower bytes are Read Only */ + case SONIC_RCR: + s->regs[reg] = val & 0xffe0; + break; + /* Ignore most significant bit */ + case SONIC_IMR: + s->regs[reg] = val & 0x7fff; + dp8393x_update_irq(s); + break; + /* Clear bits by writing 1 to them */ + case SONIC_ISR: + val &= s->regs[reg]; + s->regs[reg] &= ~val; + if (val & SONIC_ISR_RBE) { + dp8393x_do_read_rra(s); + } + dp8393x_update_irq(s); + break; + /* The guest is required to store aligned pointers here */ + case SONIC_RSA: + case SONIC_REA: + case SONIC_RRP: + case SONIC_RWP: + if (s->regs[SONIC_DCR] & SONIC_DCR_DW) { + s->regs[reg] = val & 0xfffc; + } else { + s->regs[reg] = val & 0xfffe; + } + break; + /* Invert written value for some registers */ + case SONIC_CRCT: + case SONIC_FAET: + case SONIC_MPT: + s->regs[reg] = val ^ 0xffff; + break; + /* All other registers have no special contrainst */ + default: + s->regs[reg] = val; } if (reg == SONIC_WT0 || reg == SONIC_WT1) { @@ -698,11 +676,16 @@ static void dp8393x_write(void *opaque, hwaddr addr, uint64_t data, } } +/* + * Since .impl.max_access_size is effectively controlled by the it_shift + * property, leave it unspecified for now to allow the memory API to + * correctly zero extend the 16-bit register values to the access size up to and + * including it_shift. + */ static const MemoryRegionOps dp8393x_ops = { .read = dp8393x_read, .write = dp8393x_write, - .impl.min_access_size = 4, - .impl.max_access_size = 4, + .impl.min_access_size = 2, .endianness = DEVICE_NATIVE_ENDIAN, }; @@ -747,17 +730,18 @@ static int dp8393x_receive_filter(dp8393xState *s, const uint8_t * buf, } /* Check broadcast */ - if ((s->regs[SONIC_RCR] & SONIC_RCR_BRD) && !memcmp(buf, bcast, sizeof(bcast))) { + if ((s->regs[SONIC_RCR] & SONIC_RCR_BRD) && + !memcmp(buf, bcast, sizeof(bcast))) { return SONIC_RCR_BC; } /* Check CAM */ for (i = 0; i < 16; i++) { if (s->regs[SONIC_CE] & (1 << i)) { - /* Entry enabled */ - if (!memcmp(buf, s->cam[i], sizeof(s->cam[i]))) { - return 0; - } + /* Entry enabled */ + if (!memcmp(buf, s->cam[i], sizeof(s->cam[i]))) { + return 0; + } } } @@ -770,7 +754,7 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, dp8393xState *s = qemu_get_nic_opaque(nc); int packet_type; uint32_t available, address; - int width, rx_len, padded_len; + int rx_len, padded_len; uint32_t checksum; int size; @@ -783,15 +767,13 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, rx_len = pkt_size + sizeof(checksum); if (s->regs[SONIC_DCR] & SONIC_DCR_DW) { - width = 2; padded_len = ((rx_len - 1) | 3) + 1; } else { - width = 1; padded_len = ((rx_len - 1) | 1) + 1; } if (padded_len > dp8393x_rbwc(s) * 2) { - DPRINTF("oversize packet, pkt_size is %d\n", pkt_size); + trace_dp8393x_receive_oversize(pkt_size); s->regs[SONIC_ISR] |= SONIC_ISR_RBAE; dp8393x_update_irq(s); s->regs[SONIC_RCR] |= SONIC_RCR_LPKT; @@ -800,18 +782,14 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, packet_type = dp8393x_receive_filter(s, buf, pkt_size); if (packet_type < 0) { - DPRINTF("packet not for netcard\n"); + trace_dp8393x_receive_not_netcard(); return -1; } /* Check for EOL */ if (s->regs[SONIC_LLFA] & SONIC_DESC_EOL) { /* Are we still in resource exhaustion? */ - size = sizeof(uint16_t) * 1 * width; - address = dp8393x_crda(s) + sizeof(uint16_t) * 5 * width; - address_space_read(&s->as, address, MEMTXATTRS_UNSPECIFIED, - s->data, size); - s->regs[SONIC_LLFA] = dp8393x_get(s, width, 0); + s->regs[SONIC_LLFA] = dp8393x_get(s, dp8393x_crda(s), 5); if (s->regs[SONIC_LLFA] & SONIC_DESC_EOL) { /* Still EOL ; stop reception */ return -1; @@ -819,11 +797,7 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, /* Link has been updated by host */ /* Clear in_use */ - size = sizeof(uint16_t) * width; - address = dp8393x_crda(s) + sizeof(uint16_t) * 6 * width; - dp8393x_put(s, width, 0, 0); - address_space_rw(&s->as, address, MEMTXATTRS_UNSPECIFIED, - (uint8_t *)s->data, size, 1); + dp8393x_put(s, dp8393x_crda(s), 6, 0x0000); /* Move to next descriptor */ s->regs[SONIC_CRDA] = s->regs[SONIC_LLFA]; @@ -838,7 +812,7 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, checksum = cpu_to_le32(crc32(0, buf, pkt_size)); /* Put packet into RBA */ - DPRINTF("Receive packet at %08x\n", dp8393x_crba(s)); + trace_dp8393x_receive_packet(dp8393x_crba(s)); address = dp8393x_crba(s); address_space_write(&s->as, address, MEMTXATTRS_UNSPECIFIED, buf, pkt_size); @@ -852,8 +826,8 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, /* Pad short packets to keep pointers aligned */ if (rx_len < padded_len) { size = padded_len - rx_len; - address_space_rw(&s->as, address, MEMTXATTRS_UNSPECIFIED, - (uint8_t *)"\xFF\xFF\xFF", size, 1); + address_space_write(&s->as, address, MEMTXATTRS_UNSPECIFIED, + "\xFF\xFF\xFF", size); address += size; } @@ -876,33 +850,21 @@ static ssize_t dp8393x_receive(NetClientState *nc, const uint8_t * buf, } /* Write status to memory */ - DPRINTF("Write status at %08x\n", dp8393x_crda(s)); - dp8393x_put(s, width, 0, s->regs[SONIC_RCR]); /* status */ - dp8393x_put(s, width, 1, rx_len); /* byte count */ - dp8393x_put(s, width, 2, s->regs[SONIC_TRBA0]); /* pkt_ptr0 */ - dp8393x_put(s, width, 3, s->regs[SONIC_TRBA1]); /* pkt_ptr1 */ - dp8393x_put(s, width, 4, s->regs[SONIC_RSC]); /* seq_no */ - size = sizeof(uint16_t) * 5 * width; - address_space_write(&s->as, dp8393x_crda(s), - MEMTXATTRS_UNSPECIFIED, - s->data, size); + trace_dp8393x_receive_write_status(dp8393x_crda(s)); + dp8393x_put(s, dp8393x_crda(s), 0, s->regs[SONIC_RCR]); /* status */ + dp8393x_put(s, dp8393x_crda(s), 1, rx_len); /* byte count */ + dp8393x_put(s, dp8393x_crda(s), 2, s->regs[SONIC_TRBA0]); /* pkt_ptr0 */ + dp8393x_put(s, dp8393x_crda(s), 3, s->regs[SONIC_TRBA1]); /* pkt_ptr1 */ + dp8393x_put(s, dp8393x_crda(s), 4, s->regs[SONIC_RSC]); /* seq_no */ /* Check link field */ - size = sizeof(uint16_t) * width; - address_space_read(&s->as, - dp8393x_crda(s) + sizeof(uint16_t) * 5 * width, - MEMTXATTRS_UNSPECIFIED, s->data, size); - s->regs[SONIC_LLFA] = dp8393x_get(s, width, 0); + s->regs[SONIC_LLFA] = dp8393x_get(s, dp8393x_crda(s), 5); if (s->regs[SONIC_LLFA] & SONIC_DESC_EOL) { /* EOL detected */ s->regs[SONIC_ISR] |= SONIC_ISR_RDE; } else { /* Clear in_use */ - size = sizeof(uint16_t) * width; - address = dp8393x_crda(s) + sizeof(uint16_t) * 6 * width; - dp8393x_put(s, width, 0, 0); - address_space_write(&s->as, address, MEMTXATTRS_UNSPECIFIED, - s->data, size); + dp8393x_put(s, dp8393x_crda(s), 6, 0x0000); /* Move to next descriptor */ s->regs[SONIC_CRDA] = s->regs[SONIC_LLFA]; @@ -938,7 +900,8 @@ static void dp8393x_reset(DeviceState *dev) s->regs[SONIC_SR] = 0x0004; /* only revision recognized by Linux/mips */ s->regs[SONIC_CR] = SONIC_CR_RST | SONIC_CR_STP | SONIC_CR_RXDIS; s->regs[SONIC_DCR] &= ~(SONIC_DCR_EXBUS | SONIC_DCR_LBR); - s->regs[SONIC_RCR] &= ~(SONIC_RCR_LB0 | SONIC_RCR_LB1 | SONIC_RCR_BRD | SONIC_RCR_RNT); + s->regs[SONIC_RCR] &= ~(SONIC_RCR_LB0 | SONIC_RCR_LB1 | SONIC_RCR_BRD | + SONIC_RCR_RNT); s->regs[SONIC_TCR] |= SONIC_TCR_NCRS | SONIC_TCR_PTX; s->regs[SONIC_TCR] &= ~SONIC_TCR_BCM; s->regs[SONIC_IMR] = 0; @@ -968,52 +931,31 @@ static void dp8393x_instance_init(Object *obj) dp8393xState *s = DP8393X(obj); sysbus_init_mmio(sbd, &s->mmio); - sysbus_init_mmio(sbd, &s->prom); sysbus_init_irq(sbd, &s->irq); } static void dp8393x_realize(DeviceState *dev, Error **errp) { dp8393xState *s = DP8393X(dev); - int i, checksum; - uint8_t *prom; - Error *local_err = NULL; address_space_init(&s->as, s->dma_mr, "dp8393x"); memory_region_init_io(&s->mmio, OBJECT(dev), &dp8393x_ops, s, - "dp8393x-regs", 0x40 << s->it_shift); + "dp8393x-regs", SONIC_REG_COUNT << s->it_shift); s->nic = qemu_new_nic(&net_dp83932_info, &s->conf, object_get_typename(OBJECT(dev)), dev->id, s); qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); s->watchdog = timer_new_ns(QEMU_CLOCK_VIRTUAL, dp8393x_watchdog, s); - - memory_region_init_rom(&s->prom, OBJECT(dev), "dp8393x-prom", - SONIC_PROM_SIZE, &local_err); - if (local_err) { - error_propagate(errp, local_err); - return; - } - prom = memory_region_get_ram_ptr(&s->prom); - checksum = 0; - for (i = 0; i < 6; i++) { - prom[i] = s->conf.macaddr.a[i]; - checksum += prom[i]; - if (checksum > 0xff) { - checksum = (checksum + 1) & 0xff; - } - } - prom[7] = 0xff - checksum; } static const VMStateDescription vmstate_dp8393x = { .name = "dp8393x", - .version_id = 0, - .minimum_version_id = 0, + .version_id = 1, + .minimum_version_id = 1, .fields = (VMStateField []) { - VMSTATE_BUFFER_UNSAFE(cam, dp8393xState, 0, 16 * 6), - VMSTATE_UINT16_ARRAY(regs, dp8393xState, 0x40), + VMSTATE_UINT16_2DARRAY(cam, dp8393xState, 16, 3), + VMSTATE_UINT16_ARRAY(regs, dp8393xState, SONIC_REG_COUNT), VMSTATE_END_OF_LIST() } }; diff --git a/hw/net/e1000.c b/hw/net/e1000.c index 4f75b44cfc..a30546c5d5 100644 --- a/hw/net/e1000.c +++ b/hw/net/e1000.c @@ -29,6 +29,7 @@ #include "hw/pci/pci.h" #include "hw/qdev-properties.h" #include "migration/vmstate.h" +#include "net/eth.h" #include "net/net.h" #include "net/checksum.h" #include "sysemu/sysemu.h" @@ -130,10 +131,13 @@ struct E1000State_st { #define E1000_FLAG_MIT_BIT 1 #define E1000_FLAG_MAC_BIT 2 #define E1000_FLAG_TSO_BIT 3 +#define E1000_FLAG_VET_BIT 4 #define E1000_FLAG_AUTONEG (1 << E1000_FLAG_AUTONEG_BIT) #define E1000_FLAG_MIT (1 << E1000_FLAG_MIT_BIT) #define E1000_FLAG_MAC (1 << E1000_FLAG_MAC_BIT) #define E1000_FLAG_TSO (1 << E1000_FLAG_TSO_BIT) +#define E1000_FLAG_VET (1 << E1000_FLAG_VET_BIT) + uint32_t compat_flags; bool received_tx_tso; bool use_tso_for_migration; @@ -361,6 +365,13 @@ e1000_autoneg_timer(void *opaque) } } +static bool e1000_vet_init_need(void *opaque) +{ + E1000State *s = opaque; + + return chkflag(VET); +} + static void e1000_reset(void *opaque) { E1000State *d = opaque; @@ -386,6 +397,10 @@ static void e1000_reset(void *opaque) } e1000x_reset_mac_addr(d->nic, d->mac_reg, macaddr); + + if (e1000_vet_init_need(d)) { + d->mac_reg[VET] = ETH_P_VLAN; + } } static void @@ -1737,6 +1752,8 @@ static Property e1000_properties[] = { compat_flags, E1000_FLAG_MAC_BIT, true), DEFINE_PROP_BIT("migrate_tso_props", E1000State, compat_flags, E1000_FLAG_TSO_BIT, true), + DEFINE_PROP_BIT("init-vet", E1000State, + compat_flags, E1000_FLAG_VET_BIT, true), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/net/e1000e.c b/hw/net/e1000e.c index a8a77eca95..ac96f7665a 100644 --- a/hw/net/e1000e.c +++ b/hw/net/e1000e.c @@ -35,6 +35,7 @@ #include "qemu/osdep.h" #include "qemu/units.h" +#include "net/eth.h" #include "net/net.h" #include "net/tap.h" #include "qemu/module.h" @@ -79,7 +80,7 @@ struct E1000EState { bool disable_vnet; E1000ECore core; - + bool init_vet; }; #define E1000E_MMIO_IDX 0 @@ -527,6 +528,10 @@ static void e1000e_qdev_reset(DeviceState *dev) trace_e1000e_cb_qdev_reset(); e1000e_core_reset(&s->core); + + if (s->init_vet) { + s->core.mac[VET] = ETH_P_VLAN; + } } static int e1000e_pre_save(void *opaque) @@ -666,6 +671,7 @@ static Property e1000e_properties[] = { e1000e_prop_subsys_ven, uint16_t), DEFINE_PROP_SIGNED("subsys", E1000EState, subsys, 0, e1000e_prop_subsys, uint16_t), + DEFINE_PROP_BOOL("init-vet", E1000EState, init_vet, true), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c index b75f2ab8fc..8ae6fb7e14 100644 --- a/hw/net/e1000e_core.c +++ b/hw/net/e1000e_core.c @@ -731,7 +731,7 @@ e1000e_process_tx_desc(E1000ECore *core, if (e1000x_vlan_enabled(core->mac) && e1000x_is_vlan_txd(txd_lower)) { net_tx_pkt_setup_vlan_header_ex(tx->tx_pkt, - le16_to_cpu(dp->upper.fields.special), core->vet); + le16_to_cpu(dp->upper.fields.special), core->mac[VET]); } if (e1000e_tx_pkt_send(core, tx, queue_index)) { e1000e_on_tx_done_update_stats(core, tx->tx_pkt); @@ -1012,7 +1012,7 @@ e1000e_receive_filter(E1000ECore *core, const uint8_t *buf, int size) { uint32_t rctl = core->mac[RCTL]; - if (e1000x_is_vlan_packet(buf, core->vet) && + if (e1000x_is_vlan_packet(buf, core->mac[VET]) && e1000x_vlan_rx_filter_enabled(core->mac)) { uint16_t vid = lduw_be_p(buf + 14); uint32_t vfta = ldl_le_p((uint32_t *)(core->mac + VFTA) + @@ -1285,7 +1285,6 @@ e1000e_write_lgcy_rx_descr(E1000ECore *core, uint8_t *desc, &d->special); d->errors = (uint8_t) (le32_to_cpu(status_flags) >> 24); d->status = (uint8_t) le32_to_cpu(status_flags); - d->special = 0; } static inline void @@ -1686,7 +1685,7 @@ e1000e_receive_iov(E1000ECore *core, const struct iovec *iov, int iovcnt) } net_rx_pkt_attach_iovec_ex(core->rx_pkt, iov, iovcnt, iov_ofs, - e1000x_vlan_enabled(core->mac), core->vet); + e1000x_vlan_enabled(core->mac), core->mac[VET]); e1000e_rss_parse_packet(core, core->rx_pkt, &rss_info); e1000e_rx_ring_init(core, &rxr, rss_info.queue); @@ -2397,8 +2396,7 @@ static void e1000e_set_vet(E1000ECore *core, int index, uint32_t val) { core->mac[VET] = val & 0xffff; - core->vet = le16_to_cpu(core->mac[VET]); - trace_e1000e_vlan_vet(core->vet); + trace_e1000e_vlan_vet(core->mac[VET]); } static void diff --git a/hw/net/i82596.c b/hw/net/i82596.c index 055c3a1470..ec21e2699a 100644 --- a/hw/net/i82596.c +++ b/hw/net/i82596.c @@ -12,7 +12,6 @@ #include "qemu/timer.h" #include "net/net.h" #include "net/eth.h" -#include "sysemu/sysemu.h" #include "hw/irq.h" #include "hw/qdev-properties.h" #include "migration/vmstate.h" diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c index f03450c028..9c7035bc94 100644 --- a/hw/net/imx_fec.c +++ b/hw/net/imx_fec.c @@ -283,9 +283,8 @@ static uint32_t imx_phy_read(IMXFECState *s, int reg) uint32_t phy = reg / 32; if (phy != s->phy_num) { - qemu_log_mask(LOG_GUEST_ERROR, "[%s.phy]%s: Bad phy num %u\n", - TYPE_IMX_FEC, __func__, phy); - return 0; + trace_imx_phy_read_num(phy, s->phy_num); + return 0xffff; } reg %= 32; @@ -345,8 +344,7 @@ static void imx_phy_write(IMXFECState *s, int reg, uint32_t val) uint32_t phy = reg / 32; if (phy != s->phy_num) { - qemu_log_mask(LOG_GUEST_ERROR, "[%s.phy]%s: Bad phy num %u\n", - TYPE_IMX_FEC, __func__, phy); + trace_imx_phy_write_num(phy, s->phy_num); return; } diff --git a/hw/net/lasi_i82596.c b/hw/net/lasi_i82596.c index 820b63f350..e37f7fabe9 100644 --- a/hw/net/lasi_i82596.c +++ b/hw/net/lasi_i82596.c @@ -18,7 +18,6 @@ #include "hw/net/lasi_82596.h" #include "hw/net/i82596.h" #include "trace.h" -#include "sysemu/sysemu.h" #include "hw/qdev-properties.h" #include "migration/vmstate.h" diff --git a/hw/net/meson.build b/hw/net/meson.build index af0749c42b..bdf71f1f40 100644 --- a/hw/net/meson.build +++ b/hw/net/meson.build @@ -39,7 +39,6 @@ softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_emc.c')) softmmu_ss.add(when: 'CONFIG_ETRAXFS', if_true: files('etraxfs_eth.c')) softmmu_ss.add(when: 'CONFIG_COLDFIRE', if_true: files('mcf_fec.c')) -specific_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-minimac2.c')) specific_ss.add(when: 'CONFIG_PSERIES', if_true: files('spapr_llan.c')) specific_ss.add(when: 'CONFIG_XILINX_ETHLITE', if_true: files('xilinx_ethlite.c')) diff --git a/hw/net/milkymist-minimac2.c b/hw/net/milkymist-minimac2.c deleted file mode 100644 index 5826944fd5..0000000000 --- a/hw/net/milkymist-minimac2.c +++ /dev/null @@ -1,547 +0,0 @@ -/* - * QEMU model of the Milkymist minimac2 block. - * - * Copyright (c) 2011 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * not available yet - * - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "qom/object.h" -#include "cpu.h" /* FIXME: why does this use TARGET_PAGE_ALIGN? */ -#include "hw/irq.h" -#include "hw/qdev-properties.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "net/net.h" -#include "qemu/log.h" -#include "qemu/module.h" -#include "qemu/error-report.h" - -#include - -enum { - R_SETUP = 0, - R_MDIO, - R_STATE0, - R_COUNT0, - R_STATE1, - R_COUNT1, - R_TXCOUNT, - R_MAX -}; - -enum { - SETUP_PHY_RST = (1<<0), -}; - -enum { - MDIO_DO = (1<<0), - MDIO_DI = (1<<1), - MDIO_OE = (1<<2), - MDIO_CLK = (1<<3), -}; - -enum { - STATE_EMPTY = 0, - STATE_LOADED = 1, - STATE_PENDING = 2, -}; - -enum { - MDIO_OP_WRITE = 1, - MDIO_OP_READ = 2, -}; - -enum mdio_state { - MDIO_STATE_IDLE, - MDIO_STATE_READING, - MDIO_STATE_WRITING, -}; - -enum { - R_PHY_ID1 = 2, - R_PHY_ID2 = 3, - R_PHY_MAX = 32 -}; - -#define MINIMAC2_MTU 1530 -#define MINIMAC2_BUFFER_SIZE 2048 - -struct MilkymistMinimac2MdioState { - int last_clk; - int count; - uint32_t data; - uint16_t data_out; - int state; - - uint8_t phy_addr; - uint8_t reg_addr; -}; -typedef struct MilkymistMinimac2MdioState MilkymistMinimac2MdioState; - -#define TYPE_MILKYMIST_MINIMAC2 "milkymist-minimac2" -OBJECT_DECLARE_SIMPLE_TYPE(MilkymistMinimac2State, MILKYMIST_MINIMAC2) - -struct MilkymistMinimac2State { - SysBusDevice parent_obj; - - NICState *nic; - NICConf conf; - char *phy_model; - MemoryRegion buffers; - MemoryRegion regs_region; - - qemu_irq rx_irq; - qemu_irq tx_irq; - - uint32_t regs[R_MAX]; - - MilkymistMinimac2MdioState mdio; - - uint16_t phy_regs[R_PHY_MAX]; - - uint8_t *rx0_buf; - uint8_t *rx1_buf; - uint8_t *tx_buf; -}; - -static const uint8_t preamble_sfd[] = { - 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0xd5 -}; - -static void minimac2_mdio_write_reg(MilkymistMinimac2State *s, - uint8_t phy_addr, uint8_t reg_addr, uint16_t value) -{ - trace_milkymist_minimac2_mdio_write(phy_addr, reg_addr, value); - - /* nop */ -} - -static uint16_t minimac2_mdio_read_reg(MilkymistMinimac2State *s, - uint8_t phy_addr, uint8_t reg_addr) -{ - uint16_t r = s->phy_regs[reg_addr]; - - trace_milkymist_minimac2_mdio_read(phy_addr, reg_addr, r); - - return r; -} - -static void minimac2_update_mdio(MilkymistMinimac2State *s) -{ - MilkymistMinimac2MdioState *m = &s->mdio; - - /* detect rising clk edge */ - if (m->last_clk == 0 && (s->regs[R_MDIO] & MDIO_CLK)) { - /* shift data in */ - int bit = ((s->regs[R_MDIO] & MDIO_DO) - && (s->regs[R_MDIO] & MDIO_OE)) ? 1 : 0; - m->data = (m->data << 1) | bit; - - /* check for sync */ - if (m->data == 0xffffffff) { - m->count = 32; - } - - if (m->count == 16) { - uint8_t start = (m->data >> 14) & 0x3; - uint8_t op = (m->data >> 12) & 0x3; - uint8_t ta = (m->data) & 0x3; - - if (start == 1 && op == MDIO_OP_WRITE && ta == 2) { - m->state = MDIO_STATE_WRITING; - } else if (start == 1 && op == MDIO_OP_READ && (ta & 1) == 0) { - m->state = MDIO_STATE_READING; - } else { - m->state = MDIO_STATE_IDLE; - } - - if (m->state != MDIO_STATE_IDLE) { - m->phy_addr = (m->data >> 7) & 0x1f; - m->reg_addr = (m->data >> 2) & 0x1f; - } - - if (m->state == MDIO_STATE_READING) { - m->data_out = minimac2_mdio_read_reg(s, m->phy_addr, - m->reg_addr); - } - } - - if (m->count < 16 && m->state == MDIO_STATE_READING) { - int bit = (m->data_out & 0x8000) ? 1 : 0; - m->data_out <<= 1; - - if (bit) { - s->regs[R_MDIO] |= MDIO_DI; - } else { - s->regs[R_MDIO] &= ~MDIO_DI; - } - } - - if (m->count == 0 && m->state) { - if (m->state == MDIO_STATE_WRITING) { - uint16_t data = m->data & 0xffff; - minimac2_mdio_write_reg(s, m->phy_addr, m->reg_addr, data); - } - m->state = MDIO_STATE_IDLE; - } - m->count--; - } - - m->last_clk = (s->regs[R_MDIO] & MDIO_CLK) ? 1 : 0; -} - -static size_t assemble_frame(uint8_t *buf, size_t size, - const uint8_t *payload, size_t payload_size) -{ - uint32_t crc; - - if (size < payload_size + 12) { - qemu_log_mask(LOG_GUEST_ERROR, "milkymist_minimac2: frame too big " - "(%zd bytes)\n", payload_size); - return 0; - } - - /* prepend preamble and sfd */ - memcpy(buf, preamble_sfd, 8); - - /* now copy the payload */ - memcpy(buf + 8, payload, payload_size); - - /* pad frame if needed */ - if (payload_size < 60) { - memset(buf + payload_size + 8, 0, 60 - payload_size); - payload_size = 60; - } - - /* append fcs */ - crc = cpu_to_le32(crc32(0, buf + 8, payload_size)); - memcpy(buf + payload_size + 8, &crc, 4); - - return payload_size + 12; -} - -static void minimac2_tx(MilkymistMinimac2State *s) -{ - uint32_t txcount = s->regs[R_TXCOUNT]; - uint8_t *buf = s->tx_buf; - - if (txcount < 64) { - error_report("milkymist_minimac2: ethernet frame too small (%u < %u)", - txcount, 64); - goto err; - } - - if (txcount > MINIMAC2_MTU) { - error_report("milkymist_minimac2: MTU exceeded (%u > %u)", - txcount, MINIMAC2_MTU); - goto err; - } - - if (memcmp(buf, preamble_sfd, 8) != 0) { - error_report("milkymist_minimac2: frame doesn't contain the preamble " - "and/or the SFD (%02x %02x %02x %02x %02x %02x %02x %02x)", - buf[0], buf[1], buf[2], buf[3], buf[4], buf[5], buf[6], buf[7]); - goto err; - } - - trace_milkymist_minimac2_tx_frame(txcount - 12); - - /* send packet, skipping preamble and sfd */ - qemu_send_packet_raw(qemu_get_queue(s->nic), buf + 8, txcount - 12); - - s->regs[R_TXCOUNT] = 0; - -err: - trace_milkymist_minimac2_pulse_irq_tx(); - qemu_irq_pulse(s->tx_irq); -} - -static void update_rx_interrupt(MilkymistMinimac2State *s) -{ - if (s->regs[R_STATE0] == STATE_PENDING - || s->regs[R_STATE1] == STATE_PENDING) { - trace_milkymist_minimac2_raise_irq_rx(); - qemu_irq_raise(s->rx_irq); - } else { - trace_milkymist_minimac2_lower_irq_rx(); - qemu_irq_lower(s->rx_irq); - } -} - -static ssize_t minimac2_rx(NetClientState *nc, const uint8_t *buf, size_t size) -{ - MilkymistMinimac2State *s = qemu_get_nic_opaque(nc); - - uint32_t r_count; - uint32_t r_state; - uint8_t *rx_buf; - - size_t frame_size; - - trace_milkymist_minimac2_rx_frame(buf, size); - - /* choose appropriate slot */ - if (s->regs[R_STATE0] == STATE_LOADED) { - r_count = R_COUNT0; - r_state = R_STATE0; - rx_buf = s->rx0_buf; - } else if (s->regs[R_STATE1] == STATE_LOADED) { - r_count = R_COUNT1; - r_state = R_STATE1; - rx_buf = s->rx1_buf; - } else { - return 0; - } - - /* assemble frame */ - frame_size = assemble_frame(rx_buf, MINIMAC2_BUFFER_SIZE, buf, size); - - if (frame_size == 0) { - return size; - } - - trace_milkymist_minimac2_rx_transfer(rx_buf, frame_size); - - /* update slot */ - s->regs[r_count] = frame_size; - s->regs[r_state] = STATE_PENDING; - - update_rx_interrupt(s); - - return size; -} - -static uint64_t -minimac2_read(void *opaque, hwaddr addr, unsigned size) -{ - MilkymistMinimac2State *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_SETUP: - case R_MDIO: - case R_STATE0: - case R_COUNT0: - case R_STATE1: - case R_COUNT1: - case R_TXCOUNT: - r = s->regs[addr]; - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "milkymist_minimac2_rd%d: 0x%" HWADDR_PRIx "\n", - size, addr << 2); - break; - } - - trace_milkymist_minimac2_memory_read(addr << 2, r); - - return r; -} - -static int minimac2_can_rx(MilkymistMinimac2State *s) -{ - if (s->regs[R_STATE0] == STATE_LOADED) { - return 1; - } - if (s->regs[R_STATE1] == STATE_LOADED) { - return 1; - } - - return 0; -} - -static void -minimac2_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - MilkymistMinimac2State *s = opaque; - - trace_milkymist_minimac2_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_MDIO: - { - /* MDIO_DI is read only */ - int mdio_di = (s->regs[R_MDIO] & MDIO_DI); - s->regs[R_MDIO] = value; - if (mdio_di) { - s->regs[R_MDIO] |= mdio_di; - } else { - s->regs[R_MDIO] &= ~mdio_di; - } - - minimac2_update_mdio(s); - } break; - case R_TXCOUNT: - s->regs[addr] = value; - if (value > 0) { - minimac2_tx(s); - } - break; - case R_STATE0: - case R_STATE1: - s->regs[addr] = value; - update_rx_interrupt(s); - if (minimac2_can_rx(s)) { - qemu_flush_queued_packets(qemu_get_queue(s->nic)); - } - break; - case R_SETUP: - case R_COUNT0: - case R_COUNT1: - s->regs[addr] = value; - break; - - default: - qemu_log_mask(LOG_GUEST_ERROR, - "milkymist_minimac2_wr%d: 0x%" HWADDR_PRIx - " = 0x%" PRIx64 "\n", - size, addr << 2, value); - break; - } -} - -static const MemoryRegionOps minimac2_ops = { - .read = minimac2_read, - .write = minimac2_write, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void milkymist_minimac2_reset(DeviceState *d) -{ - MilkymistMinimac2State *s = MILKYMIST_MINIMAC2(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } - for (i = 0; i < R_PHY_MAX; i++) { - s->phy_regs[i] = 0; - } - - /* defaults */ - s->phy_regs[R_PHY_ID1] = 0x0022; /* Micrel KSZ8001L */ - s->phy_regs[R_PHY_ID2] = 0x161a; -} - -static NetClientInfo net_milkymist_minimac2_info = { - .type = NET_CLIENT_DRIVER_NIC, - .size = sizeof(NICState), - .receive = minimac2_rx, -}; - -static void milkymist_minimac2_realize(DeviceState *dev, Error **errp) -{ - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - MilkymistMinimac2State *s = MILKYMIST_MINIMAC2(dev); - size_t buffers_size = TARGET_PAGE_ALIGN(3 * MINIMAC2_BUFFER_SIZE); - - sysbus_init_irq(sbd, &s->rx_irq); - sysbus_init_irq(sbd, &s->tx_irq); - - memory_region_init_io(&s->regs_region, OBJECT(dev), &minimac2_ops, s, - "milkymist-minimac2", R_MAX * 4); - sysbus_init_mmio(sbd, &s->regs_region); - - /* register buffers memory */ - memory_region_init_ram_nomigrate(&s->buffers, OBJECT(dev), "milkymist-minimac2.buffers", - buffers_size, &error_fatal); - vmstate_register_ram_global(&s->buffers); - s->rx0_buf = memory_region_get_ram_ptr(&s->buffers); - s->rx1_buf = s->rx0_buf + MINIMAC2_BUFFER_SIZE; - s->tx_buf = s->rx1_buf + MINIMAC2_BUFFER_SIZE; - - sysbus_init_mmio(sbd, &s->buffers); - - qemu_macaddr_default_if_unset(&s->conf.macaddr); - s->nic = qemu_new_nic(&net_milkymist_minimac2_info, &s->conf, - object_get_typename(OBJECT(dev)), dev->id, s); - qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); -} - -static const VMStateDescription vmstate_milkymist_minimac2_mdio = { - .name = "milkymist-minimac2-mdio", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_INT32(last_clk, MilkymistMinimac2MdioState), - VMSTATE_INT32(count, MilkymistMinimac2MdioState), - VMSTATE_UINT32(data, MilkymistMinimac2MdioState), - VMSTATE_UINT16(data_out, MilkymistMinimac2MdioState), - VMSTATE_INT32(state, MilkymistMinimac2MdioState), - VMSTATE_UINT8(phy_addr, MilkymistMinimac2MdioState), - VMSTATE_UINT8(reg_addr, MilkymistMinimac2MdioState), - VMSTATE_END_OF_LIST() - } -}; - -static const VMStateDescription vmstate_milkymist_minimac2 = { - .name = "milkymist-minimac2", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, MilkymistMinimac2State, R_MAX), - VMSTATE_UINT16_ARRAY(phy_regs, MilkymistMinimac2State, R_PHY_MAX), - VMSTATE_STRUCT(mdio, MilkymistMinimac2State, 0, - vmstate_milkymist_minimac2_mdio, MilkymistMinimac2MdioState), - VMSTATE_END_OF_LIST() - } -}; - -static Property milkymist_minimac2_properties[] = { - DEFINE_NIC_PROPERTIES(MilkymistMinimac2State, conf), - DEFINE_PROP_STRING("phy_model", MilkymistMinimac2State, phy_model), - DEFINE_PROP_END_OF_LIST(), -}; - -static void milkymist_minimac2_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = milkymist_minimac2_realize; - dc->reset = milkymist_minimac2_reset; - dc->vmsd = &vmstate_milkymist_minimac2; - device_class_set_props(dc, milkymist_minimac2_properties); -} - -static const TypeInfo milkymist_minimac2_info = { - .name = TYPE_MILKYMIST_MINIMAC2, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(MilkymistMinimac2State), - .class_init = milkymist_minimac2_class_init, -}; - -static void milkymist_minimac2_register_types(void) -{ - type_register_static(&milkymist_minimac2_info); -} - -type_init(milkymist_minimac2_register_types) diff --git a/hw/net/msf2-emac.c b/hw/net/msf2-emac.c index 3e6206044f..9278fdce0b 100644 --- a/hw/net/msf2-emac.c +++ b/hw/net/msf2-emac.c @@ -32,7 +32,6 @@ #include "qemu-common.h" #include "qemu/log.h" #include "qapi/error.h" -#include "exec/address-spaces.h" #include "hw/registerfields.h" #include "hw/net/msf2-emac.h" #include "hw/net/mii.h" diff --git a/hw/net/net_tx_pkt.c b/hw/net/net_tx_pkt.c index 1f9aa59eca..1cb1125d9f 100644 --- a/hw/net/net_tx_pkt.c +++ b/hw/net/net_tx_pkt.c @@ -450,11 +450,13 @@ void net_tx_pkt_reset(struct NetTxPkt *pkt) pkt->payload_len = 0; pkt->payload_frags = 0; - assert(pkt->raw); - for (i = 0; i < pkt->raw_frags; i++) { - assert(pkt->raw[i].iov_base); - pci_dma_unmap(pkt->pci_dev, pkt->raw[i].iov_base, pkt->raw[i].iov_len, - DMA_DIRECTION_TO_DEVICE, 0); + if (pkt->max_raw_frags > 0) { + assert(pkt->raw); + for (i = 0; i < pkt->raw_frags; i++) { + assert(pkt->raw[i].iov_base); + pci_dma_unmap(pkt->pci_dev, pkt->raw[i].iov_base, + pkt->raw[i].iov_len, DMA_DIRECTION_TO_DEVICE, 0); + } } pkt->raw_frags = 0; diff --git a/hw/net/rocker/rocker.h b/hw/net/rocker/rocker.h index 941c932265..412fa44d01 100644 --- a/hw/net/rocker/rocker.h +++ b/hw/net/rocker/rocker.h @@ -25,14 +25,9 @@ #if defined(DEBUG_ROCKER) # define DPRINTF(fmt, ...) \ do { \ - struct timeval tv; \ - char timestr[64]; \ - time_t now; \ - gettimeofday(&tv, NULL); \ - now = tv.tv_sec; \ - strftime(timestr, sizeof(timestr), "%T", localtime(&now)); \ - fprintf(stderr, "%s.%06ld ", timestr, tv.tv_usec); \ - fprintf(stderr, "ROCKER: " fmt, ## __VA_ARGS__); \ + g_autoptr(GDateTime) now = g_date_time_new_now_local(); \ + g_autofree char *nowstr = g_date_time_format(now, "%T.%f");\ + fprintf(stderr, "%s ROCKER: " fmt, nowstr, ## __VA_ARGS__);\ } while (0) #else static inline GCC_FMT_ATTR(1, 2) int DPRINTF(const char *fmt, ...) diff --git a/hw/net/spapr_llan.c b/hw/net/spapr_llan.c index 10e85a4556..a6876a936d 100644 --- a/hw/net/spapr_llan.c +++ b/hw/net/spapr_llan.c @@ -26,7 +26,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "qemu/log.h" #include "qemu/module.h" #include "net/net.h" diff --git a/hw/net/trace-events b/hw/net/trace-events index baf25ffa7e..643338f610 100644 --- a/hw/net/trace-events +++ b/hw/net/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # allwinner-sun8i-emac.c allwinner_sun8i_emac_mii_write_reg(uint32_t reg, uint32_t value) "MII write: reg=0x%" PRIx32 " value=0x%" PRIx32 @@ -19,18 +19,6 @@ mdio_bitbang(bool mdc, bool mdio, int state, uint16_t cnt, unsigned int drive) " lance_mem_readw(uint64_t addr, uint32_t ret) "addr=0x%"PRIx64"val=0x%04x" lance_mem_writew(uint64_t addr, uint32_t val) "addr=0x%"PRIx64"val=0x%04x" -# milkymist-minimac2.c -milkymist_minimac2_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_minimac2_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_minimac2_mdio_write(uint8_t phy_addr, uint8_t addr, uint16_t value) "phy_addr 0x%02x addr 0x%02x value 0x%04x" -milkymist_minimac2_mdio_read(uint8_t phy_addr, uint8_t addr, uint16_t value) "phy_addr 0x%02x addr 0x%02x value 0x%04x" -milkymist_minimac2_tx_frame(uint32_t length) "length %u" -milkymist_minimac2_rx_frame(const void *buf, uint32_t length) "buf %p length %u" -milkymist_minimac2_rx_transfer(const void *buf, uint32_t length) "buf %p length %d" -milkymist_minimac2_raise_irq_rx(void) "Raise IRQ RX" -milkymist_minimac2_lower_irq_rx(void) "Lower IRQ RX" -milkymist_minimac2_pulse_irq_tx(void) "Pulse IRQ TX" - # mipsnet.c mipsnet_send(uint32_t size) "sending len=%u" mipsnet_receive(uint32_t size) "receiving len=%u" @@ -414,7 +402,9 @@ i82596_channel_attention(void *s) "%p: Received CHANNEL ATTENTION" # imx_fec.c imx_phy_read(uint32_t val, int phy, int reg) "0x%04"PRIx32" <= phy[%d].reg[%d]" +imx_phy_read_num(int phy, int configured) "read request from unconfigured phy %d (configured %d)" imx_phy_write(uint32_t val, int phy, int reg) "0x%04"PRIx32" => phy[%d].reg[%d]" +imx_phy_write_num(int phy, int configured) "write request to unconfigured phy %d (configured %d)" imx_phy_update_link(const char *s) "%s" imx_phy_reset(void) "" imx_fec_read_bd(uint64_t addr, int flags, int len, int data) "tx_bd 0x%"PRIx64" flags 0x%04x len %d data 0x%08x" @@ -446,3 +436,20 @@ npcm7xx_emc_received_packet(uint32_t len) "Received %u byte packet" npcm7xx_emc_rx_done(uint32_t crxdsa) "RX done, CRXDSA=0x%x" npcm7xx_emc_reg_read(int emc_num, uint32_t result, const char *name, int regno) "emc%d: 0x%x = reg[%s/%d]" npcm7xx_emc_reg_write(int emc_num, const char *name, int regno, uint32_t value) "emc%d: reg[%s/%d] = 0x%x" + +# dp8398x.c +dp8393x_raise_irq(int isr) "raise irq, isr is 0x%04x" +dp8393x_lower_irq(void) "lower irq" +dp8393x_load_cam(int idx, int cam0, int cam1, int cam2, int cam3, int cam4, int cam5) "load cam[%d] with 0x%02x0x%02x0x%02x0x%02x0x%02x0x%02x" +dp8393x_load_cam_done(int cen) "load cam done. cam enable mask 0x%04x" +dp8393x_read_rra_regs(int crba0, int crba1, int rbwc0, int rbwc1) "CRBA0/1: 0x%04x/0x%04x, RBWC0/1: 0x%04x/0x%04x" +dp8393x_transmit_packet(int ttda) "Transmit packet at 0x%"PRIx32 +dp8393x_transmit_txlen_error(int len) "tx_len is %d" +dp8393x_read(int reg, const char *name, int val, int size) "reg=0x%x [%s] val=0x%04x size=%d" +dp8393x_write(int reg, const char *name, int val, int size) "reg=0x%x [%s] val=0x%04x size=%d" +dp8393x_write_invalid(int reg) "writing to reg %d invalid" +dp8393x_write_invalid_dcr(const char *name) "writing to %s invalid" +dp8393x_receive_oversize(int size) "oversize packet, pkt_size is %d" +dp8393x_receive_not_netcard(void) "packet not for netcard" +dp8393x_receive_packet(int crba) "Receive packet at 0x%"PRIx32 +dp8393x_receive_write_status(int crba) "Write status at 0x%"PRIx32 diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 24d555e764..10a7780a13 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -22,6 +22,7 @@ #include "standard-headers/linux/vhost_types.h" #include "hw/virtio/virtio-net.h" #include "net/vhost_net.h" +#include "qapi/error.h" #include "qemu/error-report.h" #include "qemu/main-loop.h" @@ -45,6 +46,7 @@ static const int kernel_feature_bits[] = { VIRTIO_NET_F_MTU, VIRTIO_F_IOMMU_PLATFORM, VIRTIO_F_RING_PACKED, + VIRTIO_NET_F_HASH_REPORT, VHOST_INVALID_FEATURE_BIT }; @@ -71,6 +73,8 @@ static const int user_feature_bits[] = { VIRTIO_NET_F_MTU, VIRTIO_F_IOMMU_PLATFORM, VIRTIO_F_RING_PACKED, + VIRTIO_NET_F_RSS, + VIRTIO_NET_F_HASH_REPORT, /* This bit implies RARP isn't sent by QEMU out of band */ VIRTIO_NET_F_GUEST_ANNOUNCE, @@ -113,7 +117,7 @@ uint64_t vhost_net_get_features(struct vhost_net *net, uint64_t features) int vhost_net_get_config(struct vhost_net *net, uint8_t *config, uint32_t config_len) { - return vhost_dev_get_config(&net->dev, config, config_len); + return vhost_dev_get_config(&net->dev, config, config_len, NULL); } int vhost_net_set_config(struct vhost_net *net, const uint8_t *data, uint32_t offset, uint32_t size, uint32_t flags) @@ -154,6 +158,7 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) bool backend_kernel = options->backend_type == VHOST_BACKEND_TYPE_KERNEL; struct vhost_net *net = g_new0(struct vhost_net, 1); uint64_t features = 0; + Error *local_err = NULL; if (!options->net_backend) { fprintf(stderr, "vhost-net requires net backend to be setup\n"); @@ -184,8 +189,10 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) } r = vhost_dev_init(&net->dev, options->opaque, - options->backend_type, options->busyloop_timeout); + options->backend_type, options->busyloop_timeout, + &local_err); if (r < 0) { + error_report_err(local_err); goto fail; } if (backend_kernel) { diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 66b9ff4511..16d20cdee5 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -89,7 +89,7 @@ VIRTIO_NET_RSS_HASH_TYPE_TCP_EX | \ VIRTIO_NET_RSS_HASH_TYPE_UDP_EX) -static VirtIOFeature feature_sizes[] = { +static const VirtIOFeature feature_sizes[] = { {.flags = 1ULL << VIRTIO_NET_F_MAC, .end = endof(struct virtio_net_config, mac)}, {.flags = 1ULL << VIRTIO_NET_F_STATUS, @@ -737,8 +737,9 @@ static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features, return features; } - virtio_clear_feature(&features, VIRTIO_NET_F_RSS); - virtio_clear_feature(&features, VIRTIO_NET_F_HASH_REPORT); + if (!ebpf_rss_is_loaded(&n->ebpf_rss)) { + virtio_clear_feature(&features, VIRTIO_NET_F_RSS); + } features = vhost_net_get_features(get_vhost_net(nc->peer), features); vdev->backend_features = features; @@ -1163,12 +1164,79 @@ static int virtio_net_handle_announce(VirtIONet *n, uint8_t cmd, } } +static void virtio_net_detach_epbf_rss(VirtIONet *n); + static void virtio_net_disable_rss(VirtIONet *n) { if (n->rss_data.enabled) { trace_virtio_net_rss_disable(); } n->rss_data.enabled = false; + + virtio_net_detach_epbf_rss(n); +} + +static bool virtio_net_attach_ebpf_to_backend(NICState *nic, int prog_fd) +{ + NetClientState *nc = qemu_get_peer(qemu_get_queue(nic), 0); + if (nc == NULL || nc->info->set_steering_ebpf == NULL) { + return false; + } + + return nc->info->set_steering_ebpf(nc, prog_fd); +} + +static void rss_data_to_rss_config(struct VirtioNetRssData *data, + struct EBPFRSSConfig *config) +{ + config->redirect = data->redirect; + config->populate_hash = data->populate_hash; + config->hash_types = data->hash_types; + config->indirections_len = data->indirections_len; + config->default_queue = data->default_queue; +} + +static bool virtio_net_attach_epbf_rss(VirtIONet *n) +{ + struct EBPFRSSConfig config = {}; + + if (!ebpf_rss_is_loaded(&n->ebpf_rss)) { + return false; + } + + rss_data_to_rss_config(&n->rss_data, &config); + + if (!ebpf_rss_set_all(&n->ebpf_rss, &config, + n->rss_data.indirections_table, n->rss_data.key)) { + return false; + } + + if (!virtio_net_attach_ebpf_to_backend(n->nic, n->ebpf_rss.program_fd)) { + return false; + } + + return true; +} + +static void virtio_net_detach_epbf_rss(VirtIONet *n) +{ + virtio_net_attach_ebpf_to_backend(n->nic, -1); +} + +static bool virtio_net_load_ebpf(VirtIONet *n) +{ + if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) { + /* backend does't support steering ebpf */ + return false; + } + + return ebpf_rss_load(&n->ebpf_rss); +} + +static void virtio_net_unload_ebpf(VirtIONet *n) +{ + virtio_net_attach_ebpf_to_backend(n->nic, -1); + ebpf_rss_unload(&n->ebpf_rss); } static uint16_t virtio_net_handle_rss(VirtIONet *n, @@ -1283,6 +1351,25 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n, goto error; } n->rss_data.enabled = true; + + if (!n->rss_data.populate_hash) { + if (!virtio_net_attach_epbf_rss(n)) { + /* EBPF must be loaded for vhost */ + if (get_vhost_net(qemu_get_queue(n->nic)->peer)) { + warn_report("Can't load eBPF RSS for vhost"); + goto error; + } + /* fallback to software RSS */ + warn_report("Can't load eBPF RSS - fallback to software RSS"); + n->rss_data.enabled_software_rss = true; + } + } else { + /* use software RSS for hash populating */ + /* and detach eBPF if was loaded before */ + virtio_net_detach_epbf_rss(n); + n->rss_data.enabled_software_rss = true; + } + trace_virtio_net_rss_enable(n->rss_data.hash_types, n->rss_data.indirections_len, temp.b); @@ -1668,7 +1755,7 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, return -1; } - if (!no_rss && n->rss_data.enabled) { + if (!no_rss && n->rss_data.enabled && n->rss_data.enabled_software_rss) { int index = virtio_net_process_rss(nc, buf, size); if (index >= 0) { NetClientState *nc2 = qemu_get_subqueue(n->nic, index); @@ -2772,6 +2859,19 @@ static int virtio_net_post_load_device(void *opaque, int version_id) } if (n->rss_data.enabled) { + n->rss_data.enabled_software_rss = n->rss_data.populate_hash; + if (!n->rss_data.populate_hash) { + if (!virtio_net_attach_epbf_rss(n)) { + if (get_vhost_net(qemu_get_queue(n->nic)->peer)) { + warn_report("Can't post-load eBPF RSS for vhost"); + } else { + warn_report("Can't post-load eBPF RSS - " + "fallback to software RSS"); + n->rss_data.enabled_software_rss = true; + } + } + } + trace_virtio_net_rss_enable(n->rss_data.hash_types, n->rss_data.indirections_len, sizeof(n->rss_data.key)); @@ -3134,6 +3234,7 @@ static bool failover_replug_primary(VirtIONet *n, DeviceState *dev, } hotplug_handler_plug(hotplug_ctrl, dev, &err); } + pdev->partially_hotplugged = false; out: error_propagate(errp, err); @@ -3352,6 +3453,10 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) n->qdev = dev; net_rx_pkt_init(&n->rx_pkt, false); + + if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) { + virtio_net_load_ebpf(n); + } } static void virtio_net_device_unrealize(DeviceState *dev) @@ -3360,6 +3465,10 @@ static void virtio_net_device_unrealize(DeviceState *dev) VirtIONet *n = VIRTIO_NET(dev); int i, max_queues; + if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) { + virtio_net_unload_ebpf(n); + } + /* This will stop vhost backend if appropriate. */ virtio_net_set_status(vdev, 0); @@ -3373,6 +3482,7 @@ static void virtio_net_device_unrealize(DeviceState *dev) if (n->failover) { device_listener_unregister(&n->primary_listener); + remove_migration_state_change_notifier(&n->migration_state); } max_queues = n->multiqueue ? n->max_queues : 1; @@ -3402,6 +3512,8 @@ static void virtio_net_instance_init(Object *obj) device_add_bootindex_property(obj, &n->nic_conf.bootindex, "bootindex", "/ethernet-phy@0", DEVICE(n)); + + ebpf_rss_init(&n->ebpf_rss); } static int virtio_net_pre_save(void *opaque) diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c index eff299f629..41f796a247 100644 --- a/hw/net/vmxnet3.c +++ b/hw/net/vmxnet3.c @@ -23,6 +23,7 @@ #include "net/checksum.h" #include "sysemu/sysemu.h" #include "qemu/bswap.h" +#include "qemu/log.h" #include "qemu/module.h" #include "hw/pci/msix.h" #include "hw/pci/msi.h" @@ -1093,8 +1094,12 @@ vmxnet3_io_bar0_write(void *opaque, hwaddr addr, int tx_queue_idx = VMW_MULTIREG_IDX_BY_ADDR(addr, VMXNET3_REG_TXPROD, VMXNET3_REG_ALIGN); - assert(tx_queue_idx <= s->txq_num); - vmxnet3_process_tx_queue(s, tx_queue_idx); + if (tx_queue_idx <= s->txq_num) { + vmxnet3_process_tx_queue(s, tx_queue_idx); + } else { + qemu_log_mask(LOG_GUEST_ERROR, "vmxnet3: Illegal TX queue %d/%d\n", + tx_queue_idx, s->txq_num); + } return; } @@ -1376,7 +1381,7 @@ static void vmxnet3_validate_interrupts(VMXNET3State *s) } } -static void vmxnet3_validate_queues(VMXNET3State *s) +static bool vmxnet3_validate_queues(VMXNET3State *s) { /* * txq_num and rxq_num are total number of queues @@ -1385,12 +1390,18 @@ static void vmxnet3_validate_queues(VMXNET3State *s) */ if (s->txq_num > VMXNET3_DEVICE_MAX_TX_QUEUES) { - hw_error("Bad TX queues number: %d\n", s->txq_num); + qemu_log_mask(LOG_GUEST_ERROR, "vmxnet3: Bad TX queues number: %d\n", + s->txq_num); + return false; } if (s->rxq_num > VMXNET3_DEVICE_MAX_RX_QUEUES) { - hw_error("Bad RX queues number: %d\n", s->rxq_num); + qemu_log_mask(LOG_GUEST_ERROR, "vmxnet3: Bad RX queues number: %d\n", + s->rxq_num); + return false; } + + return true; } static void vmxnet3_activate_device(VMXNET3State *s) @@ -1414,6 +1425,16 @@ static void vmxnet3_activate_device(VMXNET3State *s) return; } + s->txq_num = + VMXNET3_READ_DRV_SHARED8(d, s->drv_shmem, devRead.misc.numTxQueues); + s->rxq_num = + VMXNET3_READ_DRV_SHARED8(d, s->drv_shmem, devRead.misc.numRxQueues); + + VMW_CFPRN("Number of TX/RX queues %u/%u", s->txq_num, s->rxq_num); + if (!vmxnet3_validate_queues(s)) { + return; + } + vmxnet3_adjust_by_guest_type(s); vmxnet3_update_features(s); vmxnet3_update_pm_state(s); @@ -1440,14 +1461,6 @@ static void vmxnet3_activate_device(VMXNET3State *s) VMXNET3_READ_DRV_SHARED8(d, s->drv_shmem, devRead.intrConf.autoMask); VMW_CFPRN("Automatic interrupt masking is %d", (int)s->auto_int_masking); - s->txq_num = - VMXNET3_READ_DRV_SHARED8(d, s->drv_shmem, devRead.misc.numTxQueues); - s->rxq_num = - VMXNET3_READ_DRV_SHARED8(d, s->drv_shmem, devRead.misc.numRxQueues); - - VMW_CFPRN("Number of TX/RX queues %u/%u", s->txq_num, s->rxq_num); - vmxnet3_validate_queues(s); - qdescr_table_pa = VMXNET3_READ_DRV_SHARED64(d, s->drv_shmem, devRead.misc.queueDescPA); VMW_CFPRN("TX queues descriptors table is at 0x%" PRIx64, qdescr_table_pa); @@ -2399,7 +2412,9 @@ static int vmxnet3_post_load(void *opaque, int version_id) } } - vmxnet3_validate_queues(s); + if (!vmxnet3_validate_queues(s)) { + return -1; + } vmxnet3_validate_interrupts(s); return 0; diff --git a/hw/net/xgmac.c b/hw/net/xgmac.c index 00859a7d50..0ab6ae91aa 100644 --- a/hw/net/xgmac.c +++ b/hw/net/xgmac.c @@ -29,7 +29,6 @@ #include "hw/qdev-properties.h" #include "hw/sysbus.h" #include "migration/vmstate.h" -#include "qemu/log.h" #include "qemu/module.h" #include "net/net.h" #include "qom/object.h" diff --git a/hw/nios2/10m50_devboard.c b/hw/nios2/10m50_devboard.c index a14fc31e86..3d1205b8bd 100644 --- a/hw/nios2/10m50_devboard.c +++ b/hw/nios2/10m50_devboard.c @@ -24,7 +24,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/sysbus.h" #include "hw/char/serial.h" diff --git a/hw/nios2/boot.c b/hw/nios2/boot.c index d9969ac148..5b3e4efed5 100644 --- a/hw/nios2/boot.c +++ b/hw/nios2/boot.c @@ -32,13 +32,11 @@ #include "qemu/units.h" #include "qemu-common.h" #include "qemu/datadir.h" -#include "cpu.h" #include "qemu/option.h" #include "qemu/config-file.h" #include "qemu/error-report.h" #include "sysemu/device_tree.h" #include "sysemu/reset.h" -#include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/loader.h" #include "elf.h" diff --git a/hw/nios2/generic_nommu.c b/hw/nios2/generic_nommu.c index 19899e2c1e..fbc18dbd04 100644 --- a/hw/nios2/generic_nommu.c +++ b/hw/nios2/generic_nommu.c @@ -29,9 +29,7 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu-common.h" -#include "cpu.h" -#include "hw/sysbus.h" #include "hw/char/serial.h" #include "hw/boards.h" #include "exec/memory.h" diff --git a/hw/nubus/nubus-bus.c b/hw/nubus/nubus-bus.c index 942a6d5342..5c13452308 100644 --- a/hw/nubus/nubus-bus.c +++ b/hw/nubus/nubus-bus.c @@ -10,7 +10,6 @@ #include "qemu/osdep.h" #include "hw/nubus/nubus.h" -#include "hw/sysbus.h" #include "qapi/error.h" diff --git a/hw/nvme/Kconfig b/hw/nvme/Kconfig new file mode 100644 index 0000000000..8ac90942e5 --- /dev/null +++ b/hw/nvme/Kconfig @@ -0,0 +1,4 @@ +config NVME_PCI + bool + default y if PCI_DEVICES + depends on PCI diff --git a/hw/block/nvme.c b/hw/nvme/ctrl.c similarity index 79% rename from hw/block/nvme.c rename to hw/nvme/ctrl.c index 5fe082ec34..6baf9e0420 100644 --- a/hw/block/nvme.c +++ b/hw/nvme/ctrl.c @@ -12,10 +12,19 @@ * Reference Specs: http://www.nvmexpress.org, 1.4, 1.3, 1.2, 1.1, 1.0e * * https://nvmexpress.org/developers/nvme-specification/ - */ - -/** - * Usage: add options: + * + * + * Notes on coding style + * --------------------- + * While QEMU coding style prefers lowercase hexadecimals in constants, the + * NVMe subsystem use thes format from the NVMe specifications in the comments + * (i.e. 'h' suffix instead of '0x' prefix). + * + * Usage + * ----- + * See docs/system/nvme.rst for extensive documentation. + * + * Add options: * -drive file=,if=none,id= * -device nvme-subsys,id=,nqn= * -device nvme,serial=,id=, \ @@ -25,6 +34,7 @@ * aerl=,aer_max_queued=, \ * mdts=,vsl=, \ * zoned.zasl=, \ + * zoned.auto_transition=, \ * subsys= * -device nvme-ns,drive=,bus=,nsid=,\ * zoned=, \ @@ -91,6 +101,11 @@ * the minimum memory page size (CAP.MPSMIN). The default value is 0 (i.e. * defaulting to the value of `mdts`). * + * - `zoned.auto_transition` + * Indicates if zones in zone state implicitly opened can be automatically + * transitioned to zone state closed for resource management purposes. + * Defaults to 'on'. + * * nvme namespace device parameters * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * - `shared` @@ -105,7 +120,7 @@ * This parameter is only valid together with the `subsys` parameter. If left * at the default value (`false/off`), the namespace will be attached to all * controllers in the NVMe subsystem at boot-up. If set to `true/on`, the - * namespace will be be available in the subsystem not not attached to any + * namespace will be available in the subsystem but not attached to any * controllers. * * Setting `zoned` to true selects Zoned Command Set at the namespace. @@ -135,26 +150,20 @@ */ #include "qemu/osdep.h" -#include "qemu/units.h" +#include "qemu/cutils.h" #include "qemu/error-report.h" -#include "hw/block/block.h" -#include "hw/pci/msix.h" -#include "hw/pci/pci.h" -#include "hw/qdev-properties.h" -#include "migration/vmstate.h" -#include "sysemu/sysemu.h" +#include "qemu/log.h" +#include "qemu/units.h" #include "qapi/error.h" #include "qapi/visitor.h" -#include "sysemu/hostmem.h" +#include "sysemu/sysemu.h" #include "sysemu/block-backend.h" -#include "exec/memory.h" -#include "qemu/log.h" -#include "qemu/module.h" -#include "qemu/cutils.h" -#include "trace.h" +#include "sysemu/hostmem.h" +#include "hw/pci/msix.h" +#include "migration/vmstate.h" + #include "nvme.h" -#include "nvme-ns.h" -#include "nvme-dif.h" +#include "trace.h" #define NVME_MAX_IOQPAIRS 0xffff #define NVME_DB_SIZE 4 @@ -165,6 +174,7 @@ #define NVME_TEMPERATURE_WARNING 0x157 #define NVME_TEMPERATURE_CRITICAL 0x175 #define NVME_NUM_FW_SLOTS 1 +#define NVME_DEFAULT_MAX_ZA_SIZE (128 * KiB) #define NVME_GUEST_ERR(trace, fmt, ...) \ do { \ @@ -185,6 +195,7 @@ static const bool nvme_feature_support[NVME_FID_MAX] = { [NVME_WRITE_ATOMICITY] = true, [NVME_ASYNCHRONOUS_EVENT_CONF] = true, [NVME_TIMESTAMP] = true, + [NVME_COMMAND_SET_PROFILE] = true, }; static const uint32_t nvme_feature_cap[NVME_FID_MAX] = { @@ -194,6 +205,7 @@ static const uint32_t nvme_feature_cap[NVME_FID_MAX] = { [NVME_NUMBER_OF_QUEUES] = NVME_FEAT_CAP_CHANGE, [NVME_ASYNCHRONOUS_EVENT_CONF] = NVME_FEAT_CAP_CHANGE, [NVME_TIMESTAMP] = NVME_FEAT_CAP_CHANGE, + [NVME_COMMAND_SET_PROFILE] = NVME_FEAT_CAP_CHANGE, }; static const uint32_t nvme_cse_acs[256] = { @@ -387,7 +399,8 @@ static int nvme_addr_write(NvmeCtrl *n, hwaddr addr, void *buf, int size) static bool nvme_nsid_valid(NvmeCtrl *n, uint32_t nsid) { - return nsid && (nsid == NVME_NSID_BROADCAST || nsid <= n->num_namespaces); + return nsid && + (nsid == NVME_NSID_BROADCAST || nsid <= NVME_MAX_NAMESPACES); } static int nvme_check_sqid(NvmeCtrl *n, uint16_t sqid) @@ -426,10 +439,12 @@ static uint8_t nvme_sq_empty(NvmeSQueue *sq) static void nvme_irq_check(NvmeCtrl *n) { + uint32_t intms = ldl_le_p(&n->bar.intms); + if (msix_enabled(&(n->parent_obj))) { return; } - if (~n->bar.intms & n->irq_status) { + if (~intms & n->irq_status) { pci_irq_assert(&n->parent_obj); } else { pci_irq_deassert(&n->parent_obj); @@ -460,7 +475,9 @@ static void nvme_irq_deassert(NvmeCtrl *n, NvmeCQueue *cq) return; } else { assert(cq->vector < 32); - n->irq_status &= ~(1 << cq->vector); + if (!n->cq_pending) { + n->irq_status &= ~(1 << cq->vector); + } nvme_irq_check(n); } } @@ -511,9 +528,7 @@ static void nvme_sg_split(NvmeSg *sg, NvmeNamespace *ns, NvmeSg *data, NvmeSg *mdata) { NvmeSg *dst = data; - size_t size = nvme_lsize(ns); - size_t msize = nvme_msize(ns); - uint32_t trans_len, count = size; + uint32_t trans_len, count = ns->lbasz; uint64_t offset = 0; bool dma = sg->flags & NVME_SG_DMA; size_t sge_len; @@ -545,7 +560,7 @@ static void nvme_sg_split(NvmeSg *sg, NvmeNamespace *ns, NvmeSg *data, if (count == 0) { dst = (dst == data) ? mdata : data; - count = (dst == data) ? size : msize; + count = (dst == data) ? ns->lbasz : ns->lbaf.ms; } if (sge_len == offset) { @@ -574,7 +589,7 @@ static uint16_t nvme_map_addr_cmb(NvmeCtrl *n, QEMUIOVector *iov, hwaddr addr, } static uint16_t nvme_map_addr_pmr(NvmeCtrl *n, QEMUIOVector *iov, hwaddr addr, - size_t len) + size_t len) { if (!len) { return NVME_SUCCESS; @@ -610,6 +625,10 @@ static uint16_t nvme_map_addr(NvmeCtrl *n, NvmeSg *sg, hwaddr addr, size_t len) return NVME_INVALID_USE_OF_CMB | NVME_DNR; } + if (sg->iov.niov + 1 > IOV_MAX) { + goto max_mappings_exceeded; + } + if (cmb) { return nvme_map_addr_cmb(n, &sg->iov, addr, len); } else { @@ -621,9 +640,18 @@ static uint16_t nvme_map_addr(NvmeCtrl *n, NvmeSg *sg, hwaddr addr, size_t len) return NVME_INVALID_USE_OF_CMB | NVME_DNR; } + if (sg->qsg.nsg + 1 > IOV_MAX) { + goto max_mappings_exceeded; + } + qemu_sglist_add(&sg->qsg, addr, len); return NVME_SUCCESS; + +max_mappings_exceeded: + NVME_GUEST_ERR(pci_nvme_ub_too_many_mappings, + "number of mappings exceed 1024"); + return NVME_INTERNAL_DEV_ERROR | NVME_DNR; } static inline bool nvme_addr_is_dma(NvmeCtrl *n, hwaddr addr) @@ -999,16 +1027,12 @@ static uint16_t nvme_map_data(NvmeCtrl *n, uint32_t nlb, NvmeRequest *req) { NvmeNamespace *ns = req->ns; NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; - uint16_t ctrl = le16_to_cpu(rw->control); + bool pi = !!NVME_ID_NS_DPS_TYPE(ns->id_ns.dps); + bool pract = !!(le16_to_cpu(rw->control) & NVME_RW_PRINFO_PRACT); size_t len = nvme_l2b(ns, nlb); uint16_t status; - if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps) && - (ctrl & NVME_RW_PRINFO_PRACT && nvme_msize(ns) == 8)) { - goto out; - } - - if (nvme_ns_ext(ns)) { + if (nvme_ns_ext(ns) && !(pi && pract && ns->lbaf.ms == 8)) { NvmeSg sg; len += nvme_m2b(ns, nlb); @@ -1025,7 +1049,6 @@ static uint16_t nvme_map_data(NvmeCtrl *n, uint32_t nlb, NvmeRequest *req) return NVME_SUCCESS; } -out: return nvme_map_dptr(n, &req->sg, len, &req->cmd); } @@ -1184,15 +1207,12 @@ uint16_t nvme_bounce_data(NvmeCtrl *n, uint8_t *ptr, uint32_t len, { NvmeNamespace *ns = req->ns; NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; - uint16_t ctrl = le16_to_cpu(rw->control); + bool pi = !!NVME_ID_NS_DPS_TYPE(ns->id_ns.dps); + bool pract = !!(le16_to_cpu(rw->control) & NVME_RW_PRINFO_PRACT); - if (nvme_ns_ext(ns) && - !(ctrl & NVME_RW_PRINFO_PRACT && nvme_msize(ns) == 8)) { - size_t lsize = nvme_lsize(ns); - size_t msize = nvme_msize(ns); - - return nvme_tx_interleaved(n, &req->sg, ptr, len, lsize, msize, 0, - dir); + if (nvme_ns_ext(ns) && !(pi && pract && ns->lbaf.ms == 8)) { + return nvme_tx_interleaved(n, &req->sg, ptr, len, ns->lbasz, + ns->lbaf.ms, 0, dir); } return nvme_tx(n, &req->sg, ptr, len, dir); @@ -1205,11 +1225,8 @@ uint16_t nvme_bounce_mdata(NvmeCtrl *n, uint8_t *ptr, uint32_t len, uint16_t status; if (nvme_ns_ext(ns)) { - size_t lsize = nvme_lsize(ns); - size_t msize = nvme_msize(ns); - - return nvme_tx_interleaved(n, &req->sg, ptr, len, msize, lsize, lsize, - dir); + return nvme_tx_interleaved(n, &req->sg, ptr, len, ns->lbaf.ms, + ns->lbasz, ns->lbasz, dir); } nvme_sg_unmap(&req->sg); @@ -1253,6 +1270,7 @@ static void nvme_post_cqes(void *opaque) NvmeCQueue *cq = opaque; NvmeCtrl *n = cq->ctrl; NvmeRequest *req, *next; + bool pending = cq->head != cq->tail; int ret; QTAILQ_FOREACH_SAFE(req, &cq->req_list, entry, next) { @@ -1273,7 +1291,7 @@ static void nvme_post_cqes(void *opaque) if (ret) { trace_pci_nvme_err_addr_write(addr); trace_pci_nvme_err_cfs(); - n->bar.csts = NVME_CSTS_FAILED; + stl_le_p(&n->bar.csts, NVME_CSTS_FAILED); break; } QTAILQ_REMOVE(&cq->req_list, req, entry); @@ -1282,6 +1300,10 @@ static void nvme_post_cqes(void *opaque) QTAILQ_INSERT_TAIL(&sq->req_list, req, entry); } if (cq->tail != cq->head) { + if (cq->irq_enabled && !pending) { + n->cq_pending++; + } + nvme_irq_assert(n, cq); } } @@ -1290,6 +1312,8 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req) { assert(cq->cqid == req->sq->cqid); trace_pci_nvme_enqueue_req_completion(nvme_cid(req), cq->cqid, + le32_to_cpu(req->cqe.result), + le32_to_cpu(req->cqe.dw1), req->status); if (req->status) { @@ -1426,24 +1450,22 @@ static inline uint16_t nvme_check_bounds(NvmeNamespace *ns, uint64_t slba, uint64_t nsze = le64_to_cpu(ns->id_ns.nsze); if (unlikely(UINT64_MAX - slba < nlb || slba + nlb > nsze)) { + trace_pci_nvme_err_invalid_lba_range(slba, nlb, nsze); return NVME_LBA_RANGE | NVME_DNR; } return NVME_SUCCESS; } -static uint16_t nvme_check_dulbe(NvmeNamespace *ns, uint64_t slba, - uint32_t nlb) +static int nvme_block_status_all(NvmeNamespace *ns, uint64_t slba, + uint32_t nlb, int flags) { BlockDriverState *bs = blk_bs(ns->blkconf.blk); int64_t pnum = 0, bytes = nvme_l2b(ns, nlb); int64_t offset = nvme_l2b(ns, slba); - bool zeroed; int ret; - Error *local_err = NULL; - /* * `pnum` holds the number of bytes after offset that shares the same * allocation status as the byte at offset. If `pnum` is different from @@ -1455,23 +1477,41 @@ static uint16_t nvme_check_dulbe(NvmeNamespace *ns, uint64_t slba, ret = bdrv_block_status(bs, offset, bytes, &pnum, NULL, NULL); if (ret < 0) { - error_setg_errno(&local_err, -ret, "unable to get block status"); - error_report_err(local_err); - - return NVME_INTERNAL_DEV_ERROR; + return ret; } - zeroed = !!(ret & BDRV_BLOCK_ZERO); - trace_pci_nvme_block_status(offset, bytes, pnum, ret, zeroed); + trace_pci_nvme_block_status(offset, bytes, pnum, ret, + !!(ret & BDRV_BLOCK_ZERO)); - if (zeroed) { - return NVME_DULB; + if (!(ret & flags)) { + return 1; } offset += pnum; } while (pnum != bytes); + return 0; +} + +static uint16_t nvme_check_dulbe(NvmeNamespace *ns, uint64_t slba, + uint32_t nlb) +{ + int ret; + Error *err = NULL; + + ret = nvme_block_status_all(ns, slba, nlb, BDRV_BLOCK_DATA); + if (ret) { + if (ret < 0) { + error_setg_errno(&err, -ret, "unable to get block status"); + error_report_err(err); + + return NVME_INTERNAL_DEV_ERROR; + } + + return NVME_DULB; + } + return NVME_SUCCESS; } @@ -1521,7 +1561,10 @@ static inline NvmeZone *nvme_get_zone_by_slba(NvmeNamespace *ns, uint64_t slba) { uint32_t zone_idx = nvme_zone_idx(ns, slba); - assert(zone_idx < ns->num_zones); + if (zone_idx >= ns->num_zones) { + return NULL; + } + return &ns->zone_array[zone_idx]; } @@ -1598,11 +1641,16 @@ static uint16_t nvme_check_zone_state_for_read(NvmeZone *zone) static uint16_t nvme_check_zone_read(NvmeNamespace *ns, uint64_t slba, uint32_t nlb) { - NvmeZone *zone = nvme_get_zone_by_slba(ns, slba); - uint64_t bndry = nvme_zone_rd_boundary(ns, zone); - uint64_t end = slba + nlb; + NvmeZone *zone; + uint64_t bndry, end; uint16_t status; + zone = nvme_get_zone_by_slba(ns, slba); + assert(zone); + + bndry = nvme_zone_rd_boundary(ns, zone); + end = slba + nlb; + status = nvme_check_zone_state_for_read(zone); if (status) { ; @@ -1665,6 +1713,29 @@ static uint16_t nvme_zrm_close(NvmeNamespace *ns, NvmeZone *zone) } } +static uint16_t nvme_zrm_reset(NvmeNamespace *ns, NvmeZone *zone) +{ + switch (nvme_get_zone_state(zone)) { + case NVME_ZONE_STATE_EXPLICITLY_OPEN: + case NVME_ZONE_STATE_IMPLICITLY_OPEN: + nvme_aor_dec_open(ns); + /* fallthrough */ + case NVME_ZONE_STATE_CLOSED: + nvme_aor_dec_active(ns); + /* fallthrough */ + case NVME_ZONE_STATE_FULL: + zone->w_ptr = zone->d.zslba; + zone->d.wp = zone->w_ptr; + nvme_assign_zone_state(ns, zone, NVME_ZONE_STATE_EMPTY); + /* fallthrough */ + case NVME_ZONE_STATE_EMPTY: + return NVME_SUCCESS; + + default: + return NVME_ZONE_INVAL_TRANSITION; + } +} + static void nvme_zrm_auto_transition_zone(NvmeNamespace *ns) { NvmeZone *zone; @@ -1682,8 +1753,12 @@ static void nvme_zrm_auto_transition_zone(NvmeNamespace *ns) } } -static uint16_t __nvme_zrm_open(NvmeNamespace *ns, NvmeZone *zone, - bool implicit) +enum { + NVME_ZRM_AUTO = 1 << 0, +}; + +static uint16_t nvme_zrm_open_flags(NvmeCtrl *n, NvmeNamespace *ns, + NvmeZone *zone, int flags) { int act = 0; uint16_t status; @@ -1695,7 +1770,9 @@ static uint16_t __nvme_zrm_open(NvmeNamespace *ns, NvmeZone *zone, /* fallthrough */ case NVME_ZONE_STATE_CLOSED: - nvme_zrm_auto_transition_zone(ns); + if (n->params.auto_transition_zones) { + nvme_zrm_auto_transition_zone(ns); + } status = nvme_aor_check(ns, act, 1); if (status) { return status; @@ -1707,7 +1784,7 @@ static uint16_t __nvme_zrm_open(NvmeNamespace *ns, NvmeZone *zone, nvme_aor_inc_open(ns); - if (implicit) { + if (flags & NVME_ZRM_AUTO) { nvme_assign_zone_state(ns, zone, NVME_ZONE_STATE_IMPLICITLY_OPEN); return NVME_SUCCESS; } @@ -1715,7 +1792,7 @@ static uint16_t __nvme_zrm_open(NvmeNamespace *ns, NvmeZone *zone, /* fallthrough */ case NVME_ZONE_STATE_IMPLICITLY_OPEN: - if (implicit) { + if (flags & NVME_ZRM_AUTO) { return NVME_SUCCESS; } @@ -1731,18 +1808,20 @@ static uint16_t __nvme_zrm_open(NvmeNamespace *ns, NvmeZone *zone, } } -static inline uint16_t nvme_zrm_auto(NvmeNamespace *ns, NvmeZone *zone) +static inline uint16_t nvme_zrm_auto(NvmeCtrl *n, NvmeNamespace *ns, + NvmeZone *zone) { - return __nvme_zrm_open(ns, zone, true); + return nvme_zrm_open_flags(n, ns, zone, NVME_ZRM_AUTO); } -static inline uint16_t nvme_zrm_open(NvmeNamespace *ns, NvmeZone *zone) +static inline uint16_t nvme_zrm_open(NvmeCtrl *n, NvmeNamespace *ns, + NvmeZone *zone) { - return __nvme_zrm_open(ns, zone, false); + return nvme_zrm_open_flags(n, ns, zone, 0); } -static void __nvme_advance_zone_wp(NvmeNamespace *ns, NvmeZone *zone, - uint32_t nlb) +static void nvme_advance_zone_wp(NvmeNamespace *ns, NvmeZone *zone, + uint32_t nlb) { zone->d.wp += nlb; @@ -1761,8 +1840,9 @@ static void nvme_finalize_zoned_write(NvmeNamespace *ns, NvmeRequest *req) slba = le64_to_cpu(rw->slba); nlb = le16_to_cpu(rw->nlb) + 1; zone = nvme_get_zone_by_slba(ns, slba); + assert(zone); - __nvme_advance_zone_wp(ns, zone, nlb); + nvme_advance_zone_wp(ns, zone, nlb); } static inline bool nvme_is_write(NvmeRequest *req) @@ -1774,22 +1854,19 @@ static inline bool nvme_is_write(NvmeRequest *req) rw->opcode == NVME_CMD_WRITE_ZEROES; } +static AioContext *nvme_get_aio_context(BlockAIOCB *acb) +{ + return qemu_get_aio_context(); +} + static void nvme_misc_cb(void *opaque, int ret) { NvmeRequest *req = opaque; - NvmeNamespace *ns = req->ns; - BlockBackend *blk = ns->blkconf.blk; - BlockAcctCookie *acct = &req->acct; - BlockAcctStats *stats = blk_get_stats(blk); - - trace_pci_nvme_misc_cb(nvme_cid(req), blk_name(blk)); + trace_pci_nvme_misc_cb(nvme_cid(req)); if (ret) { - block_acct_failed(stats, acct); nvme_aio_err(req, ret); - } else { - block_acct_done(stats, acct); } nvme_enqueue_req_completion(nvme_cq(req), req); @@ -1832,11 +1909,11 @@ static void nvme_rw_cb(void *opaque, int ret) goto out; } - if (nvme_msize(ns)) { + if (ns->lbaf.ms) { NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; uint64_t slba = le64_to_cpu(rw->slba); uint32_t nlb = (uint32_t)le16_to_cpu(rw->nlb) + 1; - uint64_t offset = ns->mdata_offset + nvme_m2b(ns, slba); + uint64_t offset = nvme_moff(ns, slba); if (req->cmd.opcode == NVME_CMD_WRITE_ZEROES) { size_t mlen = nvme_m2b(ns, nlb); @@ -1869,77 +1946,6 @@ out: nvme_rw_complete_cb(req, ret); } -struct nvme_aio_format_ctx { - NvmeRequest *req; - NvmeNamespace *ns; - - /* number of outstanding write zeroes for this namespace */ - int *count; -}; - -static void nvme_aio_format_cb(void *opaque, int ret) -{ - struct nvme_aio_format_ctx *ctx = opaque; - NvmeRequest *req = ctx->req; - NvmeNamespace *ns = ctx->ns; - uintptr_t *num_formats = (uintptr_t *)&req->opaque; - int *count = ctx->count; - - g_free(ctx); - - if (ret) { - nvme_aio_err(req, ret); - } - - if (--(*count)) { - return; - } - - g_free(count); - ns->status = 0x0; - - if (--(*num_formats)) { - return; - } - - nvme_enqueue_req_completion(nvme_cq(req), req); -} - -struct nvme_aio_flush_ctx { - NvmeRequest *req; - NvmeNamespace *ns; - BlockAcctCookie acct; -}; - -static void nvme_aio_flush_cb(void *opaque, int ret) -{ - struct nvme_aio_flush_ctx *ctx = opaque; - NvmeRequest *req = ctx->req; - uintptr_t *num_flushes = (uintptr_t *)&req->opaque; - - BlockBackend *blk = ctx->ns->blkconf.blk; - BlockAcctCookie *acct = &ctx->acct; - BlockAcctStats *stats = blk_get_stats(blk); - - trace_pci_nvme_aio_flush_cb(nvme_cid(req), blk_name(blk)); - - if (!ret) { - block_acct_done(stats, acct); - } else { - block_acct_failed(stats, acct); - nvme_aio_err(req, ret); - } - - (*num_flushes)--; - g_free(ctx); - - if (*num_flushes) { - return; - } - - nvme_enqueue_req_completion(nvme_cq(req), req); -} - static void nvme_verify_cb(void *opaque, int ret) { NvmeBounceContext *ctx = opaque; @@ -1950,14 +1956,13 @@ static void nvme_verify_cb(void *opaque, int ret) BlockAcctStats *stats = blk_get_stats(blk); NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; uint64_t slba = le64_to_cpu(rw->slba); - uint16_t ctrl = le16_to_cpu(rw->control); + uint8_t prinfo = NVME_RW_PRINFO(le16_to_cpu(rw->control)); uint16_t apptag = le16_to_cpu(rw->apptag); uint16_t appmask = le16_to_cpu(rw->appmask); uint32_t reftag = le32_to_cpu(rw->reftag); uint16_t status; - trace_pci_nvme_verify_cb(nvme_cid(req), NVME_RW_PRINFO(ctrl), apptag, - appmask, reftag); + trace_pci_nvme_verify_cb(nvme_cid(req), prinfo, apptag, appmask, reftag); if (ret) { block_acct_failed(stats, acct); @@ -1977,7 +1982,7 @@ static void nvme_verify_cb(void *opaque, int ret) req->status = nvme_dif_check(ns, ctx->data.bounce, ctx->data.iov.size, ctx->mdata.bounce, ctx->mdata.iov.size, - ctrl, slba, apptag, appmask, reftag); + prinfo, slba, apptag, appmask, &reftag); } out: @@ -2002,7 +2007,7 @@ static void nvme_verify_mdata_in_cb(void *opaque, int ret) uint64_t slba = le64_to_cpu(rw->slba); uint32_t nlb = le16_to_cpu(rw->nlb) + 1; size_t mlen = nvme_m2b(ns, nlb); - uint64_t offset = ns->mdata_offset + nvme_m2b(ns, slba); + uint64_t offset = nvme_moff(ns, slba); BlockBackend *blk = ns->blkconf.blk; trace_pci_nvme_verify_mdata_in_cb(nvme_cid(req), blk_name(blk)); @@ -2024,327 +2029,6 @@ out: nvme_verify_cb(ctx, ret); } -static void nvme_aio_discard_cb(void *opaque, int ret) -{ - NvmeRequest *req = opaque; - uintptr_t *discards = (uintptr_t *)&req->opaque; - - trace_pci_nvme_aio_discard_cb(nvme_cid(req)); - - if (ret) { - nvme_aio_err(req, ret); - } - - (*discards)--; - - if (*discards) { - return; - } - - nvme_enqueue_req_completion(nvme_cq(req), req); -} - -struct nvme_zone_reset_ctx { - NvmeRequest *req; - NvmeZone *zone; -}; - -static void nvme_aio_zone_reset_complete_cb(void *opaque, int ret) -{ - struct nvme_zone_reset_ctx *ctx = opaque; - NvmeRequest *req = ctx->req; - NvmeNamespace *ns = req->ns; - NvmeZone *zone = ctx->zone; - uintptr_t *resets = (uintptr_t *)&req->opaque; - - if (ret) { - nvme_aio_err(req, ret); - goto out; - } - - switch (nvme_get_zone_state(zone)) { - case NVME_ZONE_STATE_EXPLICITLY_OPEN: - case NVME_ZONE_STATE_IMPLICITLY_OPEN: - nvme_aor_dec_open(ns); - /* fall through */ - case NVME_ZONE_STATE_CLOSED: - nvme_aor_dec_active(ns); - /* fall through */ - case NVME_ZONE_STATE_FULL: - zone->w_ptr = zone->d.zslba; - zone->d.wp = zone->w_ptr; - nvme_assign_zone_state(ns, zone, NVME_ZONE_STATE_EMPTY); - /* fall through */ - default: - break; - } - -out: - g_free(ctx); - - (*resets)--; - - if (*resets) { - return; - } - - nvme_enqueue_req_completion(nvme_cq(req), req); -} - -static void nvme_aio_zone_reset_cb(void *opaque, int ret) -{ - struct nvme_zone_reset_ctx *ctx = opaque; - NvmeRequest *req = ctx->req; - NvmeNamespace *ns = req->ns; - NvmeZone *zone = ctx->zone; - - trace_pci_nvme_aio_zone_reset_cb(nvme_cid(req), zone->d.zslba); - - if (ret) { - goto out; - } - - if (nvme_msize(ns)) { - int64_t offset = ns->mdata_offset + nvme_m2b(ns, zone->d.zslba); - - blk_aio_pwrite_zeroes(ns->blkconf.blk, offset, - nvme_m2b(ns, ns->zone_size), BDRV_REQ_MAY_UNMAP, - nvme_aio_zone_reset_complete_cb, ctx); - return; - } - -out: - nvme_aio_zone_reset_complete_cb(opaque, ret); -} - -struct nvme_copy_ctx { - int copies; - uint8_t *bounce; - uint8_t *mbounce; - uint32_t nlb; - NvmeCopySourceRange *ranges; -}; - -struct nvme_copy_in_ctx { - NvmeRequest *req; - QEMUIOVector iov; - NvmeCopySourceRange *range; -}; - -static void nvme_copy_complete_cb(void *opaque, int ret) -{ - NvmeRequest *req = opaque; - NvmeNamespace *ns = req->ns; - struct nvme_copy_ctx *ctx = req->opaque; - - if (ret) { - block_acct_failed(blk_get_stats(ns->blkconf.blk), &req->acct); - nvme_aio_err(req, ret); - goto out; - } - - block_acct_done(blk_get_stats(ns->blkconf.blk), &req->acct); - -out: - if (ns->params.zoned) { - NvmeCopyCmd *copy = (NvmeCopyCmd *)&req->cmd; - uint64_t sdlba = le64_to_cpu(copy->sdlba); - NvmeZone *zone = nvme_get_zone_by_slba(ns, sdlba); - - __nvme_advance_zone_wp(ns, zone, ctx->nlb); - } - - g_free(ctx->bounce); - g_free(ctx->mbounce); - g_free(ctx); - - nvme_enqueue_req_completion(nvme_cq(req), req); -} - -static void nvme_copy_cb(void *opaque, int ret) -{ - NvmeRequest *req = opaque; - NvmeNamespace *ns = req->ns; - struct nvme_copy_ctx *ctx = req->opaque; - - trace_pci_nvme_copy_cb(nvme_cid(req)); - - if (ret) { - goto out; - } - - if (nvme_msize(ns)) { - NvmeCopyCmd *copy = (NvmeCopyCmd *)&req->cmd; - uint64_t sdlba = le64_to_cpu(copy->sdlba); - int64_t offset = ns->mdata_offset + nvme_m2b(ns, sdlba); - - qemu_iovec_reset(&req->sg.iov); - qemu_iovec_add(&req->sg.iov, ctx->mbounce, nvme_m2b(ns, ctx->nlb)); - - req->aiocb = blk_aio_pwritev(ns->blkconf.blk, offset, &req->sg.iov, 0, - nvme_copy_complete_cb, req); - return; - } - -out: - nvme_copy_complete_cb(opaque, ret); -} - -static void nvme_copy_in_complete(NvmeRequest *req) -{ - NvmeNamespace *ns = req->ns; - NvmeCopyCmd *copy = (NvmeCopyCmd *)&req->cmd; - struct nvme_copy_ctx *ctx = req->opaque; - uint64_t sdlba = le64_to_cpu(copy->sdlba); - uint16_t status; - - trace_pci_nvme_copy_in_complete(nvme_cid(req)); - - block_acct_done(blk_get_stats(ns->blkconf.blk), &req->acct); - - if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps)) { - uint16_t prinfor = (copy->control[0] >> 4) & 0xf; - uint16_t prinfow = (copy->control[2] >> 2) & 0xf; - uint16_t nr = copy->nr + 1; - NvmeCopySourceRange *range; - uint64_t slba; - uint32_t nlb; - uint16_t apptag, appmask; - uint32_t reftag; - uint8_t *buf = ctx->bounce, *mbuf = ctx->mbounce; - size_t len, mlen; - int i; - - /* - * The dif helpers expects prinfo to be similar to the control field of - * the NvmeRwCmd, so shift by 10 to fake it. - */ - prinfor = prinfor << 10; - prinfow = prinfow << 10; - - for (i = 0; i < nr; i++) { - range = &ctx->ranges[i]; - slba = le64_to_cpu(range->slba); - nlb = le16_to_cpu(range->nlb) + 1; - len = nvme_l2b(ns, nlb); - mlen = nvme_m2b(ns, nlb); - apptag = le16_to_cpu(range->apptag); - appmask = le16_to_cpu(range->appmask); - reftag = le32_to_cpu(range->reftag); - - status = nvme_dif_check(ns, buf, len, mbuf, mlen, prinfor, slba, - apptag, appmask, reftag); - if (status) { - goto invalid; - } - - buf += len; - mbuf += mlen; - } - - apptag = le16_to_cpu(copy->apptag); - appmask = le16_to_cpu(copy->appmask); - reftag = le32_to_cpu(copy->reftag); - - if (prinfow & NVME_RW_PRINFO_PRACT) { - size_t len = nvme_l2b(ns, ctx->nlb); - size_t mlen = nvme_m2b(ns, ctx->nlb); - - status = nvme_check_prinfo(ns, prinfow, sdlba, reftag); - if (status) { - goto invalid; - } - - nvme_dif_pract_generate_dif(ns, ctx->bounce, len, ctx->mbounce, - mlen, apptag, reftag); - } else { - status = nvme_dif_check(ns, ctx->bounce, len, ctx->mbounce, mlen, - prinfow, sdlba, apptag, appmask, reftag); - if (status) { - goto invalid; - } - } - } - - status = nvme_check_bounds(ns, sdlba, ctx->nlb); - if (status) { - trace_pci_nvme_err_invalid_lba_range(sdlba, ctx->nlb, ns->id_ns.nsze); - goto invalid; - } - - if (ns->params.zoned) { - NvmeZone *zone = nvme_get_zone_by_slba(ns, sdlba); - - status = nvme_check_zone_write(ns, zone, sdlba, ctx->nlb); - if (status) { - goto invalid; - } - - status = nvme_zrm_auto(ns, zone); - if (status) { - goto invalid; - } - - zone->w_ptr += ctx->nlb; - } - - qemu_iovec_init(&req->sg.iov, 1); - qemu_iovec_add(&req->sg.iov, ctx->bounce, nvme_l2b(ns, ctx->nlb)); - - block_acct_start(blk_get_stats(ns->blkconf.blk), &req->acct, 0, - BLOCK_ACCT_WRITE); - - req->aiocb = blk_aio_pwritev(ns->blkconf.blk, nvme_l2b(ns, sdlba), - &req->sg.iov, 0, nvme_copy_cb, req); - - return; - -invalid: - req->status = status; - - g_free(ctx->bounce); - g_free(ctx); - - nvme_enqueue_req_completion(nvme_cq(req), req); -} - -static void nvme_aio_copy_in_cb(void *opaque, int ret) -{ - struct nvme_copy_in_ctx *in_ctx = opaque; - NvmeRequest *req = in_ctx->req; - NvmeNamespace *ns = req->ns; - struct nvme_copy_ctx *ctx = req->opaque; - - qemu_iovec_destroy(&in_ctx->iov); - g_free(in_ctx); - - trace_pci_nvme_aio_copy_in_cb(nvme_cid(req)); - - if (ret) { - nvme_aio_err(req, ret); - } - - ctx->copies--; - - if (ctx->copies) { - return; - } - - if (req->status) { - block_acct_failed(blk_get_stats(ns->blkconf.blk), &req->acct); - - g_free(ctx->bounce); - g_free(ctx->mbounce); - g_free(ctx); - - nvme_enqueue_req_completion(nvme_cq(req), req); - - return; - } - - nvme_copy_in_complete(req); -} - struct nvme_compare_ctx { struct { QEMUIOVector iov; @@ -2363,16 +2047,25 @@ static void nvme_compare_mdata_cb(void *opaque, int ret) NvmeNamespace *ns = req->ns; NvmeCtrl *n = nvme_ctrl(req); NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; - uint16_t ctrl = le16_to_cpu(rw->control); + uint8_t prinfo = NVME_RW_PRINFO(le16_to_cpu(rw->control)); uint16_t apptag = le16_to_cpu(rw->apptag); uint16_t appmask = le16_to_cpu(rw->appmask); uint32_t reftag = le32_to_cpu(rw->reftag); struct nvme_compare_ctx *ctx = req->opaque; g_autofree uint8_t *buf = NULL; + BlockBackend *blk = ns->blkconf.blk; + BlockAcctCookie *acct = &req->acct; + BlockAcctStats *stats = blk_get_stats(blk); uint16_t status = NVME_SUCCESS; trace_pci_nvme_compare_mdata_cb(nvme_cid(req)); + if (ret) { + block_acct_failed(stats, acct); + nvme_aio_err(req, ret); + goto out; + } + buf = g_malloc(ctx->mdata.iov.size); status = nvme_bounce_mdata(n, buf, ctx->mdata.iov.size, @@ -2387,12 +2080,11 @@ static void nvme_compare_mdata_cb(void *opaque, int ret) uint8_t *bufp; uint8_t *mbufp = ctx->mdata.bounce; uint8_t *end = mbufp + ctx->mdata.iov.size; - size_t msize = nvme_msize(ns); int16_t pil = 0; status = nvme_dif_check(ns, ctx->data.bounce, ctx->data.iov.size, - ctx->mdata.bounce, ctx->mdata.iov.size, ctrl, - slba, apptag, appmask, reftag); + ctx->mdata.bounce, ctx->mdata.iov.size, prinfo, + slba, apptag, appmask, &reftag); if (status) { req->status = status; goto out; @@ -2403,11 +2095,11 @@ static void nvme_compare_mdata_cb(void *opaque, int ret) * tuple. */ if (!(ns->id_ns.dps & NVME_ID_NS_DPS_FIRST_EIGHT)) { - pil = nvme_msize(ns) - sizeof(NvmeDifTuple); + pil = ns->lbaf.ms - sizeof(NvmeDifTuple); } - for (bufp = buf; mbufp < end; bufp += msize, mbufp += msize) { - if (memcmp(bufp + pil, mbufp + pil, msize - pil)) { + for (bufp = buf; mbufp < end; bufp += ns->lbaf.ms, mbufp += ns->lbaf.ms) { + if (memcmp(bufp + pil, mbufp + pil, ns->lbaf.ms - pil)) { req->status = NVME_CMP_FAILURE; goto out; } @@ -2421,6 +2113,8 @@ static void nvme_compare_mdata_cb(void *opaque, int ret) goto out; } + block_acct_done(stats, acct); + out: qemu_iovec_destroy(&ctx->data.iov); g_free(ctx->data.bounce); @@ -2468,12 +2162,12 @@ static void nvme_compare_data_cb(void *opaque, int ret) goto out; } - if (nvme_msize(ns)) { + if (ns->lbaf.ms) { NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; uint64_t slba = le64_to_cpu(rw->slba); uint32_t nlb = le16_to_cpu(rw->nlb) + 1; size_t mlen = nvme_m2b(ns, nlb); - uint64_t offset = ns->mdata_offset + nvme_m2b(ns, slba); + uint64_t offset = nvme_moff(ns, slba); ctx->mdata.bounce = g_malloc(mlen); @@ -2495,77 +2189,182 @@ out: nvme_enqueue_req_completion(nvme_cq(req), req); } +typedef struct NvmeDSMAIOCB { + BlockAIOCB common; + BlockAIOCB *aiocb; + NvmeRequest *req; + QEMUBH *bh; + int ret; + + NvmeDsmRange *range; + unsigned int nr; + unsigned int idx; +} NvmeDSMAIOCB; + +static void nvme_dsm_cancel(BlockAIOCB *aiocb) +{ + NvmeDSMAIOCB *iocb = container_of(aiocb, NvmeDSMAIOCB, common); + + /* break nvme_dsm_cb loop */ + iocb->idx = iocb->nr; + iocb->ret = -ECANCELED; + + if (iocb->aiocb) { + blk_aio_cancel_async(iocb->aiocb); + iocb->aiocb = NULL; + } else { + /* + * We only reach this if nvme_dsm_cancel() has already been called or + * the command ran to completion and nvme_dsm_bh is scheduled to run. + */ + assert(iocb->idx == iocb->nr); + } +} + +static const AIOCBInfo nvme_dsm_aiocb_info = { + .aiocb_size = sizeof(NvmeDSMAIOCB), + .cancel_async = nvme_dsm_cancel, +}; + +static void nvme_dsm_bh(void *opaque) +{ + NvmeDSMAIOCB *iocb = opaque; + + iocb->common.cb(iocb->common.opaque, iocb->ret); + + qemu_bh_delete(iocb->bh); + iocb->bh = NULL; + qemu_aio_unref(iocb); +} + +static void nvme_dsm_cb(void *opaque, int ret); + +static void nvme_dsm_md_cb(void *opaque, int ret) +{ + NvmeDSMAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = req->ns; + NvmeDsmRange *range; + uint64_t slba; + uint32_t nlb; + + if (ret < 0) { + iocb->ret = ret; + goto done; + } + + if (!ns->lbaf.ms) { + nvme_dsm_cb(iocb, 0); + return; + } + + range = &iocb->range[iocb->idx - 1]; + slba = le64_to_cpu(range->slba); + nlb = le32_to_cpu(range->nlb); + + /* + * Check that all block were discarded (zeroed); otherwise we do not zero + * the metadata. + */ + + ret = nvme_block_status_all(ns, slba, nlb, BDRV_BLOCK_ZERO); + if (ret) { + if (ret < 0) { + iocb->ret = ret; + goto done; + } + + nvme_dsm_cb(iocb, 0); + } + + iocb->aiocb = blk_aio_pwrite_zeroes(ns->blkconf.blk, nvme_moff(ns, slba), + nvme_m2b(ns, nlb), BDRV_REQ_MAY_UNMAP, + nvme_dsm_cb, iocb); + return; + +done: + iocb->aiocb = NULL; + qemu_bh_schedule(iocb->bh); +} + +static void nvme_dsm_cb(void *opaque, int ret) +{ + NvmeDSMAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeCtrl *n = nvme_ctrl(req); + NvmeNamespace *ns = req->ns; + NvmeDsmRange *range; + uint64_t slba; + uint32_t nlb; + + if (ret < 0) { + iocb->ret = ret; + goto done; + } + +next: + if (iocb->idx == iocb->nr) { + goto done; + } + + range = &iocb->range[iocb->idx++]; + slba = le64_to_cpu(range->slba); + nlb = le32_to_cpu(range->nlb); + + trace_pci_nvme_dsm_deallocate(slba, nlb); + + if (nlb > n->dmrsl) { + trace_pci_nvme_dsm_single_range_limit_exceeded(nlb, n->dmrsl); + goto next; + } + + if (nvme_check_bounds(ns, slba, nlb)) { + trace_pci_nvme_err_invalid_lba_range(slba, nlb, + ns->id_ns.nsze); + goto next; + } + + iocb->aiocb = blk_aio_pdiscard(ns->blkconf.blk, nvme_l2b(ns, slba), + nvme_l2b(ns, nlb), + nvme_dsm_md_cb, iocb); + return; + +done: + iocb->aiocb = NULL; + qemu_bh_schedule(iocb->bh); +} + static uint16_t nvme_dsm(NvmeCtrl *n, NvmeRequest *req) { NvmeNamespace *ns = req->ns; NvmeDsmCmd *dsm = (NvmeDsmCmd *) &req->cmd; - uint32_t attr = le32_to_cpu(dsm->attributes); uint32_t nr = (le32_to_cpu(dsm->nr) & 0xff) + 1; - uint16_t status = NVME_SUCCESS; - trace_pci_nvme_dsm(nvme_cid(req), nvme_nsid(ns), nr, attr); + trace_pci_nvme_dsm(nr, attr); if (attr & NVME_DSMGMT_AD) { - int64_t offset; - size_t len; - NvmeDsmRange range[nr]; - uintptr_t *discards = (uintptr_t *)&req->opaque; + NvmeDSMAIOCB *iocb = blk_aio_get(&nvme_dsm_aiocb_info, ns->blkconf.blk, + nvme_misc_cb, req); - status = nvme_h2c(n, (uint8_t *)range, sizeof(range), req); + iocb->req = req; + iocb->bh = qemu_bh_new(nvme_dsm_bh, iocb); + iocb->ret = 0; + iocb->range = g_new(NvmeDsmRange, nr); + iocb->nr = nr; + iocb->idx = 0; + + status = nvme_h2c(n, (uint8_t *)iocb->range, sizeof(NvmeDsmRange) * nr, + req); if (status) { return status; } - /* - * AIO callbacks may be called immediately, so initialize discards to 1 - * to make sure the the callback does not complete the request before - * all discards have been issued. - */ - *discards = 1; + req->aiocb = &iocb->common; + nvme_dsm_cb(iocb, 0); - for (int i = 0; i < nr; i++) { - uint64_t slba = le64_to_cpu(range[i].slba); - uint32_t nlb = le32_to_cpu(range[i].nlb); - - if (nvme_check_bounds(ns, slba, nlb)) { - trace_pci_nvme_err_invalid_lba_range(slba, nlb, - ns->id_ns.nsze); - continue; - } - - trace_pci_nvme_dsm_deallocate(nvme_cid(req), nvme_nsid(ns), slba, - nlb); - - if (nlb > n->dmrsl) { - trace_pci_nvme_dsm_single_range_limit_exceeded(nlb, n->dmrsl); - } - - offset = nvme_l2b(ns, slba); - len = nvme_l2b(ns, nlb); - - while (len) { - size_t bytes = MIN(BDRV_REQUEST_MAX_BYTES, len); - - (*discards)++; - - blk_aio_pdiscard(ns->blkconf.blk, offset, bytes, - nvme_aio_discard_cb, req); - - offset += bytes; - len -= bytes; - } - } - - /* account for the 1-initialization */ - (*discards)--; - - if (*discards) { - status = NVME_NO_COMPLETE; - } else { - status = req->status; - } + return NVME_NO_COMPLETE; } return status; @@ -2580,7 +2379,7 @@ static uint16_t nvme_verify(NvmeCtrl *n, NvmeRequest *req) uint32_t nlb = le16_to_cpu(rw->nlb) + 1; size_t len = nvme_l2b(ns, nlb); int64_t offset = nvme_l2b(ns, slba); - uint16_t ctrl = le16_to_cpu(rw->control); + uint8_t prinfo = NVME_RW_PRINFO(le16_to_cpu(rw->control)); uint32_t reftag = le32_to_cpu(rw->reftag); NvmeBounceContext *ctx = NULL; uint16_t status; @@ -2588,12 +2387,12 @@ static uint16_t nvme_verify(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_verify(nvme_cid(req), nvme_nsid(ns), slba, nlb); if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps)) { - status = nvme_check_prinfo(ns, ctrl, slba, reftag); + status = nvme_check_prinfo(ns, prinfo, slba, reftag); if (status) { return status; } - if (ctrl & NVME_RW_PRINFO_PRACT) { + if (prinfo & NVME_PRINFO_PRACT) { return NVME_INVALID_PROT_INFO | NVME_DNR; } } @@ -2604,7 +2403,6 @@ static uint16_t nvme_verify(NvmeCtrl *n, NvmeRequest *req) status = nvme_check_bounds(ns, slba, nlb); if (status) { - trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); return status; } @@ -2631,159 +2429,433 @@ static uint16_t nvme_verify(NvmeCtrl *n, NvmeRequest *req) return NVME_NO_COMPLETE; } +typedef struct NvmeCopyAIOCB { + BlockAIOCB common; + BlockAIOCB *aiocb; + NvmeRequest *req; + QEMUBH *bh; + int ret; + + NvmeCopySourceRange *ranges; + int nr; + int idx; + + uint8_t *bounce; + QEMUIOVector iov; + struct { + BlockAcctCookie read; + BlockAcctCookie write; + } acct; + + uint32_t reftag; + uint64_t slba; + + NvmeZone *zone; +} NvmeCopyAIOCB; + +static void nvme_copy_cancel(BlockAIOCB *aiocb) +{ + NvmeCopyAIOCB *iocb = container_of(aiocb, NvmeCopyAIOCB, common); + + iocb->ret = -ECANCELED; + + if (iocb->aiocb) { + blk_aio_cancel_async(iocb->aiocb); + iocb->aiocb = NULL; + } +} + +static const AIOCBInfo nvme_copy_aiocb_info = { + .aiocb_size = sizeof(NvmeCopyAIOCB), + .cancel_async = nvme_copy_cancel, +}; + +static void nvme_copy_bh(void *opaque) +{ + NvmeCopyAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = req->ns; + BlockAcctStats *stats = blk_get_stats(ns->blkconf.blk); + + if (iocb->idx != iocb->nr) { + req->cqe.result = cpu_to_le32(iocb->idx); + } + + qemu_iovec_destroy(&iocb->iov); + g_free(iocb->bounce); + + qemu_bh_delete(iocb->bh); + iocb->bh = NULL; + + if (iocb->ret < 0) { + block_acct_failed(stats, &iocb->acct.read); + block_acct_failed(stats, &iocb->acct.write); + } else { + block_acct_done(stats, &iocb->acct.read); + block_acct_done(stats, &iocb->acct.write); + } + + iocb->common.cb(iocb->common.opaque, iocb->ret); + qemu_aio_unref(iocb); +} + +static void nvme_copy_cb(void *opaque, int ret); + +static void nvme_copy_out_completed_cb(void *opaque, int ret) +{ + NvmeCopyAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = req->ns; + NvmeCopySourceRange *range = &iocb->ranges[iocb->idx]; + uint32_t nlb = le32_to_cpu(range->nlb) + 1; + + if (ret < 0) { + iocb->ret = ret; + goto out; + } else if (iocb->ret < 0) { + goto out; + } + + if (ns->params.zoned) { + nvme_advance_zone_wp(ns, iocb->zone, nlb); + } + + iocb->idx++; + iocb->slba += nlb; +out: + nvme_copy_cb(iocb, iocb->ret); +} + +static void nvme_copy_out_cb(void *opaque, int ret) +{ + NvmeCopyAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = req->ns; + NvmeCopySourceRange *range; + uint32_t nlb; + size_t mlen; + uint8_t *mbounce; + + if (ret < 0) { + iocb->ret = ret; + goto out; + } else if (iocb->ret < 0) { + goto out; + } + + if (!ns->lbaf.ms) { + nvme_copy_out_completed_cb(iocb, 0); + return; + } + + range = &iocb->ranges[iocb->idx]; + nlb = le32_to_cpu(range->nlb) + 1; + + mlen = nvme_m2b(ns, nlb); + mbounce = iocb->bounce + nvme_l2b(ns, nlb); + + qemu_iovec_reset(&iocb->iov); + qemu_iovec_add(&iocb->iov, mbounce, mlen); + + iocb->aiocb = blk_aio_pwritev(ns->blkconf.blk, nvme_moff(ns, iocb->slba), + &iocb->iov, 0, nvme_copy_out_completed_cb, + iocb); + + return; + +out: + nvme_copy_cb(iocb, ret); +} + +static void nvme_copy_in_completed_cb(void *opaque, int ret) +{ + NvmeCopyAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = req->ns; + NvmeCopySourceRange *range; + uint32_t nlb; + size_t len; + uint16_t status; + + if (ret < 0) { + iocb->ret = ret; + goto out; + } else if (iocb->ret < 0) { + goto out; + } + + range = &iocb->ranges[iocb->idx]; + nlb = le32_to_cpu(range->nlb) + 1; + len = nvme_l2b(ns, nlb); + + trace_pci_nvme_copy_out(iocb->slba, nlb); + + if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps)) { + NvmeCopyCmd *copy = (NvmeCopyCmd *)&req->cmd; + + uint16_t prinfor = ((copy->control[0] >> 4) & 0xf); + uint16_t prinfow = ((copy->control[2] >> 2) & 0xf); + + uint16_t apptag = le16_to_cpu(range->apptag); + uint16_t appmask = le16_to_cpu(range->appmask); + uint32_t reftag = le32_to_cpu(range->reftag); + + uint64_t slba = le64_to_cpu(range->slba); + size_t mlen = nvme_m2b(ns, nlb); + uint8_t *mbounce = iocb->bounce + nvme_l2b(ns, nlb); + + status = nvme_dif_check(ns, iocb->bounce, len, mbounce, mlen, prinfor, + slba, apptag, appmask, &reftag); + if (status) { + goto invalid; + } + + apptag = le16_to_cpu(copy->apptag); + appmask = le16_to_cpu(copy->appmask); + + if (prinfow & NVME_PRINFO_PRACT) { + status = nvme_check_prinfo(ns, prinfow, iocb->slba, iocb->reftag); + if (status) { + goto invalid; + } + + nvme_dif_pract_generate_dif(ns, iocb->bounce, len, mbounce, mlen, + apptag, &iocb->reftag); + } else { + status = nvme_dif_check(ns, iocb->bounce, len, mbounce, mlen, + prinfow, iocb->slba, apptag, appmask, + &iocb->reftag); + if (status) { + goto invalid; + } + } + } + + status = nvme_check_bounds(ns, iocb->slba, nlb); + if (status) { + goto invalid; + } + + if (ns->params.zoned) { + status = nvme_check_zone_write(ns, iocb->zone, iocb->slba, nlb); + if (status) { + goto invalid; + } + + iocb->zone->w_ptr += nlb; + } + + qemu_iovec_reset(&iocb->iov); + qemu_iovec_add(&iocb->iov, iocb->bounce, len); + + iocb->aiocb = blk_aio_pwritev(ns->blkconf.blk, nvme_l2b(ns, iocb->slba), + &iocb->iov, 0, nvme_copy_out_cb, iocb); + + return; + +invalid: + req->status = status; + iocb->aiocb = NULL; + if (iocb->bh) { + qemu_bh_schedule(iocb->bh); + } + + return; + +out: + nvme_copy_cb(iocb, ret); +} + +static void nvme_copy_in_cb(void *opaque, int ret) +{ + NvmeCopyAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = req->ns; + NvmeCopySourceRange *range; + uint64_t slba; + uint32_t nlb; + + if (ret < 0) { + iocb->ret = ret; + goto out; + } else if (iocb->ret < 0) { + goto out; + } + + if (!ns->lbaf.ms) { + nvme_copy_in_completed_cb(iocb, 0); + return; + } + + range = &iocb->ranges[iocb->idx]; + slba = le64_to_cpu(range->slba); + nlb = le32_to_cpu(range->nlb) + 1; + + qemu_iovec_reset(&iocb->iov); + qemu_iovec_add(&iocb->iov, iocb->bounce + nvme_l2b(ns, nlb), + nvme_m2b(ns, nlb)); + + iocb->aiocb = blk_aio_preadv(ns->blkconf.blk, nvme_moff(ns, slba), + &iocb->iov, 0, nvme_copy_in_completed_cb, + iocb); + return; + +out: + nvme_copy_cb(iocb, iocb->ret); +} + +static void nvme_copy_cb(void *opaque, int ret) +{ + NvmeCopyAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = req->ns; + NvmeCopySourceRange *range; + uint64_t slba; + uint32_t nlb; + size_t len; + uint16_t status; + + if (ret < 0) { + iocb->ret = ret; + goto done; + } else if (iocb->ret < 0) { + goto done; + } + + if (iocb->idx == iocb->nr) { + goto done; + } + + range = &iocb->ranges[iocb->idx]; + slba = le64_to_cpu(range->slba); + nlb = le32_to_cpu(range->nlb) + 1; + len = nvme_l2b(ns, nlb); + + trace_pci_nvme_copy_source_range(slba, nlb); + + if (nlb > le16_to_cpu(ns->id_ns.mssrl)) { + status = NVME_CMD_SIZE_LIMIT | NVME_DNR; + goto invalid; + } + + status = nvme_check_bounds(ns, slba, nlb); + if (status) { + goto invalid; + } + + if (NVME_ERR_REC_DULBE(ns->features.err_rec)) { + status = nvme_check_dulbe(ns, slba, nlb); + if (status) { + goto invalid; + } + } + + if (ns->params.zoned) { + status = nvme_check_zone_read(ns, slba, nlb); + if (status) { + goto invalid; + } + } + + qemu_iovec_reset(&iocb->iov); + qemu_iovec_add(&iocb->iov, iocb->bounce, len); + + iocb->aiocb = blk_aio_preadv(ns->blkconf.blk, nvme_l2b(ns, slba), + &iocb->iov, 0, nvme_copy_in_cb, iocb); + return; + +invalid: + req->status = status; +done: + iocb->aiocb = NULL; + if (iocb->bh) { + qemu_bh_schedule(iocb->bh); + } +} + + static uint16_t nvme_copy(NvmeCtrl *n, NvmeRequest *req) { NvmeNamespace *ns = req->ns; NvmeCopyCmd *copy = (NvmeCopyCmd *)&req->cmd; - + NvmeCopyAIOCB *iocb = blk_aio_get(&nvme_copy_aiocb_info, ns->blkconf.blk, + nvme_misc_cb, req); uint16_t nr = copy->nr + 1; uint8_t format = copy->control[0] & 0xf; + uint16_t prinfor = ((copy->control[0] >> 4) & 0xf); + uint16_t prinfow = ((copy->control[2] >> 2) & 0xf); - /* - * Shift the PRINFOR/PRINFOW values by 10 to allow reusing the - * NVME_RW_PRINFO constants. - */ - uint16_t prinfor = ((copy->control[0] >> 4) & 0xf) << 10; - uint16_t prinfow = ((copy->control[2] >> 2) & 0xf) << 10; - - uint32_t nlb = 0; - uint8_t *bounce = NULL, *bouncep = NULL; - uint8_t *mbounce = NULL, *mbouncep = NULL; - struct nvme_copy_ctx *ctx; uint16_t status; - int i; trace_pci_nvme_copy(nvme_cid(req), nvme_nsid(ns), nr, format); + iocb->ranges = NULL; + iocb->zone = NULL; + if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps) && - ((prinfor & NVME_RW_PRINFO_PRACT) != (prinfow & NVME_RW_PRINFO_PRACT))) { - return NVME_INVALID_FIELD | NVME_DNR; + ((prinfor & NVME_PRINFO_PRACT) != (prinfow & NVME_PRINFO_PRACT))) { + status = NVME_INVALID_FIELD | NVME_DNR; + goto invalid; } if (!(n->id_ctrl.ocfs & (1 << format))) { trace_pci_nvme_err_copy_invalid_format(format); - return NVME_INVALID_FIELD | NVME_DNR; + status = NVME_INVALID_FIELD | NVME_DNR; + goto invalid; } if (nr > ns->id_ns.msrc + 1) { - return NVME_CMD_SIZE_LIMIT | NVME_DNR; - } - - ctx = g_new(struct nvme_copy_ctx, 1); - ctx->ranges = g_new(NvmeCopySourceRange, nr); - - status = nvme_h2c(n, (uint8_t *)ctx->ranges, - nr * sizeof(NvmeCopySourceRange), req); - if (status) { - goto out; - } - - for (i = 0; i < nr; i++) { - uint64_t slba = le64_to_cpu(ctx->ranges[i].slba); - uint32_t _nlb = le16_to_cpu(ctx->ranges[i].nlb) + 1; - - if (_nlb > le16_to_cpu(ns->id_ns.mssrl)) { - status = NVME_CMD_SIZE_LIMIT | NVME_DNR; - goto out; - } - - status = nvme_check_bounds(ns, slba, _nlb); - if (status) { - trace_pci_nvme_err_invalid_lba_range(slba, _nlb, ns->id_ns.nsze); - goto out; - } - - if (NVME_ERR_REC_DULBE(ns->features.err_rec)) { - status = nvme_check_dulbe(ns, slba, _nlb); - if (status) { - goto out; - } - } - - if (ns->params.zoned) { - status = nvme_check_zone_read(ns, slba, _nlb); - if (status) { - goto out; - } - } - - nlb += _nlb; - } - - if (nlb > le32_to_cpu(ns->id_ns.mcl)) { status = NVME_CMD_SIZE_LIMIT | NVME_DNR; - goto out; + goto invalid; } - bounce = bouncep = g_malloc(nvme_l2b(ns, nlb)); - if (nvme_msize(ns)) { - mbounce = mbouncep = g_malloc(nvme_m2b(ns, nlb)); + iocb->ranges = g_new(NvmeCopySourceRange, nr); + + status = nvme_h2c(n, (uint8_t *)iocb->ranges, + sizeof(NvmeCopySourceRange) * nr, req); + if (status) { + goto invalid; } - block_acct_start(blk_get_stats(ns->blkconf.blk), &req->acct, 0, - BLOCK_ACCT_READ); + iocb->slba = le64_to_cpu(copy->sdlba); - ctx->bounce = bounce; - ctx->mbounce = mbounce; - ctx->nlb = nlb; - ctx->copies = 1; + if (ns->params.zoned) { + iocb->zone = nvme_get_zone_by_slba(ns, iocb->slba); + if (!iocb->zone) { + status = NVME_LBA_RANGE | NVME_DNR; + goto invalid; + } - req->opaque = ctx; - - for (i = 0; i < nr; i++) { - uint64_t slba = le64_to_cpu(ctx->ranges[i].slba); - uint32_t nlb = le16_to_cpu(ctx->ranges[i].nlb) + 1; - - size_t len = nvme_l2b(ns, nlb); - int64_t offset = nvme_l2b(ns, slba); - - trace_pci_nvme_copy_source_range(slba, nlb); - - struct nvme_copy_in_ctx *in_ctx = g_new(struct nvme_copy_in_ctx, 1); - in_ctx->req = req; - - qemu_iovec_init(&in_ctx->iov, 1); - qemu_iovec_add(&in_ctx->iov, bouncep, len); - - ctx->copies++; - - blk_aio_preadv(ns->blkconf.blk, offset, &in_ctx->iov, 0, - nvme_aio_copy_in_cb, in_ctx); - - bouncep += len; - - if (nvme_msize(ns)) { - len = nvme_m2b(ns, nlb); - offset = ns->mdata_offset + nvme_m2b(ns, slba); - - in_ctx = g_new(struct nvme_copy_in_ctx, 1); - in_ctx->req = req; - - qemu_iovec_init(&in_ctx->iov, 1); - qemu_iovec_add(&in_ctx->iov, mbouncep, len); - - ctx->copies++; - - blk_aio_preadv(ns->blkconf.blk, offset, &in_ctx->iov, 0, - nvme_aio_copy_in_cb, in_ctx); - - mbouncep += len; + status = nvme_zrm_auto(n, ns, iocb->zone); + if (status) { + goto invalid; } } - /* account for the 1-initialization */ - ctx->copies--; + iocb->req = req; + iocb->bh = qemu_bh_new(nvme_copy_bh, iocb); + iocb->ret = 0; + iocb->nr = nr; + iocb->idx = 0; + iocb->reftag = le32_to_cpu(copy->reftag); + iocb->bounce = g_malloc_n(le16_to_cpu(ns->id_ns.mssrl), + ns->lbasz + ns->lbaf.ms); - if (!ctx->copies) { - nvme_copy_in_complete(req); - } + qemu_iovec_init(&iocb->iov, 1); + + block_acct_start(blk_get_stats(ns->blkconf.blk), &iocb->acct.read, 0, + BLOCK_ACCT_READ); + block_acct_start(blk_get_stats(ns->blkconf.blk), &iocb->acct.write, 0, + BLOCK_ACCT_WRITE); + + req->aiocb = &iocb->common; + nvme_copy_cb(iocb, 0); return NVME_NO_COMPLETE; -out: - g_free(ctx->ranges); - g_free(ctx); - +invalid: + g_free(iocb->ranges); + qemu_aio_unref(iocb); return status; } @@ -2794,7 +2866,7 @@ static uint16_t nvme_compare(NvmeCtrl *n, NvmeRequest *req) BlockBackend *blk = ns->blkconf.blk; uint64_t slba = le64_to_cpu(rw->slba); uint32_t nlb = le16_to_cpu(rw->nlb) + 1; - uint16_t ctrl = le16_to_cpu(rw->control); + uint8_t prinfo = NVME_RW_PRINFO(le16_to_cpu(rw->control)); size_t data_len = nvme_l2b(ns, nlb); size_t len = data_len; int64_t offset = nvme_l2b(ns, slba); @@ -2803,7 +2875,7 @@ static uint16_t nvme_compare(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_compare(nvme_cid(req), nvme_nsid(ns), slba, nlb); - if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps) && (ctrl & NVME_RW_PRINFO_PRACT)) { + if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps) && (prinfo & NVME_PRINFO_PRACT)) { return NVME_INVALID_PROT_INFO | NVME_DNR; } @@ -2818,7 +2890,6 @@ static uint16_t nvme_compare(NvmeCtrl *n, NvmeRequest *req) status = nvme_check_bounds(ns, slba, nlb); if (status) { - trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); return status; } @@ -2850,56 +2921,138 @@ static uint16_t nvme_compare(NvmeCtrl *n, NvmeRequest *req) return NVME_NO_COMPLETE; } +typedef struct NvmeFlushAIOCB { + BlockAIOCB common; + BlockAIOCB *aiocb; + NvmeRequest *req; + QEMUBH *bh; + int ret; + + NvmeNamespace *ns; + uint32_t nsid; + bool broadcast; +} NvmeFlushAIOCB; + +static void nvme_flush_cancel(BlockAIOCB *acb) +{ + NvmeFlushAIOCB *iocb = container_of(acb, NvmeFlushAIOCB, common); + + iocb->ret = -ECANCELED; + + if (iocb->aiocb) { + blk_aio_cancel_async(iocb->aiocb); + } +} + +static const AIOCBInfo nvme_flush_aiocb_info = { + .aiocb_size = sizeof(NvmeFlushAIOCB), + .cancel_async = nvme_flush_cancel, + .get_aio_context = nvme_get_aio_context, +}; + +static void nvme_flush_ns_cb(void *opaque, int ret) +{ + NvmeFlushAIOCB *iocb = opaque; + NvmeNamespace *ns = iocb->ns; + + if (ret < 0) { + iocb->ret = ret; + goto out; + } else if (iocb->ret < 0) { + goto out; + } + + if (ns) { + trace_pci_nvme_flush_ns(iocb->nsid); + + iocb->ns = NULL; + iocb->aiocb = blk_aio_flush(ns->blkconf.blk, nvme_flush_ns_cb, iocb); + return; + } + +out: + iocb->aiocb = NULL; + qemu_bh_schedule(iocb->bh); +} + +static void nvme_flush_bh(void *opaque) +{ + NvmeFlushAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeCtrl *n = nvme_ctrl(req); + int i; + + if (iocb->ret < 0) { + goto done; + } + + if (iocb->broadcast) { + for (i = iocb->nsid + 1; i <= NVME_MAX_NAMESPACES; i++) { + iocb->ns = nvme_ns(n, i); + if (iocb->ns) { + iocb->nsid = i; + break; + } + } + } + + if (!iocb->ns) { + goto done; + } + + nvme_flush_ns_cb(iocb, 0); + return; + +done: + qemu_bh_delete(iocb->bh); + iocb->bh = NULL; + + iocb->common.cb(iocb->common.opaque, iocb->ret); + + qemu_aio_unref(iocb); + + return; +} + static uint16_t nvme_flush(NvmeCtrl *n, NvmeRequest *req) { + NvmeFlushAIOCB *iocb; uint32_t nsid = le32_to_cpu(req->cmd.nsid); - uintptr_t *num_flushes = (uintptr_t *)&req->opaque; uint16_t status; - struct nvme_aio_flush_ctx *ctx; - NvmeNamespace *ns; - trace_pci_nvme_flush(nvme_cid(req), nsid); + iocb = qemu_aio_get(&nvme_flush_aiocb_info, NULL, nvme_misc_cb, req); - if (nsid != NVME_NSID_BROADCAST) { - req->ns = nvme_ns(n, nsid); - if (unlikely(!req->ns)) { - return NVME_INVALID_FIELD | NVME_DNR; + iocb->req = req; + iocb->bh = qemu_bh_new(nvme_flush_bh, iocb); + iocb->ret = 0; + iocb->ns = NULL; + iocb->nsid = 0; + iocb->broadcast = (nsid == NVME_NSID_BROADCAST); + + if (!iocb->broadcast) { + if (!nvme_nsid_valid(n, nsid)) { + status = NVME_INVALID_NSID | NVME_DNR; + goto out; } - block_acct_start(blk_get_stats(req->ns->blkconf.blk), &req->acct, 0, - BLOCK_ACCT_FLUSH); - req->aiocb = blk_aio_flush(req->ns->blkconf.blk, nvme_misc_cb, req); - return NVME_NO_COMPLETE; - } - - /* 1-initialize; see comment in nvme_dsm */ - *num_flushes = 1; - - for (int i = 1; i <= n->num_namespaces; i++) { - ns = nvme_ns(n, i); - if (!ns) { - continue; + iocb->ns = nvme_ns(n, nsid); + if (!iocb->ns) { + status = NVME_INVALID_FIELD | NVME_DNR; + goto out; } - ctx = g_new(struct nvme_aio_flush_ctx, 1); - ctx->req = req; - ctx->ns = ns; - - (*num_flushes)++; - - block_acct_start(blk_get_stats(ns->blkconf.blk), &ctx->acct, 0, - BLOCK_ACCT_FLUSH); - blk_aio_flush(ns->blkconf.blk, nvme_aio_flush_cb, ctx); + iocb->nsid = nsid; } - /* account for the 1-initialization */ - (*num_flushes)--; + req->aiocb = &iocb->common; + qemu_bh_schedule(iocb->bh); - if (*num_flushes) { - status = NVME_NO_COMPLETE; - } else { - status = req->status; - } + return NVME_NO_COMPLETE; + +out: + qemu_bh_delete(iocb->bh); + iocb->bh = NULL; + qemu_aio_unref(iocb); return status; } @@ -2910,7 +3063,7 @@ static uint16_t nvme_read(NvmeCtrl *n, NvmeRequest *req) NvmeNamespace *ns = req->ns; uint64_t slba = le64_to_cpu(rw->slba); uint32_t nlb = (uint32_t)le16_to_cpu(rw->nlb) + 1; - uint16_t ctrl = le16_to_cpu(rw->control); + uint8_t prinfo = NVME_RW_PRINFO(le16_to_cpu(rw->control)); uint64_t data_size = nvme_l2b(ns, nlb); uint64_t mapped_size = data_size; uint64_t data_offset; @@ -2921,9 +3074,9 @@ static uint16_t nvme_read(NvmeCtrl *n, NvmeRequest *req) mapped_size += nvme_m2b(ns, nlb); if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps)) { - bool pract = ctrl & NVME_RW_PRINFO_PRACT; + bool pract = prinfo & NVME_PRINFO_PRACT; - if (pract && nvme_msize(ns) == 8) { + if (pract && ns->lbaf.ms == 8) { mapped_size = data_size; } } @@ -2938,7 +3091,6 @@ static uint16_t nvme_read(NvmeCtrl *n, NvmeRequest *req) status = nvme_check_bounds(ns, slba, nlb); if (status) { - trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); goto invalid; } @@ -2986,6 +3138,7 @@ static uint16_t nvme_do_write(NvmeCtrl *n, NvmeRequest *req, bool append, uint64_t slba = le64_to_cpu(rw->slba); uint32_t nlb = (uint32_t)le16_to_cpu(rw->nlb) + 1; uint16_t ctrl = le16_to_cpu(rw->control); + uint8_t prinfo = NVME_RW_PRINFO(ctrl); uint64_t data_size = nvme_l2b(ns, nlb); uint64_t mapped_size = data_size; uint64_t data_offset; @@ -2998,9 +3151,9 @@ static uint16_t nvme_do_write(NvmeCtrl *n, NvmeRequest *req, bool append, mapped_size += nvme_m2b(ns, nlb); if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps)) { - bool pract = ctrl & NVME_RW_PRINFO_PRACT; + bool pract = prinfo & NVME_PRINFO_PRACT; - if (pract && nvme_msize(ns) == 8) { + if (pract && ns->lbaf.ms == 8) { mapped_size -= nvme_m2b(ns, nlb); } } @@ -3018,12 +3171,12 @@ static uint16_t nvme_do_write(NvmeCtrl *n, NvmeRequest *req, bool append, status = nvme_check_bounds(ns, slba, nlb); if (status) { - trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); goto invalid; } if (ns->params.zoned) { zone = nvme_get_zone_by_slba(ns, slba); + assert(zone); if (append) { bool piremap = !!(ctrl & NVME_RW_PIREMAP); @@ -3074,7 +3227,7 @@ static uint16_t nvme_do_write(NvmeCtrl *n, NvmeRequest *req, bool append, goto invalid; } - status = nvme_zrm_auto(ns, zone); + status = nvme_zrm_auto(n, ns, zone); if (status) { goto invalid; } @@ -3163,7 +3316,7 @@ enum NvmeZoneProcessingMask { static uint16_t nvme_open_zone(NvmeNamespace *ns, NvmeZone *zone, NvmeZoneState state, NvmeRequest *req) { - return nvme_zrm_open(ns, zone); + return nvme_zrm_open(nvme_ctrl(req), ns, zone); } static uint16_t nvme_close_zone(NvmeNamespace *ns, NvmeZone *zone, @@ -3178,41 +3331,6 @@ static uint16_t nvme_finish_zone(NvmeNamespace *ns, NvmeZone *zone, return nvme_zrm_finish(ns, zone); } -static uint16_t nvme_reset_zone(NvmeNamespace *ns, NvmeZone *zone, - NvmeZoneState state, NvmeRequest *req) -{ - uintptr_t *resets = (uintptr_t *)&req->opaque; - struct nvme_zone_reset_ctx *ctx; - - switch (state) { - case NVME_ZONE_STATE_EMPTY: - return NVME_SUCCESS; - case NVME_ZONE_STATE_EXPLICITLY_OPEN: - case NVME_ZONE_STATE_IMPLICITLY_OPEN: - case NVME_ZONE_STATE_CLOSED: - case NVME_ZONE_STATE_FULL: - break; - default: - return NVME_ZONE_INVAL_TRANSITION; - } - - /* - * The zone reset aio callback needs to know the zone that is being reset - * in order to transition the zone on completion. - */ - ctx = g_new(struct nvme_zone_reset_ctx, 1); - ctx->req = req; - ctx->zone = zone; - - (*resets)++; - - blk_aio_pwrite_zeroes(ns->blkconf.blk, nvme_l2b(ns, zone->d.zslba), - nvme_l2b(ns, ns->zone_size), BDRV_REQ_MAY_UNMAP, - nvme_aio_zone_reset_cb, ctx); - - return NVME_NO_COMPLETE; -} - static uint16_t nvme_offline_zone(NvmeNamespace *ns, NvmeZone *zone, NvmeZoneState state, NvmeRequest *req) { @@ -3341,12 +3459,144 @@ out: return status; } +typedef struct NvmeZoneResetAIOCB { + BlockAIOCB common; + BlockAIOCB *aiocb; + NvmeRequest *req; + QEMUBH *bh; + int ret; + + bool all; + int idx; + NvmeZone *zone; +} NvmeZoneResetAIOCB; + +static void nvme_zone_reset_cancel(BlockAIOCB *aiocb) +{ + NvmeZoneResetAIOCB *iocb = container_of(aiocb, NvmeZoneResetAIOCB, common); + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = req->ns; + + iocb->idx = ns->num_zones; + + iocb->ret = -ECANCELED; + + if (iocb->aiocb) { + blk_aio_cancel_async(iocb->aiocb); + iocb->aiocb = NULL; + } +} + +static const AIOCBInfo nvme_zone_reset_aiocb_info = { + .aiocb_size = sizeof(NvmeZoneResetAIOCB), + .cancel_async = nvme_zone_reset_cancel, +}; + +static void nvme_zone_reset_bh(void *opaque) +{ + NvmeZoneResetAIOCB *iocb = opaque; + + iocb->common.cb(iocb->common.opaque, iocb->ret); + + qemu_bh_delete(iocb->bh); + iocb->bh = NULL; + qemu_aio_unref(iocb); +} + +static void nvme_zone_reset_cb(void *opaque, int ret); + +static void nvme_zone_reset_epilogue_cb(void *opaque, int ret) +{ + NvmeZoneResetAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = req->ns; + int64_t moff; + int count; + + if (ret < 0) { + nvme_zone_reset_cb(iocb, ret); + return; + } + + if (!ns->lbaf.ms) { + nvme_zone_reset_cb(iocb, 0); + return; + } + + moff = nvme_moff(ns, iocb->zone->d.zslba); + count = nvme_m2b(ns, ns->zone_size); + + iocb->aiocb = blk_aio_pwrite_zeroes(ns->blkconf.blk, moff, count, + BDRV_REQ_MAY_UNMAP, + nvme_zone_reset_cb, iocb); + return; +} + +static void nvme_zone_reset_cb(void *opaque, int ret) +{ + NvmeZoneResetAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = req->ns; + + if (ret < 0) { + iocb->ret = ret; + goto done; + } + + if (iocb->zone) { + nvme_zrm_reset(ns, iocb->zone); + + if (!iocb->all) { + goto done; + } + } + + while (iocb->idx < ns->num_zones) { + NvmeZone *zone = &ns->zone_array[iocb->idx++]; + + switch (nvme_get_zone_state(zone)) { + case NVME_ZONE_STATE_EMPTY: + if (!iocb->all) { + goto done; + } + + continue; + + case NVME_ZONE_STATE_EXPLICITLY_OPEN: + case NVME_ZONE_STATE_IMPLICITLY_OPEN: + case NVME_ZONE_STATE_CLOSED: + case NVME_ZONE_STATE_FULL: + iocb->zone = zone; + break; + + default: + continue; + } + + trace_pci_nvme_zns_zone_reset(zone->d.zslba); + + iocb->aiocb = blk_aio_pwrite_zeroes(ns->blkconf.blk, + nvme_l2b(ns, zone->d.zslba), + nvme_l2b(ns, ns->zone_size), + BDRV_REQ_MAY_UNMAP, + nvme_zone_reset_epilogue_cb, + iocb); + return; + } + +done: + iocb->aiocb = NULL; + if (iocb->bh) { + qemu_bh_schedule(iocb->bh); + } +} + static uint16_t nvme_zone_mgmt_send(NvmeCtrl *n, NvmeRequest *req) { NvmeCmd *cmd = (NvmeCmd *)&req->cmd; NvmeNamespace *ns = req->ns; NvmeZone *zone; - uintptr_t *resets; + NvmeZoneResetAIOCB *iocb; uint8_t *zd_ext; uint32_t dw13 = le32_to_cpu(cmd->cdw13); uint64_t slba = 0; @@ -3357,7 +3607,7 @@ static uint16_t nvme_zone_mgmt_send(NvmeCtrl *n, NvmeRequest *req) enum NvmeZoneProcessingMask proc_mask = NVME_PROC_CURRENT_ZONE; action = dw13 & 0xff; - all = dw13 & 0x100; + all = !!(dw13 & 0x100); req->status = NVME_SUCCESS; @@ -3401,21 +3651,22 @@ static uint16_t nvme_zone_mgmt_send(NvmeCtrl *n, NvmeRequest *req) break; case NVME_ZONE_ACTION_RESET: - resets = (uintptr_t *)&req->opaque; - - if (all) { - proc_mask = NVME_PROC_OPENED_ZONES | NVME_PROC_CLOSED_ZONES | - NVME_PROC_FULL_ZONES; - } trace_pci_nvme_reset_zone(slba, zone_idx, all); - *resets = 1; + iocb = blk_aio_get(&nvme_zone_reset_aiocb_info, ns->blkconf.blk, + nvme_misc_cb, req); - status = nvme_do_zone_op(ns, zone, proc_mask, nvme_reset_zone, req); + iocb->req = req; + iocb->bh = qemu_bh_new(nvme_zone_reset_bh, iocb); + iocb->ret = 0; + iocb->all = all; + iocb->idx = zone_idx; + iocb->zone = NULL; - (*resets)--; + req->aiocb = &iocb->common; + nvme_zone_reset_cb(iocb, 0); - return *resets ? NVME_NO_COMPLETE : req->status; + return NVME_NO_COMPLETE; case NVME_ZONE_ACTION_OFFLINE: if (all) { @@ -3595,8 +3846,8 @@ static uint16_t nvme_zone_mgmt_recv(NvmeCtrl *n, NvmeRequest *req) static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req) { + NvmeNamespace *ns; uint32_t nsid = le32_to_cpu(req->cmd.nsid); - uint16_t status; trace_pci_nvme_io_cmd(nvme_cid(req), nsid, nvme_sqid(req), req->cmd.opcode, nvme_io_opc_str(req->cmd.opcode)); @@ -3607,18 +3858,18 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req) /* * In the base NVM command set, Flush may apply to all namespaces - * (indicated by NSID being set to 0xFFFFFFFF). But if that feature is used + * (indicated by NSID being set to FFFFFFFFh). But if that feature is used * along with TP 4056 (Namespace Types), it may be pretty screwed up. * - * If NSID is indeed set to 0xFFFFFFFF, we simply cannot associate the + * If NSID is indeed set to FFFFFFFFh, we simply cannot associate the * opcode with a specific command since we cannot determine a unique I/O - * command set. Opcode 0x0 could have any other meaning than something + * command set. Opcode 0h could have any other meaning than something * equivalent to flushing and say it DOES have completely different - * semantics in some other command set - does an NSID of 0xFFFFFFFF then + * semantics in some other command set - does an NSID of FFFFFFFFh then * mean "for all namespaces, apply whatever command set specific command - * that uses the 0x0 opcode?" Or does it mean "for all namespaces, apply - * whatever command that uses the 0x0 opcode if, and only if, it allows - * NSID to be 0xFFFFFFFF"? + * that uses the 0h opcode?" Or does it mean "for all namespaces, apply + * whatever command that uses the 0h opcode if, and only if, it allows NSID + * to be FFFFFFFFh"? * * Anyway (and luckily), for now, we do not care about this since the * device only supports namespace types that includes the NVM Flush command @@ -3628,21 +3879,22 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req) return nvme_flush(n, req); } - req->ns = nvme_ns(n, nsid); - if (unlikely(!req->ns)) { + ns = nvme_ns(n, nsid); + if (unlikely(!ns)) { return NVME_INVALID_FIELD | NVME_DNR; } - if (!(req->ns->iocs[req->cmd.opcode] & NVME_CMD_EFF_CSUPP)) { + if (!(ns->iocs[req->cmd.opcode] & NVME_CMD_EFF_CSUPP)) { trace_pci_nvme_err_invalid_opc(req->cmd.opcode); return NVME_INVALID_OPCODE | NVME_DNR; } - status = nvme_ns_status(req->ns); - if (unlikely(status)) { - return status; + if (ns->status) { + return ns->status; } + req->ns = ns; + switch (req->cmd.opcode) { case NVME_CMD_WRITE_ZEROES: return nvme_write_zeroes(n, req); @@ -3688,7 +3940,6 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeRequest *req) NvmeSQueue *sq; NvmeCQueue *cq; uint16_t qid = le16_to_cpu(c->qid); - uint32_t nsid; if (unlikely(!qid || nvme_check_sqid(n, qid))) { trace_pci_nvme_err_invalid_del_sq(qid); @@ -3700,22 +3951,8 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeRequest *req) sq = n->sq[qid]; while (!QTAILQ_EMPTY(&sq->out_req_list)) { r = QTAILQ_FIRST(&sq->out_req_list); - if (r->aiocb) { - blk_aio_cancel(r->aiocb); - } - } - - /* - * Drain all namespaces if there are still outstanding requests that we - * could not cancel explicitly. - */ - if (!QTAILQ_EMPTY(&sq->out_req_list)) { - for (nsid = 1; nsid <= NVME_MAX_NAMESPACES; nsid++) { - NvmeNamespace *ns = nvme_ns(n, nsid); - if (ns) { - nvme_ns_drain(ns); - } - } + assert(r->aiocb); + blk_aio_cancel(r->aiocb); } assert(QTAILQ_EMPTY(&sq->out_req_list)); @@ -3787,7 +4024,7 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_err_invalid_create_sq_sqid(sqid); return NVME_INVALID_QID | NVME_DNR; } - if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) { + if (unlikely(!qsize || qsize > NVME_CAP_MQES(ldq_le_p(&n->bar.cap)))) { trace_pci_nvme_err_invalid_create_sq_size(qsize); return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR; } @@ -3844,7 +4081,7 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, uint8_t rae, uint32_t buf_len, } else { int i; - for (i = 1; i <= n->num_namespaces; i++) { + for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { ns = nvme_ns(n, i); if (!ns) { continue; @@ -3934,7 +4171,7 @@ static uint16_t nvme_changed_nslist(NvmeCtrl *n, uint8_t rae, uint32_t buf_len, NVME_CHANGED_NSID_SIZE) { /* * If more than 1024 namespaces, the first entry in the log page should - * be set to 0xffffffff and the others to 0 as spec. + * be set to FFFFFFFFh and the others to 0 as spec. */ if (i == ARRAY_SIZE(nslist)) { memset(nslist, 0x0, sizeof(nslist)); @@ -3973,7 +4210,7 @@ static uint16_t nvme_cmd_effects(NvmeCtrl *n, uint8_t csi, uint32_t buf_len, return NVME_INVALID_FIELD | NVME_DNR; } - switch (NVME_CC_CSS(n->bar.cc)) { + switch (NVME_CC_CSS(ldl_le_p(&n->bar.cc))) { case NVME_CC_CSS_NVM: src_iocs = nvme_cse_iocs_nvm; /* fall through */ @@ -4082,6 +4319,11 @@ static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_err_invalid_del_cq_notempty(qid); return NVME_INVALID_QUEUE_DEL; } + + if (cq->irq_enabled && cq->tail != cq->head) { + n->cq_pending--; + } + nvme_irq_deassert(n, cq); trace_pci_nvme_del_cq(qid); nvme_free_cq(cq, n); @@ -4130,7 +4372,7 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest *req) trace_pci_nvme_err_invalid_create_cq_cqid(cqid); return NVME_INVALID_QID | NVME_DNR; } - if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) { + if (unlikely(!qsize || qsize > NVME_CAP_MQES(ldq_le_p(&n->bar.cap)))) { trace_pci_nvme_err_invalid_create_cq_size(qsize); return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR; } @@ -4171,16 +4413,6 @@ static uint16_t nvme_rpt_empty_id_struct(NvmeCtrl *n, NvmeRequest *req) return nvme_c2h(n, id, sizeof(id), req); } -static inline bool nvme_csi_has_nvm_support(NvmeNamespace *ns) -{ - switch (ns->csi) { - case NVME_CSI_NVM: - case NVME_CSI_ZONED: - return true; - } - return false; -} - static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeRequest *req) { trace_pci_nvme_identify_ctrl(); @@ -4237,16 +4469,18 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeRequest *req, bool active) } } - if (c->csi == NVME_CSI_NVM && nvme_csi_has_nvm_support(ns)) { + if (active || ns->csi == NVME_CSI_NVM) { return nvme_c2h(n, (uint8_t *)&ns->id_ns, sizeof(NvmeIdNs), req); } return NVME_INVALID_CMD_SET | NVME_DNR; } -static uint16_t nvme_identify_ns_attached_list(NvmeCtrl *n, NvmeRequest *req) +static uint16_t nvme_identify_ctrl_list(NvmeCtrl *n, NvmeRequest *req, + bool attached) { NvmeIdentify *c = (NvmeIdentify *)&req->cmd; + uint32_t nsid = le32_to_cpu(c->nsid); uint16_t min_id = le16_to_cpu(c->ctrlid); uint16_t list[NVME_CONTROLLER_LIST_SIZE] = {}; uint16_t *ids = &list[1]; @@ -4254,15 +4488,21 @@ static uint16_t nvme_identify_ns_attached_list(NvmeCtrl *n, NvmeRequest *req) NvmeCtrl *ctrl; int cntlid, nr_ids = 0; - trace_pci_nvme_identify_ns_attached_list(min_id); + trace_pci_nvme_identify_ctrl_list(c->cns, min_id); - if (c->nsid == NVME_NSID_BROADCAST) { + if (!n->subsys) { return NVME_INVALID_FIELD | NVME_DNR; } - ns = nvme_subsys_ns(n->subsys, c->nsid); - if (!ns) { - return NVME_INVALID_FIELD | NVME_DNR; + if (attached) { + if (nsid == NVME_NSID_BROADCAST) { + return NVME_INVALID_FIELD | NVME_DNR; + } + + ns = nvme_subsys_ns(n->subsys, nsid); + if (!ns) { + return NVME_INVALID_FIELD | NVME_DNR; + } } for (cntlid = min_id; cntlid < ARRAY_SIZE(n->subsys->ctrls); cntlid++) { @@ -4271,7 +4511,7 @@ static uint16_t nvme_identify_ns_attached_list(NvmeCtrl *n, NvmeRequest *req) continue; } - if (!nvme_ns(ctrl, c->nsid)) { + if (attached && !nvme_ns(ctrl, nsid)) { continue; } @@ -4284,7 +4524,7 @@ static uint16_t nvme_identify_ns_attached_list(NvmeCtrl *n, NvmeRequest *req) } static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req, - bool active) + bool active) { NvmeNamespace *ns; NvmeIdentify *c = (NvmeIdentify *)&req->cmd; @@ -4308,7 +4548,7 @@ static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req, } } - if (c->csi == NVME_CSI_NVM && nvme_csi_has_nvm_support(ns)) { + if (c->csi == NVME_CSI_NVM) { return nvme_rpt_empty_id_struct(n, req); } else if (c->csi == NVME_CSI_ZONED && ns->csi == NVME_CSI_ZONED) { return nvme_c2h(n, (uint8_t *)ns->id_ns_zoned, sizeof(NvmeIdNsZoned), @@ -4319,7 +4559,7 @@ static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req, } static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req, - bool active) + bool active) { NvmeNamespace *ns; NvmeIdentify *c = (NvmeIdentify *)&req->cmd; @@ -4332,7 +4572,7 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req, trace_pci_nvme_identify_nslist(min_nsid); /* - * Both 0xffffffff (NVME_NSID_BROADCAST) and 0xfffffffe are invalid values + * Both FFFFFFFFh (NVME_NSID_BROADCAST) and FFFFFFFFEh are invalid values * since the Active Namespace ID List should return namespaces with ids * *higher* than the NSID specified in the command. This is also specified * in the spec (NVM Express v1.3d, Section 5.15.4). @@ -4341,7 +4581,7 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req, return NVME_INVALID_NSID | NVME_DNR; } - for (i = 1; i <= n->num_namespaces; i++) { + for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { ns = nvme_ns(n, i); if (!ns) { if (!active) { @@ -4366,7 +4606,7 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req, } static uint16_t nvme_identify_nslist_csi(NvmeCtrl *n, NvmeRequest *req, - bool active) + bool active) { NvmeNamespace *ns; NvmeIdentify *c = (NvmeIdentify *)&req->cmd; @@ -4379,7 +4619,7 @@ static uint16_t nvme_identify_nslist_csi(NvmeCtrl *n, NvmeRequest *req, trace_pci_nvme_identify_nslist_csi(min_nsid, c->csi); /* - * Same as in nvme_identify_nslist(), 0xffffffff/0xfffffffe are invalid. + * Same as in nvme_identify_nslist(), FFFFFFFFh/FFFFFFFFEh are invalid. */ if (min_nsid >= NVME_NSID_BROADCAST - 1) { return NVME_INVALID_NSID | NVME_DNR; @@ -4389,7 +4629,7 @@ static uint16_t nvme_identify_nslist_csi(NvmeCtrl *n, NvmeRequest *req, return NVME_INVALID_FIELD | NVME_DNR; } - for (i = 1; i <= n->num_namespaces; i++) { + for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { ns = nvme_ns(n, i); if (!ns) { if (!active) { @@ -4419,19 +4659,19 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeRequest *req) NvmeIdentify *c = (NvmeIdentify *)&req->cmd; uint32_t nsid = le32_to_cpu(c->nsid); uint8_t list[NVME_IDENTIFY_DATA_SIZE] = {}; - - struct data { - struct { - NvmeIdNsDescr hdr; - uint8_t v[NVME_NIDL_UUID]; - } uuid; - struct { - NvmeIdNsDescr hdr; - uint8_t v; - } csi; - }; - - struct data *ns_descrs = (struct data *)list; + uint8_t *pos = list; + struct { + NvmeIdNsDescr hdr; + uint8_t v[NVME_NIDL_UUID]; + } QEMU_PACKED uuid = {}; + struct { + NvmeIdNsDescr hdr; + uint64_t v; + } QEMU_PACKED eui64 = {}; + struct { + NvmeIdNsDescr hdr; + uint8_t v; + } QEMU_PACKED csi = {}; trace_pci_nvme_identify_ns_descr_list(nsid); @@ -4445,17 +4685,29 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeRequest *req) } /* - * Because the NGUID and EUI64 fields are 0 in the Identify Namespace data - * structure, a Namespace UUID (nidt = 0x3) must be reported in the - * Namespace Identification Descriptor. Add the namespace UUID here. + * If the EUI-64 field is 0 and the NGUID field is 0, the namespace must + * provide a valid Namespace UUID in the Namespace Identification Descriptor + * data structure. QEMU does not yet support setting NGUID. */ - ns_descrs->uuid.hdr.nidt = NVME_NIDT_UUID; - ns_descrs->uuid.hdr.nidl = NVME_NIDL_UUID; - memcpy(&ns_descrs->uuid.v, ns->params.uuid.data, NVME_NIDL_UUID); + uuid.hdr.nidt = NVME_NIDT_UUID; + uuid.hdr.nidl = NVME_NIDL_UUID; + memcpy(uuid.v, ns->params.uuid.data, NVME_NIDL_UUID); + memcpy(pos, &uuid, sizeof(uuid)); + pos += sizeof(uuid); - ns_descrs->csi.hdr.nidt = NVME_NIDT_CSI; - ns_descrs->csi.hdr.nidl = NVME_NIDL_CSI; - ns_descrs->csi.v = ns->csi; + if (ns->params.eui64) { + eui64.hdr.nidt = NVME_NIDT_EUI64; + eui64.hdr.nidl = NVME_NIDL_EUI64; + eui64.v = cpu_to_be64(ns->params.eui64); + memcpy(pos, &eui64, sizeof(eui64)); + pos += sizeof(eui64); + } + + csi.hdr.nidt = NVME_NIDT_CSI; + csi.hdr.nidl = NVME_NIDL_CSI; + csi.v = ns->csi; + memcpy(pos, &csi, sizeof(csi)); + pos += sizeof(csi); return nvme_c2h(n, list, sizeof(list), req); } @@ -4486,7 +4738,9 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest *req) case NVME_ID_CNS_NS_PRESENT: return nvme_identify_ns(n, req, false); case NVME_ID_CNS_NS_ATTACHED_CTRL_LIST: - return nvme_identify_ns_attached_list(n, req); + return nvme_identify_ctrl_list(n, req, true); + case NVME_ID_CNS_CTRL_LIST: + return nvme_identify_ctrl_list(n, req, false); case NVME_ID_CNS_CS_NS: return nvme_identify_ns_csi(n, req, true); case NVME_ID_CNS_CS_NS_PRESENT: @@ -4595,7 +4849,7 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeRequest *req) /* * The Reservation Notification Mask and Reservation Persistence * features require a status code of Invalid Field in Command when - * NSID is 0xFFFFFFFF. Since the device does not support those + * NSID is FFFFFFFFh. Since the device does not support those * features we can always return Invalid Namespace or Format as we * should do for all other features. */ @@ -4655,7 +4909,7 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeRequest *req) goto out; case NVME_VOLATILE_WRITE_CACHE: result = 0; - for (i = 1; i <= n->num_namespaces; i++) { + for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { ns = nvme_ns(n, i); if (!ns) { continue; @@ -4707,9 +4961,6 @@ defaults: result |= NVME_INTVC_NOCOALESCING; } break; - case NVME_COMMAND_SET_PROFILE: - result = 0; - break; default: result = nvme_feature_default[fid]; break; @@ -4805,7 +5056,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req) break; case NVME_ERROR_RECOVERY: if (nsid == NVME_NSID_BROADCAST) { - for (i = 1; i <= n->num_namespaces; i++) { + for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { ns = nvme_ns(n, i); if (!ns) { @@ -4826,7 +5077,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req) } break; case NVME_VOLATILE_WRITE_CACHE: - for (i = 1; i <= n->num_namespaces; i++) { + for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { ns = nvme_ns(n, i); if (!ns) { continue; @@ -4847,15 +5098,15 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req) } /* - * NVMe v1.3, Section 5.21.1.7: 0xffff is not an allowed value for NCQR + * NVMe v1.3, Section 5.21.1.7: FFFFh is not an allowed value for NCQR * and NSQR. */ if ((dw11 & 0xffff) == 0xffff || ((dw11 >> 16) & 0xffff) == 0xffff) { return NVME_INVALID_FIELD | NVME_DNR; } - trace_pci_nvme_setfeat_numq((dw11 & 0xFFFF) + 1, - ((dw11 >> 16) & 0xFFFF) + 1, + trace_pci_nvme_setfeat_numq((dw11 & 0xffff) + 1, + ((dw11 >> 16) & 0xffff) + 1, n->params.max_ioqpairs, n->params.max_ioqpairs); req->cqe.result = cpu_to_le32((n->params.max_ioqpairs - 1) | @@ -4912,7 +5163,27 @@ static void nvme_update_dmrsl(NvmeCtrl *n) } } -static void __nvme_select_ns_iocs(NvmeCtrl *n, NvmeNamespace *ns); +static void nvme_select_iocs_ns(NvmeCtrl *n, NvmeNamespace *ns) +{ + uint32_t cc = ldl_le_p(&n->bar.cc); + + ns->iocs = nvme_cse_iocs_none; + switch (ns->csi) { + case NVME_CSI_NVM: + if (NVME_CC_CSS(cc) != NVME_CC_CSS_ADMIN_ONLY) { + ns->iocs = nvme_cse_iocs_nvm; + } + break; + case NVME_CSI_ZONED: + if (NVME_CC_CSS(cc) == NVME_CC_CSS_CSI) { + ns->iocs = nvme_cse_iocs_zoned; + } else if (NVME_CC_CSS(cc) == NVME_CC_CSS_NVM) { + ns->iocs = nvme_cse_iocs_nvm; + } + break; + } +} + static uint16_t nvme_ns_attachment(NvmeCtrl *n, NvmeRequest *req) { NvmeNamespace *ns; @@ -4963,13 +5234,13 @@ static uint16_t nvme_ns_attachment(NvmeCtrl *n, NvmeRequest *req) } nvme_attach_ns(ctrl, ns); - __nvme_select_ns_iocs(ctrl, ns); + nvme_select_iocs_ns(ctrl, ns); } else { if (!nvme_ns(ctrl, nsid)) { return NVME_NS_NOT_ATTACHED | NVME_DNR; } - ctrl->namespaces[nsid - 1] = NULL; + ctrl->namespaces[nsid] = NULL; ns->attached--; nvme_update_dmrsl(ctrl); @@ -4989,30 +5260,98 @@ static uint16_t nvme_ns_attachment(NvmeCtrl *n, NvmeRequest *req) return NVME_SUCCESS; } -static uint16_t nvme_format_ns(NvmeCtrl *n, NvmeNamespace *ns, uint8_t lbaf, - uint8_t mset, uint8_t pi, uint8_t pil, - NvmeRequest *req) -{ - int64_t len, offset; - struct nvme_aio_format_ctx *ctx; - BlockBackend *blk = ns->blkconf.blk; - uint16_t ms; - uintptr_t *num_formats = (uintptr_t *)&req->opaque; - int *count; +typedef struct NvmeFormatAIOCB { + BlockAIOCB common; + BlockAIOCB *aiocb; + QEMUBH *bh; + NvmeRequest *req; + int ret; + NvmeNamespace *ns; + uint32_t nsid; + bool broadcast; + int64_t offset; +} NvmeFormatAIOCB; + +static void nvme_format_bh(void *opaque); + +static void nvme_format_cancel(BlockAIOCB *aiocb) +{ + NvmeFormatAIOCB *iocb = container_of(aiocb, NvmeFormatAIOCB, common); + + if (iocb->aiocb) { + blk_aio_cancel_async(iocb->aiocb); + } +} + +static const AIOCBInfo nvme_format_aiocb_info = { + .aiocb_size = sizeof(NvmeFormatAIOCB), + .cancel_async = nvme_format_cancel, + .get_aio_context = nvme_get_aio_context, +}; + +static void nvme_format_set(NvmeNamespace *ns, NvmeCmd *cmd) +{ + uint32_t dw10 = le32_to_cpu(cmd->cdw10); + uint8_t lbaf = dw10 & 0xf; + uint8_t pi = (dw10 >> 5) & 0x7; + uint8_t mset = (dw10 >> 4) & 0x1; + uint8_t pil = (dw10 >> 8) & 0x1; + + trace_pci_nvme_format_set(ns->params.nsid, lbaf, mset, pi, pil); + + ns->id_ns.dps = (pil << 3) | pi; + ns->id_ns.flbas = lbaf | (mset << 4); + + nvme_ns_init_format(ns); +} + +static void nvme_format_ns_cb(void *opaque, int ret) +{ + NvmeFormatAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeNamespace *ns = iocb->ns; + int bytes; + + if (ret < 0) { + iocb->ret = ret; + goto done; + } + + assert(ns); + + if (iocb->offset < ns->size) { + bytes = MIN(BDRV_REQUEST_MAX_BYTES, ns->size - iocb->offset); + + iocb->aiocb = blk_aio_pwrite_zeroes(ns->blkconf.blk, iocb->offset, + bytes, BDRV_REQ_MAY_UNMAP, + nvme_format_ns_cb, iocb); + + iocb->offset += bytes; + return; + } + + nvme_format_set(ns, &req->cmd); + ns->status = 0x0; + iocb->ns = NULL; + iocb->offset = 0; + +done: + iocb->aiocb = NULL; + qemu_bh_schedule(iocb->bh); +} + +static uint16_t nvme_format_check(NvmeNamespace *ns, uint8_t lbaf, uint8_t pi) +{ if (ns->params.zoned) { return NVME_INVALID_FORMAT | NVME_DNR; } - trace_pci_nvme_format_ns(nvme_cid(req), nvme_nsid(ns), lbaf, mset, pi, pil); - if (lbaf > ns->id_ns.nlbaf) { return NVME_INVALID_FORMAT | NVME_DNR; } - ms = ns->id_ns.lbaf[lbaf].ms; - - if (pi && (ms < sizeof(NvmeDifTuple))) { + if (pi && (ns->id_ns.lbaf[lbaf].ms < sizeof(NvmeDifTuple))) { return NVME_INVALID_FORMAT | NVME_DNR; } @@ -5020,107 +5359,96 @@ static uint16_t nvme_format_ns(NvmeCtrl *n, NvmeNamespace *ns, uint8_t lbaf, return NVME_INVALID_FIELD | NVME_DNR; } - nvme_ns_drain(ns); - nvme_ns_shutdown(ns); - nvme_ns_cleanup(ns); - - ns->id_ns.dps = (pil << 3) | pi; - ns->id_ns.flbas = lbaf | (mset << 4); - - nvme_ns_init_format(ns); - - ns->status = NVME_FORMAT_IN_PROGRESS; - - len = ns->size; - offset = 0; - - count = g_new(int, 1); - *count = 1; - - (*num_formats)++; - - while (len) { - ctx = g_new(struct nvme_aio_format_ctx, 1); - ctx->req = req; - ctx->ns = ns; - ctx->count = count; - - size_t bytes = MIN(BDRV_REQUEST_MAX_BYTES, len); - - (*count)++; - - blk_aio_pwrite_zeroes(blk, offset, bytes, BDRV_REQ_MAY_UNMAP, - nvme_aio_format_cb, ctx); - - offset += bytes; - len -= bytes; - - } - - if (--(*count)) { - return NVME_NO_COMPLETE; - } - - g_free(count); - ns->status = 0x0; - (*num_formats)--; - return NVME_SUCCESS; } -static uint16_t nvme_format(NvmeCtrl *n, NvmeRequest *req) +static void nvme_format_bh(void *opaque) { - NvmeNamespace *ns; + NvmeFormatAIOCB *iocb = opaque; + NvmeRequest *req = iocb->req; + NvmeCtrl *n = nvme_ctrl(req); uint32_t dw10 = le32_to_cpu(req->cmd.cdw10); - uint32_t nsid = le32_to_cpu(req->cmd.nsid); uint8_t lbaf = dw10 & 0xf; - uint8_t mset = (dw10 >> 4) & 0x1; uint8_t pi = (dw10 >> 5) & 0x7; - uint8_t pil = (dw10 >> 8) & 0x1; - uintptr_t *num_formats = (uintptr_t *)&req->opaque; uint16_t status; int i; - trace_pci_nvme_format(nvme_cid(req), nsid, lbaf, mset, pi, pil); + if (iocb->ret < 0) { + goto done; + } - /* 1-initialize; see the comment in nvme_dsm */ - *num_formats = 1; - - if (nsid != NVME_NSID_BROADCAST) { - if (!nvme_nsid_valid(n, nsid)) { - return NVME_INVALID_NSID | NVME_DNR; - } - - ns = nvme_ns(n, nsid); - if (!ns) { - return NVME_INVALID_FIELD | NVME_DNR; - } - - status = nvme_format_ns(n, ns, lbaf, mset, pi, pil, req); - if (status && status != NVME_NO_COMPLETE) { - req->status = status; - } - } else { - for (i = 1; i <= n->num_namespaces; i++) { - ns = nvme_ns(n, i); - if (!ns) { - continue; - } - - status = nvme_format_ns(n, ns, lbaf, mset, pi, pil, req); - if (status && status != NVME_NO_COMPLETE) { - req->status = status; + if (iocb->broadcast) { + for (i = iocb->nsid + 1; i <= NVME_MAX_NAMESPACES; i++) { + iocb->ns = nvme_ns(n, i); + if (iocb->ns) { + iocb->nsid = i; break; } } } - /* account for the 1-initialization */ - if (--(*num_formats)) { - return NVME_NO_COMPLETE; + if (!iocb->ns) { + goto done; } - return req->status; + status = nvme_format_check(iocb->ns, lbaf, pi); + if (status) { + req->status = status; + goto done; + } + + iocb->ns->status = NVME_FORMAT_IN_PROGRESS; + nvme_format_ns_cb(iocb, 0); + return; + +done: + qemu_bh_delete(iocb->bh); + iocb->bh = NULL; + + iocb->common.cb(iocb->common.opaque, iocb->ret); + + qemu_aio_unref(iocb); +} + +static uint16_t nvme_format(NvmeCtrl *n, NvmeRequest *req) +{ + NvmeFormatAIOCB *iocb; + uint32_t nsid = le32_to_cpu(req->cmd.nsid); + uint16_t status; + + iocb = qemu_aio_get(&nvme_format_aiocb_info, NULL, nvme_misc_cb, req); + + iocb->req = req; + iocb->bh = qemu_bh_new(nvme_format_bh, iocb); + iocb->ret = 0; + iocb->ns = NULL; + iocb->nsid = 0; + iocb->broadcast = (nsid == NVME_NSID_BROADCAST); + iocb->offset = 0; + + if (!iocb->broadcast) { + if (!nvme_nsid_valid(n, nsid)) { + status = NVME_INVALID_NSID | NVME_DNR; + goto out; + } + + iocb->ns = nvme_ns(n, nsid); + if (!iocb->ns) { + status = NVME_INVALID_FIELD | NVME_DNR; + goto out; + } + } + + req->aiocb = &iocb->common; + qemu_bh_schedule(iocb->bh); + + return NVME_NO_COMPLETE; + +out: + qemu_bh_delete(iocb->bh); + iocb->bh = NULL; + qemu_aio_unref(iocb); + return status; } static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req) @@ -5186,7 +5514,7 @@ static void nvme_process_sq(void *opaque) if (nvme_addr_read(n, addr, (void *)&cmd, sizeof(cmd))) { trace_pci_nvme_err_addr_read(addr); trace_pci_nvme_err_cfs(); - n->bar.csts = NVME_CSTS_FAILED; + stl_le_p(&n->bar.csts, NVME_CSTS_FAILED); break; } nvme_inc_sq_head(sq); @@ -5212,7 +5540,7 @@ static void nvme_ctrl_reset(NvmeCtrl *n) NvmeNamespace *ns; int i; - for (i = 1; i <= n->num_namespaces; i++) { + for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { ns = nvme_ns(n, i); if (!ns) { continue; @@ -5241,8 +5569,6 @@ static void nvme_ctrl_reset(NvmeCtrl *n) n->aer_queued = 0; n->outstanding_aers = 0; n->qs_created = false; - - n->bar.cc = 0; } static void nvme_ctrl_shutdown(NvmeCtrl *n) @@ -5254,7 +5580,7 @@ static void nvme_ctrl_shutdown(NvmeCtrl *n) memory_region_msync(&n->pmr.dev->mr, 0, n->pmr.dev->size); } - for (i = 1; i <= n->num_namespaces; i++) { + for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { ns = nvme_ns(n, i); if (!ns) { continue; @@ -5264,43 +5590,29 @@ static void nvme_ctrl_shutdown(NvmeCtrl *n) } } -static void __nvme_select_ns_iocs(NvmeCtrl *n, NvmeNamespace *ns) -{ - ns->iocs = nvme_cse_iocs_none; - switch (ns->csi) { - case NVME_CSI_NVM: - if (NVME_CC_CSS(n->bar.cc) != NVME_CC_CSS_ADMIN_ONLY) { - ns->iocs = nvme_cse_iocs_nvm; - } - break; - case NVME_CSI_ZONED: - if (NVME_CC_CSS(n->bar.cc) == NVME_CC_CSS_CSI) { - ns->iocs = nvme_cse_iocs_zoned; - } else if (NVME_CC_CSS(n->bar.cc) == NVME_CC_CSS_NVM) { - ns->iocs = nvme_cse_iocs_nvm; - } - break; - } -} - -static void nvme_select_ns_iocs(NvmeCtrl *n) +static void nvme_select_iocs(NvmeCtrl *n) { NvmeNamespace *ns; int i; - for (i = 1; i <= n->num_namespaces; i++) { + for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { ns = nvme_ns(n, i); if (!ns) { continue; } - __nvme_select_ns_iocs(n, ns); + nvme_select_iocs_ns(n, ns); } } static int nvme_start_ctrl(NvmeCtrl *n) { - uint32_t page_bits = NVME_CC_MPS(n->bar.cc) + 12; + uint64_t cap = ldq_le_p(&n->bar.cap); + uint32_t cc = ldl_le_p(&n->bar.cc); + uint32_t aqa = ldl_le_p(&n->bar.aqa); + uint64_t asq = ldq_le_p(&n->bar.asq); + uint64_t acq = ldq_le_p(&n->bar.acq); + uint32_t page_bits = NVME_CC_MPS(cc) + 12; uint32_t page_size = 1 << page_bits; if (unlikely(n->cq[0])) { @@ -5311,73 +5623,72 @@ static int nvme_start_ctrl(NvmeCtrl *n) trace_pci_nvme_err_startfail_sq(); return -1; } - if (unlikely(!n->bar.asq)) { + if (unlikely(!asq)) { trace_pci_nvme_err_startfail_nbarasq(); return -1; } - if (unlikely(!n->bar.acq)) { + if (unlikely(!acq)) { trace_pci_nvme_err_startfail_nbaracq(); return -1; } - if (unlikely(n->bar.asq & (page_size - 1))) { - trace_pci_nvme_err_startfail_asq_misaligned(n->bar.asq); + if (unlikely(asq & (page_size - 1))) { + trace_pci_nvme_err_startfail_asq_misaligned(asq); return -1; } - if (unlikely(n->bar.acq & (page_size - 1))) { - trace_pci_nvme_err_startfail_acq_misaligned(n->bar.acq); + if (unlikely(acq & (page_size - 1))) { + trace_pci_nvme_err_startfail_acq_misaligned(acq); return -1; } - if (unlikely(!(NVME_CAP_CSS(n->bar.cap) & (1 << NVME_CC_CSS(n->bar.cc))))) { - trace_pci_nvme_err_startfail_css(NVME_CC_CSS(n->bar.cc)); + if (unlikely(!(NVME_CAP_CSS(cap) & (1 << NVME_CC_CSS(cc))))) { + trace_pci_nvme_err_startfail_css(NVME_CC_CSS(cc)); return -1; } - if (unlikely(NVME_CC_MPS(n->bar.cc) < - NVME_CAP_MPSMIN(n->bar.cap))) { + if (unlikely(NVME_CC_MPS(cc) < NVME_CAP_MPSMIN(cap))) { trace_pci_nvme_err_startfail_page_too_small( - NVME_CC_MPS(n->bar.cc), - NVME_CAP_MPSMIN(n->bar.cap)); + NVME_CC_MPS(cc), + NVME_CAP_MPSMIN(cap)); return -1; } - if (unlikely(NVME_CC_MPS(n->bar.cc) > - NVME_CAP_MPSMAX(n->bar.cap))) { + if (unlikely(NVME_CC_MPS(cc) > + NVME_CAP_MPSMAX(cap))) { trace_pci_nvme_err_startfail_page_too_large( - NVME_CC_MPS(n->bar.cc), - NVME_CAP_MPSMAX(n->bar.cap)); + NVME_CC_MPS(cc), + NVME_CAP_MPSMAX(cap)); return -1; } - if (unlikely(NVME_CC_IOCQES(n->bar.cc) < + if (unlikely(NVME_CC_IOCQES(cc) < NVME_CTRL_CQES_MIN(n->id_ctrl.cqes))) { trace_pci_nvme_err_startfail_cqent_too_small( - NVME_CC_IOCQES(n->bar.cc), - NVME_CTRL_CQES_MIN(n->bar.cap)); + NVME_CC_IOCQES(cc), + NVME_CTRL_CQES_MIN(cap)); return -1; } - if (unlikely(NVME_CC_IOCQES(n->bar.cc) > + if (unlikely(NVME_CC_IOCQES(cc) > NVME_CTRL_CQES_MAX(n->id_ctrl.cqes))) { trace_pci_nvme_err_startfail_cqent_too_large( - NVME_CC_IOCQES(n->bar.cc), - NVME_CTRL_CQES_MAX(n->bar.cap)); + NVME_CC_IOCQES(cc), + NVME_CTRL_CQES_MAX(cap)); return -1; } - if (unlikely(NVME_CC_IOSQES(n->bar.cc) < + if (unlikely(NVME_CC_IOSQES(cc) < NVME_CTRL_SQES_MIN(n->id_ctrl.sqes))) { trace_pci_nvme_err_startfail_sqent_too_small( - NVME_CC_IOSQES(n->bar.cc), - NVME_CTRL_SQES_MIN(n->bar.cap)); + NVME_CC_IOSQES(cc), + NVME_CTRL_SQES_MIN(cap)); return -1; } - if (unlikely(NVME_CC_IOSQES(n->bar.cc) > + if (unlikely(NVME_CC_IOSQES(cc) > NVME_CTRL_SQES_MAX(n->id_ctrl.sqes))) { trace_pci_nvme_err_startfail_sqent_too_large( - NVME_CC_IOSQES(n->bar.cc), - NVME_CTRL_SQES_MAX(n->bar.cap)); + NVME_CC_IOSQES(cc), + NVME_CTRL_SQES_MAX(cap)); return -1; } - if (unlikely(!NVME_AQA_ASQS(n->bar.aqa))) { + if (unlikely(!NVME_AQA_ASQS(aqa))) { trace_pci_nvme_err_startfail_asqent_sz_zero(); return -1; } - if (unlikely(!NVME_AQA_ACQS(n->bar.aqa))) { + if (unlikely(!NVME_AQA_ACQS(aqa))) { trace_pci_nvme_err_startfail_acqent_sz_zero(); return -1; } @@ -5385,40 +5696,49 @@ static int nvme_start_ctrl(NvmeCtrl *n) n->page_bits = page_bits; n->page_size = page_size; n->max_prp_ents = n->page_size / sizeof(uint64_t); - n->cqe_size = 1 << NVME_CC_IOCQES(n->bar.cc); - n->sqe_size = 1 << NVME_CC_IOSQES(n->bar.cc); - nvme_init_cq(&n->admin_cq, n, n->bar.acq, 0, 0, - NVME_AQA_ACQS(n->bar.aqa) + 1, 1); - nvme_init_sq(&n->admin_sq, n, n->bar.asq, 0, 0, - NVME_AQA_ASQS(n->bar.aqa) + 1); + n->cqe_size = 1 << NVME_CC_IOCQES(cc); + n->sqe_size = 1 << NVME_CC_IOSQES(cc); + nvme_init_cq(&n->admin_cq, n, acq, 0, 0, NVME_AQA_ACQS(aqa) + 1, 1); + nvme_init_sq(&n->admin_sq, n, asq, 0, 0, NVME_AQA_ASQS(aqa) + 1); nvme_set_timestamp(n, 0ULL); QTAILQ_INIT(&n->aer_queue); - nvme_select_ns_iocs(n); + nvme_select_iocs(n); return 0; } static void nvme_cmb_enable_regs(NvmeCtrl *n) { - NVME_CMBLOC_SET_CDPCILS(n->bar.cmbloc, 1); - NVME_CMBLOC_SET_CDPMLS(n->bar.cmbloc, 1); - NVME_CMBLOC_SET_BIR(n->bar.cmbloc, NVME_CMB_BIR); + uint32_t cmbloc = ldl_le_p(&n->bar.cmbloc); + uint32_t cmbsz = ldl_le_p(&n->bar.cmbsz); - NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1); - NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0); - NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 1); - NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1); - NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1); - NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2); /* MBs */ - NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb); + NVME_CMBLOC_SET_CDPCILS(cmbloc, 1); + NVME_CMBLOC_SET_CDPMLS(cmbloc, 1); + NVME_CMBLOC_SET_BIR(cmbloc, NVME_CMB_BIR); + stl_le_p(&n->bar.cmbloc, cmbloc); + + NVME_CMBSZ_SET_SQS(cmbsz, 1); + NVME_CMBSZ_SET_CQS(cmbsz, 0); + NVME_CMBSZ_SET_LISTS(cmbsz, 1); + NVME_CMBSZ_SET_RDS(cmbsz, 1); + NVME_CMBSZ_SET_WDS(cmbsz, 1); + NVME_CMBSZ_SET_SZU(cmbsz, 2); /* MBs */ + NVME_CMBSZ_SET_SZ(cmbsz, n->params.cmb_size_mb); + stl_le_p(&n->bar.cmbsz, cmbsz); } static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, unsigned size) { + uint64_t cap = ldq_le_p(&n->bar.cap); + uint32_t cc = ldl_le_p(&n->bar.cc); + uint32_t intms = ldl_le_p(&n->bar.intms); + uint32_t csts = ldl_le_p(&n->bar.csts); + uint32_t pmrsts = ldl_le_p(&n->bar.pmrsts); + if (unlikely(offset & (sizeof(uint32_t) - 1))) { NVME_GUEST_ERR(pci_nvme_ub_mmiowr_misaligned32, "MMIO write not 32-bit aligned," @@ -5435,65 +5755,77 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, } switch (offset) { - case 0xc: /* INTMS */ + case NVME_REG_INTMS: if (unlikely(msix_enabled(&(n->parent_obj)))) { NVME_GUEST_ERR(pci_nvme_ub_mmiowr_intmask_with_msix, "undefined access to interrupt mask set" " when MSI-X is enabled"); /* should be ignored, fall through for now */ } - n->bar.intms |= data & 0xffffffff; + intms |= data; + stl_le_p(&n->bar.intms, intms); n->bar.intmc = n->bar.intms; - trace_pci_nvme_mmio_intm_set(data & 0xffffffff, n->bar.intmc); + trace_pci_nvme_mmio_intm_set(data & 0xffffffff, intms); nvme_irq_check(n); break; - case 0x10: /* INTMC */ + case NVME_REG_INTMC: if (unlikely(msix_enabled(&(n->parent_obj)))) { NVME_GUEST_ERR(pci_nvme_ub_mmiowr_intmask_with_msix, "undefined access to interrupt mask clr" " when MSI-X is enabled"); /* should be ignored, fall through for now */ } - n->bar.intms &= ~(data & 0xffffffff); + intms &= ~data; + stl_le_p(&n->bar.intms, intms); n->bar.intmc = n->bar.intms; - trace_pci_nvme_mmio_intm_clr(data & 0xffffffff, n->bar.intmc); + trace_pci_nvme_mmio_intm_clr(data & 0xffffffff, intms); nvme_irq_check(n); break; - case 0x14: /* CC */ + case NVME_REG_CC: trace_pci_nvme_mmio_cfg(data & 0xffffffff); + /* Windows first sends data, then sends enable bit */ - if (!NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc) && - !NVME_CC_SHN(data) && !NVME_CC_SHN(n->bar.cc)) + if (!NVME_CC_EN(data) && !NVME_CC_EN(cc) && + !NVME_CC_SHN(data) && !NVME_CC_SHN(cc)) { - n->bar.cc = data; + cc = data; } - if (NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc)) { - n->bar.cc = data; + if (NVME_CC_EN(data) && !NVME_CC_EN(cc)) { + cc = data; + + /* flush CC since nvme_start_ctrl() needs the value */ + stl_le_p(&n->bar.cc, cc); if (unlikely(nvme_start_ctrl(n))) { trace_pci_nvme_err_startfail(); - n->bar.csts = NVME_CSTS_FAILED; + csts = NVME_CSTS_FAILED; } else { trace_pci_nvme_mmio_start_success(); - n->bar.csts = NVME_CSTS_READY; + csts = NVME_CSTS_READY; } - } else if (!NVME_CC_EN(data) && NVME_CC_EN(n->bar.cc)) { + } else if (!NVME_CC_EN(data) && NVME_CC_EN(cc)) { trace_pci_nvme_mmio_stopped(); nvme_ctrl_reset(n); - n->bar.csts &= ~NVME_CSTS_READY; + cc = 0; + csts &= ~NVME_CSTS_READY; } - if (NVME_CC_SHN(data) && !(NVME_CC_SHN(n->bar.cc))) { + + if (NVME_CC_SHN(data) && !(NVME_CC_SHN(cc))) { trace_pci_nvme_mmio_shutdown_set(); nvme_ctrl_shutdown(n); - n->bar.cc = data; - n->bar.csts |= NVME_CSTS_SHST_COMPLETE; - } else if (!NVME_CC_SHN(data) && NVME_CC_SHN(n->bar.cc)) { + cc = data; + csts |= NVME_CSTS_SHST_COMPLETE; + } else if (!NVME_CC_SHN(data) && NVME_CC_SHN(cc)) { trace_pci_nvme_mmio_shutdown_cleared(); - n->bar.csts &= ~NVME_CSTS_SHST_COMPLETE; - n->bar.cc = data; + csts &= ~NVME_CSTS_SHST_COMPLETE; + cc = data; } + + stl_le_p(&n->bar.cc, cc); + stl_le_p(&n->bar.csts, csts); + break; - case 0x1C: /* CSTS */ + case NVME_REG_CSTS: if (data & (1 << 4)) { NVME_GUEST_ERR(pci_nvme_ub_mmiowr_ssreset_w1c_unsupported, "attempted to W1C CSTS.NSSRO" @@ -5504,61 +5836,61 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, " of controller status"); } break; - case 0x20: /* NSSR */ - if (data == 0x4E564D65) { + case NVME_REG_NSSR: + if (data == 0x4e564d65) { trace_pci_nvme_ub_mmiowr_ssreset_unsupported(); } else { /* The spec says that writes of other values have no effect */ return; } break; - case 0x24: /* AQA */ - n->bar.aqa = data & 0xffffffff; + case NVME_REG_AQA: + stl_le_p(&n->bar.aqa, data); trace_pci_nvme_mmio_aqattr(data & 0xffffffff); break; - case 0x28: /* ASQ */ - n->bar.asq = size == 8 ? data : - (n->bar.asq & ~0xffffffffULL) | (data & 0xffffffff); + case NVME_REG_ASQ: + stn_le_p(&n->bar.asq, size, data); trace_pci_nvme_mmio_asqaddr(data); break; - case 0x2c: /* ASQ hi */ - n->bar.asq = (n->bar.asq & 0xffffffff) | (data << 32); - trace_pci_nvme_mmio_asqaddr_hi(data, n->bar.asq); + case NVME_REG_ASQ + 4: + stl_le_p((uint8_t *)&n->bar.asq + 4, data); + trace_pci_nvme_mmio_asqaddr_hi(data, ldq_le_p(&n->bar.asq)); break; - case 0x30: /* ACQ */ + case NVME_REG_ACQ: trace_pci_nvme_mmio_acqaddr(data); - n->bar.acq = size == 8 ? data : - (n->bar.acq & ~0xffffffffULL) | (data & 0xffffffff); + stn_le_p(&n->bar.acq, size, data); break; - case 0x34: /* ACQ hi */ - n->bar.acq = (n->bar.acq & 0xffffffff) | (data << 32); - trace_pci_nvme_mmio_acqaddr_hi(data, n->bar.acq); + case NVME_REG_ACQ + 4: + stl_le_p((uint8_t *)&n->bar.acq + 4, data); + trace_pci_nvme_mmio_acqaddr_hi(data, ldq_le_p(&n->bar.acq)); break; - case 0x38: /* CMBLOC */ + case NVME_REG_CMBLOC: NVME_GUEST_ERR(pci_nvme_ub_mmiowr_cmbloc_reserved, "invalid write to reserved CMBLOC" " when CMBSZ is zero, ignored"); return; - case 0x3C: /* CMBSZ */ + case NVME_REG_CMBSZ: NVME_GUEST_ERR(pci_nvme_ub_mmiowr_cmbsz_readonly, "invalid write to read only CMBSZ, ignored"); return; - case 0x50: /* CMBMSC */ - if (!NVME_CAP_CMBS(n->bar.cap)) { + case NVME_REG_CMBMSC: + if (!NVME_CAP_CMBS(cap)) { return; } - n->bar.cmbmsc = size == 8 ? data : - (n->bar.cmbmsc & ~0xffffffff) | (data & 0xffffffff); + stn_le_p(&n->bar.cmbmsc, size, data); n->cmb.cmse = false; if (NVME_CMBMSC_CRE(data)) { nvme_cmb_enable_regs(n); if (NVME_CMBMSC_CMSE(data)) { - hwaddr cba = NVME_CMBMSC_CBA(data) << CMBMSC_CBA_SHIFT; + uint64_t cmbmsc = ldq_le_p(&n->bar.cmbmsc); + hwaddr cba = NVME_CMBMSC_CBA(cmbmsc) << CMBMSC_CBA_SHIFT; if (cba + int128_get64(n->cmb.mem.size) < cba) { - NVME_CMBSTS_SET_CBAI(n->bar.cmbsts, 1); + uint32_t cmbsts = ldl_le_p(&n->bar.cmbsts); + NVME_CMBSTS_SET_CBAI(cmbsts, 1); + stl_le_p(&n->bar.cmbsts, cmbsts); return; } @@ -5571,49 +5903,57 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, } return; - case 0x54: /* CMBMSC hi */ - n->bar.cmbmsc = (n->bar.cmbmsc & 0xffffffff) | (data << 32); + case NVME_REG_CMBMSC + 4: + stl_le_p((uint8_t *)&n->bar.cmbmsc + 4, data); return; - case 0xE00: /* PMRCAP */ + case NVME_REG_PMRCAP: NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrcap_readonly, "invalid write to PMRCAP register, ignored"); return; - case 0xE04: /* PMRCTL */ - n->bar.pmrctl = data; - if (NVME_PMRCTL_EN(data)) { - memory_region_set_enabled(&n->pmr.dev->mr, true); - n->bar.pmrsts = 0; - } else { - memory_region_set_enabled(&n->pmr.dev->mr, false); - NVME_PMRSTS_SET_NRDY(n->bar.pmrsts, 1); - n->pmr.cmse = false; - } - return; - case 0xE08: /* PMRSTS */ - NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrsts_readonly, - "invalid write to PMRSTS register, ignored"); - return; - case 0xE0C: /* PMREBS */ - NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrebs_readonly, - "invalid write to PMREBS register, ignored"); - return; - case 0xE10: /* PMRSWTP */ - NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrswtp_readonly, - "invalid write to PMRSWTP register, ignored"); - return; - case 0xE14: /* PMRMSCL */ - if (!NVME_CAP_PMRS(n->bar.cap)) { + case NVME_REG_PMRCTL: + if (!NVME_CAP_PMRS(cap)) { return; } - n->bar.pmrmsc = (n->bar.pmrmsc & ~0xffffffff) | (data & 0xffffffff); + stl_le_p(&n->bar.pmrctl, data); + if (NVME_PMRCTL_EN(data)) { + memory_region_set_enabled(&n->pmr.dev->mr, true); + pmrsts = 0; + } else { + memory_region_set_enabled(&n->pmr.dev->mr, false); + NVME_PMRSTS_SET_NRDY(pmrsts, 1); + n->pmr.cmse = false; + } + stl_le_p(&n->bar.pmrsts, pmrsts); + return; + case NVME_REG_PMRSTS: + NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrsts_readonly, + "invalid write to PMRSTS register, ignored"); + return; + case NVME_REG_PMREBS: + NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrebs_readonly, + "invalid write to PMREBS register, ignored"); + return; + case NVME_REG_PMRSWTP: + NVME_GUEST_ERR(pci_nvme_ub_mmiowr_pmrswtp_readonly, + "invalid write to PMRSWTP register, ignored"); + return; + case NVME_REG_PMRMSCL: + if (!NVME_CAP_PMRS(cap)) { + return; + } + + stl_le_p(&n->bar.pmrmscl, data); n->pmr.cmse = false; - if (NVME_PMRMSC_CMSE(n->bar.pmrmsc)) { - hwaddr cba = NVME_PMRMSC_CBA(n->bar.pmrmsc) << PMRMSC_CBA_SHIFT; + if (NVME_PMRMSCL_CMSE(data)) { + uint64_t pmrmscu = ldl_le_p(&n->bar.pmrmscu); + hwaddr cba = pmrmscu << 32 | + (NVME_PMRMSCL_CBA(data) << PMRMSCL_CBA_SHIFT); if (cba + int128_get64(n->pmr.dev->mr.size) < cba) { - NVME_PMRSTS_SET_CBAI(n->bar.pmrsts, 1); + NVME_PMRSTS_SET_CBAI(pmrsts, 1); + stl_le_p(&n->bar.pmrsts, pmrsts); return; } @@ -5622,12 +5962,12 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, } return; - case 0xE18: /* PMRMSCU */ - if (!NVME_CAP_PMRS(n->bar.cap)) { + case NVME_REG_PMRMSCU: + if (!NVME_CAP_PMRS(cap)) { return; } - n->bar.pmrmsc = (n->bar.pmrmsc & 0xffffffff) | (data << 32); + stl_le_p(&n->bar.pmrmscu, data); return; default: NVME_GUEST_ERR(pci_nvme_ub_mmiowr_invalid, @@ -5642,7 +5982,6 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) { NvmeCtrl *n = (NvmeCtrl *)opaque; uint8_t *ptr = (uint8_t *)&n->bar; - uint64_t val = 0; trace_pci_nvme_mmio_read(addr, size); @@ -5658,24 +5997,25 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) /* should RAZ, fall through for now */ } - if (addr < sizeof(n->bar)) { - /* - * When PMRWBM bit 1 is set then read from - * from PMRSTS should ensure prior writes - * made it to persistent media - */ - if (addr == 0xE08 && - (NVME_PMRCAP_PMRWBM(n->bar.pmrcap) & 0x02)) { - memory_region_msync(&n->pmr.dev->mr, 0, n->pmr.dev->size); - } - memcpy(&val, ptr + addr, size); - } else { + if (addr > sizeof(n->bar) - size) { NVME_GUEST_ERR(pci_nvme_ub_mmiord_invalid_ofs, "MMIO read beyond last register," " offset=0x%"PRIx64", returning 0", addr); + + return 0; } - return val; + /* + * When PMRWBM bit 1 is set then read from + * from PMRSTS should ensure prior writes + * made it to persistent media + */ + if (addr == NVME_REG_PMRSTS && + (NVME_PMRCAP_PMRWBM(ldl_le_p(&n->bar.pmrcap)) & 0x02)) { + memory_region_msync(&n->pmr.dev->mr, 0, n->pmr.dev->size); + } + + return ldn_le_p(ptr + addr, size); } static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) @@ -5755,6 +6095,10 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) } if (cq->tail == cq->head) { + if (cq->irq_enabled) { + n->cq_pending--; + } + nvme_irq_deassert(n, cq); } } else { @@ -5915,7 +6259,6 @@ static void nvme_check_constraints(NvmeCtrl *n, Error **errp) static void nvme_init_state(NvmeCtrl *n) { - n->num_namespaces = NVME_MAX_NAMESPACES; /* add one to max_ioqpairs to account for the admin queue pair */ n->reg_size = pow2ceil(sizeof(NvmeBar) + 2 * (n->params.max_ioqpairs + 1) * NVME_DB_SIZE); @@ -5930,6 +6273,7 @@ static void nvme_init_state(NvmeCtrl *n) static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev) { uint64_t cmb_size = n->params.cmb_size_mb * MiB; + uint64_t cap = ldq_le_p(&n->bar.cap); n->cmb.buf = g_malloc0(cmb_size); memory_region_init_io(&n->cmb.mem, OBJECT(n), &nvme_cmb_ops, n, @@ -5939,7 +6283,8 @@ static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev) PCI_BASE_ADDRESS_MEM_TYPE_64 | PCI_BASE_ADDRESS_MEM_PREFETCH, &n->cmb.mem); - NVME_CAP_SET_CMBS(n->bar.cap, 1); + NVME_CAP_SET_CMBS(cap, 1); + stq_le_p(&n->bar.cap, cap); if (n->params.legacy_cmb) { nvme_cmb_enable_regs(n); @@ -5949,14 +6294,17 @@ static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev) static void nvme_init_pmr(NvmeCtrl *n, PCIDevice *pci_dev) { - NVME_PMRCAP_SET_RDS(n->bar.pmrcap, 1); - NVME_PMRCAP_SET_WDS(n->bar.pmrcap, 1); - NVME_PMRCAP_SET_BIR(n->bar.pmrcap, NVME_PMR_BIR); - /* Turn on bit 1 support */ - NVME_PMRCAP_SET_PMRWBM(n->bar.pmrcap, 0x02); - NVME_PMRCAP_SET_CMSS(n->bar.pmrcap, 1); + uint32_t pmrcap = ldl_le_p(&n->bar.pmrcap); - pci_register_bar(pci_dev, NVME_PMRCAP_BIR(n->bar.pmrcap), + NVME_PMRCAP_SET_RDS(pmrcap, 1); + NVME_PMRCAP_SET_WDS(pmrcap, 1); + NVME_PMRCAP_SET_BIR(pmrcap, NVME_PMR_BIR); + /* Turn on bit 1 support */ + NVME_PMRCAP_SET_PMRWBM(pmrcap, 0x02); + NVME_PMRCAP_SET_CMSS(pmrcap, 1); + stl_le_p(&n->bar.pmrcap, pmrcap); + + pci_register_bar(pci_dev, NVME_PMR_BIR, PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 | PCI_BASE_ADDRESS_MEM_PREFETCH, &n->pmr.dev->mr); @@ -6046,6 +6394,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) { NvmeIdCtrl *id = &n->id_ctrl; uint8_t *pci_conf = pci_dev->config; + uint64_t cap = ldq_le_p(&n->bar.cap); id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID)); id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID)); @@ -6096,7 +6445,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) id->sqes = (0x6 << 4) | 0x6; id->cqes = (0x4 << 4) | 0x4; - id->nn = cpu_to_le32(n->num_namespaces); + id->nn = cpu_to_le32(NVME_MAX_NAMESPACES); id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROES | NVME_ONCS_TIMESTAMP | NVME_ONCS_FEATURES | NVME_ONCS_DSM | NVME_ONCS_COMPARE | NVME_ONCS_COPY); @@ -6124,17 +6473,18 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) id->cmic |= NVME_CMIC_MULTI_CTRL; } - NVME_CAP_SET_MQES(n->bar.cap, 0x7ff); - NVME_CAP_SET_CQR(n->bar.cap, 1); - NVME_CAP_SET_TO(n->bar.cap, 0xf); - NVME_CAP_SET_CSS(n->bar.cap, NVME_CAP_CSS_NVM); - NVME_CAP_SET_CSS(n->bar.cap, NVME_CAP_CSS_CSI_SUPP); - NVME_CAP_SET_CSS(n->bar.cap, NVME_CAP_CSS_ADMIN_ONLY); - NVME_CAP_SET_MPSMAX(n->bar.cap, 4); - NVME_CAP_SET_CMBS(n->bar.cap, n->params.cmb_size_mb ? 1 : 0); - NVME_CAP_SET_PMRS(n->bar.cap, n->pmr.dev ? 1 : 0); + NVME_CAP_SET_MQES(cap, 0x7ff); + NVME_CAP_SET_CQR(cap, 1); + NVME_CAP_SET_TO(cap, 0xf); + NVME_CAP_SET_CSS(cap, NVME_CAP_CSS_NVM); + NVME_CAP_SET_CSS(cap, NVME_CAP_CSS_CSI_SUPP); + NVME_CAP_SET_CSS(cap, NVME_CAP_CSS_ADMIN_ONLY); + NVME_CAP_SET_MPSMAX(cap, 4); + NVME_CAP_SET_CMBS(cap, n->params.cmb_size_mb ? 1 : 0); + NVME_CAP_SET_PMRS(cap, n->pmr.dev ? 1 : 0); + stq_le_p(&n->bar.cap, cap); - n->bar.vs = NVME_SPEC_VER; + stl_le_p(&n->bar.vs, NVME_SPEC_VER); n->bar.intmc = n->bar.intms = 0; } @@ -6161,7 +6511,7 @@ void nvme_attach_ns(NvmeCtrl *n, NvmeNamespace *ns) uint32_t nsid = ns->params.nsid; assert(nsid && nsid <= NVME_MAX_NAMESPACES); - n->namespaces[nsid - 1] = ns; + n->namespaces[nsid] = ns; ns->attached++; n->dmrsl = MIN_NON_ZERO(n->dmrsl, @@ -6199,7 +6549,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) ns = &n->namespace; ns->params.nsid = 1; - if (nvme_ns_setup(n, ns, errp)) { + if (nvme_ns_setup(ns, errp)) { return; } @@ -6215,13 +6565,15 @@ static void nvme_exit(PCIDevice *pci_dev) nvme_ctrl_reset(n); - for (i = 1; i <= n->num_namespaces; i++) { - ns = nvme_ns(n, i); - if (!ns) { - continue; + if (n->subsys) { + for (i = 1; i <= NVME_MAX_NAMESPACES; i++) { + ns = nvme_ns(n, i); + if (ns) { + ns->attached--; + } } - nvme_ns_cleanup(ns); + nvme_subsys_unregister_ctrl(n->subsys, n); } g_free(n->cq); @@ -6257,6 +6609,8 @@ static Property nvme_props[] = { DEFINE_PROP_BOOL("use-intel-id", NvmeCtrl, params.use_intel_id, false), DEFINE_PROP_BOOL("legacy-cmb", NvmeCtrl, params.legacy_cmb, false), DEFINE_PROP_UINT8("zoned.zasl", NvmeCtrl, params.zasl, 0), + DEFINE_PROP_BOOL("zoned.auto_transition", NvmeCtrl, + params.auto_transition_zones, true), DEFINE_PROP_END_OF_LIST(), }; @@ -6281,7 +6635,7 @@ static void nvme_set_smart_warning(Object *obj, Visitor *v, const char *name, cap = NVME_SMART_SPARE | NVME_SMART_TEMPERATURE | NVME_SMART_RELIABILITY | NVME_SMART_MEDIA_READ_ONLY | NVME_SMART_FAILED_VOLATILE_MEDIA; - if (NVME_CAP_PMRS(n->bar.cap)) { + if (NVME_CAP_PMRS(ldq_le_p(&n->bar.cap))) { cap |= NVME_SMART_PMR_UNRELIABLE; } diff --git a/hw/block/nvme-dif.c b/hw/nvme/dif.c similarity index 80% rename from hw/block/nvme-dif.c rename to hw/nvme/dif.c index 81b0a4cb13..5dbd18b2a4 100644 --- a/hw/block/nvme-dif.c +++ b/hw/nvme/dif.c @@ -9,19 +9,17 @@ */ #include "qemu/osdep.h" -#include "hw/block/block.h" -#include "sysemu/dma.h" -#include "sysemu/block-backend.h" #include "qapi/error.h" -#include "trace.h" -#include "nvme.h" -#include "nvme-dif.h" +#include "sysemu/block-backend.h" -uint16_t nvme_check_prinfo(NvmeNamespace *ns, uint16_t ctrl, uint64_t slba, +#include "nvme.h" +#include "trace.h" + +uint16_t nvme_check_prinfo(NvmeNamespace *ns, uint8_t prinfo, uint64_t slba, uint32_t reftag) { if ((NVME_ID_NS_DPS_TYPE(ns->id_ns.dps) == NVME_ID_NS_DPS_TYPE_1) && - (ctrl & NVME_RW_PRINFO_PRCHK_REF) && (slba & 0xffffffff) != reftag) { + (prinfo & NVME_PRINFO_PRCHK_REF) && (slba & 0xffffffff) != reftag) { return NVME_INVALID_PROT_INFO | NVME_DNR; } @@ -43,23 +41,21 @@ static uint16_t crc_t10dif(uint16_t crc, const unsigned char *buffer, void nvme_dif_pract_generate_dif(NvmeNamespace *ns, uint8_t *buf, size_t len, uint8_t *mbuf, size_t mlen, uint16_t apptag, - uint32_t reftag) + uint32_t *reftag) { uint8_t *end = buf + len; - size_t lsize = nvme_lsize(ns); - size_t msize = nvme_msize(ns); int16_t pil = 0; if (!(ns->id_ns.dps & NVME_ID_NS_DPS_FIRST_EIGHT)) { - pil = nvme_msize(ns) - sizeof(NvmeDifTuple); + pil = ns->lbaf.ms - sizeof(NvmeDifTuple); } - trace_pci_nvme_dif_pract_generate_dif(len, lsize, lsize + pil, apptag, - reftag); + trace_pci_nvme_dif_pract_generate_dif(len, ns->lbasz, ns->lbasz + pil, + apptag, *reftag); - for (; buf < end; buf += lsize, mbuf += msize) { + for (; buf < end; buf += ns->lbasz, mbuf += ns->lbaf.ms) { NvmeDifTuple *dif = (NvmeDifTuple *)(mbuf + pil); - uint16_t crc = crc_t10dif(0x0, buf, lsize); + uint16_t crc = crc_t10dif(0x0, buf, ns->lbasz); if (pil) { crc = crc_t10dif(crc, mbuf, pil); @@ -67,17 +63,17 @@ void nvme_dif_pract_generate_dif(NvmeNamespace *ns, uint8_t *buf, size_t len, dif->guard = cpu_to_be16(crc); dif->apptag = cpu_to_be16(apptag); - dif->reftag = cpu_to_be32(reftag); + dif->reftag = cpu_to_be32(*reftag); if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps) != NVME_ID_NS_DPS_TYPE_3) { - reftag++; + (*reftag)++; } } } static uint16_t nvme_dif_prchk(NvmeNamespace *ns, NvmeDifTuple *dif, uint8_t *buf, uint8_t *mbuf, size_t pil, - uint16_t ctrl, uint16_t apptag, + uint8_t prinfo, uint16_t apptag, uint16_t appmask, uint32_t reftag) { switch (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps)) { @@ -99,8 +95,8 @@ static uint16_t nvme_dif_prchk(NvmeNamespace *ns, NvmeDifTuple *dif, return NVME_SUCCESS; } - if (ctrl & NVME_RW_PRINFO_PRCHK_GUARD) { - uint16_t crc = crc_t10dif(0x0, buf, nvme_lsize(ns)); + if (prinfo & NVME_PRINFO_PRCHK_GUARD) { + uint16_t crc = crc_t10dif(0x0, buf, ns->lbasz); if (pil) { crc = crc_t10dif(crc, mbuf, pil); @@ -113,7 +109,7 @@ static uint16_t nvme_dif_prchk(NvmeNamespace *ns, NvmeDifTuple *dif, } } - if (ctrl & NVME_RW_PRINFO_PRCHK_APP) { + if (prinfo & NVME_PRINFO_PRCHK_APP) { trace_pci_nvme_dif_prchk_apptag(be16_to_cpu(dif->apptag), apptag, appmask); @@ -122,7 +118,7 @@ static uint16_t nvme_dif_prchk(NvmeNamespace *ns, NvmeDifTuple *dif, } } - if (ctrl & NVME_RW_PRINFO_PRCHK_REF) { + if (prinfo & NVME_PRINFO_PRCHK_REF) { trace_pci_nvme_dif_prchk_reftag(be32_to_cpu(dif->reftag), reftag); if (be32_to_cpu(dif->reftag) != reftag) { @@ -134,38 +130,36 @@ static uint16_t nvme_dif_prchk(NvmeNamespace *ns, NvmeDifTuple *dif, } uint16_t nvme_dif_check(NvmeNamespace *ns, uint8_t *buf, size_t len, - uint8_t *mbuf, size_t mlen, uint16_t ctrl, + uint8_t *mbuf, size_t mlen, uint8_t prinfo, uint64_t slba, uint16_t apptag, - uint16_t appmask, uint32_t reftag) + uint16_t appmask, uint32_t *reftag) { uint8_t *end = buf + len; - size_t lsize = nvme_lsize(ns); - size_t msize = nvme_msize(ns); int16_t pil = 0; uint16_t status; - status = nvme_check_prinfo(ns, ctrl, slba, reftag); + status = nvme_check_prinfo(ns, prinfo, slba, *reftag); if (status) { return status; } if (!(ns->id_ns.dps & NVME_ID_NS_DPS_FIRST_EIGHT)) { - pil = nvme_msize(ns) - sizeof(NvmeDifTuple); + pil = ns->lbaf.ms - sizeof(NvmeDifTuple); } - trace_pci_nvme_dif_check(NVME_RW_PRINFO(ctrl), lsize + pil); + trace_pci_nvme_dif_check(prinfo, ns->lbasz + pil); - for (; buf < end; buf += lsize, mbuf += msize) { + for (; buf < end; buf += ns->lbasz, mbuf += ns->lbaf.ms) { NvmeDifTuple *dif = (NvmeDifTuple *)(mbuf + pil); - status = nvme_dif_prchk(ns, dif, buf, mbuf, pil, ctrl, apptag, - appmask, reftag); + status = nvme_dif_prchk(ns, dif, buf, mbuf, pil, prinfo, apptag, + appmask, *reftag); if (status) { return status; } if (NVME_ID_NS_DPS_TYPE(ns->id_ns.dps) != NVME_ID_NS_DPS_TYPE_3) { - reftag++; + (*reftag)++; } } @@ -178,20 +172,18 @@ uint16_t nvme_dif_mangle_mdata(NvmeNamespace *ns, uint8_t *mbuf, size_t mlen, BlockBackend *blk = ns->blkconf.blk; BlockDriverState *bs = blk_bs(blk); - size_t msize = nvme_msize(ns); - size_t lsize = nvme_lsize(ns); int64_t moffset = 0, offset = nvme_l2b(ns, slba); uint8_t *mbufp, *end; bool zeroed; int16_t pil = 0; - int64_t bytes = (mlen / msize) * lsize; + int64_t bytes = (mlen / ns->lbaf.ms) << ns->lbaf.ds; int64_t pnum = 0; Error *err = NULL; if (!(ns->id_ns.dps & NVME_ID_NS_DPS_FIRST_EIGHT)) { - pil = nvme_msize(ns) - sizeof(NvmeDifTuple); + pil = ns->lbaf.ms - sizeof(NvmeDifTuple); } do { @@ -213,15 +205,15 @@ uint16_t nvme_dif_mangle_mdata(NvmeNamespace *ns, uint8_t *mbuf, size_t mlen, if (zeroed) { mbufp = mbuf + moffset; - mlen = (pnum / lsize) * msize; + mlen = (pnum >> ns->lbaf.ds) * ns->lbaf.ms; end = mbufp + mlen; - for (; mbufp < end; mbufp += msize) { + for (; mbufp < end; mbufp += ns->lbaf.ms) { memset(mbufp + pil, 0xff, sizeof(NvmeDifTuple)); } } - moffset += (pnum / lsize) * msize; + moffset += (pnum >> ns->lbaf.ds) * ns->lbaf.ms; offset += pnum; } while (pnum != bytes); @@ -256,14 +248,14 @@ static void nvme_dif_rw_check_cb(void *opaque, int ret) NvmeCtrl *n = nvme_ctrl(req); NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; uint64_t slba = le64_to_cpu(rw->slba); - uint16_t ctrl = le16_to_cpu(rw->control); + uint8_t prinfo = NVME_RW_PRINFO(le16_to_cpu(rw->control)); uint16_t apptag = le16_to_cpu(rw->apptag); uint16_t appmask = le16_to_cpu(rw->appmask); uint32_t reftag = le32_to_cpu(rw->reftag); uint16_t status; - trace_pci_nvme_dif_rw_check_cb(nvme_cid(req), NVME_RW_PRINFO(ctrl), apptag, - appmask, reftag); + trace_pci_nvme_dif_rw_check_cb(nvme_cid(req), prinfo, apptag, appmask, + reftag); if (ret) { goto out; @@ -277,8 +269,8 @@ static void nvme_dif_rw_check_cb(void *opaque, int ret) } status = nvme_dif_check(ns, ctx->data.bounce, ctx->data.iov.size, - ctx->mdata.bounce, ctx->mdata.iov.size, ctrl, - slba, apptag, appmask, reftag); + ctx->mdata.bounce, ctx->mdata.iov.size, prinfo, + slba, apptag, appmask, &reftag); if (status) { req->status = status; goto out; @@ -291,7 +283,7 @@ static void nvme_dif_rw_check_cb(void *opaque, int ret) goto out; } - if (ctrl & NVME_RW_PRINFO_PRACT && nvme_msize(ns) == 8) { + if (prinfo & NVME_PRINFO_PRACT && ns->lbaf.ms == 8) { goto out; } @@ -314,7 +306,7 @@ static void nvme_dif_rw_mdata_in_cb(void *opaque, int ret) uint64_t slba = le64_to_cpu(rw->slba); uint32_t nlb = le16_to_cpu(rw->nlb) + 1; size_t mlen = nvme_m2b(ns, nlb); - uint64_t offset = ns->mdata_offset + nvme_m2b(ns, slba); + uint64_t offset = nvme_moff(ns, slba); BlockBackend *blk = ns->blkconf.blk; trace_pci_nvme_dif_rw_mdata_in_cb(nvme_cid(req), blk_name(blk)); @@ -343,7 +335,7 @@ static void nvme_dif_rw_mdata_out_cb(void *opaque, int ret) NvmeNamespace *ns = req->ns; NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd; uint64_t slba = le64_to_cpu(rw->slba); - uint64_t offset = ns->mdata_offset + nvme_m2b(ns, slba); + uint64_t offset = nvme_moff(ns, slba); BlockBackend *blk = ns->blkconf.blk; trace_pci_nvme_dif_rw_mdata_out_cb(nvme_cid(req), blk_name(blk)); @@ -372,15 +364,15 @@ uint16_t nvme_dif_rw(NvmeCtrl *n, NvmeRequest *req) size_t mlen = nvme_m2b(ns, nlb); size_t mapped_len = len; int64_t offset = nvme_l2b(ns, slba); - uint16_t ctrl = le16_to_cpu(rw->control); + uint8_t prinfo = NVME_RW_PRINFO(le16_to_cpu(rw->control)); uint16_t apptag = le16_to_cpu(rw->apptag); uint16_t appmask = le16_to_cpu(rw->appmask); uint32_t reftag = le32_to_cpu(rw->reftag); - bool pract = !!(ctrl & NVME_RW_PRINFO_PRACT); + bool pract = !!(prinfo & NVME_PRINFO_PRACT); NvmeBounceContext *ctx; uint16_t status; - trace_pci_nvme_dif_rw(pract, NVME_RW_PRINFO(ctrl)); + trace_pci_nvme_dif_rw(pract, prinfo); ctx = g_new0(NvmeBounceContext, 1); ctx->req = req; @@ -388,17 +380,16 @@ uint16_t nvme_dif_rw(NvmeCtrl *n, NvmeRequest *req) if (wrz) { BdrvRequestFlags flags = BDRV_REQ_MAY_UNMAP; - if (ctrl & NVME_RW_PRINFO_PRCHK_MASK) { + if (prinfo & NVME_PRINFO_PRCHK_MASK) { status = NVME_INVALID_PROT_INFO | NVME_DNR; goto err; } if (pract) { uint8_t *mbuf, *end; - size_t msize = nvme_msize(ns); - int16_t pil = msize - sizeof(NvmeDifTuple); + int16_t pil = ns->lbaf.ms - sizeof(NvmeDifTuple); - status = nvme_check_prinfo(ns, ctrl, slba, reftag); + status = nvme_check_prinfo(ns, prinfo, slba, reftag); if (status) { goto err; } @@ -417,7 +408,7 @@ uint16_t nvme_dif_rw(NvmeCtrl *n, NvmeRequest *req) pil = 0; } - for (; mbuf < end; mbuf += msize) { + for (; mbuf < end; mbuf += ns->lbaf.ms) { NvmeDifTuple *dif = (NvmeDifTuple *)(mbuf + pil); dif->apptag = cpu_to_be16(apptag); @@ -436,7 +427,7 @@ uint16_t nvme_dif_rw(NvmeCtrl *n, NvmeRequest *req) return NVME_NO_COMPLETE; } - if (nvme_ns_ext(ns) && !(pract && nvme_msize(ns) == 8)) { + if (nvme_ns_ext(ns) && !(pract && ns->lbaf.ms == 8)) { mapped_len += mlen; } @@ -470,7 +461,7 @@ uint16_t nvme_dif_rw(NvmeCtrl *n, NvmeRequest *req) qemu_iovec_init(&ctx->mdata.iov, 1); qemu_iovec_add(&ctx->mdata.iov, ctx->mdata.bounce, mlen); - if (!(pract && nvme_msize(ns) == 8)) { + if (!(pract && ns->lbaf.ms == 8)) { status = nvme_bounce_mdata(n, ctx->mdata.bounce, ctx->mdata.iov.size, NVME_TX_DIRECTION_TO_DEVICE, req); if (status) { @@ -478,7 +469,7 @@ uint16_t nvme_dif_rw(NvmeCtrl *n, NvmeRequest *req) } } - status = nvme_check_prinfo(ns, ctrl, slba, reftag); + status = nvme_check_prinfo(ns, prinfo, slba, reftag); if (status) { goto err; } @@ -487,11 +478,11 @@ uint16_t nvme_dif_rw(NvmeCtrl *n, NvmeRequest *req) /* splice generated protection information into the buffer */ nvme_dif_pract_generate_dif(ns, ctx->data.bounce, ctx->data.iov.size, ctx->mdata.bounce, ctx->mdata.iov.size, - apptag, reftag); + apptag, &reftag); } else { status = nvme_dif_check(ns, ctx->data.bounce, ctx->data.iov.size, - ctx->mdata.bounce, ctx->mdata.iov.size, ctrl, - slba, apptag, appmask, reftag); + ctx->mdata.bounce, ctx->mdata.iov.size, prinfo, + slba, apptag, appmask, &reftag); if (status) { goto err; } diff --git a/hw/nvme/meson.build b/hw/nvme/meson.build new file mode 100644 index 0000000000..3cf40046ee --- /dev/null +++ b/hw/nvme/meson.build @@ -0,0 +1 @@ +softmmu_ss.add(when: 'CONFIG_NVME_PCI', if_true: files('ctrl.c', 'dif.c', 'ns.c', 'subsys.c')) diff --git a/hw/block/nvme-ns.c b/hw/nvme/ns.c similarity index 79% rename from hw/block/nvme-ns.c rename to hw/nvme/ns.c index 7bb618f182..b7cf1494e7 100644 --- a/hw/block/nvme-ns.c +++ b/hw/nvme/ns.c @@ -14,23 +14,16 @@ #include "qemu/osdep.h" #include "qemu/units.h" -#include "qemu/cutils.h" -#include "qemu/log.h" #include "qemu/error-report.h" -#include "hw/block/block.h" -#include "hw/pci/pci.h" +#include "qapi/error.h" #include "sysemu/sysemu.h" #include "sysemu/block-backend.h" -#include "qapi/error.h" -#include "hw/qdev-properties.h" -#include "hw/qdev-core.h" - -#include "trace.h" #include "nvme.h" -#include "nvme-ns.h" +#include "trace.h" #define MIN_DISCARD_GRANULARITY (4 * KiB) +#define NVME_DEFAULT_ZONE_SIZE (128 * MiB) void nvme_ns_init_format(NvmeNamespace *ns) { @@ -38,7 +31,10 @@ void nvme_ns_init_format(NvmeNamespace *ns) BlockDriverInfo bdi; int npdg, nlbas, ret; - nlbas = nvme_ns_nlbas(ns); + ns->lbaf = id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(id_ns->flbas)]; + ns->lbasz = 1 << ns->lbaf.ds; + + nlbas = ns->size / (ns->lbasz + ns->lbaf.ms); id_ns->nsze = cpu_to_le64(nlbas); @@ -46,13 +42,13 @@ void nvme_ns_init_format(NvmeNamespace *ns) id_ns->ncap = id_ns->nsze; id_ns->nuse = id_ns->ncap; - ns->mdata_offset = nvme_l2b(ns, nlbas); + ns->moff = (int64_t)nlbas << ns->lbaf.ds; - npdg = ns->blkconf.discard_granularity / nvme_lsize(ns); + npdg = ns->blkconf.discard_granularity / ns->lbasz; ret = bdrv_get_info(blk_bs(ns->blkconf.blk), &bdi); if (ret >= 0 && bdi.cluster_size > ns->blkconf.discard_granularity) { - npdg = bdi.cluster_size / nvme_lsize(ns); + npdg = bdi.cluster_size / ns->lbasz; } id_ns->npda = id_ns->npdg = npdg - 1; @@ -60,6 +56,7 @@ void nvme_ns_init_format(NvmeNamespace *ns) static int nvme_ns_init(NvmeNamespace *ns, Error **errp) { + static uint64_t ns_count; NvmeIdNs *id_ns = &ns->id_ns; uint8_t ds; uint16_t ms; @@ -77,47 +74,47 @@ static int nvme_ns_init(NvmeNamespace *ns, Error **errp) id_ns->nmic |= NVME_NMIC_NS_SHARED; } + /* Substitute a missing EUI-64 by an autogenerated one */ + ++ns_count; + if (!ns->params.eui64 && ns->params.eui64_default) { + ns->params.eui64 = ns_count + NVME_EUI64_DEFAULT; + } + /* simple copy */ id_ns->mssrl = cpu_to_le16(ns->params.mssrl); id_ns->mcl = cpu_to_le32(ns->params.mcl); id_ns->msrc = ns->params.msrc; + id_ns->eui64 = cpu_to_be64(ns->params.eui64); ds = 31 - clz32(ns->blkconf.logical_block_size); ms = ns->params.ms; - if (ns->params.ms) { - id_ns->mc = 0x3; + id_ns->mc = NVME_ID_NS_MC_EXTENDED | NVME_ID_NS_MC_SEPARATE; - if (ns->params.mset) { - id_ns->flbas |= 0x10; - } - - id_ns->dpc = 0x1f; - id_ns->dps = ((ns->params.pil & 0x1) << 3) | ns->params.pi; - - NvmeLBAF lbaf[16] = { - [0] = { .ds = 9 }, - [1] = { .ds = 9, .ms = 8 }, - [2] = { .ds = 9, .ms = 16 }, - [3] = { .ds = 9, .ms = 64 }, - [4] = { .ds = 12 }, - [5] = { .ds = 12, .ms = 8 }, - [6] = { .ds = 12, .ms = 16 }, - [7] = { .ds = 12, .ms = 64 }, - }; - - memcpy(&id_ns->lbaf, &lbaf, sizeof(lbaf)); - id_ns->nlbaf = 7; - } else { - NvmeLBAF lbaf[16] = { - [0] = { .ds = 9 }, - [1] = { .ds = 12 }, - }; - - memcpy(&id_ns->lbaf, &lbaf, sizeof(lbaf)); - id_ns->nlbaf = 1; + if (ms && ns->params.mset) { + id_ns->flbas |= NVME_ID_NS_FLBAS_EXTENDED; } + id_ns->dpc = 0x1f; + id_ns->dps = ns->params.pi; + if (ns->params.pi && ns->params.pil) { + id_ns->dps |= NVME_ID_NS_DPS_FIRST_EIGHT; + } + + static const NvmeLBAF lbaf[16] = { + [0] = { .ds = 9 }, + [1] = { .ds = 9, .ms = 8 }, + [2] = { .ds = 9, .ms = 16 }, + [3] = { .ds = 9, .ms = 64 }, + [4] = { .ds = 12 }, + [5] = { .ds = 12, .ms = 8 }, + [6] = { .ds = 12, .ms = 16 }, + [7] = { .ds = 12, .ms = 64 }, + }; + + memcpy(&id_ns->lbaf, &lbaf, sizeof(lbaf)); + id_ns->nlbaf = 7; + for (i = 0; i <= id_ns->nlbaf; i++) { NvmeLBAF *lbaf = &id_ns->lbaf[i]; if (lbaf->ds == ds) { @@ -170,7 +167,6 @@ static int nvme_ns_init_blk(NvmeNamespace *ns, Error **errp) static int nvme_ns_zoned_check_calc_geometry(NvmeNamespace *ns, Error **errp) { uint64_t zone_size, zone_cap; - uint32_t lbasz = nvme_lsize(ns); /* Make sure that the values of ZNS properties are sane */ if (ns->params.zone_size_bs) { @@ -188,14 +184,14 @@ static int nvme_ns_zoned_check_calc_geometry(NvmeNamespace *ns, Error **errp) "zone size %"PRIu64"B", zone_cap, zone_size); return -1; } - if (zone_size < lbasz) { + if (zone_size < ns->lbasz) { error_setg(errp, "zone size %"PRIu64"B too small, " - "must be at least %"PRIu32"B", zone_size, lbasz); + "must be at least %zuB", zone_size, ns->lbasz); return -1; } - if (zone_cap < lbasz) { + if (zone_cap < ns->lbasz) { error_setg(errp, "zone capacity %"PRIu64"B too small, " - "must be at least %"PRIu32"B", zone_cap, lbasz); + "must be at least %zuB", zone_cap, ns->lbasz); return -1; } @@ -203,9 +199,9 @@ static int nvme_ns_zoned_check_calc_geometry(NvmeNamespace *ns, Error **errp) * Save the main zone geometry values to avoid * calculating them later again. */ - ns->zone_size = zone_size / lbasz; - ns->zone_capacity = zone_cap / lbasz; - ns->num_zones = nvme_ns_nlbas(ns) / ns->zone_size; + ns->zone_size = zone_size / ns->lbasz; + ns->zone_capacity = zone_cap / ns->lbasz; + ns->num_zones = le64_to_cpu(ns->id_ns.nsze) / ns->zone_size; /* Do a few more sanity checks of ZNS properties */ if (!ns->num_zones) { @@ -215,43 +211,6 @@ static int nvme_ns_zoned_check_calc_geometry(NvmeNamespace *ns, Error **errp) return -1; } - if (ns->params.max_open_zones > ns->num_zones) { - error_setg(errp, - "max_open_zones value %u exceeds the number of zones %u", - ns->params.max_open_zones, ns->num_zones); - return -1; - } - if (ns->params.max_active_zones > ns->num_zones) { - error_setg(errp, - "max_active_zones value %u exceeds the number of zones %u", - ns->params.max_active_zones, ns->num_zones); - return -1; - } - - if (ns->params.max_active_zones) { - if (ns->params.max_open_zones > ns->params.max_active_zones) { - error_setg(errp, "max_open_zones (%u) exceeds max_active_zones (%u)", - ns->params.max_open_zones, ns->params.max_active_zones); - return -1; - } - - if (!ns->params.max_open_zones) { - ns->params.max_open_zones = ns->params.max_active_zones; - } - } - - if (ns->params.zd_extension_size) { - if (ns->params.zd_extension_size & 0x3f) { - error_setg(errp, - "zone descriptor extension size must be a multiple of 64B"); - return -1; - } - if ((ns->params.zd_extension_size >> 6) > 0xff) { - error_setg(errp, "zone descriptor extension size is too large"); - return -1; - } - } - return 0; } @@ -303,7 +262,7 @@ static void nvme_ns_init_zoned(NvmeNamespace *ns) id_ns_z = g_malloc0(sizeof(NvmeIdNsZoned)); - /* MAR/MOR are zeroes-based, 0xffffffff means no limit */ + /* MAR/MOR are zeroes-based, FFFFFFFFFh means no limit */ id_ns_z->mar = cpu_to_le32(ns->params.max_active_zones - 1); id_ns_z->mor = cpu_to_le32(ns->params.max_open_zones - 1); id_ns_z->zoc = 0; @@ -387,8 +346,7 @@ static void nvme_zoned_ns_shutdown(NvmeNamespace *ns) assert(ns->nr_open_zones == 0); } -static int nvme_ns_check_constraints(NvmeCtrl *n, NvmeNamespace *ns, - Error **errp) +static int nvme_ns_check_constraints(NvmeNamespace *ns, Error **errp) { if (!ns->blkconf.blk) { error_setg(errp, "block backend not configured"); @@ -407,26 +365,40 @@ static int nvme_ns_check_constraints(NvmeCtrl *n, NvmeNamespace *ns, return -1; } - if (!n->subsys) { - if (ns->params.detached) { - error_setg(errp, "detached requires that the nvme device is " - "linked to an nvme-subsys device"); - return -1; + if (ns->params.zoned) { + if (ns->params.max_active_zones) { + if (ns->params.max_open_zones > ns->params.max_active_zones) { + error_setg(errp, "max_open_zones (%u) exceeds " + "max_active_zones (%u)", ns->params.max_open_zones, + ns->params.max_active_zones); + return -1; + } + + if (!ns->params.max_open_zones) { + ns->params.max_open_zones = ns->params.max_active_zones; + } } - if (ns->params.shared) { - error_setg(errp, "shared requires that the nvme device is " - "linked to an nvme-subsys device"); - return -1; + if (ns->params.zd_extension_size) { + if (ns->params.zd_extension_size & 0x3f) { + error_setg(errp, "zone descriptor extension size must be a " + "multiple of 64B"); + return -1; + } + if ((ns->params.zd_extension_size >> 6) > 0xff) { + error_setg(errp, + "zone descriptor extension size is too large"); + return -1; + } } } return 0; } -int nvme_ns_setup(NvmeCtrl *n, NvmeNamespace *ns, Error **errp) +int nvme_ns_setup(NvmeNamespace *ns, Error **errp) { - if (nvme_ns_check_constraints(n, ns, errp)) { + if (nvme_ns_check_constraints(ns, errp)) { return -1; } @@ -469,6 +441,15 @@ void nvme_ns_cleanup(NvmeNamespace *ns) } } +static void nvme_ns_unrealize(DeviceState *dev) +{ + NvmeNamespace *ns = NVME_NS(dev); + + nvme_ns_drain(ns); + nvme_ns_shutdown(ns); + nvme_ns_cleanup(ns); +} + static void nvme_ns_realize(DeviceState *dev, Error **errp) { NvmeNamespace *ns = NVME_NS(dev); @@ -478,7 +459,29 @@ static void nvme_ns_realize(DeviceState *dev, Error **errp) uint32_t nsid = ns->params.nsid; int i; - if (nvme_ns_setup(n, ns, errp)) { + if (!n->subsys) { + if (ns->params.detached) { + error_setg(errp, "detached requires that the nvme device is " + "linked to an nvme-subsys device"); + return; + } + + if (ns->params.shared) { + error_setg(errp, "shared requires that the nvme device is " + "linked to an nvme-subsys device"); + return; + } + } else { + /* + * If this namespace belongs to a subsystem (through a link on the + * controller device), reparent the device. + */ + if (!qdev_set_parent_bus(dev, &subsys->bus.parent_bus, errp)) { + return; + } + } + + if (nvme_ns_setup(ns, errp)) { return; } @@ -532,6 +535,7 @@ static Property nvme_ns_props[] = { DEFINE_PROP_BOOL("shared", NvmeNamespace, params.shared, false), DEFINE_PROP_UINT32("nsid", NvmeNamespace, params.nsid, 0), DEFINE_PROP_UUID("uuid", NvmeNamespace, params.uuid), + DEFINE_PROP_UINT64("eui64", NvmeNamespace, params.eui64, 0), DEFINE_PROP_UINT16("ms", NvmeNamespace, params.ms, 0), DEFINE_PROP_UINT8("mset", NvmeNamespace, params.mset, 0), DEFINE_PROP_UINT8("pi", NvmeNamespace, params.pi, 0), @@ -552,6 +556,8 @@ static Property nvme_ns_props[] = { params.max_open_zones, 0), DEFINE_PROP_UINT32("zoned.descr_ext_size", NvmeNamespace, params.zd_extension_size, 0), + DEFINE_PROP_BOOL("eui64-default", NvmeNamespace, params.eui64_default, + true), DEFINE_PROP_END_OF_LIST(), }; @@ -563,6 +569,7 @@ static void nvme_ns_class_init(ObjectClass *oc, void *data) dc->bus_type = TYPE_NVME_BUS; dc->realize = nvme_ns_realize; + dc->unrealize = nvme_ns_unrealize; device_class_set_props(dc, nvme_ns_props); dc->desc = "Virtual NVMe namespace"; } diff --git a/hw/nvme/nvme.h b/hw/nvme/nvme.h new file mode 100644 index 0000000000..83ffabade4 --- /dev/null +++ b/hw/nvme/nvme.h @@ -0,0 +1,556 @@ +/* + * QEMU NVM Express + * + * Copyright (c) 2012 Intel Corporation + * Copyright (c) 2021 Minwoo Im + * Copyright (c) 2021 Samsung Electronics Co., Ltd. + * + * Authors: + * Keith Busch + * Klaus Jensen + * Gollu Appalanaidu + * Dmitry Fomichev + * Minwoo Im + * + * This code is licensed under the GNU GPL v2 or later. + */ + +#ifndef HW_NVME_INTERNAL_H +#define HW_NVME_INTERNAL_H + +#include "qemu/uuid.h" +#include "hw/pci/pci.h" +#include "hw/block/block.h" + +#include "block/nvme.h" + +#define NVME_MAX_CONTROLLERS 32 +#define NVME_MAX_NAMESPACES 256 +#define NVME_EUI64_DEFAULT ((uint64_t)0x5254000000000000) + +QEMU_BUILD_BUG_ON(NVME_MAX_NAMESPACES > NVME_NSID_BROADCAST - 1); + +typedef struct NvmeCtrl NvmeCtrl; +typedef struct NvmeNamespace NvmeNamespace; + +#define TYPE_NVME_BUS "nvme-bus" +OBJECT_DECLARE_SIMPLE_TYPE(NvmeBus, NVME_BUS) + +typedef struct NvmeBus { + BusState parent_bus; +} NvmeBus; + +#define TYPE_NVME_SUBSYS "nvme-subsys" +#define NVME_SUBSYS(obj) \ + OBJECT_CHECK(NvmeSubsystem, (obj), TYPE_NVME_SUBSYS) + +typedef struct NvmeSubsystem { + DeviceState parent_obj; + NvmeBus bus; + uint8_t subnqn[256]; + + NvmeCtrl *ctrls[NVME_MAX_CONTROLLERS]; + NvmeNamespace *namespaces[NVME_MAX_NAMESPACES + 1]; + + struct { + char *nqn; + } params; +} NvmeSubsystem; + +int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp); +void nvme_subsys_unregister_ctrl(NvmeSubsystem *subsys, NvmeCtrl *n); + +static inline NvmeCtrl *nvme_subsys_ctrl(NvmeSubsystem *subsys, + uint32_t cntlid) +{ + if (!subsys || cntlid >= NVME_MAX_CONTROLLERS) { + return NULL; + } + + return subsys->ctrls[cntlid]; +} + +static inline NvmeNamespace *nvme_subsys_ns(NvmeSubsystem *subsys, + uint32_t nsid) +{ + if (!subsys || !nsid || nsid > NVME_MAX_NAMESPACES) { + return NULL; + } + + return subsys->namespaces[nsid]; +} + +#define TYPE_NVME_NS "nvme-ns" +#define NVME_NS(obj) \ + OBJECT_CHECK(NvmeNamespace, (obj), TYPE_NVME_NS) + +typedef struct NvmeZone { + NvmeZoneDescr d; + uint64_t w_ptr; + QTAILQ_ENTRY(NvmeZone) entry; +} NvmeZone; + +typedef struct NvmeNamespaceParams { + bool detached; + bool shared; + uint32_t nsid; + QemuUUID uuid; + uint64_t eui64; + bool eui64_default; + + uint16_t ms; + uint8_t mset; + uint8_t pi; + uint8_t pil; + + uint16_t mssrl; + uint32_t mcl; + uint8_t msrc; + + bool zoned; + bool cross_zone_read; + uint64_t zone_size_bs; + uint64_t zone_cap_bs; + uint32_t max_active_zones; + uint32_t max_open_zones; + uint32_t zd_extension_size; +} NvmeNamespaceParams; + +typedef struct NvmeNamespace { + DeviceState parent_obj; + BlockConf blkconf; + int32_t bootindex; + int64_t size; + int64_t moff; + NvmeIdNs id_ns; + NvmeLBAF lbaf; + size_t lbasz; + const uint32_t *iocs; + uint8_t csi; + uint16_t status; + int attached; + + QTAILQ_ENTRY(NvmeNamespace) entry; + + NvmeIdNsZoned *id_ns_zoned; + NvmeZone *zone_array; + QTAILQ_HEAD(, NvmeZone) exp_open_zones; + QTAILQ_HEAD(, NvmeZone) imp_open_zones; + QTAILQ_HEAD(, NvmeZone) closed_zones; + QTAILQ_HEAD(, NvmeZone) full_zones; + uint32_t num_zones; + uint64_t zone_size; + uint64_t zone_capacity; + uint32_t zone_size_log2; + uint8_t *zd_extensions; + int32_t nr_open_zones; + int32_t nr_active_zones; + + NvmeNamespaceParams params; + + struct { + uint32_t err_rec; + } features; +} NvmeNamespace; + +static inline uint32_t nvme_nsid(NvmeNamespace *ns) +{ + if (ns) { + return ns->params.nsid; + } + + return 0; +} + +static inline size_t nvme_l2b(NvmeNamespace *ns, uint64_t lba) +{ + return lba << ns->lbaf.ds; +} + +static inline size_t nvme_m2b(NvmeNamespace *ns, uint64_t lba) +{ + return ns->lbaf.ms * lba; +} + +static inline int64_t nvme_moff(NvmeNamespace *ns, uint64_t lba) +{ + return ns->moff + nvme_m2b(ns, lba); +} + +static inline bool nvme_ns_ext(NvmeNamespace *ns) +{ + return !!NVME_ID_NS_FLBAS_EXTENDED(ns->id_ns.flbas); +} + +static inline NvmeZoneState nvme_get_zone_state(NvmeZone *zone) +{ + return zone->d.zs >> 4; +} + +static inline void nvme_set_zone_state(NvmeZone *zone, NvmeZoneState state) +{ + zone->d.zs = state << 4; +} + +static inline uint64_t nvme_zone_rd_boundary(NvmeNamespace *ns, NvmeZone *zone) +{ + return zone->d.zslba + ns->zone_size; +} + +static inline uint64_t nvme_zone_wr_boundary(NvmeZone *zone) +{ + return zone->d.zslba + zone->d.zcap; +} + +static inline bool nvme_wp_is_valid(NvmeZone *zone) +{ + uint8_t st = nvme_get_zone_state(zone); + + return st != NVME_ZONE_STATE_FULL && + st != NVME_ZONE_STATE_READ_ONLY && + st != NVME_ZONE_STATE_OFFLINE; +} + +static inline uint8_t *nvme_get_zd_extension(NvmeNamespace *ns, + uint32_t zone_idx) +{ + return &ns->zd_extensions[zone_idx * ns->params.zd_extension_size]; +} + +static inline void nvme_aor_inc_open(NvmeNamespace *ns) +{ + assert(ns->nr_open_zones >= 0); + if (ns->params.max_open_zones) { + ns->nr_open_zones++; + assert(ns->nr_open_zones <= ns->params.max_open_zones); + } +} + +static inline void nvme_aor_dec_open(NvmeNamespace *ns) +{ + if (ns->params.max_open_zones) { + assert(ns->nr_open_zones > 0); + ns->nr_open_zones--; + } + assert(ns->nr_open_zones >= 0); +} + +static inline void nvme_aor_inc_active(NvmeNamespace *ns) +{ + assert(ns->nr_active_zones >= 0); + if (ns->params.max_active_zones) { + ns->nr_active_zones++; + assert(ns->nr_active_zones <= ns->params.max_active_zones); + } +} + +static inline void nvme_aor_dec_active(NvmeNamespace *ns) +{ + if (ns->params.max_active_zones) { + assert(ns->nr_active_zones > 0); + ns->nr_active_zones--; + assert(ns->nr_active_zones >= ns->nr_open_zones); + } + assert(ns->nr_active_zones >= 0); +} + +void nvme_ns_init_format(NvmeNamespace *ns); +int nvme_ns_setup(NvmeNamespace *ns, Error **errp); +void nvme_ns_drain(NvmeNamespace *ns); +void nvme_ns_shutdown(NvmeNamespace *ns); +void nvme_ns_cleanup(NvmeNamespace *ns); + +typedef struct NvmeAsyncEvent { + QTAILQ_ENTRY(NvmeAsyncEvent) entry; + NvmeAerResult result; +} NvmeAsyncEvent; + +enum { + NVME_SG_ALLOC = 1 << 0, + NVME_SG_DMA = 1 << 1, +}; + +typedef struct NvmeSg { + int flags; + + union { + QEMUSGList qsg; + QEMUIOVector iov; + }; +} NvmeSg; + +typedef enum NvmeTxDirection { + NVME_TX_DIRECTION_TO_DEVICE = 0, + NVME_TX_DIRECTION_FROM_DEVICE = 1, +} NvmeTxDirection; + +typedef struct NvmeRequest { + struct NvmeSQueue *sq; + struct NvmeNamespace *ns; + BlockAIOCB *aiocb; + uint16_t status; + void *opaque; + NvmeCqe cqe; + NvmeCmd cmd; + BlockAcctCookie acct; + NvmeSg sg; + QTAILQ_ENTRY(NvmeRequest)entry; +} NvmeRequest; + +typedef struct NvmeBounceContext { + NvmeRequest *req; + + struct { + QEMUIOVector iov; + uint8_t *bounce; + } data, mdata; +} NvmeBounceContext; + +static inline const char *nvme_adm_opc_str(uint8_t opc) +{ + switch (opc) { + case NVME_ADM_CMD_DELETE_SQ: return "NVME_ADM_CMD_DELETE_SQ"; + case NVME_ADM_CMD_CREATE_SQ: return "NVME_ADM_CMD_CREATE_SQ"; + case NVME_ADM_CMD_GET_LOG_PAGE: return "NVME_ADM_CMD_GET_LOG_PAGE"; + case NVME_ADM_CMD_DELETE_CQ: return "NVME_ADM_CMD_DELETE_CQ"; + case NVME_ADM_CMD_CREATE_CQ: return "NVME_ADM_CMD_CREATE_CQ"; + case NVME_ADM_CMD_IDENTIFY: return "NVME_ADM_CMD_IDENTIFY"; + case NVME_ADM_CMD_ABORT: return "NVME_ADM_CMD_ABORT"; + case NVME_ADM_CMD_SET_FEATURES: return "NVME_ADM_CMD_SET_FEATURES"; + case NVME_ADM_CMD_GET_FEATURES: return "NVME_ADM_CMD_GET_FEATURES"; + case NVME_ADM_CMD_ASYNC_EV_REQ: return "NVME_ADM_CMD_ASYNC_EV_REQ"; + case NVME_ADM_CMD_NS_ATTACHMENT: return "NVME_ADM_CMD_NS_ATTACHMENT"; + case NVME_ADM_CMD_FORMAT_NVM: return "NVME_ADM_CMD_FORMAT_NVM"; + default: return "NVME_ADM_CMD_UNKNOWN"; + } +} + +static inline const char *nvme_io_opc_str(uint8_t opc) +{ + switch (opc) { + case NVME_CMD_FLUSH: return "NVME_NVM_CMD_FLUSH"; + case NVME_CMD_WRITE: return "NVME_NVM_CMD_WRITE"; + case NVME_CMD_READ: return "NVME_NVM_CMD_READ"; + case NVME_CMD_COMPARE: return "NVME_NVM_CMD_COMPARE"; + case NVME_CMD_WRITE_ZEROES: return "NVME_NVM_CMD_WRITE_ZEROES"; + case NVME_CMD_DSM: return "NVME_NVM_CMD_DSM"; + case NVME_CMD_VERIFY: return "NVME_NVM_CMD_VERIFY"; + case NVME_CMD_COPY: return "NVME_NVM_CMD_COPY"; + case NVME_CMD_ZONE_MGMT_SEND: return "NVME_ZONED_CMD_MGMT_SEND"; + case NVME_CMD_ZONE_MGMT_RECV: return "NVME_ZONED_CMD_MGMT_RECV"; + case NVME_CMD_ZONE_APPEND: return "NVME_ZONED_CMD_ZONE_APPEND"; + default: return "NVME_NVM_CMD_UNKNOWN"; + } +} + +typedef struct NvmeSQueue { + struct NvmeCtrl *ctrl; + uint16_t sqid; + uint16_t cqid; + uint32_t head; + uint32_t tail; + uint32_t size; + uint64_t dma_addr; + QEMUTimer *timer; + NvmeRequest *io_req; + QTAILQ_HEAD(, NvmeRequest) req_list; + QTAILQ_HEAD(, NvmeRequest) out_req_list; + QTAILQ_ENTRY(NvmeSQueue) entry; +} NvmeSQueue; + +typedef struct NvmeCQueue { + struct NvmeCtrl *ctrl; + uint8_t phase; + uint16_t cqid; + uint16_t irq_enabled; + uint32_t head; + uint32_t tail; + uint32_t vector; + uint32_t size; + uint64_t dma_addr; + QEMUTimer *timer; + QTAILQ_HEAD(, NvmeSQueue) sq_list; + QTAILQ_HEAD(, NvmeRequest) req_list; +} NvmeCQueue; + +#define TYPE_NVME "nvme" +#define NVME(obj) \ + OBJECT_CHECK(NvmeCtrl, (obj), TYPE_NVME) + +typedef struct NvmeParams { + char *serial; + uint32_t num_queues; /* deprecated since 5.1 */ + uint32_t max_ioqpairs; + uint16_t msix_qsize; + uint32_t cmb_size_mb; + uint8_t aerl; + uint32_t aer_max_queued; + uint8_t mdts; + uint8_t vsl; + bool use_intel_id; + uint8_t zasl; + bool auto_transition_zones; + bool legacy_cmb; +} NvmeParams; + +typedef struct NvmeCtrl { + PCIDevice parent_obj; + MemoryRegion bar0; + MemoryRegion iomem; + NvmeBar bar; + NvmeParams params; + NvmeBus bus; + + uint16_t cntlid; + bool qs_created; + uint32_t page_size; + uint16_t page_bits; + uint16_t max_prp_ents; + uint16_t cqe_size; + uint16_t sqe_size; + uint32_t reg_size; + uint32_t max_q_ents; + uint8_t outstanding_aers; + uint32_t irq_status; + int cq_pending; + uint64_t host_timestamp; /* Timestamp sent by the host */ + uint64_t timestamp_set_qemu_clock_ms; /* QEMU clock time */ + uint64_t starttime_ms; + uint16_t temperature; + uint8_t smart_critical_warning; + + struct { + MemoryRegion mem; + uint8_t *buf; + bool cmse; + hwaddr cba; + } cmb; + + struct { + HostMemoryBackend *dev; + bool cmse; + hwaddr cba; + } pmr; + + uint8_t aer_mask; + NvmeRequest **aer_reqs; + QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue; + int aer_queued; + + uint32_t dmrsl; + + /* Namespace ID is started with 1 so bitmap should be 1-based */ +#define NVME_CHANGED_NSID_SIZE (NVME_MAX_NAMESPACES + 1) + DECLARE_BITMAP(changed_nsids, NVME_CHANGED_NSID_SIZE); + + NvmeSubsystem *subsys; + + NvmeNamespace namespace; + NvmeNamespace *namespaces[NVME_MAX_NAMESPACES + 1]; + NvmeSQueue **sq; + NvmeCQueue **cq; + NvmeSQueue admin_sq; + NvmeCQueue admin_cq; + NvmeIdCtrl id_ctrl; + + struct { + struct { + uint16_t temp_thresh_hi; + uint16_t temp_thresh_low; + }; + uint32_t async_config; + } features; +} NvmeCtrl; + +static inline NvmeNamespace *nvme_ns(NvmeCtrl *n, uint32_t nsid) +{ + if (!nsid || nsid > NVME_MAX_NAMESPACES) { + return NULL; + } + + return n->namespaces[nsid]; +} + +static inline NvmeCQueue *nvme_cq(NvmeRequest *req) +{ + NvmeSQueue *sq = req->sq; + NvmeCtrl *n = sq->ctrl; + + return n->cq[sq->cqid]; +} + +static inline NvmeCtrl *nvme_ctrl(NvmeRequest *req) +{ + NvmeSQueue *sq = req->sq; + return sq->ctrl; +} + +static inline uint16_t nvme_cid(NvmeRequest *req) +{ + if (!req) { + return 0xffff; + } + + return le16_to_cpu(req->cqe.cid); +} + +void nvme_attach_ns(NvmeCtrl *n, NvmeNamespace *ns); +uint16_t nvme_bounce_data(NvmeCtrl *n, uint8_t *ptr, uint32_t len, + NvmeTxDirection dir, NvmeRequest *req); +uint16_t nvme_bounce_mdata(NvmeCtrl *n, uint8_t *ptr, uint32_t len, + NvmeTxDirection dir, NvmeRequest *req); +void nvme_rw_complete_cb(void *opaque, int ret); +uint16_t nvme_map_dptr(NvmeCtrl *n, NvmeSg *sg, size_t len, + NvmeCmd *cmd); + +/* from Linux kernel (crypto/crct10dif_common.c) */ +static const uint16_t t10_dif_crc_table[256] = { + 0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B, + 0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6, + 0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6, + 0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B, + 0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1, + 0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C, + 0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C, + 0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781, + 0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8, + 0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255, + 0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925, + 0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698, + 0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472, + 0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF, + 0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF, + 0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02, + 0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA, + 0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067, + 0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17, + 0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA, + 0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640, + 0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD, + 0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D, + 0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30, + 0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759, + 0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4, + 0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394, + 0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29, + 0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3, + 0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E, + 0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E, + 0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3 +}; + +uint16_t nvme_check_prinfo(NvmeNamespace *ns, uint8_t prinfo, uint64_t slba, + uint32_t reftag); +uint16_t nvme_dif_mangle_mdata(NvmeNamespace *ns, uint8_t *mbuf, size_t mlen, + uint64_t slba); +void nvme_dif_pract_generate_dif(NvmeNamespace *ns, uint8_t *buf, size_t len, + uint8_t *mbuf, size_t mlen, uint16_t apptag, + uint32_t *reftag); +uint16_t nvme_dif_check(NvmeNamespace *ns, uint8_t *buf, size_t len, + uint8_t *mbuf, size_t mlen, uint8_t prinfo, + uint64_t slba, uint16_t apptag, + uint16_t appmask, uint32_t *reftag); +uint16_t nvme_dif_rw(NvmeCtrl *n, NvmeRequest *req); + + +#endif /* HW_NVME_INTERNAL_H */ diff --git a/hw/block/nvme-subsys.c b/hw/nvme/subsys.c similarity index 85% rename from hw/block/nvme-subsys.c rename to hw/nvme/subsys.c index 283a97b79d..93c35950d6 100644 --- a/hw/block/nvme-subsys.c +++ b/hw/nvme/subsys.c @@ -6,21 +6,10 @@ * This code is licensed under the GNU GPL v2. Refer COPYING. */ -#include "qemu/units.h" #include "qemu/osdep.h" -#include "qemu/uuid.h" -#include "qemu/iov.h" -#include "qemu/cutils.h" #include "qapi/error.h" -#include "hw/qdev-properties.h" -#include "hw/qdev-core.h" -#include "hw/block/block.h" -#include "block/aio.h" -#include "block/accounting.h" -#include "sysemu/sysemu.h" -#include "hw/pci/pci.h" + #include "nvme.h" -#include "nvme-subsys.h" int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp) { @@ -43,6 +32,11 @@ int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp) return cntlid; } +void nvme_subsys_unregister_ctrl(NvmeSubsystem *subsys, NvmeCtrl *n) +{ + subsys->ctrls[n->cntlid] = NULL; +} + static void nvme_subsys_setup(NvmeSubsystem *subsys) { const char *nqn = subsys->params.nqn ? @@ -56,6 +50,9 @@ static void nvme_subsys_realize(DeviceState *dev, Error **errp) { NvmeSubsystem *subsys = NVME_SUBSYS(dev); + qbus_create_inplace(&subsys->bus, sizeof(NvmeBus), TYPE_NVME_BUS, dev, + dev->id); + nvme_subsys_setup(subsys); } @@ -72,6 +69,7 @@ static void nvme_subsys_class_init(ObjectClass *oc, void *data) dc->realize = nvme_subsys_realize; dc->desc = "Virtual NVMe subsystem"; + dc->hotpluggable = false; device_class_set_props(dc, nvme_subsystem_props); } diff --git a/hw/nvme/trace-events b/hw/nvme/trace-events new file mode 100644 index 0000000000..430eeb395b --- /dev/null +++ b/hw/nvme/trace-events @@ -0,0 +1,202 @@ +# successful events +pci_nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u" +pci_nvme_irq_pin(void) "pulsing IRQ pin" +pci_nvme_irq_masked(void) "IRQ is masked" +pci_nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64"" +pci_nvme_map_addr(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" +pci_nvme_map_addr_cmb(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" +pci_nvme_map_prp(uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d" +pci_nvme_map_sgl(uint8_t typ, uint64_t len) "type 0x%"PRIx8" len %"PRIu64"" +pci_nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode, const char *opname) "cid %"PRIu16" nsid 0x%"PRIx32" sqid %"PRIu16" opc 0x%"PRIx8" opname '%s'" +pci_nvme_admin_cmd(uint16_t cid, uint16_t sqid, uint8_t opcode, const char *opname) "cid %"PRIu16" sqid %"PRIu16" opc 0x%"PRIx8" opname '%s'" +pci_nvme_flush_ns(uint32_t nsid) "nsid 0x%"PRIx32"" +pci_nvme_format_set(uint32_t nsid, uint8_t lbaf, uint8_t mset, uint8_t pi, uint8_t pil) "nsid %"PRIu32" lbaf %"PRIu8" mset %"PRIu8" pi %"PRIu8" pil %"PRIu8"" +pci_nvme_read(uint16_t cid, uint32_t nsid, uint32_t nlb, uint64_t count, uint64_t lba) "cid %"PRIu16" nsid %"PRIu32" nlb %"PRIu32" count %"PRIu64" lba 0x%"PRIx64"" +pci_nvme_write(uint16_t cid, const char *verb, uint32_t nsid, uint32_t nlb, uint64_t count, uint64_t lba) "cid %"PRIu16" opname '%s' nsid %"PRIu32" nlb %"PRIu32" count %"PRIu64" lba 0x%"PRIx64"" +pci_nvme_rw_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" +pci_nvme_misc_cb(uint16_t cid) "cid %"PRIu16"" +pci_nvme_dif_rw(uint8_t pract, uint8_t prinfo) "pract 0x%"PRIx8" prinfo 0x%"PRIx8"" +pci_nvme_dif_rw_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" +pci_nvme_dif_rw_mdata_in_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" +pci_nvme_dif_rw_mdata_out_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" +pci_nvme_dif_rw_check_cb(uint16_t cid, uint8_t prinfo, uint16_t apptag, uint16_t appmask, uint32_t reftag) "cid %"PRIu16" prinfo 0x%"PRIx8" apptag 0x%"PRIx16" appmask 0x%"PRIx16" reftag 0x%"PRIx32"" +pci_nvme_dif_pract_generate_dif(size_t len, size_t lba_size, size_t chksum_len, uint16_t apptag, uint32_t reftag) "len %zu lba_size %zu chksum_len %zu apptag 0x%"PRIx16" reftag 0x%"PRIx32"" +pci_nvme_dif_check(uint8_t prinfo, uint16_t chksum_len) "prinfo 0x%"PRIx8" chksum_len %"PRIu16"" +pci_nvme_dif_prchk_disabled(uint16_t apptag, uint32_t reftag) "apptag 0x%"PRIx16" reftag 0x%"PRIx32"" +pci_nvme_dif_prchk_guard(uint16_t guard, uint16_t crc) "guard 0x%"PRIx16" crc 0x%"PRIx16"" +pci_nvme_dif_prchk_apptag(uint16_t apptag, uint16_t elbat, uint16_t elbatm) "apptag 0x%"PRIx16" elbat 0x%"PRIx16" elbatm 0x%"PRIx16"" +pci_nvme_dif_prchk_reftag(uint32_t reftag, uint32_t elbrt) "reftag 0x%"PRIx32" elbrt 0x%"PRIx32"" +pci_nvme_copy(uint16_t cid, uint32_t nsid, uint16_t nr, uint8_t format) "cid %"PRIu16" nsid %"PRIu32" nr %"PRIu16" format 0x%"PRIx8"" +pci_nvme_copy_source_range(uint64_t slba, uint32_t nlb) "slba 0x%"PRIx64" nlb %"PRIu32"" +pci_nvme_copy_out(uint64_t slba, uint32_t nlb) "slba 0x%"PRIx64" nlb %"PRIu32"" +pci_nvme_verify(uint16_t cid, uint32_t nsid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" nsid %"PRIu32" slba 0x%"PRIx64" nlb %"PRIu32"" +pci_nvme_verify_mdata_in_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" +pci_nvme_verify_cb(uint16_t cid, uint8_t prinfo, uint16_t apptag, uint16_t appmask, uint32_t reftag) "cid %"PRIu16" prinfo 0x%"PRIx8" apptag 0x%"PRIx16" appmask 0x%"PRIx16" reftag 0x%"PRIx32"" +pci_nvme_rw_complete_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" +pci_nvme_block_status(int64_t offset, int64_t bytes, int64_t pnum, int ret, bool zeroed) "offset %"PRId64" bytes %"PRId64" pnum %"PRId64" ret 0x%x zeroed %d" +pci_nvme_dsm(uint32_t nr, uint32_t attr) "nr %"PRIu32" attr 0x%"PRIx32"" +pci_nvme_dsm_deallocate(uint64_t slba, uint32_t nlb) "slba %"PRIu64" nlb %"PRIu32"" +pci_nvme_dsm_single_range_limit_exceeded(uint32_t nlb, uint32_t dmrsl) "nlb %"PRIu32" dmrsl %"PRIu32"" +pci_nvme_compare(uint16_t cid, uint32_t nsid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" nsid %"PRIu32" slba 0x%"PRIx64" nlb %"PRIu32"" +pci_nvme_compare_data_cb(uint16_t cid) "cid %"PRIu16"" +pci_nvme_compare_mdata_cb(uint16_t cid) "cid %"PRIu16"" +pci_nvme_aio_discard_cb(uint16_t cid) "cid %"PRIu16"" +pci_nvme_aio_copy_in_cb(uint16_t cid) "cid %"PRIu16"" +pci_nvme_aio_flush_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'" +pci_nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16"" +pci_nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d" +pci_nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16"" +pci_nvme_del_cq(uint16_t cqid) "deleted completion queue, cqid=%"PRIu16"" +pci_nvme_identify(uint16_t cid, uint8_t cns, uint16_t ctrlid, uint8_t csi) "cid %"PRIu16" cns 0x%"PRIx8" ctrlid %"PRIu16" csi 0x%"PRIx8"" +pci_nvme_identify_ctrl(void) "identify controller" +pci_nvme_identify_ctrl_csi(uint8_t csi) "identify controller, csi=0x%"PRIx8"" +pci_nvme_identify_ns(uint32_t ns) "nsid %"PRIu32"" +pci_nvme_identify_ctrl_list(uint8_t cns, uint16_t cntid) "cns 0x%"PRIx8" cntid %"PRIu16"" +pci_nvme_identify_ns_csi(uint32_t ns, uint8_t csi) "nsid=%"PRIu32", csi=0x%"PRIx8"" +pci_nvme_identify_nslist(uint32_t ns) "nsid %"PRIu32"" +pci_nvme_identify_nslist_csi(uint16_t ns, uint8_t csi) "nsid=%"PRIu16", csi=0x%"PRIx8"" +pci_nvme_identify_cmd_set(void) "identify i/o command set" +pci_nvme_identify_ns_descr_list(uint32_t ns) "nsid %"PRIu32"" +pci_nvme_get_log(uint16_t cid, uint8_t lid, uint8_t lsp, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx8" lsp 0x%"PRIx8" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64"" +pci_nvme_getfeat(uint16_t cid, uint32_t nsid, uint8_t fid, uint8_t sel, uint32_t cdw11) "cid %"PRIu16" nsid 0x%"PRIx32" fid 0x%"PRIx8" sel 0x%"PRIx8" cdw11 0x%"PRIx32"" +pci_nvme_setfeat(uint16_t cid, uint32_t nsid, uint8_t fid, uint8_t save, uint32_t cdw11) "cid %"PRIu16" nsid 0x%"PRIx32" fid 0x%"PRIx8" save 0x%"PRIx8" cdw11 0x%"PRIx32"" +pci_nvme_getfeat_vwcache(const char* result) "get feature volatile write cache, result=%s" +pci_nvme_getfeat_numq(int result) "get feature number of queues, result=%d" +pci_nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d" +pci_nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64"" +pci_nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64"" +pci_nvme_process_aers(int queued) "queued %d" +pci_nvme_aer(uint16_t cid) "cid %"PRIu16"" +pci_nvme_aer_aerl_exceeded(void) "aerl exceeded" +pci_nvme_aer_masked(uint8_t type, uint8_t mask) "type 0x%"PRIx8" mask 0x%"PRIx8"" +pci_nvme_aer_post_cqe(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8"" +pci_nvme_ns_attachment(uint16_t cid, uint8_t sel) "cid %"PRIu16", sel=0x%"PRIx8"" +pci_nvme_ns_attachment_attach(uint16_t cntlid, uint32_t nsid) "cntlid=0x%"PRIx16", nsid=0x%"PRIx32"" +pci_nvme_enqueue_event(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8"" +pci_nvme_enqueue_event_noqueue(int queued) "queued %d" +pci_nvme_enqueue_event_masked(uint8_t typ) "type 0x%"PRIx8"" +pci_nvme_no_outstanding_aers(void) "ignoring event; no outstanding AERs" +pci_nvme_enqueue_req_completion(uint16_t cid, uint16_t cqid, uint32_t dw0, uint32_t dw1, uint16_t status) "cid %"PRIu16" cqid %"PRIu16" dw0 0x%"PRIx32" dw1 0x%"PRIx32" status 0x%"PRIx16"" +pci_nvme_mmio_read(uint64_t addr, unsigned size) "addr 0x%"PRIx64" size %d" +pci_nvme_mmio_write(uint64_t addr, uint64_t data, unsigned size) "addr 0x%"PRIx64" data 0x%"PRIx64" size %d" +pci_nvme_mmio_doorbell_cq(uint16_t cqid, uint16_t new_head) "cqid %"PRIu16" new_head %"PRIu16"" +pci_nvme_mmio_doorbell_sq(uint16_t sqid, uint16_t new_tail) "sqid %"PRIu16" new_tail %"PRIu16"" +pci_nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64"" +pci_nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64"" +pci_nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64"" +pci_nvme_mmio_aqattr(uint64_t data) "wrote MMIO, admin queue attributes=0x%"PRIx64"" +pci_nvme_mmio_asqaddr(uint64_t data) "wrote MMIO, admin submission queue address=0x%"PRIx64"" +pci_nvme_mmio_acqaddr(uint64_t data) "wrote MMIO, admin completion queue address=0x%"PRIx64"" +pci_nvme_mmio_asqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin submission queue high half=0x%"PRIx64", new_address=0x%"PRIx64"" +pci_nvme_mmio_acqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin completion queue high half=0x%"PRIx64", new_address=0x%"PRIx64"" +pci_nvme_mmio_start_success(void) "setting controller enable bit succeeded" +pci_nvme_mmio_stopped(void) "cleared controller enable bit" +pci_nvme_mmio_shutdown_set(void) "shutdown bit set" +pci_nvme_mmio_shutdown_cleared(void) "shutdown bit cleared" +pci_nvme_open_zone(uint64_t slba, uint32_t zone_idx, int all) "open zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32"" +pci_nvme_close_zone(uint64_t slba, uint32_t zone_idx, int all) "close zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32"" +pci_nvme_finish_zone(uint64_t slba, uint32_t zone_idx, int all) "finish zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32"" +pci_nvme_reset_zone(uint64_t slba, uint32_t zone_idx, int all) "reset zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32"" +pci_nvme_zns_zone_reset(uint64_t zslba) "zslba 0x%"PRIx64"" +pci_nvme_offline_zone(uint64_t slba, uint32_t zone_idx, int all) "offline zone, slba=%"PRIu64", idx=%"PRIu32", all=%"PRIi32"" +pci_nvme_set_descriptor_extension(uint64_t slba, uint32_t zone_idx) "set zone descriptor extension, slba=%"PRIu64", idx=%"PRIu32"" +pci_nvme_zd_extension_set(uint32_t zone_idx) "set descriptor extension for zone_idx=%"PRIu32"" +pci_nvme_clear_ns_close(uint32_t state, uint64_t slba) "zone state=%"PRIu32", slba=%"PRIu64" transitioned to Closed state" +pci_nvme_clear_ns_reset(uint32_t state, uint64_t slba) "zone state=%"PRIu32", slba=%"PRIu64" transitioned to Empty state" + +# error conditions +pci_nvme_err_mdts(size_t len) "len %zu" +pci_nvme_err_zasl(size_t len) "len %zu" +pci_nvme_err_req_status(uint16_t cid, uint32_t nsid, uint16_t status, uint8_t opc) "cid %"PRIu16" nsid %"PRIu32" status 0x%"PRIx16" opc 0x%"PRIx8"" +pci_nvme_err_addr_read(uint64_t addr) "addr 0x%"PRIx64"" +pci_nvme_err_addr_write(uint64_t addr) "addr 0x%"PRIx64"" +pci_nvme_err_cfs(void) "controller fatal status" +pci_nvme_err_aio(uint16_t cid, const char *errname, uint16_t status) "cid %"PRIu16" err '%s' status 0x%"PRIx16"" +pci_nvme_err_copy_invalid_format(uint8_t format) "format 0x%"PRIx8"" +pci_nvme_err_invalid_sgld(uint16_t cid, uint8_t typ) "cid %"PRIu16" type 0x%"PRIx8"" +pci_nvme_err_invalid_num_sgld(uint16_t cid, uint8_t typ) "cid %"PRIu16" type 0x%"PRIx8"" +pci_nvme_err_invalid_sgl_excess_length(uint32_t residual) "residual %"PRIu32"" +pci_nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size" +pci_nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is not page aligned: 0x%"PRIx64"" +pci_nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64"" +pci_nvme_err_invalid_opc(uint8_t opc) "invalid opcode 0x%"PRIx8"" +pci_nvme_err_invalid_admin_opc(uint8_t opc) "invalid admin opcode 0x%"PRIx8"" +pci_nvme_err_invalid_lba_range(uint64_t start, uint64_t len, uint64_t limit) "Invalid LBA start=%"PRIu64" len=%"PRIu64" limit=%"PRIu64"" +pci_nvme_err_invalid_log_page_offset(uint64_t ofs, uint64_t size) "must be <= %"PRIu64", got %"PRIu64"" +pci_nvme_err_cmb_invalid_cba(uint64_t cmbmsc) "cmbmsc 0x%"PRIx64"" +pci_nvme_err_cmb_not_enabled(uint64_t cmbmsc) "cmbmsc 0x%"PRIx64"" +pci_nvme_err_unaligned_zone_cmd(uint8_t action, uint64_t slba, uint64_t zslba) "unaligned zone op 0x%"PRIx32", got slba=%"PRIu64", zslba=%"PRIu64"" +pci_nvme_err_invalid_zone_state_transition(uint8_t action, uint64_t slba, uint8_t attrs) "action=0x%"PRIx8", slba=%"PRIu64", attrs=0x%"PRIx32"" +pci_nvme_err_write_not_at_wp(uint64_t slba, uint64_t zone, uint64_t wp) "writing at slba=%"PRIu64", zone=%"PRIu64", but wp=%"PRIu64"" +pci_nvme_err_append_not_at_start(uint64_t slba, uint64_t zone) "appending at slba=%"PRIu64", but zone=%"PRIu64"" +pci_nvme_err_zone_is_full(uint64_t zslba) "zslba 0x%"PRIx64"" +pci_nvme_err_zone_is_read_only(uint64_t zslba) "zslba 0x%"PRIx64"" +pci_nvme_err_zone_is_offline(uint64_t zslba) "zslba 0x%"PRIx64"" +pci_nvme_err_zone_boundary(uint64_t slba, uint32_t nlb, uint64_t zcap) "lba 0x%"PRIx64" nlb %"PRIu32" zcap 0x%"PRIx64"" +pci_nvme_err_zone_invalid_write(uint64_t slba, uint64_t wp) "lba 0x%"PRIx64" wp 0x%"PRIx64"" +pci_nvme_err_zone_write_not_ok(uint64_t slba, uint32_t nlb, uint16_t status) "slba=%"PRIu64", nlb=%"PRIu32", status=0x%"PRIx16"" +pci_nvme_err_zone_read_not_ok(uint64_t slba, uint32_t nlb, uint16_t status) "slba=%"PRIu64", nlb=%"PRIu32", status=0x%"PRIx16"" +pci_nvme_err_insuff_active_res(uint32_t max_active) "max_active=%"PRIu32" zone limit exceeded" +pci_nvme_err_insuff_open_res(uint32_t max_open) "max_open=%"PRIu32" zone limit exceeded" +pci_nvme_err_zd_extension_map_error(uint32_t zone_idx) "can't map descriptor extension for zone_idx=%"PRIu32"" +pci_nvme_err_invalid_iocsci(uint32_t idx) "unsupported command set combination index %"PRIu32"" +pci_nvme_err_invalid_del_sq(uint16_t qid) "invalid submission queue deletion, sid=%"PRIu16"" +pci_nvme_err_invalid_create_sq_cqid(uint16_t cqid) "failed creating submission queue, invalid cqid=%"PRIu16"" +pci_nvme_err_invalid_create_sq_sqid(uint16_t sqid) "failed creating submission queue, invalid sqid=%"PRIu16"" +pci_nvme_err_invalid_create_sq_size(uint16_t qsize) "failed creating submission queue, invalid qsize=%"PRIu16"" +pci_nvme_err_invalid_create_sq_addr(uint64_t addr) "failed creating submission queue, addr=0x%"PRIx64"" +pci_nvme_err_invalid_create_sq_qflags(uint16_t qflags) "failed creating submission queue, qflags=%"PRIu16"" +pci_nvme_err_invalid_del_cq_cqid(uint16_t cqid) "failed deleting completion queue, cqid=%"PRIu16"" +pci_nvme_err_invalid_del_cq_notempty(uint16_t cqid) "failed deleting completion queue, it is not empty, cqid=%"PRIu16"" +pci_nvme_err_invalid_create_cq_cqid(uint16_t cqid) "failed creating completion queue, cqid=%"PRIu16"" +pci_nvme_err_invalid_create_cq_size(uint16_t size) "failed creating completion queue, size=%"PRIu16"" +pci_nvme_err_invalid_create_cq_addr(uint64_t addr) "failed creating completion queue, addr=0x%"PRIx64"" +pci_nvme_err_invalid_create_cq_vector(uint16_t vector) "failed creating completion queue, vector=%"PRIu16"" +pci_nvme_err_invalid_create_cq_qflags(uint16_t qflags) "failed creating completion queue, qflags=%"PRIu16"" +pci_nvme_err_invalid_identify_cns(uint16_t cns) "identify, invalid cns=0x%"PRIx16"" +pci_nvme_err_invalid_getfeat(int dw10) "invalid get features, dw10=0x%"PRIx32"" +pci_nvme_err_invalid_setfeat(uint32_t dw10) "invalid set features, dw10=0x%"PRIx32"" +pci_nvme_err_invalid_log_page(uint16_t cid, uint16_t lid) "cid %"PRIu16" lid 0x%"PRIx16"" +pci_nvme_err_startfail_cq(void) "nvme_start_ctrl failed because there are non-admin completion queues" +pci_nvme_err_startfail_sq(void) "nvme_start_ctrl failed because there are non-admin submission queues" +pci_nvme_err_startfail_nbarasq(void) "nvme_start_ctrl failed because the admin submission queue address is null" +pci_nvme_err_startfail_nbaracq(void) "nvme_start_ctrl failed because the admin completion queue address is null" +pci_nvme_err_startfail_asq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin submission queue address is misaligned: 0x%"PRIx64"" +pci_nvme_err_startfail_acq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin completion queue address is misaligned: 0x%"PRIx64"" +pci_nvme_err_startfail_page_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too small: log2size=%u, min=%u" +pci_nvme_err_startfail_page_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too large: log2size=%u, max=%u" +pci_nvme_err_startfail_cqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too small: log2size=%u, min=%u" +pci_nvme_err_startfail_cqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too large: log2size=%u, max=%u" +pci_nvme_err_startfail_sqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too small: log2size=%u, min=%u" +pci_nvme_err_startfail_sqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too large: log2size=%u, max=%u" +pci_nvme_err_startfail_css(uint8_t css) "nvme_start_ctrl failed because invalid command set selected:%u" +pci_nvme_err_startfail_asqent_sz_zero(void) "nvme_start_ctrl failed because the admin submission queue size is zero" +pci_nvme_err_startfail_acqent_sz_zero(void) "nvme_start_ctrl failed because the admin completion queue size is zero" +pci_nvme_err_startfail_zasl_too_small(uint32_t zasl, uint32_t pagesz) "nvme_start_ctrl failed because zone append size limit %"PRIu32" is too small, needs to be >= %"PRIu32"" +pci_nvme_err_startfail(void) "setting controller enable bit failed" +pci_nvme_err_invalid_mgmt_action(uint8_t action) "action=0x%"PRIx8"" + +# undefined behavior +pci_nvme_ub_mmiowr_misaligned32(uint64_t offset) "MMIO write not 32-bit aligned, offset=0x%"PRIx64"" +pci_nvme_ub_mmiowr_toosmall(uint64_t offset, unsigned size) "MMIO write smaller than 32 bits, offset=0x%"PRIx64", size=%u" +pci_nvme_ub_mmiowr_intmask_with_msix(void) "undefined access to interrupt mask set when MSI-X is enabled" +pci_nvme_ub_mmiowr_ro_csts(void) "attempted to set a read only bit of controller status" +pci_nvme_ub_mmiowr_ssreset_w1c_unsupported(void) "attempted to W1C CSTS.NSSRO but CAP.NSSRS is zero (not supported)" +pci_nvme_ub_mmiowr_ssreset_unsupported(void) "attempted NVM subsystem reset but CAP.NSSRS is zero (not supported)" +pci_nvme_ub_mmiowr_cmbloc_reserved(void) "invalid write to reserved CMBLOC when CMBSZ is zero, ignored" +pci_nvme_ub_mmiowr_cmbsz_readonly(void) "invalid write to read only CMBSZ, ignored" +pci_nvme_ub_mmiowr_pmrcap_readonly(void) "invalid write to read only PMRCAP, ignored" +pci_nvme_ub_mmiowr_pmrsts_readonly(void) "invalid write to read only PMRSTS, ignored" +pci_nvme_ub_mmiowr_pmrebs_readonly(void) "invalid write to read only PMREBS, ignored" +pci_nvme_ub_mmiowr_pmrswtp_readonly(void) "invalid write to read only PMRSWTP, ignored" +pci_nvme_ub_mmiowr_invalid(uint64_t offset, uint64_t data) "invalid MMIO write, offset=0x%"PRIx64", data=0x%"PRIx64"" +pci_nvme_ub_mmiord_misaligned32(uint64_t offset) "MMIO read not 32-bit aligned, offset=0x%"PRIx64"" +pci_nvme_ub_mmiord_toosmall(uint64_t offset) "MMIO read smaller than 32-bits, offset=0x%"PRIx64"" +pci_nvme_ub_mmiord_invalid_ofs(uint64_t offset) "MMIO read beyond last register, offset=0x%"PRIx64", returning 0" +pci_nvme_ub_db_wr_misaligned(uint64_t offset) "doorbell write not 32-bit aligned, offset=0x%"PRIx64", ignoring" +pci_nvme_ub_db_wr_invalid_cq(uint32_t qid) "completion queue doorbell write for nonexistent queue, cqid=%"PRIu32", ignoring" +pci_nvme_ub_db_wr_invalid_cqhead(uint32_t qid, uint16_t new_head) "completion queue doorbell write value beyond queue size, cqid=%"PRIu32", new_head=%"PRIu16", ignoring" +pci_nvme_ub_db_wr_invalid_sq(uint32_t qid) "submission queue doorbell write for nonexistent queue, sqid=%"PRIu32", ignoring" +pci_nvme_ub_db_wr_invalid_sqtail(uint32_t qid, uint16_t new_tail) "submission queue doorbell write value beyond queue size, sqid=%"PRIu32", new_head=%"PRIu16", ignoring" +pci_nvme_ub_unknown_css_value(void) "unknown value in cc.css field" +pci_nvme_ub_too_many_mappings(void) "too many prp/sgl mappings" diff --git a/hw/nvme/trace.h b/hw/nvme/trace.h new file mode 100644 index 0000000000..b398ea107f --- /dev/null +++ b/hw/nvme/trace.h @@ -0,0 +1 @@ +#include "trace/trace-hw_nvme.h" diff --git a/hw/nvram/nrf51_nvm.c b/hw/nvram/nrf51_nvm.c index 7b3460d52d..7f1db8c423 100644 --- a/hw/nvram/nrf51_nvm.c +++ b/hw/nvram/nrf51_nvm.c @@ -21,7 +21,6 @@ #include "qapi/error.h" #include "qemu/log.h" #include "qemu/module.h" -#include "exec/address-spaces.h" #include "hw/arm/nrf51.h" #include "hw/nvram/nrf51_nvm.h" #include "hw/qdev-properties.h" diff --git a/hw/nvram/spapr_nvram.c b/hw/nvram/spapr_nvram.c index 01f7752014..fbfdf47e26 100644 --- a/hw/nvram/spapr_nvram.c +++ b/hw/nvram/spapr_nvram.c @@ -26,14 +26,12 @@ #include "qemu/module.h" #include "qemu/units.h" #include "qapi/error.h" -#include "cpu.h" #include #include "sysemu/block-backend.h" #include "sysemu/device_tree.h" #include "sysemu/sysemu.h" #include "sysemu/runstate.h" -#include "hw/sysbus.h" #include "migration/vmstate.h" #include "hw/nvram/chrp_nvram.h" #include "hw/ppc/spapr.h" diff --git a/hw/nvram/trace-events b/hw/nvram/trace-events index e023193295..5e33b24d47 100644 --- a/hw/nvram/trace-events +++ b/hw/nvram/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # ds1225y.c nvram_read(uint32_t addr, uint32_t ret) "read addr %d: 0x%02x" diff --git a/hw/openrisc/openrisc_sim.c b/hw/openrisc/openrisc_sim.c index 39f1d344ae..73fe383c2d 100644 --- a/hw/openrisc/openrisc_sim.c +++ b/hw/openrisc/openrisc_sim.c @@ -29,7 +29,6 @@ #include "net/net.h" #include "hw/loader.h" #include "hw/qdev-properties.h" -#include "exec/address-spaces.h" #include "sysemu/sysemu.h" #include "hw/sysbus.h" #include "sysemu/qtest.h" diff --git a/hw/pci-bridge/gen_pcie_root_port.c b/hw/pci-bridge/gen_pcie_root_port.c index ec9907917e..20099a8ae3 100644 --- a/hw/pci-bridge/gen_pcie_root_port.c +++ b/hw/pci-bridge/gen_pcie_root_port.c @@ -28,6 +28,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(GenPCIERootPort, GEN_PCIE_ROOT_PORT) (GEN_PCIE_ROOT_PORT_AER_OFFSET + PCI_ERR_SIZEOF) #define GEN_PCIE_ROOT_PORT_MSIX_NR_VECTOR 1 +#define GEN_PCIE_ROOT_DEFAULT_IO_RANGE 4096 struct GenPCIERootPort { /*< private >*/ @@ -75,6 +76,7 @@ static bool gen_rp_test_migrate_msix(void *opaque, int version_id) static void gen_rp_realize(DeviceState *dev, Error **errp) { PCIDevice *d = PCI_DEVICE(dev); + PCIESlot *s = PCIE_SLOT(d); GenPCIERootPort *grp = GEN_PCIE_ROOT_PORT(d); PCIERootPortClass *rpc = PCIE_ROOT_PORT_GET_CLASS(d); Error *local_err = NULL; @@ -85,6 +87,9 @@ static void gen_rp_realize(DeviceState *dev, Error **errp) return; } + if (grp->res_reserve.io == -1 && s->hotplug && !s->native_hotplug) { + grp->res_reserve.io = GEN_PCIE_ROOT_DEFAULT_IO_RANGE; + } int rc = pci_bridge_qemu_reserve_cap_init(d, 0, grp->res_reserve, errp); diff --git a/hw/pci-bridge/pci_expander_bridge.c b/hw/pci-bridge/pci_expander_bridge.c index aedded1064..7112dc3062 100644 --- a/hw/pci-bridge/pci_expander_bridge.c +++ b/hw/pci-bridge/pci_expander_bridge.c @@ -57,6 +57,7 @@ struct PXBDev { uint8_t bus_nr; uint16_t numa_node; + bool bypass_iommu; }; static PXBDev *convert_to_pxb(PCIDevice *dev) @@ -255,6 +256,7 @@ static void pxb_dev_realize_common(PCIDevice *dev, bool pcie, Error **errp) bus->map_irq = pxb_map_irq_fn; PCI_HOST_BRIDGE(ds)->bus = bus; + PCI_HOST_BRIDGE(ds)->bypass_iommu = pxb->bypass_iommu; pxb_register_bus(dev, bus, &local_err); if (local_err) { @@ -301,6 +303,7 @@ static Property pxb_dev_properties[] = { /* Note: 0 is not a legal PXB bus number. */ DEFINE_PROP_UINT8("bus_nr", PXBDev, bus_nr, 0), DEFINE_PROP_UINT16("numa_node", PXBDev, numa_node, NUMA_NODE_UNASSIGNED), + DEFINE_PROP_BOOL("bypass_iommu", PXBDev, bypass_iommu, false), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/pci-host/Kconfig b/hw/pci-host/Kconfig index 2ccc96f02c..2b5f7d58cc 100644 --- a/hw/pci-host/Kconfig +++ b/hw/pci-host/Kconfig @@ -6,7 +6,7 @@ config XEN_IGD_PASSTHROUGH default y depends on XEN && PCI_I440FX -config PREP_PCI +config RAVEN_PCI bool select PCI select OR_IRQ @@ -72,3 +72,8 @@ config REMOTE_PCIHOST config SH_PCI bool select PCI + +config MV64361 + bool + select PCI + select I8259 diff --git a/hw/pci-host/bonito.c b/hw/pci-host/bonito.c index 2a2db7cea6..a57e81e3a9 100644 --- a/hw/pci-host/bonito.c +++ b/hw/pci-host/bonito.c @@ -49,10 +49,10 @@ #include "migration/vmstate.h" #include "sysemu/reset.h" #include "sysemu/runstate.h" -#include "exec/address-spaces.h" #include "hw/misc/unimp.h" #include "hw/registerfields.h" #include "qom/object.h" +#include "trace.h" /* #define DEBUG_BONITO */ @@ -186,7 +186,8 @@ FIELD(BONGENCFG, PCIQUEUE, 12, 1) #define BONITO_PCICONF_IDSEL_OFFSET 11 #define BONITO_PCICONF_FUN_MASK 0x700 /* [10:8] */ #define BONITO_PCICONF_FUN_OFFSET 8 -#define BONITO_PCICONF_REG_MASK 0xFC +#define BONITO_PCICONF_REG_MASK_DS (~3) /* Per datasheet */ +#define BONITO_PCICONF_REG_MASK_HW 0xff /* As seen running PMON */ #define BONITO_PCICONF_REG_OFFSET 0 @@ -465,7 +466,7 @@ static uint32_t bonito_sbridge_pciaddr(void *opaque, hwaddr addr) BONITO_PCICONF_IDSEL_OFFSET; devno = ctz32(idsel); funno = (cfgaddr & BONITO_PCICONF_FUN_MASK) >> BONITO_PCICONF_FUN_OFFSET; - regno = (cfgaddr & BONITO_PCICONF_REG_MASK) >> BONITO_PCICONF_REG_OFFSET; + regno = (cfgaddr & BONITO_PCICONF_REG_MASK_HW) >> BONITO_PCICONF_REG_OFFSET; if (idsel == 0) { error_report("error in bonito pci config address 0x" TARGET_FMT_plx @@ -496,6 +497,9 @@ static void bonito_spciconf_write(void *opaque, hwaddr addr, uint64_t val, if (pciaddr == 0xffffffff) { return; } + if (addr & ~BONITO_PCICONF_REG_MASK_DS) { + trace_bonito_spciconf_small_access(addr, size); + } /* set the pci address in s->config_reg */ phb->config_reg = (pciaddr) | (1u << 31); @@ -522,6 +526,9 @@ static uint64_t bonito_spciconf_read(void *opaque, hwaddr addr, unsigned size) if (pciaddr == 0xffffffff) { return MAKE_64BIT_MASK(0, size * 8); } + if (addr & ~BONITO_PCICONF_REG_MASK_DS) { + trace_bonito_spciconf_small_access(addr, size); + } /* set the pci address in s->config_reg */ phb->config_reg = (pciaddr) | (1u << 31); diff --git a/hw/pci-host/gpex-acpi.c b/hw/pci-host/gpex-acpi.c index 0f01f13a6e..e7e162a00a 100644 --- a/hw/pci-host/gpex-acpi.c +++ b/hw/pci-host/gpex-acpi.c @@ -112,26 +112,10 @@ static void acpi_dsdt_add_pci_osc(Aml *dev) UUID = aml_touuid("E5C937D0-3553-4D7A-9117-EA4D19C3434D"); ifctx = aml_if(aml_equal(aml_arg(0), UUID)); ifctx1 = aml_if(aml_equal(aml_arg(2), aml_int(0))); - uint8_t byte_list[] = { - 0x1 << 0 /* support for functions other than function 0 */ | - 0x1 << 5 /* support for function 5 */ - }; - buf = aml_buffer(ARRAY_SIZE(byte_list), byte_list); + uint8_t byte_list[1] = {1}; + buf = aml_buffer(1, byte_list); aml_append(ifctx1, aml_return(buf)); aml_append(ifctx, ifctx1); - - /* - * PCI Firmware Specification 3.1 - * 4.6.5. _DSM for Ignoring PCI Boot Configurations - */ - /* Arg2: Function Index: 5 */ - ifctx1 = aml_if(aml_equal(aml_arg(2), aml_int(5))); - /* - * 0 - The operating system must not ignore the PCI configuration that - * firmware has done at boot time. - */ - aml_append(ifctx1, aml_return(aml_int(0))); - aml_append(ifctx, ifctx1); aml_append(method, ifctx); byte_list[0] = 0; diff --git a/hw/pci-host/gpex.c b/hw/pci-host/gpex.c index 2bdbe7b456..a6752fac5e 100644 --- a/hw/pci-host/gpex.c +++ b/hw/pci-host/gpex.c @@ -83,12 +83,51 @@ static void gpex_host_realize(DeviceState *dev, Error **errp) int i; pcie_host_mmcfg_init(pex, PCIE_MMCFG_SIZE_MAX); + sysbus_init_mmio(sbd, &pex->mmio); + + /* + * Note that the MemoryRegions io_mmio and io_ioport that we pass + * to pci_register_root_bus() are not the same as the + * MemoryRegions io_mmio_window and io_ioport_window that we + * expose as SysBus MRs. The difference is in the behaviour of + * accesses to addresses where no PCI device has been mapped. + * + * io_mmio and io_ioport are the underlying PCI view of the PCI + * address space, and when a PCI device does a bus master access + * to a bad address this is reported back to it as a transaction + * failure. + * + * io_mmio_window and io_ioport_window implement "unmapped + * addresses read as -1 and ignore writes"; this is traditional + * x86 PC behaviour, which is not mandated by the PCI spec proper + * but expected by much PCI-using guest software, including Linux. + * + * In the interests of not being unnecessarily surprising, we + * implement it in the gpex PCI host controller, by providing the + * _window MRs, which are containers with io ops that implement + * the 'background' behaviour and which hold the real PCI MRs as + * subregions. + */ memory_region_init(&s->io_mmio, OBJECT(s), "gpex_mmio", UINT64_MAX); memory_region_init(&s->io_ioport, OBJECT(s), "gpex_ioport", 64 * 1024); - sysbus_init_mmio(sbd, &pex->mmio); - sysbus_init_mmio(sbd, &s->io_mmio); - sysbus_init_mmio(sbd, &s->io_ioport); + if (s->allow_unmapped_accesses) { + memory_region_init_io(&s->io_mmio_window, OBJECT(s), + &unassigned_io_ops, OBJECT(s), + "gpex_mmio_window", UINT64_MAX); + memory_region_init_io(&s->io_ioport_window, OBJECT(s), + &unassigned_io_ops, OBJECT(s), + "gpex_ioport_window", 64 * 1024); + + memory_region_add_subregion(&s->io_mmio_window, 0, &s->io_mmio); + memory_region_add_subregion(&s->io_ioport_window, 0, &s->io_ioport); + sysbus_init_mmio(sbd, &s->io_mmio_window); + sysbus_init_mmio(sbd, &s->io_ioport_window); + } else { + sysbus_init_mmio(sbd, &s->io_mmio); + sysbus_init_mmio(sbd, &s->io_ioport); + } + for (i = 0; i < GPEX_NUM_IRQS; i++) { sysbus_init_irq(sbd, &s->irq[i]); s->irq_num[i] = -1; @@ -108,6 +147,16 @@ static const char *gpex_host_root_bus_path(PCIHostState *host_bridge, return "0000:00"; } +static Property gpex_host_properties[] = { + /* + * Permit CPU accesses to unmapped areas of the PIO and MMIO windows + * (discarding writes and returning -1 for reads) rather than aborting. + */ + DEFINE_PROP_BOOL("allow-unmapped-accesses", GPEXHost, + allow_unmapped_accesses, true), + DEFINE_PROP_END_OF_LIST(), +}; + static void gpex_host_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -117,6 +166,7 @@ static void gpex_host_class_init(ObjectClass *klass, void *data) dc->realize = gpex_host_realize; set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); dc->fw_name = "pci"; + device_class_set_props(dc, gpex_host_properties); } static void gpex_host_initfn(Object *obj) diff --git a/hw/pci-host/meson.build b/hw/pci-host/meson.build index 87a896973e..4c4f39c15c 100644 --- a/hw/pci-host/meson.build +++ b/hw/pci-host/meson.build @@ -3,7 +3,7 @@ pci_ss.add(when: 'CONFIG_PAM', if_true: files('pam.c')) pci_ss.add(when: 'CONFIG_PCI_BONITO', if_true: files('bonito.c')) pci_ss.add(when: 'CONFIG_PCI_EXPRESS_DESIGNWARE', if_true: files('designware.c')) pci_ss.add(when: 'CONFIG_PCI_EXPRESS_GENERIC_BRIDGE', if_true: files('gpex.c')) -pci_ss.add(when: 'CONFIG_ACPI', if_true: files('gpex-acpi.c')) +pci_ss.add(when: ['CONFIG_PCI_EXPRESS_GENERIC_BRIDGE', 'CONFIG_ACPI'], if_true: files('gpex-acpi.c')) pci_ss.add(when: 'CONFIG_PCI_EXPRESS_Q35', if_true: files('q35.c')) pci_ss.add(when: 'CONFIG_PCI_EXPRESS_XILINX', if_true: files('xilinx-pcie.c')) pci_ss.add(when: 'CONFIG_PCI_I440FX', if_true: files('i440fx.c')) @@ -13,12 +13,14 @@ pci_ss.add(when: 'CONFIG_REMOTE_PCIHOST', if_true: files('remote.c')) pci_ss.add(when: 'CONFIG_SH_PCI', if_true: files('sh_pci.c')) # PPC devices -pci_ss.add(when: 'CONFIG_PREP_PCI', if_true: files('prep.c')) +pci_ss.add(when: 'CONFIG_RAVEN_PCI', if_true: files('raven.c')) pci_ss.add(when: 'CONFIG_GRACKLE_PCI', if_true: files('grackle.c')) # NewWorld PowerMac pci_ss.add(when: 'CONFIG_UNIN_PCI', if_true: files('uninorth.c')) # PowerPC E500 boards pci_ss.add(when: 'CONFIG_PPCE500_PCI', if_true: files('ppce500.c')) +# Pegasos2 +pci_ss.add(when: 'CONFIG_MV64361', if_true: files('mv64361.c')) # ARM devices pci_ss.add(when: 'CONFIG_VERSATILE_PCI', if_true: files('versatile.c')) diff --git a/hw/pci-host/mv64361.c b/hw/pci-host/mv64361.c new file mode 100644 index 0000000000..92b0f5d047 --- /dev/null +++ b/hw/pci-host/mv64361.c @@ -0,0 +1,950 @@ +/* + * Marvell Discovery II MV64361 System Controller for + * QEMU PowerPC CHRP (Genesi/bPlan Pegasos II) hardware System Emulator + * + * Copyright (c) 2018-2020 BALATON Zoltan + * + * This work is licensed under the GNU GPL license version 2 or later. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/units.h" +#include "qapi/error.h" +#include "hw/hw.h" +#include "hw/sysbus.h" +#include "hw/pci/pci.h" +#include "hw/pci/pci_host.h" +#include "hw/irq.h" +#include "hw/intc/i8259.h" +#include "hw/qdev-properties.h" +#include "exec/address-spaces.h" +#include "qemu/log.h" +#include "qemu/error-report.h" +#include "trace.h" +#include "hw/pci-host/mv64361.h" +#include "mv643xx.h" + +#define TYPE_MV64361_PCI_BRIDGE "mv64361-pcibridge" + +static void mv64361_pcibridge_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); + + k->vendor_id = PCI_VENDOR_ID_MARVELL; + k->device_id = PCI_DEVICE_ID_MARVELL_MV6436X; + k->class_id = PCI_CLASS_BRIDGE_HOST; + /* + * PCI-facing part of the host bridge, + * not usable without the host-facing part + */ + dc->user_creatable = false; +} + +static const TypeInfo mv64361_pcibridge_info = { + .name = TYPE_MV64361_PCI_BRIDGE, + .parent = TYPE_PCI_DEVICE, + .instance_size = sizeof(PCIDevice), + .class_init = mv64361_pcibridge_class_init, + .interfaces = (InterfaceInfo[]) { + { INTERFACE_CONVENTIONAL_PCI_DEVICE }, + { }, + }, +}; + + +#define TYPE_MV64361_PCI "mv64361-pcihost" +OBJECT_DECLARE_SIMPLE_TYPE(MV64361PCIState, MV64361_PCI) + +struct MV64361PCIState { + PCIHostState parent_obj; + + uint8_t index; + MemoryRegion io; + MemoryRegion mem; + qemu_irq irq[PCI_NUM_PINS]; + + uint32_t io_base; + uint32_t io_size; + uint32_t mem_base[4]; + uint32_t mem_size[4]; + uint64_t remap[5]; +}; + +static int mv64361_pcihost_map_irq(PCIDevice *pci_dev, int n) +{ + return (n + PCI_SLOT(pci_dev->devfn)) % PCI_NUM_PINS; +} + +static void mv64361_pcihost_set_irq(void *opaque, int n, int level) +{ + MV64361PCIState *s = opaque; + qemu_set_irq(s->irq[n], level); +} + +static void mv64361_pcihost_realize(DeviceState *dev, Error **errp) +{ + MV64361PCIState *s = MV64361_PCI(dev); + PCIHostState *h = PCI_HOST_BRIDGE(dev); + char *name; + + name = g_strdup_printf("pci%d-io", s->index); + memory_region_init(&s->io, OBJECT(dev), name, 0x10000); + g_free(name); + name = g_strdup_printf("pci%d-mem", s->index); + memory_region_init(&s->mem, OBJECT(dev), name, 1ULL << 32); + g_free(name); + name = g_strdup_printf("pci.%d", s->index); + h->bus = pci_register_root_bus(dev, name, mv64361_pcihost_set_irq, + mv64361_pcihost_map_irq, dev, + &s->mem, &s->io, 0, 4, TYPE_PCI_BUS); + g_free(name); + pci_create_simple(h->bus, 0, TYPE_MV64361_PCI_BRIDGE); +} + +static Property mv64361_pcihost_props[] = { + DEFINE_PROP_UINT8("index", MV64361PCIState, index, 0), + DEFINE_PROP_END_OF_LIST() +}; + +static void mv64361_pcihost_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = mv64361_pcihost_realize; + device_class_set_props(dc, mv64361_pcihost_props); + set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); +} + +static const TypeInfo mv64361_pcihost_info = { + .name = TYPE_MV64361_PCI, + .parent = TYPE_PCI_HOST_BRIDGE, + .instance_size = sizeof(MV64361PCIState), + .class_init = mv64361_pcihost_class_init, +}; + +static void mv64361_pci_register_types(void) +{ + type_register_static(&mv64361_pcihost_info); + type_register_static(&mv64361_pcibridge_info); +} + +type_init(mv64361_pci_register_types) + + +OBJECT_DECLARE_SIMPLE_TYPE(MV64361State, MV64361) + +struct MV64361State { + SysBusDevice parent_obj; + + MemoryRegion regs; + MV64361PCIState pci[2]; + MemoryRegion cpu_win[19]; + qemu_irq cpu_irq; + + /* registers state */ + uint32_t cpu_conf; + uint32_t regs_base; + uint32_t base_addr_enable; + uint64_t main_int_cr; + uint64_t cpu0_int_mask; + uint32_t gpp_io; + uint32_t gpp_level; + uint32_t gpp_value; + uint32_t gpp_int_cr; + uint32_t gpp_int_mask; + bool gpp_int_level; +}; + +enum mv64361_irq_cause { + MV64361_IRQ_DEVERR = 1, + MV64361_IRQ_DMAERR = 2, + MV64361_IRQ_CPUERR = 3, + MV64361_IRQ_IDMA0 = 4, + MV64361_IRQ_IDMA1 = 5, + MV64361_IRQ_IDMA2 = 6, + MV64361_IRQ_IDMA3 = 7, + MV64361_IRQ_TIMER0 = 8, + MV64361_IRQ_TIMER1 = 9, + MV64361_IRQ_TIMER2 = 10, + MV64361_IRQ_TIMER3 = 11, + MV64361_IRQ_PCI0 = 12, + MV64361_IRQ_SRAMERR = 13, + MV64361_IRQ_GBEERR = 14, + MV64361_IRQ_CERR = 15, + MV64361_IRQ_PCI1 = 16, + MV64361_IRQ_DRAMERR = 17, + MV64361_IRQ_WDNMI = 18, + MV64361_IRQ_WDE = 19, + MV64361_IRQ_PCI0IN = 20, + MV64361_IRQ_PCI0OUT = 21, + MV64361_IRQ_PCI1IN = 22, + MV64361_IRQ_PCI1OUT = 23, + MV64361_IRQ_P1_GPP0_7 = 24, + MV64361_IRQ_P1_GPP8_15 = 25, + MV64361_IRQ_P1_GPP16_23 = 26, + MV64361_IRQ_P1_GPP24_31 = 27, + MV64361_IRQ_P1_CPU_DB = 28, + /* 29-31: reserved */ + MV64361_IRQ_GBE0 = 32, + MV64361_IRQ_GBE1 = 33, + MV64361_IRQ_GBE2 = 34, + /* 35: reserved */ + MV64361_IRQ_SDMA0 = 36, + MV64361_IRQ_TWSI = 37, + MV64361_IRQ_SDMA1 = 38, + MV64361_IRQ_BRG = 39, + MV64361_IRQ_MPSC0 = 40, + MV64361_IRQ_MPSC1 = 41, + MV64361_IRQ_G0RX = 42, + MV64361_IRQ_G0TX = 43, + MV64361_IRQ_G0MISC = 44, + MV64361_IRQ_G1RX = 45, + MV64361_IRQ_G1TX = 46, + MV64361_IRQ_G1MISC = 47, + MV64361_IRQ_G2RX = 48, + MV64361_IRQ_G2TX = 49, + MV64361_IRQ_G2MISC = 50, + /* 51-55: reserved */ + MV64361_IRQ_P0_GPP0_7 = 56, + MV64361_IRQ_P0_GPP8_15 = 57, + MV64361_IRQ_P0_GPP16_23 = 58, + MV64361_IRQ_P0_GPP24_31 = 59, + MV64361_IRQ_P0_CPU_DB = 60, + /* 61-63: reserved */ +}; + +PCIBus *mv64361_get_pci_bus(DeviceState *dev, int n) +{ + MV64361State *mv = MV64361(dev); + return PCI_HOST_BRIDGE(&mv->pci[n])->bus; +} + +static void unmap_region(MemoryRegion *mr) +{ + if (memory_region_is_mapped(mr)) { + memory_region_del_subregion(get_system_memory(), mr); + object_unparent(OBJECT(mr)); + } +} + +static void map_pci_region(MemoryRegion *mr, MemoryRegion *parent, + struct Object *owner, const char *name, + hwaddr poffs, uint64_t size, hwaddr moffs) +{ + memory_region_init_alias(mr, owner, name, parent, poffs, size); + memory_region_add_subregion(get_system_memory(), moffs, mr); + trace_mv64361_region_map(name, poffs, size, moffs); +} + +static void set_mem_windows(MV64361State *s, uint32_t val) +{ + MV64361PCIState *p; + MemoryRegion *mr; + uint32_t mask; + int i; + + val &= 0x1fffff; + for (mask = 1, i = 0; i < 21; i++, mask <<= 1) { + if ((val & mask) != (s->base_addr_enable & mask)) { + trace_mv64361_region_enable(!(val & mask) ? "enable" : "disable", i); + /* + * 0-3 are SDRAM chip selects but we map all RAM directly + * 4-7 are device chip selects (not sure what those are) + * 8 is Boot device (ROM) chip select but we map that directly too + */ + if (i == 9) { + p = &s->pci[0]; + mr = &s->cpu_win[i]; + unmap_region(mr); + if (!(val & mask)) { + map_pci_region(mr, &p->io, OBJECT(s), "pci0-io-win", + p->remap[4], (p->io_size + 1) << 16, + (p->io_base & 0xfffff) << 16); + } + } else if (i == 10) { + p = &s->pci[0]; + mr = &s->cpu_win[i]; + unmap_region(mr); + if (!(val & mask)) { + map_pci_region(mr, &p->mem, OBJECT(s), "pci0-mem0-win", + p->remap[0], (p->mem_size[0] + 1) << 16, + (p->mem_base[0] & 0xfffff) << 16); + } + } else if (i == 11) { + p = &s->pci[0]; + mr = &s->cpu_win[i]; + unmap_region(mr); + if (!(val & mask)) { + map_pci_region(mr, &p->mem, OBJECT(s), "pci0-mem1-win", + p->remap[1], (p->mem_size[1] + 1) << 16, + (p->mem_base[1] & 0xfffff) << 16); + } + } else if (i == 12) { + p = &s->pci[0]; + mr = &s->cpu_win[i]; + unmap_region(mr); + if (!(val & mask)) { + map_pci_region(mr, &p->mem, OBJECT(s), "pci0-mem2-win", + p->remap[2], (p->mem_size[2] + 1) << 16, + (p->mem_base[2] & 0xfffff) << 16); + } + } else if (i == 13) { + p = &s->pci[0]; + mr = &s->cpu_win[i]; + unmap_region(mr); + if (!(val & mask)) { + map_pci_region(mr, &p->mem, OBJECT(s), "pci0-mem3-win", + p->remap[3], (p->mem_size[3] + 1) << 16, + (p->mem_base[3] & 0xfffff) << 16); + } + } else if (i == 14) { + p = &s->pci[1]; + mr = &s->cpu_win[i]; + unmap_region(mr); + if (!(val & mask)) { + map_pci_region(mr, &p->io, OBJECT(s), "pci1-io-win", + p->remap[4], (p->io_size + 1) << 16, + (p->io_base & 0xfffff) << 16); + } + } else if (i == 15) { + p = &s->pci[1]; + mr = &s->cpu_win[i]; + unmap_region(mr); + if (!(val & mask)) { + map_pci_region(mr, &p->mem, OBJECT(s), "pci1-mem0-win", + p->remap[0], (p->mem_size[0] + 1) << 16, + (p->mem_base[0] & 0xfffff) << 16); + } + } else if (i == 16) { + p = &s->pci[1]; + mr = &s->cpu_win[i]; + unmap_region(mr); + if (!(val & mask)) { + map_pci_region(mr, &p->mem, OBJECT(s), "pci1-mem1-win", + p->remap[1], (p->mem_size[1] + 1) << 16, + (p->mem_base[1] & 0xfffff) << 16); + } + } else if (i == 17) { + p = &s->pci[1]; + mr = &s->cpu_win[i]; + unmap_region(mr); + if (!(val & mask)) { + map_pci_region(mr, &p->mem, OBJECT(s), "pci1-mem2-win", + p->remap[2], (p->mem_size[2] + 1) << 16, + (p->mem_base[2] & 0xfffff) << 16); + } + } else if (i == 18) { + p = &s->pci[1]; + mr = &s->cpu_win[i]; + unmap_region(mr); + if (!(val & mask)) { + map_pci_region(mr, &p->mem, OBJECT(s), "pci1-mem3-win", + p->remap[3], (p->mem_size[3] + 1) << 16, + (p->mem_base[3] & 0xfffff) << 16); + } + /* 19 is integrated SRAM */ + } else if (i == 20) { + mr = &s->regs; + unmap_region(mr); + if (!(val & mask)) { + memory_region_add_subregion(get_system_memory(), + (s->regs_base & 0xfffff) << 16, mr); + } + } + } + } + s->base_addr_enable = val; +} + +static void mv64361_update_irq(void *opaque, int n, int level) +{ + MV64361State *s = opaque; + uint64_t val = s->main_int_cr; + + if (level) { + val |= BIT_ULL(n); + } else { + val &= ~BIT_ULL(n); + } + if ((s->main_int_cr & s->cpu0_int_mask) != (val & s->cpu0_int_mask)) { + qemu_set_irq(s->cpu_irq, level); + } + s->main_int_cr = val; +} + +static uint64_t mv64361_read(void *opaque, hwaddr addr, unsigned int size) +{ + MV64361State *s = MV64361(opaque); + uint32_t ret = 0; + + switch (addr) { + case MV64340_CPU_CONFIG: + ret = s->cpu_conf; + break; + case MV64340_PCI_0_IO_BASE_ADDR: + ret = s->pci[0].io_base; + break; + case MV64340_PCI_0_IO_SIZE: + ret = s->pci[0].io_size; + break; + case MV64340_PCI_0_IO_ADDR_REMAP: + ret = s->pci[0].remap[4] >> 16; + break; + case MV64340_PCI_0_MEMORY0_BASE_ADDR: + ret = s->pci[0].mem_base[0]; + break; + case MV64340_PCI_0_MEMORY0_SIZE: + ret = s->pci[0].mem_size[0]; + break; + case MV64340_PCI_0_MEMORY0_LOW_ADDR_REMAP: + ret = (s->pci[0].remap[0] & 0xffff0000) >> 16; + break; + case MV64340_PCI_0_MEMORY0_HIGH_ADDR_REMAP: + ret = s->pci[0].remap[0] >> 32; + break; + case MV64340_PCI_0_MEMORY1_BASE_ADDR: + ret = s->pci[0].mem_base[1]; + break; + case MV64340_PCI_0_MEMORY1_SIZE: + ret = s->pci[0].mem_size[1]; + break; + case MV64340_PCI_0_MEMORY1_LOW_ADDR_REMAP: + ret = (s->pci[0].remap[1] & 0xffff0000) >> 16; + break; + case MV64340_PCI_0_MEMORY1_HIGH_ADDR_REMAP: + ret = s->pci[0].remap[1] >> 32; + break; + case MV64340_PCI_0_MEMORY2_BASE_ADDR: + ret = s->pci[0].mem_base[2]; + break; + case MV64340_PCI_0_MEMORY2_SIZE: + ret = s->pci[0].mem_size[2]; + break; + case MV64340_PCI_0_MEMORY2_LOW_ADDR_REMAP: + ret = (s->pci[0].remap[2] & 0xffff0000) >> 16; + break; + case MV64340_PCI_0_MEMORY2_HIGH_ADDR_REMAP: + ret = s->pci[0].remap[2] >> 32; + break; + case MV64340_PCI_0_MEMORY3_BASE_ADDR: + ret = s->pci[0].mem_base[3]; + break; + case MV64340_PCI_0_MEMORY3_SIZE: + ret = s->pci[0].mem_size[3]; + break; + case MV64340_PCI_0_MEMORY3_LOW_ADDR_REMAP: + ret = (s->pci[0].remap[3] & 0xffff0000) >> 16; + break; + case MV64340_PCI_0_MEMORY3_HIGH_ADDR_REMAP: + ret = s->pci[0].remap[3] >> 32; + break; + case MV64340_PCI_1_IO_BASE_ADDR: + ret = s->pci[1].io_base; + break; + case MV64340_PCI_1_IO_SIZE: + ret = s->pci[1].io_size; + break; + case MV64340_PCI_1_IO_ADDR_REMAP: + ret = s->pci[1].remap[4] >> 16; + break; + case MV64340_PCI_1_MEMORY0_BASE_ADDR: + ret = s->pci[1].mem_base[0]; + break; + case MV64340_PCI_1_MEMORY0_SIZE: + ret = s->pci[1].mem_size[0]; + break; + case MV64340_PCI_1_MEMORY0_LOW_ADDR_REMAP: + ret = (s->pci[1].remap[0] & 0xffff0000) >> 16; + break; + case MV64340_PCI_1_MEMORY0_HIGH_ADDR_REMAP: + ret = s->pci[1].remap[0] >> 32; + break; + case MV64340_PCI_1_MEMORY1_BASE_ADDR: + ret = s->pci[1].mem_base[1]; + break; + case MV64340_PCI_1_MEMORY1_SIZE: + ret = s->pci[1].mem_size[1]; + break; + case MV64340_PCI_1_MEMORY1_LOW_ADDR_REMAP: + ret = (s->pci[1].remap[1] & 0xffff0000) >> 16; + break; + case MV64340_PCI_1_MEMORY1_HIGH_ADDR_REMAP: + ret = s->pci[1].remap[1] >> 32; + break; + case MV64340_PCI_1_MEMORY2_BASE_ADDR: + ret = s->pci[1].mem_base[2]; + break; + case MV64340_PCI_1_MEMORY2_SIZE: + ret = s->pci[1].mem_size[2]; + break; + case MV64340_PCI_1_MEMORY2_LOW_ADDR_REMAP: + ret = (s->pci[1].remap[2] & 0xffff0000) >> 16; + break; + case MV64340_PCI_1_MEMORY2_HIGH_ADDR_REMAP: + ret = s->pci[1].remap[2] >> 32; + break; + case MV64340_PCI_1_MEMORY3_BASE_ADDR: + ret = s->pci[1].mem_base[3]; + break; + case MV64340_PCI_1_MEMORY3_SIZE: + ret = s->pci[1].mem_size[3]; + break; + case MV64340_PCI_1_MEMORY3_LOW_ADDR_REMAP: + ret = (s->pci[1].remap[3] & 0xffff0000) >> 16; + break; + case MV64340_PCI_1_MEMORY3_HIGH_ADDR_REMAP: + ret = s->pci[1].remap[3] >> 32; + break; + case MV64340_INTERNAL_SPACE_BASE_ADDR: + ret = s->regs_base; + break; + case MV64340_BASE_ADDR_ENABLE: + ret = s->base_addr_enable; + break; + case MV64340_PCI_0_CONFIG_ADDR: + ret = pci_host_conf_le_ops.read(PCI_HOST_BRIDGE(&s->pci[0]), 0, size); + break; + case MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG ... + MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG + 3: + ret = pci_host_data_le_ops.read(PCI_HOST_BRIDGE(&s->pci[0]), + addr - MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG, size); + break; + case MV64340_PCI_1_CONFIG_ADDR: + ret = pci_host_conf_le_ops.read(PCI_HOST_BRIDGE(&s->pci[1]), 0, size); + break; + case MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG ... + MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG + 3: + ret = pci_host_data_le_ops.read(PCI_HOST_BRIDGE(&s->pci[1]), + addr - MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG, size); + break; + case MV64340_PCI_1_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG: + /* FIXME: Should this be sent via the PCI bus somehow? */ + if (s->gpp_int_level && (s->gpp_value & BIT(31))) { + ret = pic_read_irq(isa_pic); + } + break; + case MV64340_MAIN_INTERRUPT_CAUSE_LOW: + ret = s->main_int_cr; + break; + case MV64340_MAIN_INTERRUPT_CAUSE_HIGH: + ret = s->main_int_cr >> 32; + break; + case MV64340_CPU_INTERRUPT0_MASK_LOW: + ret = s->cpu0_int_mask; + break; + case MV64340_CPU_INTERRUPT0_MASK_HIGH: + ret = s->cpu0_int_mask >> 32; + break; + case MV64340_CPU_INTERRUPT0_SELECT_CAUSE: + ret = s->main_int_cr; + if (s->main_int_cr & s->cpu0_int_mask) { + if (!(s->main_int_cr & s->cpu0_int_mask & 0xffffffff)) { + ret = s->main_int_cr >> 32 | BIT(30); + } else if ((s->main_int_cr & s->cpu0_int_mask) >> 32) { + ret |= BIT(31); + } + } + break; + case MV64340_CUNIT_ARBITER_CONTROL_REG: + ret = 0x11ff0000 | (s->gpp_int_level << 10); + break; + case MV64340_GPP_IO_CONTROL: + ret = s->gpp_io; + break; + case MV64340_GPP_LEVEL_CONTROL: + ret = s->gpp_level; + break; + case MV64340_GPP_VALUE: + ret = s->gpp_value; + break; + case MV64340_GPP_VALUE_SET: + case MV64340_GPP_VALUE_CLEAR: + ret = 0; + break; + case MV64340_GPP_INTERRUPT_CAUSE: + ret = s->gpp_int_cr; + break; + case MV64340_GPP_INTERRUPT_MASK0: + case MV64340_GPP_INTERRUPT_MASK1: + ret = s->gpp_int_mask; + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: Unimplemented register read 0x%" + HWADDR_PRIx "\n", __func__, addr); + break; + } + if (addr != MV64340_PCI_1_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG) { + trace_mv64361_reg_read(addr, ret); + } + return ret; +} + +static void warn_swap_bit(uint64_t val) +{ + if ((val & 0x3000000ULL) >> 24 != 1) { + qemu_log_mask(LOG_UNIMP, "%s: Data swap not implemented", __func__); + } +} + +static void mv64361_set_pci_mem_remap(MV64361State *s, int bus, int idx, + uint64_t val, bool high) +{ + if (high) { + s->pci[bus].remap[idx] = val; + } else { + s->pci[bus].remap[idx] &= 0xffffffff00000000ULL; + s->pci[bus].remap[idx] |= (val & 0xffffULL) << 16; + } +} + +static void mv64361_write(void *opaque, hwaddr addr, uint64_t val, + unsigned int size) +{ + MV64361State *s = MV64361(opaque); + + trace_mv64361_reg_write(addr, val); + switch (addr) { + case MV64340_CPU_CONFIG: + s->cpu_conf = val & 0xe4e3bffULL; + s->cpu_conf |= BIT(23); + break; + case MV64340_PCI_0_IO_BASE_ADDR: + s->pci[0].io_base = val & 0x30fffffULL; + warn_swap_bit(val); + if (!(s->cpu_conf & BIT(27))) { + s->pci[0].remap[4] = (val & 0xffffULL) << 16; + } + break; + case MV64340_PCI_0_IO_SIZE: + s->pci[0].io_size = val & 0xffffULL; + break; + case MV64340_PCI_0_IO_ADDR_REMAP: + s->pci[0].remap[4] = (val & 0xffffULL) << 16; + break; + case MV64340_PCI_0_MEMORY0_BASE_ADDR: + s->pci[0].mem_base[0] = val & 0x70fffffULL; + warn_swap_bit(val); + if (!(s->cpu_conf & BIT(27))) { + mv64361_set_pci_mem_remap(s, 0, 0, val, false); + } + break; + case MV64340_PCI_0_MEMORY0_SIZE: + s->pci[0].mem_size[0] = val & 0xffffULL; + break; + case MV64340_PCI_0_MEMORY0_LOW_ADDR_REMAP: + case MV64340_PCI_0_MEMORY0_HIGH_ADDR_REMAP: + mv64361_set_pci_mem_remap(s, 0, 0, val, + (addr == MV64340_PCI_0_MEMORY0_HIGH_ADDR_REMAP)); + break; + case MV64340_PCI_0_MEMORY1_BASE_ADDR: + s->pci[0].mem_base[1] = val & 0x70fffffULL; + warn_swap_bit(val); + if (!(s->cpu_conf & BIT(27))) { + mv64361_set_pci_mem_remap(s, 0, 1, val, false); + } + break; + case MV64340_PCI_0_MEMORY1_SIZE: + s->pci[0].mem_size[1] = val & 0xffffULL; + break; + case MV64340_PCI_0_MEMORY1_LOW_ADDR_REMAP: + case MV64340_PCI_0_MEMORY1_HIGH_ADDR_REMAP: + mv64361_set_pci_mem_remap(s, 0, 1, val, + (addr == MV64340_PCI_0_MEMORY1_HIGH_ADDR_REMAP)); + break; + case MV64340_PCI_0_MEMORY2_BASE_ADDR: + s->pci[0].mem_base[2] = val & 0x70fffffULL; + warn_swap_bit(val); + if (!(s->cpu_conf & BIT(27))) { + mv64361_set_pci_mem_remap(s, 0, 2, val, false); + } + break; + case MV64340_PCI_0_MEMORY2_SIZE: + s->pci[0].mem_size[2] = val & 0xffffULL; + break; + case MV64340_PCI_0_MEMORY2_LOW_ADDR_REMAP: + case MV64340_PCI_0_MEMORY2_HIGH_ADDR_REMAP: + mv64361_set_pci_mem_remap(s, 0, 2, val, + (addr == MV64340_PCI_0_MEMORY2_HIGH_ADDR_REMAP)); + break; + case MV64340_PCI_0_MEMORY3_BASE_ADDR: + s->pci[0].mem_base[3] = val & 0x70fffffULL; + warn_swap_bit(val); + if (!(s->cpu_conf & BIT(27))) { + mv64361_set_pci_mem_remap(s, 0, 3, val, false); + } + break; + case MV64340_PCI_0_MEMORY3_SIZE: + s->pci[0].mem_size[3] = val & 0xffffULL; + break; + case MV64340_PCI_0_MEMORY3_LOW_ADDR_REMAP: + case MV64340_PCI_0_MEMORY3_HIGH_ADDR_REMAP: + mv64361_set_pci_mem_remap(s, 0, 3, val, + (addr == MV64340_PCI_0_MEMORY3_HIGH_ADDR_REMAP)); + break; + case MV64340_PCI_1_IO_BASE_ADDR: + s->pci[1].io_base = val & 0x30fffffULL; + warn_swap_bit(val); + if (!(s->cpu_conf & BIT(27))) { + s->pci[1].remap[4] = (val & 0xffffULL) << 16; + } + break; + case MV64340_PCI_1_IO_SIZE: + s->pci[1].io_size = val & 0xffffULL; + break; + case MV64340_PCI_1_MEMORY0_BASE_ADDR: + s->pci[1].mem_base[0] = val & 0x70fffffULL; + warn_swap_bit(val); + if (!(s->cpu_conf & BIT(27))) { + mv64361_set_pci_mem_remap(s, 1, 0, val, false); + } + break; + case MV64340_PCI_1_MEMORY0_SIZE: + s->pci[1].mem_size[0] = val & 0xffffULL; + break; + case MV64340_PCI_1_MEMORY0_LOW_ADDR_REMAP: + case MV64340_PCI_1_MEMORY0_HIGH_ADDR_REMAP: + mv64361_set_pci_mem_remap(s, 1, 0, val, + (addr == MV64340_PCI_1_MEMORY0_HIGH_ADDR_REMAP)); + break; + case MV64340_PCI_1_MEMORY1_BASE_ADDR: + s->pci[1].mem_base[1] = val & 0x70fffffULL; + warn_swap_bit(val); + if (!(s->cpu_conf & BIT(27))) { + mv64361_set_pci_mem_remap(s, 1, 1, val, false); + } + break; + case MV64340_PCI_1_MEMORY1_SIZE: + s->pci[1].mem_size[1] = val & 0xffffULL; + break; + case MV64340_PCI_1_MEMORY1_LOW_ADDR_REMAP: + case MV64340_PCI_1_MEMORY1_HIGH_ADDR_REMAP: + mv64361_set_pci_mem_remap(s, 1, 1, val, + (addr == MV64340_PCI_1_MEMORY1_HIGH_ADDR_REMAP)); + break; + case MV64340_PCI_1_MEMORY2_BASE_ADDR: + s->pci[1].mem_base[2] = val & 0x70fffffULL; + warn_swap_bit(val); + if (!(s->cpu_conf & BIT(27))) { + mv64361_set_pci_mem_remap(s, 1, 2, val, false); + } + break; + case MV64340_PCI_1_MEMORY2_SIZE: + s->pci[1].mem_size[2] = val & 0xffffULL; + break; + case MV64340_PCI_1_MEMORY2_LOW_ADDR_REMAP: + case MV64340_PCI_1_MEMORY2_HIGH_ADDR_REMAP: + mv64361_set_pci_mem_remap(s, 1, 2, val, + (addr == MV64340_PCI_1_MEMORY2_HIGH_ADDR_REMAP)); + break; + case MV64340_PCI_1_MEMORY3_BASE_ADDR: + s->pci[1].mem_base[3] = val & 0x70fffffULL; + warn_swap_bit(val); + if (!(s->cpu_conf & BIT(27))) { + mv64361_set_pci_mem_remap(s, 1, 3, val, false); + } + break; + case MV64340_PCI_1_MEMORY3_SIZE: + s->pci[1].mem_size[3] = val & 0xffffULL; + break; + case MV64340_PCI_1_MEMORY3_LOW_ADDR_REMAP: + case MV64340_PCI_1_MEMORY3_HIGH_ADDR_REMAP: + mv64361_set_pci_mem_remap(s, 1, 3, val, + (addr == MV64340_PCI_1_MEMORY3_HIGH_ADDR_REMAP)); + break; + case MV64340_INTERNAL_SPACE_BASE_ADDR: + s->regs_base = val & 0xfffffULL; + break; + case MV64340_BASE_ADDR_ENABLE: + set_mem_windows(s, val); + break; + case MV64340_PCI_0_CONFIG_ADDR: + pci_host_conf_le_ops.write(PCI_HOST_BRIDGE(&s->pci[0]), 0, val, size); + break; + case MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG ... + MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG + 3: + pci_host_data_le_ops.write(PCI_HOST_BRIDGE(&s->pci[0]), + addr - MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG, val, size); + break; + case MV64340_PCI_1_CONFIG_ADDR: + pci_host_conf_le_ops.write(PCI_HOST_BRIDGE(&s->pci[1]), 0, val, size); + break; + case MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG ... + MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG + 3: + pci_host_data_le_ops.write(PCI_HOST_BRIDGE(&s->pci[1]), + addr - MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG, val, size); + break; + case MV64340_CPU_INTERRUPT0_MASK_LOW: + s->cpu0_int_mask &= 0xffffffff00000000ULL; + s->cpu0_int_mask |= val & 0xffffffffULL; + break; + case MV64340_CPU_INTERRUPT0_MASK_HIGH: + s->cpu0_int_mask &= 0xffffffffULL; + s->cpu0_int_mask |= val << 32; + break; + case MV64340_CUNIT_ARBITER_CONTROL_REG: + s->gpp_int_level = !!(val & BIT(10)); + break; + case MV64340_GPP_IO_CONTROL: + s->gpp_io = val; + break; + case MV64340_GPP_LEVEL_CONTROL: + s->gpp_level = val; + break; + case MV64340_GPP_VALUE: + s->gpp_value &= ~s->gpp_io; + s->gpp_value |= val & s->gpp_io; + break; + case MV64340_GPP_VALUE_SET: + s->gpp_value |= val & s->gpp_io; + break; + case MV64340_GPP_VALUE_CLEAR: + s->gpp_value &= ~(val & s->gpp_io); + break; + case MV64340_GPP_INTERRUPT_CAUSE: + if (!s->gpp_int_level && val != s->gpp_int_cr) { + int i; + uint32_t ch = s->gpp_int_cr ^ val; + s->gpp_int_cr = val; + for (i = 0; i < 4; i++) { + if ((ch & 0xff << i) && !(val & 0xff << i)) { + mv64361_update_irq(opaque, MV64361_IRQ_P0_GPP0_7 + i, 0); + } + } + } else { + s->gpp_int_cr = val; + } + break; + case MV64340_GPP_INTERRUPT_MASK0: + case MV64340_GPP_INTERRUPT_MASK1: + s->gpp_int_mask = val; + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: Unimplemented register write 0x%" + HWADDR_PRIx " = %"PRIx64"\n", __func__, addr, val); + break; + } +} + +static const MemoryRegionOps mv64361_ops = { + .read = mv64361_read, + .write = mv64361_write, + .valid.min_access_size = 1, + .valid.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +static void mv64361_gpp_irq(void *opaque, int n, int level) +{ + MV64361State *s = opaque; + uint32_t mask = BIT(n); + uint32_t val = s->gpp_value & ~mask; + + if (s->gpp_level & mask) { + level = !level; + } + val |= level << n; + if (val > s->gpp_value) { + s->gpp_value = val; + s->gpp_int_cr |= mask; + if (s->gpp_int_mask & mask) { + mv64361_update_irq(opaque, MV64361_IRQ_P0_GPP0_7 + n / 8, 1); + } + } else if (val < s->gpp_value) { + int b = n / 8; + s->gpp_value = val; + if (s->gpp_int_level && !(val & 0xff << b)) { + mv64361_update_irq(opaque, MV64361_IRQ_P0_GPP0_7 + b, 0); + } + } +} + +static void mv64361_realize(DeviceState *dev, Error **errp) +{ + MV64361State *s = MV64361(dev); + int i; + + s->base_addr_enable = 0x1fffff; + memory_region_init_io(&s->regs, OBJECT(s), &mv64361_ops, s, + TYPE_MV64361, 0x10000); + for (i = 0; i < 2; i++) { + g_autofree char *name = g_strdup_printf("pcihost%d", i); + object_initialize_child(OBJECT(dev), name, &s->pci[i], + TYPE_MV64361_PCI); + DeviceState *pci = DEVICE(&s->pci[i]); + qdev_prop_set_uint8(pci, "index", i); + sysbus_realize_and_unref(SYS_BUS_DEVICE(pci), &error_fatal); + } + sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->cpu_irq); + qdev_init_gpio_in_named(dev, mv64361_gpp_irq, "gpp", 32); + /* FIXME: PCI IRQ connections may be board specific */ + for (i = 0; i < PCI_NUM_PINS; i++) { + s->pci[1].irq[i] = qdev_get_gpio_in_named(dev, "gpp", 12 + i); + } +} + +static void mv64361_reset(DeviceState *dev) +{ + MV64361State *s = MV64361(dev); + int i, j; + + /* + * These values may be board specific + * Real chip supports init from an eprom but that's not modelled + */ + set_mem_windows(s, 0x1fffff); + s->cpu_conf = 0x28000ff; + s->regs_base = 0x100f100; + s->pci[0].io_base = 0x100f800; + s->pci[0].io_size = 0xff; + s->pci[0].mem_base[0] = 0x100c000; + s->pci[0].mem_size[0] = 0x1fff; + s->pci[0].mem_base[1] = 0x100f900; + s->pci[0].mem_size[1] = 0xff; + s->pci[0].mem_base[2] = 0x100f400; + s->pci[0].mem_size[2] = 0x1ff; + s->pci[0].mem_base[3] = 0x100f600; + s->pci[0].mem_size[3] = 0x1ff; + s->pci[1].io_base = 0x100fe00; + s->pci[1].io_size = 0xff; + s->pci[1].mem_base[0] = 0x1008000; + s->pci[1].mem_size[0] = 0x3fff; + s->pci[1].mem_base[1] = 0x100fd00; + s->pci[1].mem_size[1] = 0xff; + s->pci[1].mem_base[2] = 0x1002600; + s->pci[1].mem_size[2] = 0x1ff; + s->pci[1].mem_base[3] = 0x100ff80; + s->pci[1].mem_size[3] = 0x7f; + for (i = 0; i < 2; i++) { + for (j = 0; j < 4; j++) { + s->pci[i].remap[j] = s->pci[i].mem_base[j] << 16; + } + } + s->pci[0].remap[1] = 0; + s->pci[1].remap[1] = 0; + set_mem_windows(s, 0xfbfff); +} + +static void mv64361_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = mv64361_realize; + dc->reset = mv64361_reset; +} + +static const TypeInfo mv64361_type_info = { + .name = TYPE_MV64361, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(MV64361State), + .class_init = mv64361_class_init, +}; + +static void mv64361_register_types(void) +{ + type_register_static(&mv64361_type_info); +} + +type_init(mv64361_register_types) diff --git a/hw/pci-host/mv643xx.h b/hw/pci-host/mv643xx.h new file mode 100644 index 0000000000..cd26a43f18 --- /dev/null +++ b/hw/pci-host/mv643xx.h @@ -0,0 +1,918 @@ +/* + * mv643xx.h - MV-643XX Internal registers definition file. + * + * Copyright 2002 Momentum Computer, Inc. + * Author: Matthew Dharm + * Copyright 2002 GALILEO TECHNOLOGY, LTD. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ +#ifndef ASM_MV643XX_H +#define ASM_MV643XX_H + +/****************************************/ +/* Processor Address Space */ +/****************************************/ + +/* DDR SDRAM BAR and size registers */ + +#define MV64340_CS_0_BASE_ADDR 0x008 +#define MV64340_CS_0_SIZE 0x010 +#define MV64340_CS_1_BASE_ADDR 0x208 +#define MV64340_CS_1_SIZE 0x210 +#define MV64340_CS_2_BASE_ADDR 0x018 +#define MV64340_CS_2_SIZE 0x020 +#define MV64340_CS_3_BASE_ADDR 0x218 +#define MV64340_CS_3_SIZE 0x220 + +/* Devices BAR and size registers */ + +#define MV64340_DEV_CS0_BASE_ADDR 0x028 +#define MV64340_DEV_CS0_SIZE 0x030 +#define MV64340_DEV_CS1_BASE_ADDR 0x228 +#define MV64340_DEV_CS1_SIZE 0x230 +#define MV64340_DEV_CS2_BASE_ADDR 0x248 +#define MV64340_DEV_CS2_SIZE 0x250 +#define MV64340_DEV_CS3_BASE_ADDR 0x038 +#define MV64340_DEV_CS3_SIZE 0x040 +#define MV64340_BOOTCS_BASE_ADDR 0x238 +#define MV64340_BOOTCS_SIZE 0x240 + +/* PCI 0 BAR and size registers */ + +#define MV64340_PCI_0_IO_BASE_ADDR 0x048 +#define MV64340_PCI_0_IO_SIZE 0x050 +#define MV64340_PCI_0_MEMORY0_BASE_ADDR 0x058 +#define MV64340_PCI_0_MEMORY0_SIZE 0x060 +#define MV64340_PCI_0_MEMORY1_BASE_ADDR 0x080 +#define MV64340_PCI_0_MEMORY1_SIZE 0x088 +#define MV64340_PCI_0_MEMORY2_BASE_ADDR 0x258 +#define MV64340_PCI_0_MEMORY2_SIZE 0x260 +#define MV64340_PCI_0_MEMORY3_BASE_ADDR 0x280 +#define MV64340_PCI_0_MEMORY3_SIZE 0x288 + +/* PCI 1 BAR and size registers */ +#define MV64340_PCI_1_IO_BASE_ADDR 0x090 +#define MV64340_PCI_1_IO_SIZE 0x098 +#define MV64340_PCI_1_MEMORY0_BASE_ADDR 0x0a0 +#define MV64340_PCI_1_MEMORY0_SIZE 0x0a8 +#define MV64340_PCI_1_MEMORY1_BASE_ADDR 0x0b0 +#define MV64340_PCI_1_MEMORY1_SIZE 0x0b8 +#define MV64340_PCI_1_MEMORY2_BASE_ADDR 0x2a0 +#define MV64340_PCI_1_MEMORY2_SIZE 0x2a8 +#define MV64340_PCI_1_MEMORY3_BASE_ADDR 0x2b0 +#define MV64340_PCI_1_MEMORY3_SIZE 0x2b8 + +/* SRAM base address */ +#define MV64340_INTEGRATED_SRAM_BASE_ADDR 0x268 + +/* internal registers space base address */ +#define MV64340_INTERNAL_SPACE_BASE_ADDR 0x068 + +/* Enables the CS , DEV_CS , PCI 0 and PCI 1 windows above */ +#define MV64340_BASE_ADDR_ENABLE 0x278 + +/****************************************/ +/* PCI remap registers */ +/****************************************/ + + /* PCI 0 */ +#define MV64340_PCI_0_IO_ADDR_REMAP 0x0f0 +#define MV64340_PCI_0_MEMORY0_LOW_ADDR_REMAP 0x0f8 +#define MV64340_PCI_0_MEMORY0_HIGH_ADDR_REMAP 0x320 +#define MV64340_PCI_0_MEMORY1_LOW_ADDR_REMAP 0x100 +#define MV64340_PCI_0_MEMORY1_HIGH_ADDR_REMAP 0x328 +#define MV64340_PCI_0_MEMORY2_LOW_ADDR_REMAP 0x2f8 +#define MV64340_PCI_0_MEMORY2_HIGH_ADDR_REMAP 0x330 +#define MV64340_PCI_0_MEMORY3_LOW_ADDR_REMAP 0x300 +#define MV64340_PCI_0_MEMORY3_HIGH_ADDR_REMAP 0x338 + /* PCI 1 */ +#define MV64340_PCI_1_IO_ADDR_REMAP 0x108 +#define MV64340_PCI_1_MEMORY0_LOW_ADDR_REMAP 0x110 +#define MV64340_PCI_1_MEMORY0_HIGH_ADDR_REMAP 0x340 +#define MV64340_PCI_1_MEMORY1_LOW_ADDR_REMAP 0x118 +#define MV64340_PCI_1_MEMORY1_HIGH_ADDR_REMAP 0x348 +#define MV64340_PCI_1_MEMORY2_LOW_ADDR_REMAP 0x310 +#define MV64340_PCI_1_MEMORY2_HIGH_ADDR_REMAP 0x350 +#define MV64340_PCI_1_MEMORY3_LOW_ADDR_REMAP 0x318 +#define MV64340_PCI_1_MEMORY3_HIGH_ADDR_REMAP 0x358 + +#define MV64340_CPU_PCI_0_HEADERS_RETARGET_CONTROL 0x3b0 +#define MV64340_CPU_PCI_0_HEADERS_RETARGET_BASE 0x3b8 +#define MV64340_CPU_PCI_1_HEADERS_RETARGET_CONTROL 0x3c0 +#define MV64340_CPU_PCI_1_HEADERS_RETARGET_BASE 0x3c8 +#define MV64340_CPU_GE_HEADERS_RETARGET_CONTROL 0x3d0 +#define MV64340_CPU_GE_HEADERS_RETARGET_BASE 0x3d8 +#define MV64340_CPU_IDMA_HEADERS_RETARGET_CONTROL 0x3e0 +#define MV64340_CPU_IDMA_HEADERS_RETARGET_BASE 0x3e8 + +/****************************************/ +/* CPU Control Registers */ +/****************************************/ + +#define MV64340_CPU_CONFIG 0x000 +#define MV64340_CPU_MODE 0x120 +#define MV64340_CPU_MASTER_CONTROL 0x160 +#define MV64340_CPU_CROSS_BAR_CONTROL_LOW 0x150 +#define MV64340_CPU_CROSS_BAR_CONTROL_HIGH 0x158 +#define MV64340_CPU_CROSS_BAR_TIMEOUT 0x168 + +/****************************************/ +/* SMP RegisterS */ +/****************************************/ + +#define MV64340_SMP_WHO_AM_I 0x200 +#define MV64340_SMP_CPU0_DOORBELL 0x214 +#define MV64340_SMP_CPU0_DOORBELL_CLEAR 0x21C +#define MV64340_SMP_CPU1_DOORBELL 0x224 +#define MV64340_SMP_CPU1_DOORBELL_CLEAR 0x22C +#define MV64340_SMP_CPU0_DOORBELL_MASK 0x234 +#define MV64340_SMP_CPU1_DOORBELL_MASK 0x23C +#define MV64340_SMP_SEMAPHOR0 0x244 +#define MV64340_SMP_SEMAPHOR1 0x24c +#define MV64340_SMP_SEMAPHOR2 0x254 +#define MV64340_SMP_SEMAPHOR3 0x25c +#define MV64340_SMP_SEMAPHOR4 0x264 +#define MV64340_SMP_SEMAPHOR5 0x26c +#define MV64340_SMP_SEMAPHOR6 0x274 +#define MV64340_SMP_SEMAPHOR7 0x27c + +/****************************************/ +/* CPU Sync Barrier Register */ +/****************************************/ + +#define MV64340_CPU_0_SYNC_BARRIER_TRIGGER 0x0c0 +#define MV64340_CPU_0_SYNC_BARRIER_VIRTUAL 0x0c8 +#define MV64340_CPU_1_SYNC_BARRIER_TRIGGER 0x0d0 +#define MV64340_CPU_1_SYNC_BARRIER_VIRTUAL 0x0d8 + +/****************************************/ +/* CPU Access Protect */ +/****************************************/ + +#define MV64340_CPU_PROTECT_WINDOW_0_BASE_ADDR 0x180 +#define MV64340_CPU_PROTECT_WINDOW_0_SIZE 0x188 +#define MV64340_CPU_PROTECT_WINDOW_1_BASE_ADDR 0x190 +#define MV64340_CPU_PROTECT_WINDOW_1_SIZE 0x198 +#define MV64340_CPU_PROTECT_WINDOW_2_BASE_ADDR 0x1a0 +#define MV64340_CPU_PROTECT_WINDOW_2_SIZE 0x1a8 +#define MV64340_CPU_PROTECT_WINDOW_3_BASE_ADDR 0x1b0 +#define MV64340_CPU_PROTECT_WINDOW_3_SIZE 0x1b8 + + +/****************************************/ +/* CPU Error Report */ +/****************************************/ + +#define MV64340_CPU_ERROR_ADDR_LOW 0x070 +#define MV64340_CPU_ERROR_ADDR_HIGH 0x078 +#define MV64340_CPU_ERROR_DATA_LOW 0x128 +#define MV64340_CPU_ERROR_DATA_HIGH 0x130 +#define MV64340_CPU_ERROR_PARITY 0x138 +#define MV64340_CPU_ERROR_CAUSE 0x140 +#define MV64340_CPU_ERROR_MASK 0x148 + +/****************************************/ +/* CPU Interface Debug Registers */ +/****************************************/ + +#define MV64340_PUNIT_SLAVE_DEBUG_LOW 0x360 +#define MV64340_PUNIT_SLAVE_DEBUG_HIGH 0x368 +#define MV64340_PUNIT_MASTER_DEBUG_LOW 0x370 +#define MV64340_PUNIT_MASTER_DEBUG_HIGH 0x378 +#define MV64340_PUNIT_MMASK 0x3e4 + +/****************************************/ +/* Integrated SRAM Registers */ +/****************************************/ + +#define MV64340_SRAM_CONFIG 0x380 +#define MV64340_SRAM_TEST_MODE 0X3F4 +#define MV64340_SRAM_ERROR_CAUSE 0x388 +#define MV64340_SRAM_ERROR_ADDR 0x390 +#define MV64340_SRAM_ERROR_ADDR_HIGH 0X3F8 +#define MV64340_SRAM_ERROR_DATA_LOW 0x398 +#define MV64340_SRAM_ERROR_DATA_HIGH 0x3a0 +#define MV64340_SRAM_ERROR_DATA_PARITY 0x3a8 + +/****************************************/ +/* SDRAM Configuration */ +/****************************************/ + +#define MV64340_SDRAM_CONFIG 0x1400 +#define MV64340_D_UNIT_CONTROL_LOW 0x1404 +#define MV64340_D_UNIT_CONTROL_HIGH 0x1424 +#define MV64340_SDRAM_TIMING_CONTROL_LOW 0x1408 +#define MV64340_SDRAM_TIMING_CONTROL_HIGH 0x140c +#define MV64340_SDRAM_ADDR_CONTROL 0x1410 +#define MV64340_SDRAM_OPEN_PAGES_CONTROL 0x1414 +#define MV64340_SDRAM_OPERATION 0x1418 +#define MV64340_SDRAM_MODE 0x141c +#define MV64340_EXTENDED_DRAM_MODE 0x1420 +#define MV64340_SDRAM_CROSS_BAR_CONTROL_LOW 0x1430 +#define MV64340_SDRAM_CROSS_BAR_CONTROL_HIGH 0x1434 +#define MV64340_SDRAM_CROSS_BAR_TIMEOUT 0x1438 +#define MV64340_SDRAM_ADDR_CTRL_PADS_CALIBRATION 0x14c0 +#define MV64340_SDRAM_DATA_PADS_CALIBRATION 0x14c4 + +/****************************************/ +/* SDRAM Error Report */ +/****************************************/ + +#define MV64340_SDRAM_ERROR_DATA_LOW 0x1444 +#define MV64340_SDRAM_ERROR_DATA_HIGH 0x1440 +#define MV64340_SDRAM_ERROR_ADDR 0x1450 +#define MV64340_SDRAM_RECEIVED_ECC 0x1448 +#define MV64340_SDRAM_CALCULATED_ECC 0x144c +#define MV64340_SDRAM_ECC_CONTROL 0x1454 +#define MV64340_SDRAM_ECC_ERROR_COUNTER 0x1458 + +/******************************************/ +/* Controlled Delay Line (CDL) Registers */ +/******************************************/ + +#define MV64340_DFCDL_CONFIG0 0x1480 +#define MV64340_DFCDL_CONFIG1 0x1484 +#define MV64340_DLL_WRITE 0x1488 +#define MV64340_DLL_READ 0x148c +#define MV64340_SRAM_ADDR 0x1490 +#define MV64340_SRAM_DATA0 0x1494 +#define MV64340_SRAM_DATA1 0x1498 +#define MV64340_SRAM_DATA2 0x149c +#define MV64340_DFCL_PROBE 0x14a0 + +/******************************************/ +/* Debug Registers */ +/******************************************/ + +#define MV64340_DUNIT_DEBUG_LOW 0x1460 +#define MV64340_DUNIT_DEBUG_HIGH 0x1464 +#define MV64340_DUNIT_MMASK 0X1b40 + +/****************************************/ +/* Device Parameters */ +/****************************************/ + +#define MV64340_DEVICE_BANK0_PARAMETERS 0x45c +#define MV64340_DEVICE_BANK1_PARAMETERS 0x460 +#define MV64340_DEVICE_BANK2_PARAMETERS 0x464 +#define MV64340_DEVICE_BANK3_PARAMETERS 0x468 +#define MV64340_DEVICE_BOOT_BANK_PARAMETERS 0x46c +#define MV64340_DEVICE_INTERFACE_CONTROL 0x4c0 +#define MV64340_DEVICE_INTERFACE_CROSS_BAR_CONTROL_LOW 0x4c8 +#define MV64340_DEVICE_INTERFACE_CROSS_BAR_CONTROL_HIGH 0x4cc +#define MV64340_DEVICE_INTERFACE_CROSS_BAR_TIMEOUT 0x4c4 + +/****************************************/ +/* Device interrupt registers */ +/****************************************/ + +#define MV64340_DEVICE_INTERRUPT_CAUSE 0x4d0 +#define MV64340_DEVICE_INTERRUPT_MASK 0x4d4 +#define MV64340_DEVICE_ERROR_ADDR 0x4d8 +#define MV64340_DEVICE_ERROR_DATA 0x4dc +#define MV64340_DEVICE_ERROR_PARITY 0x4e0 + +/****************************************/ +/* Device debug registers */ +/****************************************/ + +#define MV64340_DEVICE_DEBUG_LOW 0x4e4 +#define MV64340_DEVICE_DEBUG_HIGH 0x4e8 +#define MV64340_RUNIT_MMASK 0x4f0 + +/****************************************/ +/* PCI Slave Address Decoding registers */ +/****************************************/ + +#define MV64340_PCI_0_CS_0_BANK_SIZE 0xc08 +#define MV64340_PCI_1_CS_0_BANK_SIZE 0xc88 +#define MV64340_PCI_0_CS_1_BANK_SIZE 0xd08 +#define MV64340_PCI_1_CS_1_BANK_SIZE 0xd88 +#define MV64340_PCI_0_CS_2_BANK_SIZE 0xc0c +#define MV64340_PCI_1_CS_2_BANK_SIZE 0xc8c +#define MV64340_PCI_0_CS_3_BANK_SIZE 0xd0c +#define MV64340_PCI_1_CS_3_BANK_SIZE 0xd8c +#define MV64340_PCI_0_DEVCS_0_BANK_SIZE 0xc10 +#define MV64340_PCI_1_DEVCS_0_BANK_SIZE 0xc90 +#define MV64340_PCI_0_DEVCS_1_BANK_SIZE 0xd10 +#define MV64340_PCI_1_DEVCS_1_BANK_SIZE 0xd90 +#define MV64340_PCI_0_DEVCS_2_BANK_SIZE 0xd18 +#define MV64340_PCI_1_DEVCS_2_BANK_SIZE 0xd98 +#define MV64340_PCI_0_DEVCS_3_BANK_SIZE 0xc14 +#define MV64340_PCI_1_DEVCS_3_BANK_SIZE 0xc94 +#define MV64340_PCI_0_DEVCS_BOOT_BANK_SIZE 0xd14 +#define MV64340_PCI_1_DEVCS_BOOT_BANK_SIZE 0xd94 +#define MV64340_PCI_0_P2P_MEM0_BAR_SIZE 0xd1c +#define MV64340_PCI_1_P2P_MEM0_BAR_SIZE 0xd9c +#define MV64340_PCI_0_P2P_MEM1_BAR_SIZE 0xd20 +#define MV64340_PCI_1_P2P_MEM1_BAR_SIZE 0xda0 +#define MV64340_PCI_0_P2P_I_O_BAR_SIZE 0xd24 +#define MV64340_PCI_1_P2P_I_O_BAR_SIZE 0xda4 +#define MV64340_PCI_0_CPU_BAR_SIZE 0xd28 +#define MV64340_PCI_1_CPU_BAR_SIZE 0xda8 +#define MV64340_PCI_0_INTERNAL_SRAM_BAR_SIZE 0xe00 +#define MV64340_PCI_1_INTERNAL_SRAM_BAR_SIZE 0xe80 +#define MV64340_PCI_0_EXPANSION_ROM_BAR_SIZE 0xd2c +#define MV64340_PCI_1_EXPANSION_ROM_BAR_SIZE 0xd9c +#define MV64340_PCI_0_BASE_ADDR_REG_ENABLE 0xc3c +#define MV64340_PCI_1_BASE_ADDR_REG_ENABLE 0xcbc +#define MV64340_PCI_0_CS_0_BASE_ADDR_REMAP 0xc48 +#define MV64340_PCI_1_CS_0_BASE_ADDR_REMAP 0xcc8 +#define MV64340_PCI_0_CS_1_BASE_ADDR_REMAP 0xd48 +#define MV64340_PCI_1_CS_1_BASE_ADDR_REMAP 0xdc8 +#define MV64340_PCI_0_CS_2_BASE_ADDR_REMAP 0xc4c +#define MV64340_PCI_1_CS_2_BASE_ADDR_REMAP 0xccc +#define MV64340_PCI_0_CS_3_BASE_ADDR_REMAP 0xd4c +#define MV64340_PCI_1_CS_3_BASE_ADDR_REMAP 0xdcc +#define MV64340_PCI_0_CS_0_BASE_HIGH_ADDR_REMAP 0xF04 +#define MV64340_PCI_1_CS_0_BASE_HIGH_ADDR_REMAP 0xF84 +#define MV64340_PCI_0_CS_1_BASE_HIGH_ADDR_REMAP 0xF08 +#define MV64340_PCI_1_CS_1_BASE_HIGH_ADDR_REMAP 0xF88 +#define MV64340_PCI_0_CS_2_BASE_HIGH_ADDR_REMAP 0xF0C +#define MV64340_PCI_1_CS_2_BASE_HIGH_ADDR_REMAP 0xF8C +#define MV64340_PCI_0_CS_3_BASE_HIGH_ADDR_REMAP 0xF10 +#define MV64340_PCI_1_CS_3_BASE_HIGH_ADDR_REMAP 0xF90 +#define MV64340_PCI_0_DEVCS_0_BASE_ADDR_REMAP 0xc50 +#define MV64340_PCI_1_DEVCS_0_BASE_ADDR_REMAP 0xcd0 +#define MV64340_PCI_0_DEVCS_1_BASE_ADDR_REMAP 0xd50 +#define MV64340_PCI_1_DEVCS_1_BASE_ADDR_REMAP 0xdd0 +#define MV64340_PCI_0_DEVCS_2_BASE_ADDR_REMAP 0xd58 +#define MV64340_PCI_1_DEVCS_2_BASE_ADDR_REMAP 0xdd8 +#define MV64340_PCI_0_DEVCS_3_BASE_ADDR_REMAP 0xc54 +#define MV64340_PCI_1_DEVCS_3_BASE_ADDR_REMAP 0xcd4 +#define MV64340_PCI_0_DEVCS_BOOTCS_BASE_ADDR_REMAP 0xd54 +#define MV64340_PCI_1_DEVCS_BOOTCS_BASE_ADDR_REMAP 0xdd4 +#define MV64340_PCI_0_P2P_MEM0_BASE_ADDR_REMAP_LOW 0xd5c +#define MV64340_PCI_1_P2P_MEM0_BASE_ADDR_REMAP_LOW 0xddc +#define MV64340_PCI_0_P2P_MEM0_BASE_ADDR_REMAP_HIGH 0xd60 +#define MV64340_PCI_1_P2P_MEM0_BASE_ADDR_REMAP_HIGH 0xde0 +#define MV64340_PCI_0_P2P_MEM1_BASE_ADDR_REMAP_LOW 0xd64 +#define MV64340_PCI_1_P2P_MEM1_BASE_ADDR_REMAP_LOW 0xde4 +#define MV64340_PCI_0_P2P_MEM1_BASE_ADDR_REMAP_HIGH 0xd68 +#define MV64340_PCI_1_P2P_MEM1_BASE_ADDR_REMAP_HIGH 0xde8 +#define MV64340_PCI_0_P2P_I_O_BASE_ADDR_REMAP 0xd6c +#define MV64340_PCI_1_P2P_I_O_BASE_ADDR_REMAP 0xdec +#define MV64340_PCI_0_CPU_BASE_ADDR_REMAP_LOW 0xd70 +#define MV64340_PCI_1_CPU_BASE_ADDR_REMAP_LOW 0xdf0 +#define MV64340_PCI_0_CPU_BASE_ADDR_REMAP_HIGH 0xd74 +#define MV64340_PCI_1_CPU_BASE_ADDR_REMAP_HIGH 0xdf4 +#define MV64340_PCI_0_INTEGRATED_SRAM_BASE_ADDR_REMAP 0xf00 +#define MV64340_PCI_1_INTEGRATED_SRAM_BASE_ADDR_REMAP 0xf80 +#define MV64340_PCI_0_EXPANSION_ROM_BASE_ADDR_REMAP 0xf38 +#define MV64340_PCI_1_EXPANSION_ROM_BASE_ADDR_REMAP 0xfb8 +#define MV64340_PCI_0_ADDR_DECODE_CONTROL 0xd3c +#define MV64340_PCI_1_ADDR_DECODE_CONTROL 0xdbc +#define MV64340_PCI_0_HEADERS_RETARGET_CONTROL 0xF40 +#define MV64340_PCI_1_HEADERS_RETARGET_CONTROL 0xFc0 +#define MV64340_PCI_0_HEADERS_RETARGET_BASE 0xF44 +#define MV64340_PCI_1_HEADERS_RETARGET_BASE 0xFc4 +#define MV64340_PCI_0_HEADERS_RETARGET_HIGH 0xF48 +#define MV64340_PCI_1_HEADERS_RETARGET_HIGH 0xFc8 + +/***********************************/ +/* PCI Control Register Map */ +/***********************************/ + +#define MV64340_PCI_0_DLL_STATUS_AND_COMMAND 0x1d20 +#define MV64340_PCI_1_DLL_STATUS_AND_COMMAND 0x1da0 +#define MV64340_PCI_0_MPP_PADS_DRIVE_CONTROL 0x1d1C +#define MV64340_PCI_1_MPP_PADS_DRIVE_CONTROL 0x1d9C +#define MV64340_PCI_0_COMMAND 0xc00 +#define MV64340_PCI_1_COMMAND 0xc80 +#define MV64340_PCI_0_MODE 0xd00 +#define MV64340_PCI_1_MODE 0xd80 +#define MV64340_PCI_0_RETRY 0xc04 +#define MV64340_PCI_1_RETRY 0xc84 +#define MV64340_PCI_0_READ_BUFFER_DISCARD_TIMER 0xd04 +#define MV64340_PCI_1_READ_BUFFER_DISCARD_TIMER 0xd84 +#define MV64340_PCI_0_MSI_TRIGGER_TIMER 0xc38 +#define MV64340_PCI_1_MSI_TRIGGER_TIMER 0xcb8 +#define MV64340_PCI_0_ARBITER_CONTROL 0x1d00 +#define MV64340_PCI_1_ARBITER_CONTROL 0x1d80 +#define MV64340_PCI_0_CROSS_BAR_CONTROL_LOW 0x1d08 +#define MV64340_PCI_1_CROSS_BAR_CONTROL_LOW 0x1d88 +#define MV64340_PCI_0_CROSS_BAR_CONTROL_HIGH 0x1d0c +#define MV64340_PCI_1_CROSS_BAR_CONTROL_HIGH 0x1d8c +#define MV64340_PCI_0_CROSS_BAR_TIMEOUT 0x1d04 +#define MV64340_PCI_1_CROSS_BAR_TIMEOUT 0x1d84 +#define MV64340_PCI_0_SYNC_BARRIER_TRIGGER_REG 0x1D18 +#define MV64340_PCI_1_SYNC_BARRIER_TRIGGER_REG 0x1D98 +#define MV64340_PCI_0_SYNC_BARRIER_VIRTUAL_REG 0x1d10 +#define MV64340_PCI_1_SYNC_BARRIER_VIRTUAL_REG 0x1d90 +#define MV64340_PCI_0_P2P_CONFIG 0x1d14 +#define MV64340_PCI_1_P2P_CONFIG 0x1d94 + +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_0_LOW 0x1e00 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_0_HIGH 0x1e04 +#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_0 0x1e08 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_1_LOW 0x1e10 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_1_HIGH 0x1e14 +#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_1 0x1e18 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_2_LOW 0x1e20 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_2_HIGH 0x1e24 +#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_2 0x1e28 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_3_LOW 0x1e30 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_3_HIGH 0x1e34 +#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_3 0x1e38 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_4_LOW 0x1e40 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_4_HIGH 0x1e44 +#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_4 0x1e48 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_5_LOW 0x1e50 +#define MV64340_PCI_0_ACCESS_CONTROL_BASE_5_HIGH 0x1e54 +#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_5 0x1e58 + +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_0_LOW 0x1e80 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_0_HIGH 0x1e84 +#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_0 0x1e88 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_1_LOW 0x1e90 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_1_HIGH 0x1e94 +#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_1 0x1e98 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_2_LOW 0x1ea0 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_2_HIGH 0x1ea4 +#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_2 0x1ea8 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_3_LOW 0x1eb0 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_3_HIGH 0x1eb4 +#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_3 0x1eb8 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_4_LOW 0x1ec0 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_4_HIGH 0x1ec4 +#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_4 0x1ec8 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_5_LOW 0x1ed0 +#define MV64340_PCI_1_ACCESS_CONTROL_BASE_5_HIGH 0x1ed4 +#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_5 0x1ed8 + +/****************************************/ +/* PCI Configuration Access Registers */ +/****************************************/ + +#define MV64340_PCI_0_CONFIG_ADDR 0xcf8 +#define MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG 0xcfc +#define MV64340_PCI_1_CONFIG_ADDR 0xc78 +#define MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG 0xc7c +#define MV64340_PCI_0_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG 0xc34 +#define MV64340_PCI_1_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG 0xcb4 + +/****************************************/ +/* PCI Error Report Registers */ +/****************************************/ + +#define MV64340_PCI_0_SERR_MASK 0xc28 +#define MV64340_PCI_1_SERR_MASK 0xca8 +#define MV64340_PCI_0_ERROR_ADDR_LOW 0x1d40 +#define MV64340_PCI_1_ERROR_ADDR_LOW 0x1dc0 +#define MV64340_PCI_0_ERROR_ADDR_HIGH 0x1d44 +#define MV64340_PCI_1_ERROR_ADDR_HIGH 0x1dc4 +#define MV64340_PCI_0_ERROR_ATTRIBUTE 0x1d48 +#define MV64340_PCI_1_ERROR_ATTRIBUTE 0x1dc8 +#define MV64340_PCI_0_ERROR_COMMAND 0x1d50 +#define MV64340_PCI_1_ERROR_COMMAND 0x1dd0 +#define MV64340_PCI_0_ERROR_CAUSE 0x1d58 +#define MV64340_PCI_1_ERROR_CAUSE 0x1dd8 +#define MV64340_PCI_0_ERROR_MASK 0x1d5c +#define MV64340_PCI_1_ERROR_MASK 0x1ddc + +/****************************************/ +/* PCI Debug Registers */ +/****************************************/ + +#define MV64340_PCI_0_MMASK 0X1D24 +#define MV64340_PCI_1_MMASK 0X1DA4 + +/*********************************************/ +/* PCI Configuration, Function 0, Registers */ +/*********************************************/ + +#define MV64340_PCI_DEVICE_AND_VENDOR_ID 0x000 +#define MV64340_PCI_STATUS_AND_COMMAND 0x004 +#define MV64340_PCI_CLASS_CODE_AND_REVISION_ID 0x008 +#define MV64340_PCI_BIST_HEADER_TYPE_LATENCY_TIMER_CACHE_LINE 0x00C + +#define MV64340_PCI_SCS_0_BASE_ADDR_LOW 0x010 +#define MV64340_PCI_SCS_0_BASE_ADDR_HIGH 0x014 +#define MV64340_PCI_SCS_1_BASE_ADDR_LOW 0x018 +#define MV64340_PCI_SCS_1_BASE_ADDR_HIGH 0x01C +#define MV64340_PCI_INTERNAL_REG_MEM_MAPPED_BASE_ADDR_LOW 0x020 +#define MV64340_PCI_INTERNAL_REG_MEM_MAPPED_BASE_ADDR_HIGH 0x024 +#define MV64340_PCI_SUBSYSTEM_ID_AND_SUBSYSTEM_VENDOR_ID 0x02c +#define MV64340_PCI_EXPANSION_ROM_BASE_ADDR_REG 0x030 +#define MV64340_PCI_CAPABILTY_LIST_POINTER 0x034 +#define MV64340_PCI_INTERRUPT_PIN_AND_LINE 0x03C + /* capability list */ +#define MV64340_PCI_POWER_MANAGEMENT_CAPABILITY 0x040 +#define MV64340_PCI_POWER_MANAGEMENT_STATUS_AND_CONTROL 0x044 +#define MV64340_PCI_VPD_ADDR 0x048 +#define MV64340_PCI_VPD_DATA 0x04c +#define MV64340_PCI_MSI_MESSAGE_CONTROL 0x050 +#define MV64340_PCI_MSI_MESSAGE_ADDR 0x054 +#define MV64340_PCI_MSI_MESSAGE_UPPER_ADDR 0x058 +#define MV64340_PCI_MSI_MESSAGE_DATA 0x05c +#define MV64340_PCI_X_COMMAND 0x060 +#define MV64340_PCI_X_STATUS 0x064 +#define MV64340_PCI_COMPACT_PCI_HOT_SWAP 0x068 + +/***********************************************/ +/* PCI Configuration, Function 1, Registers */ +/***********************************************/ + +#define MV64340_PCI_SCS_2_BASE_ADDR_LOW 0x110 +#define MV64340_PCI_SCS_2_BASE_ADDR_HIGH 0x114 +#define MV64340_PCI_SCS_3_BASE_ADDR_LOW 0x118 +#define MV64340_PCI_SCS_3_BASE_ADDR_HIGH 0x11c +#define MV64340_PCI_INTERNAL_SRAM_BASE_ADDR_LOW 0x120 +#define MV64340_PCI_INTERNAL_SRAM_BASE_ADDR_HIGH 0x124 + +/***********************************************/ +/* PCI Configuration, Function 2, Registers */ +/***********************************************/ + +#define MV64340_PCI_DEVCS_0_BASE_ADDR_LOW 0x210 +#define MV64340_PCI_DEVCS_0_BASE_ADDR_HIGH 0x214 +#define MV64340_PCI_DEVCS_1_BASE_ADDR_LOW 0x218 +#define MV64340_PCI_DEVCS_1_BASE_ADDR_HIGH 0x21c +#define MV64340_PCI_DEVCS_2_BASE_ADDR_LOW 0x220 +#define MV64340_PCI_DEVCS_2_BASE_ADDR_HIGH 0x224 + +/***********************************************/ +/* PCI Configuration, Function 3, Registers */ +/***********************************************/ + +#define MV64340_PCI_DEVCS_3_BASE_ADDR_LOW 0x310 +#define MV64340_PCI_DEVCS_3_BASE_ADDR_HIGH 0x314 +#define MV64340_PCI_BOOT_CS_BASE_ADDR_LOW 0x318 +#define MV64340_PCI_BOOT_CS_BASE_ADDR_HIGH 0x31c +#define MV64340_PCI_CPU_BASE_ADDR_LOW 0x220 +#define MV64340_PCI_CPU_BASE_ADDR_HIGH 0x224 + +/***********************************************/ +/* PCI Configuration, Function 4, Registers */ +/***********************************************/ + +#define MV64340_PCI_P2P_MEM0_BASE_ADDR_LOW 0x410 +#define MV64340_PCI_P2P_MEM0_BASE_ADDR_HIGH 0x414 +#define MV64340_PCI_P2P_MEM1_BASE_ADDR_LOW 0x418 +#define MV64340_PCI_P2P_MEM1_BASE_ADDR_HIGH 0x41c +#define MV64340_PCI_P2P_I_O_BASE_ADDR 0x420 +#define MV64340_PCI_INTERNAL_REGS_I_O_MAPPED_BASE_ADDR 0x424 + +/****************************************/ +/* Messaging Unit Registers (I20) */ +/****************************************/ + +#define MV64340_I2O_INBOUND_MESSAGE_REG0_PCI_0_SIDE 0x010 +#define MV64340_I2O_INBOUND_MESSAGE_REG1_PCI_0_SIDE 0x014 +#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_PCI_0_SIDE 0x018 +#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_PCI_0_SIDE 0x01C +#define MV64340_I2O_INBOUND_DOORBELL_REG_PCI_0_SIDE 0x020 +#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_PCI_0_SIDE 0x024 +#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_PCI_0_SIDE 0x028 +#define MV64340_I2O_OUTBOUND_DOORBELL_REG_PCI_0_SIDE 0x02C +#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_PCI_0_SIDE 0x030 +#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_PCI_0_SIDE 0x034 +#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_0_SIDE 0x040 +#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_0_SIDE 0x044 +#define MV64340_I2O_QUEUE_CONTROL_REG_PCI_0_SIDE 0x050 +#define MV64340_I2O_QUEUE_BASE_ADDR_REG_PCI_0_SIDE 0x054 +#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_PCI_0_SIDE 0x060 +#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_PCI_0_SIDE 0x064 +#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_PCI_0_SIDE 0x068 +#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_PCI_0_SIDE 0x06C +#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_PCI_0_SIDE 0x070 +#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_PCI_0_SIDE 0x074 +#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_PCI_0_SIDE 0x0F8 +#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_PCI_0_SIDE 0x0FC + +#define MV64340_I2O_INBOUND_MESSAGE_REG0_PCI_1_SIDE 0x090 +#define MV64340_I2O_INBOUND_MESSAGE_REG1_PCI_1_SIDE 0x094 +#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_PCI_1_SIDE 0x098 +#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_PCI_1_SIDE 0x09C +#define MV64340_I2O_INBOUND_DOORBELL_REG_PCI_1_SIDE 0x0A0 +#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_PCI_1_SIDE 0x0A4 +#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_PCI_1_SIDE 0x0A8 +#define MV64340_I2O_OUTBOUND_DOORBELL_REG_PCI_1_SIDE 0x0AC +#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_PCI_1_SIDE 0x0B0 +#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_PCI_1_SIDE 0x0B4 +#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_1_SIDE 0x0C0 +#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_1_SIDE 0x0C4 +#define MV64340_I2O_QUEUE_CONTROL_REG_PCI_1_SIDE 0x0D0 +#define MV64340_I2O_QUEUE_BASE_ADDR_REG_PCI_1_SIDE 0x0D4 +#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_PCI_1_SIDE 0x0E0 +#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_PCI_1_SIDE 0x0E4 +#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_PCI_1_SIDE 0x0E8 +#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_PCI_1_SIDE 0x0EC +#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_PCI_1_SIDE 0x0F0 +#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_PCI_1_SIDE 0x0F4 +#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_PCI_1_SIDE 0x078 +#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_PCI_1_SIDE 0x07C + +#define MV64340_I2O_INBOUND_MESSAGE_REG0_CPU0_SIDE 0x1C10 +#define MV64340_I2O_INBOUND_MESSAGE_REG1_CPU0_SIDE 0x1C14 +#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_CPU0_SIDE 0x1C18 +#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_CPU0_SIDE 0x1C1C +#define MV64340_I2O_INBOUND_DOORBELL_REG_CPU0_SIDE 0x1C20 +#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_CPU0_SIDE 0x1C24 +#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_CPU0_SIDE 0x1C28 +#define MV64340_I2O_OUTBOUND_DOORBELL_REG_CPU0_SIDE 0x1C2C +#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_CPU0_SIDE 0x1C30 +#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_CPU0_SIDE 0x1C34 +#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_CPU0_SIDE 0x1C40 +#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_CPU0_SIDE 0x1C44 +#define MV64340_I2O_QUEUE_CONTROL_REG_CPU0_SIDE 0x1C50 +#define MV64340_I2O_QUEUE_BASE_ADDR_REG_CPU0_SIDE 0x1C54 +#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_CPU0_SIDE 0x1C60 +#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_CPU0_SIDE 0x1C64 +#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_CPU0_SIDE 0x1C68 +#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_CPU0_SIDE 0x1C6C +#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_CPU0_SIDE 0x1C70 +#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_CPU0_SIDE 0x1C74 +#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_CPU0_SIDE 0x1CF8 +#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_CPU0_SIDE 0x1CFC +#define MV64340_I2O_INBOUND_MESSAGE_REG0_CPU1_SIDE 0x1C90 +#define MV64340_I2O_INBOUND_MESSAGE_REG1_CPU1_SIDE 0x1C94 +#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_CPU1_SIDE 0x1C98 +#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_CPU1_SIDE 0x1C9C +#define MV64340_I2O_INBOUND_DOORBELL_REG_CPU1_SIDE 0x1CA0 +#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_CPU1_SIDE 0x1CA4 +#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_CPU1_SIDE 0x1CA8 +#define MV64340_I2O_OUTBOUND_DOORBELL_REG_CPU1_SIDE 0x1CAC +#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_CPU1_SIDE 0x1CB0 +#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_CPU1_SIDE 0x1CB4 +#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_CPU1_SIDE 0x1CC0 +#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_CPU1_SIDE 0x1CC4 +#define MV64340_I2O_QUEUE_CONTROL_REG_CPU1_SIDE 0x1CD0 +#define MV64340_I2O_QUEUE_BASE_ADDR_REG_CPU1_SIDE 0x1CD4 +#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_CPU1_SIDE 0x1CE0 +#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_CPU1_SIDE 0x1CE4 +#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_CPU1_SIDE 0x1CE8 +#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_CPU1_SIDE 0x1CEC +#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_CPU1_SIDE 0x1CF0 +#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_CPU1_SIDE 0x1CF4 +#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_CPU1_SIDE 0x1C78 +#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_CPU1_SIDE 0x1C7C + +/****************************************/ +/* Ethernet Unit Registers */ +/****************************************/ + +/*******************************************/ +/* CUNIT Registers */ +/*******************************************/ + + /* Address Decoding Register Map */ + +#define MV64340_CUNIT_BASE_ADDR_REG0 0xf200 +#define MV64340_CUNIT_BASE_ADDR_REG1 0xf208 +#define MV64340_CUNIT_BASE_ADDR_REG2 0xf210 +#define MV64340_CUNIT_BASE_ADDR_REG3 0xf218 +#define MV64340_CUNIT_SIZE0 0xf204 +#define MV64340_CUNIT_SIZE1 0xf20c +#define MV64340_CUNIT_SIZE2 0xf214 +#define MV64340_CUNIT_SIZE3 0xf21c +#define MV64340_CUNIT_HIGH_ADDR_REMAP_REG0 0xf240 +#define MV64340_CUNIT_HIGH_ADDR_REMAP_REG1 0xf244 +#define MV64340_CUNIT_BASE_ADDR_ENABLE_REG 0xf250 +#define MV64340_MPSC0_ACCESS_PROTECTION_REG 0xf254 +#define MV64340_MPSC1_ACCESS_PROTECTION_REG 0xf258 +#define MV64340_CUNIT_INTERNAL_SPACE_BASE_ADDR_REG 0xf25C + + /* Error Report Registers */ + +#define MV64340_CUNIT_INTERRUPT_CAUSE_REG 0xf310 +#define MV64340_CUNIT_INTERRUPT_MASK_REG 0xf314 +#define MV64340_CUNIT_ERROR_ADDR 0xf318 + + /* Cunit Control Registers */ + +#define MV64340_CUNIT_ARBITER_CONTROL_REG 0xf300 +#define MV64340_CUNIT_CONFIG_REG 0xb40c +#define MV64340_CUNIT_CRROSBAR_TIMEOUT_REG 0xf304 + + /* Cunit Debug Registers */ + +#define MV64340_CUNIT_DEBUG_LOW 0xf340 +#define MV64340_CUNIT_DEBUG_HIGH 0xf344 +#define MV64340_CUNIT_MMASK 0xf380 + + /* MPSCs Clocks Routing Registers */ + +#define MV64340_MPSC_ROUTING_REG 0xb400 +#define MV64340_MPSC_RX_CLOCK_ROUTING_REG 0xb404 +#define MV64340_MPSC_TX_CLOCK_ROUTING_REG 0xb408 + + /* MPSCs Interrupts Registers */ + +#define MV64340_MPSC_CAUSE_REG(port) (0xb804 + (port << 3)) +#define MV64340_MPSC_MASK_REG(port) (0xb884 + (port << 3)) + +#define MV64340_MPSC_MAIN_CONFIG_LOW(port) (0x8000 + (port << 12)) +#define MV64340_MPSC_MAIN_CONFIG_HIGH(port) (0x8004 + (port << 12)) +#define MV64340_MPSC_PROTOCOL_CONFIG(port) (0x8008 + (port << 12)) +#define MV64340_MPSC_CHANNEL_REG1(port) (0x800c + (port << 12)) +#define MV64340_MPSC_CHANNEL_REG2(port) (0x8010 + (port << 12)) +#define MV64340_MPSC_CHANNEL_REG3(port) (0x8014 + (port << 12)) +#define MV64340_MPSC_CHANNEL_REG4(port) (0x8018 + (port << 12)) +#define MV64340_MPSC_CHANNEL_REG5(port) (0x801c + (port << 12)) +#define MV64340_MPSC_CHANNEL_REG6(port) (0x8020 + (port << 12)) +#define MV64340_MPSC_CHANNEL_REG7(port) (0x8024 + (port << 12)) +#define MV64340_MPSC_CHANNEL_REG8(port) (0x8028 + (port << 12)) +#define MV64340_MPSC_CHANNEL_REG9(port) (0x802c + (port << 12)) +#define MV64340_MPSC_CHANNEL_REG10(port) (0x8030 + (port << 12)) + + /* MPSC0 Registers */ + + +/***************************************/ +/* SDMA Registers */ +/***************************************/ + +#define MV64340_SDMA_CONFIG_REG(channel) (0x4000 + (channel << 13)) +#define MV64340_SDMA_COMMAND_REG(channel) (0x4008 + (channel << 13)) +#define MV64340_SDMA_CURRENT_RX_DESCRIPTOR_POINTER(channel) (0x4810 + (channel << 13)) +#define MV64340_SDMA_CURRENT_TX_DESCRIPTOR_POINTER(channel) (0x4c10 + (channel << 13)) +#define MV64340_SDMA_FIRST_TX_DESCRIPTOR_POINTER(channel) (0x4c14 + (channel << 13)) + +#define MV64340_SDMA_CAUSE_REG 0xb800 +#define MV64340_SDMA_MASK_REG 0xb880 + +/* BRG Interrupts */ + +#define MV64340_BRG_CONFIG_REG(brg) (0xb200 + (brg << 3)) +#define MV64340_BRG_BAUDE_TUNING_REG(brg) (0xb208 + (brg << 3)) +#define MV64340_BRG_CAUSE_REG 0xb834 +#define MV64340_BRG_MASK_REG 0xb8b4 + +/****************************************/ +/* DMA Channel Control */ +/****************************************/ + +#define MV64340_DMA_CHANNEL0_CONTROL 0x840 +#define MV64340_DMA_CHANNEL0_CONTROL_HIGH 0x880 +#define MV64340_DMA_CHANNEL1_CONTROL 0x844 +#define MV64340_DMA_CHANNEL1_CONTROL_HIGH 0x884 +#define MV64340_DMA_CHANNEL2_CONTROL 0x848 +#define MV64340_DMA_CHANNEL2_CONTROL_HIGH 0x888 +#define MV64340_DMA_CHANNEL3_CONTROL 0x84C +#define MV64340_DMA_CHANNEL3_CONTROL_HIGH 0x88C + + +/****************************************/ +/* IDMA Registers */ +/****************************************/ + +#define MV64340_DMA_CHANNEL0_BYTE_COUNT 0x800 +#define MV64340_DMA_CHANNEL1_BYTE_COUNT 0x804 +#define MV64340_DMA_CHANNEL2_BYTE_COUNT 0x808 +#define MV64340_DMA_CHANNEL3_BYTE_COUNT 0x80C +#define MV64340_DMA_CHANNEL0_SOURCE_ADDR 0x810 +#define MV64340_DMA_CHANNEL1_SOURCE_ADDR 0x814 +#define MV64340_DMA_CHANNEL2_SOURCE_ADDR 0x818 +#define MV64340_DMA_CHANNEL3_SOURCE_ADDR 0x81c +#define MV64340_DMA_CHANNEL0_DESTINATION_ADDR 0x820 +#define MV64340_DMA_CHANNEL1_DESTINATION_ADDR 0x824 +#define MV64340_DMA_CHANNEL2_DESTINATION_ADDR 0x828 +#define MV64340_DMA_CHANNEL3_DESTINATION_ADDR 0x82C +#define MV64340_DMA_CHANNEL0_NEXT_DESCRIPTOR_POINTER 0x830 +#define MV64340_DMA_CHANNEL1_NEXT_DESCRIPTOR_POINTER 0x834 +#define MV64340_DMA_CHANNEL2_NEXT_DESCRIPTOR_POINTER 0x838 +#define MV64340_DMA_CHANNEL3_NEXT_DESCRIPTOR_POINTER 0x83C +#define MV64340_DMA_CHANNEL0_CURRENT_DESCRIPTOR_POINTER 0x870 +#define MV64340_DMA_CHANNEL1_CURRENT_DESCRIPTOR_POINTER 0x874 +#define MV64340_DMA_CHANNEL2_CURRENT_DESCRIPTOR_POINTER 0x878 +#define MV64340_DMA_CHANNEL3_CURRENT_DESCRIPTOR_POINTER 0x87C + + /* IDMA Address Decoding Base Address Registers */ + +#define MV64340_DMA_BASE_ADDR_REG0 0xa00 +#define MV64340_DMA_BASE_ADDR_REG1 0xa08 +#define MV64340_DMA_BASE_ADDR_REG2 0xa10 +#define MV64340_DMA_BASE_ADDR_REG3 0xa18 +#define MV64340_DMA_BASE_ADDR_REG4 0xa20 +#define MV64340_DMA_BASE_ADDR_REG5 0xa28 +#define MV64340_DMA_BASE_ADDR_REG6 0xa30 +#define MV64340_DMA_BASE_ADDR_REG7 0xa38 + + /* IDMA Address Decoding Size Address Register */ + +#define MV64340_DMA_SIZE_REG0 0xa04 +#define MV64340_DMA_SIZE_REG1 0xa0c +#define MV64340_DMA_SIZE_REG2 0xa14 +#define MV64340_DMA_SIZE_REG3 0xa1c +#define MV64340_DMA_SIZE_REG4 0xa24 +#define MV64340_DMA_SIZE_REG5 0xa2c +#define MV64340_DMA_SIZE_REG6 0xa34 +#define MV64340_DMA_SIZE_REG7 0xa3C + + /* IDMA Address Decoding High Address Remap and Access Protection Registers */ + +#define MV64340_DMA_HIGH_ADDR_REMAP_REG0 0xa60 +#define MV64340_DMA_HIGH_ADDR_REMAP_REG1 0xa64 +#define MV64340_DMA_HIGH_ADDR_REMAP_REG2 0xa68 +#define MV64340_DMA_HIGH_ADDR_REMAP_REG3 0xa6C +#define MV64340_DMA_BASE_ADDR_ENABLE_REG 0xa80 +#define MV64340_DMA_CHANNEL0_ACCESS_PROTECTION_REG 0xa70 +#define MV64340_DMA_CHANNEL1_ACCESS_PROTECTION_REG 0xa74 +#define MV64340_DMA_CHANNEL2_ACCESS_PROTECTION_REG 0xa78 +#define MV64340_DMA_CHANNEL3_ACCESS_PROTECTION_REG 0xa7c +#define MV64340_DMA_ARBITER_CONTROL 0x860 +#define MV64340_DMA_CROSS_BAR_TIMEOUT 0x8d0 + + /* IDMA Headers Retarget Registers */ + +#define MV64340_DMA_HEADERS_RETARGET_CONTROL 0xa84 +#define MV64340_DMA_HEADERS_RETARGET_BASE 0xa88 + + /* IDMA Interrupt Register */ + +#define MV64340_DMA_INTERRUPT_CAUSE_REG 0x8c0 +#define MV64340_DMA_INTERRUPT_CAUSE_MASK 0x8c4 +#define MV64340_DMA_ERROR_ADDR 0x8c8 +#define MV64340_DMA_ERROR_SELECT 0x8cc + + /* IDMA Debug Register ( for internal use ) */ + +#define MV64340_DMA_DEBUG_LOW 0x8e0 +#define MV64340_DMA_DEBUG_HIGH 0x8e4 +#define MV64340_DMA_SPARE 0xA8C + +/****************************************/ +/* Timer_Counter */ +/****************************************/ + +#define MV64340_TIMER_COUNTER0 0x850 +#define MV64340_TIMER_COUNTER1 0x854 +#define MV64340_TIMER_COUNTER2 0x858 +#define MV64340_TIMER_COUNTER3 0x85C +#define MV64340_TIMER_COUNTER_0_3_CONTROL 0x864 +#define MV64340_TIMER_COUNTER_0_3_INTERRUPT_CAUSE 0x868 +#define MV64340_TIMER_COUNTER_0_3_INTERRUPT_MASK 0x86c + +/****************************************/ +/* Watchdog registers */ +/****************************************/ + +#define MV64340_WATCHDOG_CONFIG_REG 0xb410 +#define MV64340_WATCHDOG_VALUE_REG 0xb414 + +/****************************************/ +/* I2C Registers */ +/****************************************/ + +#define MV64XXX_I2C_OFFSET 0xc000 +#define MV64XXX_I2C_REG_BLOCK_SIZE 0x0020 + +/****************************************/ +/* GPP Interface Registers */ +/****************************************/ + +#define MV64340_GPP_IO_CONTROL 0xf100 +#define MV64340_GPP_LEVEL_CONTROL 0xf110 +#define MV64340_GPP_VALUE 0xf104 +#define MV64340_GPP_INTERRUPT_CAUSE 0xf108 +#define MV64340_GPP_INTERRUPT_MASK0 0xf10c +#define MV64340_GPP_INTERRUPT_MASK1 0xf114 +#define MV64340_GPP_VALUE_SET 0xf118 +#define MV64340_GPP_VALUE_CLEAR 0xf11c + +/****************************************/ +/* Interrupt Controller Registers */ +/****************************************/ + +/****************************************/ +/* Interrupts */ +/****************************************/ + +#define MV64340_MAIN_INTERRUPT_CAUSE_LOW 0x004 +#define MV64340_MAIN_INTERRUPT_CAUSE_HIGH 0x00c +#define MV64340_CPU_INTERRUPT0_MASK_LOW 0x014 +#define MV64340_CPU_INTERRUPT0_MASK_HIGH 0x01c +#define MV64340_CPU_INTERRUPT0_SELECT_CAUSE 0x024 +#define MV64340_CPU_INTERRUPT1_MASK_LOW 0x034 +#define MV64340_CPU_INTERRUPT1_MASK_HIGH 0x03c +#define MV64340_CPU_INTERRUPT1_SELECT_CAUSE 0x044 +#define MV64340_INTERRUPT0_MASK_0_LOW 0x054 +#define MV64340_INTERRUPT0_MASK_0_HIGH 0x05c +#define MV64340_INTERRUPT0_SELECT_CAUSE 0x064 +#define MV64340_INTERRUPT1_MASK_0_LOW 0x074 +#define MV64340_INTERRUPT1_MASK_0_HIGH 0x07c +#define MV64340_INTERRUPT1_SELECT_CAUSE 0x084 + +/****************************************/ +/* MPP Interface Registers */ +/****************************************/ + +#define MV64340_MPP_CONTROL0 0xf000 +#define MV64340_MPP_CONTROL1 0xf004 +#define MV64340_MPP_CONTROL2 0xf008 +#define MV64340_MPP_CONTROL3 0xf00c + +/****************************************/ +/* Serial Initialization registers */ +/****************************************/ + +#define MV64340_SERIAL_INIT_LAST_DATA 0xf324 +#define MV64340_SERIAL_INIT_CONTROL 0xf328 +#define MV64340_SERIAL_INIT_STATUS 0xf32c + +#endif /* ASM_MV643XX_H */ diff --git a/hw/pci-host/pnv_phb4.c b/hw/pci-host/pnv_phb4.c index 54f57c660a..5c375a9f28 100644 --- a/hw/pci-host/pnv_phb4.c +++ b/hw/pci-host/pnv_phb4.c @@ -392,7 +392,7 @@ static void pnv_phb4_ioda_write(PnvPHB4 *phb, uint64_t val) v &= 0xffffffffffff0000ull; v |= 0x000000000000cfffull & val; } - *tptr = val; + *tptr = v; break; } case IODA3_TBL_MBT: diff --git a/hw/pci-host/ppce500.c b/hw/pci-host/ppce500.c index 5ad1424b31..89c1b53dd7 100644 --- a/hw/pci-host/ppce500.c +++ b/hw/pci-host/ppce500.c @@ -415,7 +415,6 @@ static const VMStateDescription vmstate_ppce500_pci = { } }; -#include "exec/address-spaces.h" static void e500_pcihost_bridge_realize(PCIDevice *d, Error **errp) { diff --git a/hw/pci-host/q35.c b/hw/pci-host/q35.c index 2eb729dff5..ab5a47aff5 100644 --- a/hw/pci-host/q35.c +++ b/hw/pci-host/q35.c @@ -29,6 +29,7 @@ */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "hw/i386/pc.h" #include "hw/pci-host/q35.h" #include "hw/qdev-properties.h" @@ -64,6 +65,8 @@ static void q35_host_realize(DeviceState *dev, Error **errp) s->mch.address_space_io, 0, TYPE_PCIE_BUS); PC_MACHINE(qdev_get_machine())->bus = pci->bus; + pci->bypass_iommu = + PC_MACHINE(qdev_get_machine())->default_bus_bypass_iommu; qdev_realize(DEVICE(&s->mch), BUS(pci->bus), &error_fatal); } @@ -318,6 +321,8 @@ static void mch_update_pciexbar(MCHPCIState *mch) addr_mask |= MCH_HOST_BRIDGE_PCIEXBAR_64ADMSK; break; case MCH_HOST_BRIDGE_PCIEXBAR_LENGTH_RVD: + qemu_log_mask(LOG_GUEST_ERROR, "Q35: Reserved PCIEXBAR LENGTH\n"); + return; default: abort(); } diff --git a/hw/pci-host/prep.c b/hw/pci-host/raven.c similarity index 97% rename from hw/pci-host/prep.c rename to hw/pci-host/raven.c index 0a9162fba9..3be27f0a14 100644 --- a/hw/pci-host/prep.c +++ b/hw/pci-host/raven.c @@ -38,7 +38,6 @@ #include "hw/irq.h" #include "hw/loader.h" #include "hw/or-irq.h" -#include "exec/address-spaces.h" #include "elf.h" #include "qom/object.h" @@ -82,6 +81,8 @@ struct PRePPCIState { #define BIOS_SIZE (1 * MiB) +#define PCI_IO_BASE_ADDR 0x80000000 /* Physical address on main bus */ + static inline uint32_t raven_pci_io_config(hwaddr addr) { int i; @@ -159,7 +160,7 @@ static uint64_t raven_io_read(void *opaque, hwaddr addr, uint8_t buf[4]; addr = raven_io_address(s, addr); - address_space_read(&s->pci_io_as, addr + 0x80000000, + address_space_read(&s->pci_io_as, addr + PCI_IO_BASE_ADDR, MEMTXATTRS_UNSPECIFIED, buf, size); if (size == 1) { @@ -191,7 +192,7 @@ static void raven_io_write(void *opaque, hwaddr addr, g_assert_not_reached(); } - address_space_write(&s->pci_io_as, addr + 0x80000000, + address_space_write(&s->pci_io_as, addr + PCI_IO_BASE_ADDR, MEMTXATTRS_UNSPECIFIED, buf, size); } @@ -294,8 +295,9 @@ static void raven_pcihost_initfn(Object *obj) address_space_init(&s->pci_io_as, &s->pci_io, "raven-io"); /* CPU address space */ - memory_region_add_subregion(address_space_mem, 0x80000000, &s->pci_io); - memory_region_add_subregion_overlap(address_space_mem, 0x80000000, + memory_region_add_subregion(address_space_mem, PCI_IO_BASE_ADDR, + &s->pci_io); + memory_region_add_subregion_overlap(address_space_mem, PCI_IO_BASE_ADDR, &s->pci_io_non_contiguous, 1); memory_region_add_subregion(address_space_mem, 0xc0000000, &s->pci_memory); pci_root_bus_new_inplace(&s->pci_bus, sizeof(s->pci_bus), DEVICE(obj), NULL, diff --git a/hw/pci-host/sabre.c b/hw/pci-host/sabre.c index f41a0cc301..949ecc21f2 100644 --- a/hw/pci-host/sabre.c +++ b/hw/pci-host/sabre.c @@ -34,7 +34,6 @@ #include "hw/irq.h" #include "hw/pci-bridge/simba.h" #include "hw/pci-host/sabre.h" -#include "exec/address-spaces.h" #include "qapi/error.h" #include "qemu/log.h" #include "qemu/module.h" diff --git a/hw/pci-host/sh_pci.c b/hw/pci-host/sh_pci.c index 734892f47c..08c1562e22 100644 --- a/hw/pci-host/sh_pci.c +++ b/hw/pci-host/sh_pci.c @@ -30,7 +30,6 @@ #include "hw/pci/pci_host.h" #include "qemu/bswap.h" #include "qemu/module.h" -#include "exec/address-spaces.h" #include "qom/object.h" #define TYPE_SH_PCI_HOST_BRIDGE "sh_pci" diff --git a/hw/pci-host/trace-events b/hw/pci-host/trace-events index 7d8063ac42..630e9fcc5e 100644 --- a/hw/pci-host/trace-events +++ b/hw/pci-host/trace-events @@ -1,8 +1,17 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. + +# bonito.c +bonito_spciconf_small_access(uint64_t addr, unsigned size) "PCI config address is smaller then 32-bit, addr: 0x%"PRIx64", size: %u" # grackle.c grackle_set_irq(int irq_num, int level) "set_irq num %d level %d" +# mv64361.c +mv64361_region_map(const char *name, uint64_t poffs, uint64_t size, uint64_t moffs) "Mapping %s 0x%"PRIx64"+0x%"PRIx64" @ 0x%"PRIx64 +mv64361_region_enable(const char *op, int num) "Should %s region %d" +mv64361_reg_read(uint64_t addr, uint32_t val) "0x%"PRIx64" -> 0x%x" +mv64361_reg_write(uint64_t addr, uint64_t val) "0x%"PRIx64" <- 0x%"PRIx64 + # sabre.c sabre_set_request(int irq_num) "request irq %d" sabre_clear_request(int irq_num) "clear request irq %d" diff --git a/hw/pci/pci.c b/hw/pci/pci.c index 8f35e13a0c..23d2ae2ab2 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -45,7 +45,6 @@ #include "trace.h" #include "hw/pci/msi.h" #include "hw/pci/msix.h" -#include "exec/address-spaces.h" #include "hw/hotplug.h" #include "hw/boards.h" #include "qapi/error.h" @@ -417,6 +416,22 @@ const char *pci_root_bus_path(PCIDevice *dev) return rootbus->qbus.name; } +bool pci_bus_bypass_iommu(PCIBus *bus) +{ + PCIBus *rootbus = bus; + PCIHostState *host_bridge; + + if (!pci_bus_is_root(bus)) { + rootbus = pci_device_root_bus(bus->parent_dev); + } + + host_bridge = PCI_HOST_BRIDGE(rootbus->qbus.parent); + + assert(host_bridge->bus == rootbus); + + return host_bridge->bypass_iommu; +} + static void pci_root_bus_init(PCIBus *bus, DeviceState *parent, MemoryRegion *address_space_mem, MemoryRegion *address_space_io, @@ -522,6 +537,22 @@ int pci_bus_num(PCIBus *s) return PCI_BUS_GET_CLASS(s)->bus_num(s); } +/* Returns the min and max bus numbers of a PCI bus hierarchy */ +void pci_bus_range(PCIBus *bus, int *min_bus, int *max_bus) +{ + int i; + *min_bus = *max_bus = pci_bus_num(bus); + + for (i = 0; i < ARRAY_SIZE(bus->devices); ++i) { + PCIDevice *dev = bus->devices[i]; + + if (dev && PCI_DEVICE_GET_CLASS(dev)->is_bridge) { + *min_bus = MIN(*min_bus, dev->config[PCI_SECONDARY_BUS]); + *max_bus = MAX(*max_bus, dev->config[PCI_SUBORDINATE_BUS]); + } + } +} + int pci_bus_numa_node(PCIBus *bus) { return PCI_BUS_GET_CLASS(bus)->numa_node(bus); @@ -2719,7 +2750,7 @@ AddressSpace *pci_device_iommu_address_space(PCIDevice *dev) iommu_bus = parent_bus; } - if (iommu_bus && iommu_bus->iommu_fn) { + if (!pci_bus_bypass_iommu(bus) && iommu_bus && iommu_bus->iommu_fn) { return iommu_bus->iommu_fn(bus, iommu_bus->iommu_opaque, devfn); } return &address_space_memory; diff --git a/hw/pci/pci_host.c b/hw/pci/pci_host.c index 8ca5fadcbd..cf02f0d6a5 100644 --- a/hw/pci/pci_host.c +++ b/hw/pci/pci_host.c @@ -222,6 +222,7 @@ const VMStateDescription vmstate_pcihost = { static Property pci_host_properties_common[] = { DEFINE_PROP_BOOL("x-config-reg-migration-enabled", PCIHostState, mig_enabled, true), + DEFINE_PROP_BOOL("bypass-iommu", PCIHostState, bypass_iommu, false), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c index fd0fa157e8..6e95d82903 100644 --- a/hw/pci/pcie.c +++ b/hw/pci/pcie.c @@ -529,7 +529,13 @@ void pcie_cap_slot_init(PCIDevice *dev, PCIESlot *s) PCI_EXP_SLTCAP_PIP | PCI_EXP_SLTCAP_AIP | PCI_EXP_SLTCAP_ABP); - if (s->hotplug) { + + /* + * Enable native hot-plug on all hot-plugged bridges unless + * hot-plug is disabled on the slot. + */ + if (s->hotplug && + (s->native_hotplug || DEVICE(dev)->hotplugged)) { pci_long_test_and_set_mask(dev->config + pos + PCI_EXP_SLTCAP, PCI_EXP_SLTCAP_HPS | PCI_EXP_SLTCAP_HPC); diff --git a/hw/pci/pcie_host.c b/hw/pci/pcie_host.c index 3534006f99..5abbe83220 100644 --- a/hw/pci/pcie_host.c +++ b/hw/pci/pcie_host.c @@ -23,7 +23,6 @@ #include "hw/pci/pci.h" #include "hw/pci/pcie_host.h" #include "qemu/module.h" -#include "exec/address-spaces.h" /* a helper function to get a PCIDevice for a given mmconfig address */ static inline PCIDevice *pcie_dev_find_by_mmcfg_addr(PCIBus *s, diff --git a/hw/pci/pcie_port.c b/hw/pci/pcie_port.c index eb563ad435..da850e8dde 100644 --- a/hw/pci/pcie_port.c +++ b/hw/pci/pcie_port.c @@ -148,6 +148,7 @@ static Property pcie_slot_props[] = { DEFINE_PROP_UINT8("chassis", PCIESlot, chassis, 0), DEFINE_PROP_UINT16("slot", PCIESlot, slot, 0), DEFINE_PROP_BOOL("hotplug", PCIESlot, hotplug, true), + DEFINE_PROP_BOOL("native-hotplug", PCIESlot, native_hotplug, true), DEFINE_PROP_END_OF_LIST() }; diff --git a/hw/pci/trace-events b/hw/pci/trace-events index def4b3926d..fc777d0b5e 100644 --- a/hw/pci/trace-events +++ b/hw/pci/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pci.c pci_update_mappings_del(void *d, uint32_t bus, uint32_t slot, uint32_t func, int bar, uint64_t addr, uint64_t size) "d=%p %02x:%02x.%x %d,0x%"PRIx64"+0x%"PRIx64 diff --git a/hw/pcmcia/meson.build b/hw/pcmcia/meson.build index ab50bd325d..51f2512b8e 100644 --- a/hw/pcmcia/meson.build +++ b/hw/pcmcia/meson.build @@ -1,2 +1,2 @@ -softmmu_ss.add(files('pcmcia.c')) +softmmu_ss.add(when: 'CONFIG_PCMCIA', if_true: files('pcmcia.c')) softmmu_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx.c')) diff --git a/hw/ppc/Kconfig b/hw/ppc/Kconfig index d11dc30509..400511c6b7 100644 --- a/hw/ppc/Kconfig +++ b/hw/ppc/Kconfig @@ -3,6 +3,7 @@ config PSERIES imply PCI_DEVICES imply TEST_DEVICES imply VIRTIO_VGA + imply NVDIMM select DIMM select PCI select SPAPR_VSCSI @@ -12,6 +13,7 @@ config PSERIES select MSI_NONBROKEN select FDT_PPC select CHRP_NVRAM + select VOF config SPAPR_RNG bool @@ -68,12 +70,23 @@ config SAM460EX select USB_OHCI select FDT_PPC +config PEGASOS2 + bool + select MV64361 + select VT82C686 + select IDE_VIA + select SMBUS_EEPROM + select VOF +# This should come with VT82C686 + select ACPI_X86 + imply ATI_VGA + config PREP bool imply PCI_DEVICES imply TEST_DEVICES select CS4231A - select PREP_PCI + select RAVEN_PCI select I82378 select LSI_SCSI_PCI select M48T59 @@ -118,6 +131,7 @@ config E500 select SERIAL select MPC_I2C select FDT_PPC + select DS1338 config VIRTEX bool @@ -134,3 +148,6 @@ config FW_CFG_PPC config FDT_PPC bool + +config VOF + bool diff --git a/hw/ppc/e500.c b/hw/ppc/e500.c index 79467ac512..95451414dd 100644 --- a/hw/ppc/e500.c +++ b/hw/ppc/e500.c @@ -25,7 +25,6 @@ #include "qemu/config-file.h" #include "hw/char/serial.h" #include "hw/pci/pci.h" -#include "hw/boards.h" #include "sysemu/sysemu.h" #include "sysemu/kvm.h" #include "sysemu/reset.h" @@ -39,7 +38,6 @@ #include "hw/loader.h" #include "elf.h" #include "hw/sysbus.h" -#include "exec/address-spaces.h" #include "qemu/host-utils.h" #include "qemu/option.h" #include "hw/pci-host/ppce500.h" diff --git a/hw/ppc/mac_newworld.c b/hw/ppc/mac_newworld.c index 2175962846..7bb7ac3997 100644 --- a/hw/ppc/mac_newworld.c +++ b/hw/ppc/mac_newworld.c @@ -58,7 +58,6 @@ #include "hw/pci/pci.h" #include "net/net.h" #include "sysemu/sysemu.h" -#include "hw/boards.h" #include "hw/nvram/fw_cfg.h" #include "hw/char/escc.h" #include "hw/misc/macio/macio.h" @@ -71,7 +70,6 @@ #include "sysemu/reset.h" #include "kvm_ppc.h" #include "hw/usb.h" -#include "exec/address-spaces.h" #include "hw/sysbus.h" #include "trace.h" @@ -157,6 +155,10 @@ static void ppc_core99_init(MachineState *machine) } /* allocate RAM */ + if (machine->ram_size > 2 * GiB) { + error_report("RAM size more than 2 GiB is not supported"); + exit(1); + } memory_region_add_subregion(get_system_memory(), 0, machine->ram); /* allocate and load firmware ROM */ diff --git a/hw/ppc/mac_oldworld.c b/hw/ppc/mac_oldworld.c index 963d247f5f..de2be960e6 100644 --- a/hw/ppc/mac_oldworld.c +++ b/hw/ppc/mac_oldworld.c @@ -38,7 +38,6 @@ #include "hw/isa/isa.h" #include "hw/pci/pci.h" #include "hw/pci/pci_host.h" -#include "hw/boards.h" #include "hw/nvram/fw_cfg.h" #include "hw/char/escc.h" #include "hw/misc/macio/macio.h" @@ -49,7 +48,6 @@ #include "sysemu/kvm.h" #include "sysemu/reset.h" #include "kvm_ppc.h" -#include "exec/address-spaces.h" #define MAX_IDE_BUS 2 #define CFG_ADDR 0xf0000510 diff --git a/hw/ppc/meson.build b/hw/ppc/meson.build index 218631c883..aa4c8e6a2e 100644 --- a/hw/ppc/meson.build +++ b/hw/ppc/meson.build @@ -29,6 +29,9 @@ ppc_ss.add(when: 'CONFIG_PSERIES', if_true: files( 'spapr_numa.c', 'pef.c', )) +ppc_ss.add(when: ['CONFIG_PSERIES', 'CONFIG_TCG'], if_true: files( + 'spapr_softmmu.c', +)) ppc_ss.add(when: 'CONFIG_SPAPR_RNG', if_true: files('spapr_rng.c')) ppc_ss.add(when: ['CONFIG_PSERIES', 'CONFIG_LINUX'], if_true: files( 'spapr_pci_vfio.c', @@ -78,5 +81,10 @@ ppc_ss.add(when: 'CONFIG_E500', if_true: files( )) # PowerPC 440 Xilinx ML507 reference board. ppc_ss.add(when: 'CONFIG_VIRTEX', if_true: files('virtex_ml507.c')) +# Pegasos2 +ppc_ss.add(when: 'CONFIG_PEGASOS2', if_true: files('pegasos2.c')) + +ppc_ss.add(when: 'CONFIG_VOF', if_true: files('vof.c')) +ppc_ss.add(when: ['CONFIG_VOF', 'CONFIG_PSERIES'], if_true: files('spapr_vof.c')) hw_arch += {'ppc': ppc_ss} diff --git a/hw/ppc/pef.c b/hw/ppc/pef.c index 573be3ed79..cc44d5e339 100644 --- a/hw/ppc/pef.c +++ b/hw/ppc/pef.c @@ -41,7 +41,7 @@ struct PefGuest { ConfidentialGuestSupport parent_obj; }; -static int kvmppc_svm_init(Error **errp) +static int kvmppc_svm_init(ConfidentialGuestSupport *cgs, Error **errp) { #ifdef CONFIG_KVM static Error *pef_mig_blocker; @@ -65,6 +65,8 @@ static int kvmppc_svm_init(Error **errp) /* NB: This can fail if --only-migratable is used */ migrate_add_blocker(pef_mig_blocker, &error_fatal); + cgs->ready = true; + return 0; #else g_assert_not_reached(); @@ -102,7 +104,7 @@ int pef_kvm_init(ConfidentialGuestSupport *cgs, Error **errp) return -1; } - return kvmppc_svm_init(errp); + return kvmppc_svm_init(cgs, errp); } int pef_kvm_reset(ConfidentialGuestSupport *cgs, Error **errp) diff --git a/hw/ppc/pegasos2.c b/hw/ppc/pegasos2.c new file mode 100644 index 0000000000..b8ce859f1a --- /dev/null +++ b/hw/ppc/pegasos2.c @@ -0,0 +1,913 @@ +/* + * QEMU PowerPC CHRP (Genesi/bPlan Pegasos II) hardware System Emulator + * + * Copyright (c) 2018-2021 BALATON Zoltan + * + * This work is licensed under the GNU GPL license version 2 or later. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/units.h" +#include "qapi/error.h" +#include "hw/hw.h" +#include "hw/ppc/ppc.h" +#include "hw/sysbus.h" +#include "hw/pci/pci_host.h" +#include "hw/irq.h" +#include "hw/pci-host/mv64361.h" +#include "hw/isa/vt82c686.h" +#include "hw/ide/pci.h" +#include "hw/i2c/smbus_eeprom.h" +#include "hw/qdev-properties.h" +#include "sysemu/reset.h" +#include "hw/boards.h" +#include "hw/loader.h" +#include "hw/fw-path-provider.h" +#include "elf.h" +#include "qemu/log.h" +#include "qemu/error-report.h" +#include "sysemu/kvm.h" +#include "kvm_ppc.h" +#include "exec/address-spaces.h" +#include "trace.h" +#include "qemu/datadir.h" +#include "sysemu/device_tree.h" +#include "hw/ppc/vof.h" + +#include + +#define PROM_FILENAME "vof.bin" +#define PROM_ADDR 0xfff00000 +#define PROM_SIZE 0x80000 + +#define KVMPPC_HCALL_BASE 0xf000 +#define KVMPPC_H_RTAS (KVMPPC_HCALL_BASE + 0x0) +#define KVMPPC_H_VOF_CLIENT (KVMPPC_HCALL_BASE + 0x5) + +#define H_SUCCESS 0 +#define H_PRIVILEGE -3 /* Caller not privileged */ +#define H_PARAMETER -4 /* Parameter invalid, out-of-range or conflicting */ + +#define BUS_FREQ_HZ 133333333 + +#define PCI0_MEM_BASE 0xc0000000 +#define PCI0_MEM_SIZE 0x20000000 +#define PCI0_IO_BASE 0xf8000000 +#define PCI0_IO_SIZE 0x10000 + +#define PCI1_MEM_BASE 0x80000000 +#define PCI1_MEM_SIZE 0x40000000 +#define PCI1_IO_BASE 0xfe000000 +#define PCI1_IO_SIZE 0x10000 + +#define TYPE_PEGASOS2_MACHINE MACHINE_TYPE_NAME("pegasos2") +OBJECT_DECLARE_TYPE(Pegasos2MachineState, MachineClass, PEGASOS2_MACHINE) + +struct Pegasos2MachineState { + MachineState parent_obj; + PowerPCCPU *cpu; + DeviceState *mv; + Vof *vof; + void *fdt_blob; + uint64_t kernel_addr; + uint64_t kernel_entry; + uint64_t kernel_size; +}; + +static void *build_fdt(MachineState *machine, int *fdt_size); + +static void pegasos2_cpu_reset(void *opaque) +{ + PowerPCCPU *cpu = opaque; + Pegasos2MachineState *pm = PEGASOS2_MACHINE(current_machine); + + cpu_reset(CPU(cpu)); + cpu->env.spr[SPR_HID1] = 7ULL << 28; + if (pm->vof) { + cpu->env.gpr[1] = 2 * VOF_STACK_SIZE - 0x20; + cpu->env.nip = 0x100; + } +} + +static void pegasos2_init(MachineState *machine) +{ + Pegasos2MachineState *pm = PEGASOS2_MACHINE(machine); + CPUPPCState *env; + MemoryRegion *rom = g_new(MemoryRegion, 1); + PCIBus *pci_bus; + PCIDevice *dev; + I2CBus *i2c_bus; + const char *fwname = machine->firmware ?: PROM_FILENAME; + char *filename; + int sz; + uint8_t *spd_data; + + /* init CPU */ + pm->cpu = POWERPC_CPU(cpu_create(machine->cpu_type)); + env = &pm->cpu->env; + if (PPC_INPUT(env) != PPC_FLAGS_INPUT_6xx) { + error_report("Incompatible CPU, only 6xx bus supported"); + exit(1); + } + + /* Set time-base frequency */ + cpu_ppc_tb_init(env, BUS_FREQ_HZ / 4); + qemu_register_reset(pegasos2_cpu_reset, pm->cpu); + + /* RAM */ + memory_region_add_subregion(get_system_memory(), 0, machine->ram); + + /* allocate and load firmware */ + filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, fwname); + if (!filename) { + error_report("Could not find firmware '%s'", fwname); + exit(1); + } + if (!machine->firmware && !pm->vof) { + pm->vof = g_malloc0(sizeof(*pm->vof)); + } + memory_region_init_rom(rom, NULL, "pegasos2.rom", PROM_SIZE, &error_fatal); + memory_region_add_subregion(get_system_memory(), PROM_ADDR, rom); + sz = load_elf(filename, NULL, NULL, NULL, NULL, NULL, NULL, NULL, 1, + PPC_ELF_MACHINE, 0, 0); + if (sz <= 0) { + sz = load_image_targphys(filename, pm->vof ? 0 : PROM_ADDR, PROM_SIZE); + } + if (sz <= 0 || sz > PROM_SIZE) { + error_report("Could not load firmware '%s'", filename); + exit(1); + } + g_free(filename); + if (pm->vof) { + pm->vof->fw_size = sz; + } + + /* Marvell Discovery II system controller */ + pm->mv = DEVICE(sysbus_create_simple(TYPE_MV64361, -1, + ((qemu_irq *)env->irq_inputs)[PPC6xx_INPUT_INT])); + pci_bus = mv64361_get_pci_bus(pm->mv, 1); + + /* VIA VT8231 South Bridge (multifunction PCI device) */ + /* VT8231 function 0: PCI-to-ISA Bridge */ + dev = pci_create_simple_multifunction(pci_bus, PCI_DEVFN(12, 0), true, + TYPE_VT8231_ISA); + qdev_connect_gpio_out(DEVICE(dev), 0, + qdev_get_gpio_in_named(pm->mv, "gpp", 31)); + + /* VT8231 function 1: IDE Controller */ + dev = pci_create_simple(pci_bus, PCI_DEVFN(12, 1), "via-ide"); + pci_ide_create_devs(dev); + + /* VT8231 function 2-3: USB Ports */ + pci_create_simple(pci_bus, PCI_DEVFN(12, 2), "vt82c686b-usb-uhci"); + pci_create_simple(pci_bus, PCI_DEVFN(12, 3), "vt82c686b-usb-uhci"); + + /* VT8231 function 4: Power Management Controller */ + dev = pci_create_simple(pci_bus, PCI_DEVFN(12, 4), TYPE_VT8231_PM); + i2c_bus = I2C_BUS(qdev_get_child_bus(DEVICE(dev), "i2c")); + spd_data = spd_data_generate(DDR, machine->ram_size); + smbus_eeprom_init_one(i2c_bus, 0x57, spd_data); + + /* VT8231 function 5-6: AC97 Audio & Modem */ + pci_create_simple(pci_bus, PCI_DEVFN(12, 5), TYPE_VIA_AC97); + pci_create_simple(pci_bus, PCI_DEVFN(12, 6), TYPE_VIA_MC97); + + /* other PC hardware */ + pci_vga_init(pci_bus); + + if (machine->kernel_filename) { + sz = load_elf(machine->kernel_filename, NULL, NULL, NULL, + &pm->kernel_entry, &pm->kernel_addr, NULL, NULL, 1, + PPC_ELF_MACHINE, 0, 0); + if (sz <= 0) { + error_report("Could not load kernel '%s'", + machine->kernel_filename); + exit(1); + } + pm->kernel_size = sz; + if (!pm->vof) { + warn_report("Option -kernel may be ineffective with -bios."); + } + } + if (!pm->vof && machine->kernel_cmdline && machine->kernel_cmdline[0]) { + warn_report("Option -append may be ineffective with -bios."); + } +} + +static uint32_t pegasos2_pci_config_read(AddressSpace *as, int bus, + uint32_t addr, uint32_t len) +{ + hwaddr pcicfg = (bus ? 0xf1000c78 : 0xf1000cf8); + uint32_t val = 0xffffffff; + + stl_le_phys(as, pcicfg, addr | BIT(31)); + switch (len) { + case 4: + val = ldl_le_phys(as, pcicfg + 4); + break; + case 2: + val = lduw_le_phys(as, pcicfg + 4); + break; + case 1: + val = ldub_phys(as, pcicfg + 4); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid length\n", __func__); + break; + } + return val; +} + +static void pegasos2_pci_config_write(AddressSpace *as, int bus, uint32_t addr, + uint32_t len, uint32_t val) +{ + hwaddr pcicfg = (bus ? 0xf1000c78 : 0xf1000cf8); + + stl_le_phys(as, pcicfg, addr | BIT(31)); + switch (len) { + case 4: + stl_le_phys(as, pcicfg + 4, val); + break; + case 2: + stw_le_phys(as, pcicfg + 4, val); + break; + case 1: + stb_phys(as, pcicfg + 4, val); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid length\n", __func__); + break; + } +} + +static void pegasos2_machine_reset(MachineState *machine) +{ + Pegasos2MachineState *pm = PEGASOS2_MACHINE(machine); + AddressSpace *as = CPU(pm->cpu)->as; + void *fdt; + uint64_t d[2]; + int sz; + + qemu_devices_reset(); + if (!pm->vof) { + return; /* Firmware should set up machine so nothing to do */ + } + + /* Otherwise, set up devices that board firmware would normally do */ + stl_le_phys(as, 0xf1000000, 0x28020ff); + stl_le_phys(as, 0xf1000278, 0xa31fc); + stl_le_phys(as, 0xf100f300, 0x11ff0400); + stl_le_phys(as, 0xf100f10c, 0x80000000); + stl_le_phys(as, 0xf100001c, 0x8000000); + pegasos2_pci_config_write(as, 0, PCI_COMMAND, 2, PCI_COMMAND_IO | + PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); + pegasos2_pci_config_write(as, 1, PCI_COMMAND, 2, PCI_COMMAND_IO | + PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); + + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 0) << 8) | + PCI_INTERRUPT_LINE, 2, 0x9); + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 0) << 8) | + 0x50, 1, 0x2); + + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 1) << 8) | + PCI_INTERRUPT_LINE, 2, 0x109); + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 1) << 8) | + PCI_CLASS_PROG, 1, 0xf); + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 1) << 8) | + 0x40, 1, 0xb); + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 1) << 8) | + 0x50, 4, 0x17171717); + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 1) << 8) | + PCI_COMMAND, 2, 0x87); + + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 2) << 8) | + PCI_INTERRUPT_LINE, 2, 0x409); + + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 3) << 8) | + PCI_INTERRUPT_LINE, 2, 0x409); + + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 4) << 8) | + PCI_INTERRUPT_LINE, 2, 0x9); + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 4) << 8) | + 0x48, 4, 0xf00); + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 4) << 8) | + 0x40, 4, 0x558020); + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 4) << 8) | + 0x90, 4, 0xd00); + + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 5) << 8) | + PCI_INTERRUPT_LINE, 2, 0x309); + + pegasos2_pci_config_write(as, 1, (PCI_DEVFN(12, 6) << 8) | + PCI_INTERRUPT_LINE, 2, 0x309); + + /* Device tree and VOF set up */ + vof_init(pm->vof, machine->ram_size, &error_fatal); + if (vof_claim(pm->vof, 0, VOF_STACK_SIZE, VOF_STACK_SIZE) == -1) { + error_report("Memory allocation for stack failed"); + exit(1); + } + if (pm->kernel_size && + vof_claim(pm->vof, pm->kernel_addr, pm->kernel_size, 0) == -1) { + error_report("Memory for kernel is in use"); + exit(1); + } + fdt = build_fdt(machine, &sz); + /* FIXME: VOF assumes entry is same as load address */ + d[0] = cpu_to_be64(pm->kernel_entry); + d[1] = cpu_to_be64(pm->kernel_size - (pm->kernel_entry - pm->kernel_addr)); + qemu_fdt_setprop(fdt, "/chosen", "qemu,boot-kernel", d, sizeof(d)); + + qemu_fdt_dumpdtb(fdt, fdt_totalsize(fdt)); + g_free(pm->fdt_blob); + pm->fdt_blob = fdt; + + vof_build_dt(fdt, pm->vof); + vof_client_open_store(fdt, pm->vof, "/chosen", "stdout", "/failsafe"); + pm->cpu->vhyp = PPC_VIRTUAL_HYPERVISOR(machine); +} + +enum pegasos2_rtas_tokens { + RTAS_RESTART_RTAS = 0, + RTAS_NVRAM_FETCH = 1, + RTAS_NVRAM_STORE = 2, + RTAS_GET_TIME_OF_DAY = 3, + RTAS_SET_TIME_OF_DAY = 4, + RTAS_EVENT_SCAN = 6, + RTAS_CHECK_EXCEPTION = 7, + RTAS_READ_PCI_CONFIG = 8, + RTAS_WRITE_PCI_CONFIG = 9, + RTAS_DISPLAY_CHARACTER = 10, + RTAS_SET_INDICATOR = 11, + RTAS_POWER_OFF = 17, + RTAS_SUSPEND = 18, + RTAS_HIBERNATE = 19, + RTAS_SYSTEM_REBOOT = 20, +}; + +static target_ulong pegasos2_rtas(PowerPCCPU *cpu, Pegasos2MachineState *pm, + target_ulong args_real) +{ + AddressSpace *as = CPU(cpu)->as; + uint32_t token = ldl_be_phys(as, args_real); + uint32_t nargs = ldl_be_phys(as, args_real + 4); + uint32_t nrets = ldl_be_phys(as, args_real + 8); + uint32_t args = args_real + 12; + uint32_t rets = args_real + 12 + nargs * 4; + + if (nrets < 1) { + qemu_log_mask(LOG_GUEST_ERROR, "Too few return values in RTAS call\n"); + return H_PARAMETER; + } + switch (token) { + case RTAS_READ_PCI_CONFIG: + { + uint32_t addr, len, val; + + if (nargs != 2 || nrets != 2) { + stl_be_phys(as, rets, -1); + return H_PARAMETER; + } + addr = ldl_be_phys(as, args); + len = ldl_be_phys(as, args + 4); + val = pegasos2_pci_config_read(as, !(addr >> 24), + addr & 0x0fffffff, len); + stl_be_phys(as, rets, 0); + stl_be_phys(as, rets + 4, val); + return H_SUCCESS; + } + case RTAS_WRITE_PCI_CONFIG: + { + uint32_t addr, len, val; + + if (nargs != 3 || nrets != 1) { + stl_be_phys(as, rets, -1); + return H_PARAMETER; + } + addr = ldl_be_phys(as, args); + len = ldl_be_phys(as, args + 4); + val = ldl_be_phys(as, args + 8); + pegasos2_pci_config_write(as, !(addr >> 24), + addr & 0x0fffffff, len, val); + stl_be_phys(as, rets, 0); + return H_SUCCESS; + } + case RTAS_DISPLAY_CHARACTER: + if (nargs != 1 || nrets != 1) { + stl_be_phys(as, rets, -1); + return H_PARAMETER; + } + qemu_log_mask(LOG_UNIMP, "%c", ldl_be_phys(as, args)); + stl_be_phys(as, rets, 0); + return H_SUCCESS; + default: + qemu_log_mask(LOG_UNIMP, "Unknown RTAS token %u (args=%u, rets=%u)\n", + token, nargs, nrets); + stl_be_phys(as, rets, 0); + return H_SUCCESS; + } +} + +static void pegasos2_hypercall(PPCVirtualHypervisor *vhyp, PowerPCCPU *cpu) +{ + Pegasos2MachineState *pm = PEGASOS2_MACHINE(vhyp); + CPUPPCState *env = &cpu->env; + + /* The TCG path should also be holding the BQL at this point */ + g_assert(qemu_mutex_iothread_locked()); + + if (msr_pr) { + qemu_log_mask(LOG_GUEST_ERROR, "Hypercall made with MSR[PR]=1\n"); + env->gpr[3] = H_PRIVILEGE; + } else if (env->gpr[3] == KVMPPC_H_RTAS) { + env->gpr[3] = pegasos2_rtas(cpu, pm, env->gpr[4]); + } else if (env->gpr[3] == KVMPPC_H_VOF_CLIENT) { + int ret = vof_client_call(MACHINE(pm), pm->vof, pm->fdt_blob, + env->gpr[4]); + env->gpr[3] = (ret ? H_PARAMETER : H_SUCCESS); + } else { + qemu_log_mask(LOG_GUEST_ERROR, "Unsupported hypercall " TARGET_FMT_lx + "\n", env->gpr[3]); + env->gpr[3] = -1; + } +} + +static void vhyp_nop(PPCVirtualHypervisor *vhyp, PowerPCCPU *cpu) +{ +} + +static target_ulong vhyp_encode_hpt_for_kvm_pr(PPCVirtualHypervisor *vhyp) +{ + return POWERPC_CPU(current_cpu)->env.spr[SPR_SDR1]; +} + +static bool pegasos2_setprop(MachineState *ms, const char *path, + const char *propname, void *val, int vallen) +{ + return true; +} + +static void pegasos2_machine_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + PPCVirtualHypervisorClass *vhc = PPC_VIRTUAL_HYPERVISOR_CLASS(oc); + VofMachineIfClass *vmc = VOF_MACHINE_CLASS(oc); + + mc->desc = "Genesi/bPlan Pegasos II"; + mc->init = pegasos2_init; + mc->reset = pegasos2_machine_reset; + mc->block_default_type = IF_IDE; + mc->default_boot_order = "cd"; + mc->default_display = "std"; + mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("7400_v2.9"); + mc->default_ram_id = "pegasos2.ram"; + mc->default_ram_size = 512 * MiB; + + vhc->hypercall = pegasos2_hypercall; + vhc->cpu_exec_enter = vhyp_nop; + vhc->cpu_exec_exit = vhyp_nop; + vhc->encode_hpt_for_kvm_pr = vhyp_encode_hpt_for_kvm_pr; + + vmc->setprop = pegasos2_setprop; +} + +static const TypeInfo pegasos2_machine_info = { + .name = TYPE_PEGASOS2_MACHINE, + .parent = TYPE_MACHINE, + .class_init = pegasos2_machine_class_init, + .instance_size = sizeof(Pegasos2MachineState), + .interfaces = (InterfaceInfo[]) { + { TYPE_PPC_VIRTUAL_HYPERVISOR }, + { TYPE_VOF_MACHINE_IF }, + { } + }, +}; + +static void pegasos2_machine_register_types(void) +{ + type_register_static(&pegasos2_machine_info); +} + +type_init(pegasos2_machine_register_types) + +/* FDT creation for passing to firmware */ + +typedef struct { + void *fdt; + const char *path; +} FDTInfo; + +/* We do everything in reverse order so it comes out right in the tree */ + +static void dt_ide(PCIBus *bus, PCIDevice *d, FDTInfo *fi) +{ + qemu_fdt_setprop_string(fi->fdt, fi->path, "device_type", "spi"); +} + +static void dt_usb(PCIBus *bus, PCIDevice *d, FDTInfo *fi) +{ + qemu_fdt_setprop_cell(fi->fdt, fi->path, "#size-cells", 0); + qemu_fdt_setprop_cell(fi->fdt, fi->path, "#address-cells", 1); + qemu_fdt_setprop_string(fi->fdt, fi->path, "device_type", "usb"); +} + +static void dt_isa(PCIBus *bus, PCIDevice *d, FDTInfo *fi) +{ + GString *name = g_string_sized_new(64); + uint32_t cells[3]; + + qemu_fdt_setprop_cell(fi->fdt, fi->path, "#size-cells", 1); + qemu_fdt_setprop_cell(fi->fdt, fi->path, "#address-cells", 2); + qemu_fdt_setprop_string(fi->fdt, fi->path, "device_type", "isa"); + qemu_fdt_setprop_string(fi->fdt, fi->path, "name", "isa"); + + /* addional devices */ + g_string_printf(name, "%s/lpt@i3bc", fi->path); + qemu_fdt_add_subnode(fi->fdt, name->str); + qemu_fdt_setprop_cell(fi->fdt, name->str, "clock-frequency", 0); + cells[0] = cpu_to_be32(7); + cells[1] = 0; + qemu_fdt_setprop(fi->fdt, name->str, "interrupts", + cells, 2 * sizeof(cells[0])); + cells[0] = cpu_to_be32(1); + cells[1] = cpu_to_be32(0x3bc); + cells[2] = cpu_to_be32(8); + qemu_fdt_setprop(fi->fdt, name->str, "reg", cells, 3 * sizeof(cells[0])); + qemu_fdt_setprop_string(fi->fdt, name->str, "device_type", "lpt"); + qemu_fdt_setprop_string(fi->fdt, name->str, "name", "lpt"); + + g_string_printf(name, "%s/fdc@i3f0", fi->path); + qemu_fdt_add_subnode(fi->fdt, name->str); + qemu_fdt_setprop_cell(fi->fdt, name->str, "clock-frequency", 0); + cells[0] = cpu_to_be32(6); + cells[1] = 0; + qemu_fdt_setprop(fi->fdt, name->str, "interrupts", + cells, 2 * sizeof(cells[0])); + cells[0] = cpu_to_be32(1); + cells[1] = cpu_to_be32(0x3f0); + cells[2] = cpu_to_be32(8); + qemu_fdt_setprop(fi->fdt, name->str, "reg", cells, 3 * sizeof(cells[0])); + qemu_fdt_setprop_string(fi->fdt, name->str, "device_type", "fdc"); + qemu_fdt_setprop_string(fi->fdt, name->str, "name", "fdc"); + + g_string_printf(name, "%s/timer@i40", fi->path); + qemu_fdt_add_subnode(fi->fdt, name->str); + qemu_fdt_setprop_cell(fi->fdt, name->str, "clock-frequency", 0); + cells[0] = cpu_to_be32(1); + cells[1] = cpu_to_be32(0x40); + cells[2] = cpu_to_be32(8); + qemu_fdt_setprop(fi->fdt, name->str, "reg", cells, 3 * sizeof(cells[0])); + qemu_fdt_setprop_string(fi->fdt, name->str, "device_type", "timer"); + qemu_fdt_setprop_string(fi->fdt, name->str, "name", "timer"); + + g_string_printf(name, "%s/rtc@i70", fi->path); + qemu_fdt_add_subnode(fi->fdt, name->str); + qemu_fdt_setprop_string(fi->fdt, name->str, "compatible", "ds1385-rtc"); + qemu_fdt_setprop_cell(fi->fdt, name->str, "clock-frequency", 0); + cells[0] = cpu_to_be32(8); + cells[1] = 0; + qemu_fdt_setprop(fi->fdt, name->str, "interrupts", + cells, 2 * sizeof(cells[0])); + cells[0] = cpu_to_be32(1); + cells[1] = cpu_to_be32(0x70); + cells[2] = cpu_to_be32(2); + qemu_fdt_setprop(fi->fdt, name->str, "reg", cells, 3 * sizeof(cells[0])); + qemu_fdt_setprop_string(fi->fdt, name->str, "device_type", "rtc"); + qemu_fdt_setprop_string(fi->fdt, name->str, "name", "rtc"); + + g_string_printf(name, "%s/keyboard@i60", fi->path); + qemu_fdt_add_subnode(fi->fdt, name->str); + cells[0] = cpu_to_be32(1); + cells[1] = 0; + qemu_fdt_setprop(fi->fdt, name->str, "interrupts", + cells, 2 * sizeof(cells[0])); + cells[0] = cpu_to_be32(1); + cells[1] = cpu_to_be32(0x60); + cells[2] = cpu_to_be32(5); + qemu_fdt_setprop(fi->fdt, name->str, "reg", cells, 3 * sizeof(cells[0])); + qemu_fdt_setprop_string(fi->fdt, name->str, "device_type", "keyboard"); + qemu_fdt_setprop_string(fi->fdt, name->str, "name", "keyboard"); + + g_string_printf(name, "%s/8042@i60", fi->path); + qemu_fdt_add_subnode(fi->fdt, name->str); + qemu_fdt_setprop_cell(fi->fdt, name->str, "#interrupt-cells", 2); + qemu_fdt_setprop_cell(fi->fdt, name->str, "#size-cells", 0); + qemu_fdt_setprop_cell(fi->fdt, name->str, "#address-cells", 1); + qemu_fdt_setprop_string(fi->fdt, name->str, "interrupt-controller", ""); + qemu_fdt_setprop_cell(fi->fdt, name->str, "clock-frequency", 0); + cells[0] = cpu_to_be32(1); + cells[1] = cpu_to_be32(0x60); + cells[2] = cpu_to_be32(5); + qemu_fdt_setprop(fi->fdt, name->str, "reg", cells, 3 * sizeof(cells[0])); + qemu_fdt_setprop_string(fi->fdt, name->str, "device_type", ""); + qemu_fdt_setprop_string(fi->fdt, name->str, "name", "8042"); + + g_string_printf(name, "%s/serial@i2f8", fi->path); + qemu_fdt_add_subnode(fi->fdt, name->str); + qemu_fdt_setprop_cell(fi->fdt, name->str, "clock-frequency", 0); + cells[0] = cpu_to_be32(3); + cells[1] = 0; + qemu_fdt_setprop(fi->fdt, name->str, "interrupts", + cells, 2 * sizeof(cells[0])); + cells[0] = cpu_to_be32(1); + cells[1] = cpu_to_be32(0x2f8); + cells[2] = cpu_to_be32(8); + qemu_fdt_setprop(fi->fdt, name->str, "reg", cells, 3 * sizeof(cells[0])); + qemu_fdt_setprop_string(fi->fdt, name->str, "device_type", "serial"); + qemu_fdt_setprop_string(fi->fdt, name->str, "name", "serial"); + + g_string_free(name, TRUE); +} + +static struct { + const char *id; + const char *name; + void (*dtf)(PCIBus *bus, PCIDevice *d, FDTInfo *fi); +} device_map[] = { + { "pci11ab,6460", "host", NULL }, + { "pci1106,8231", "isa", dt_isa }, + { "pci1106,571", "ide", dt_ide }, + { "pci1106,3044", "firewire", NULL }, + { "pci1106,3038", "usb", dt_usb }, + { "pci1106,8235", "other", NULL }, + { "pci1106,3058", "sound", NULL }, + { NULL, NULL } +}; + +static void add_pci_device(PCIBus *bus, PCIDevice *d, void *opaque) +{ + FDTInfo *fi = opaque; + GString *node = g_string_new(NULL); + uint32_t cells[(PCI_NUM_REGIONS + 1) * 5]; + int i, j; + const char *name = NULL; + g_autofree const gchar *pn = g_strdup_printf("pci%x,%x", + pci_get_word(&d->config[PCI_VENDOR_ID]), + pci_get_word(&d->config[PCI_DEVICE_ID])); + + for (i = 0; device_map[i].id; i++) { + if (!strcmp(pn, device_map[i].id)) { + name = device_map[i].name; + break; + } + } + g_string_printf(node, "%s/%s@%x", fi->path, (name ?: pn), + PCI_SLOT(d->devfn)); + if (PCI_FUNC(d->devfn)) { + g_string_append_printf(node, ",%x", PCI_FUNC(d->devfn)); + } + + qemu_fdt_add_subnode(fi->fdt, node->str); + if (device_map[i].dtf) { + FDTInfo cfi = { fi->fdt, node->str }; + device_map[i].dtf(bus, d, &cfi); + } + cells[0] = cpu_to_be32(d->devfn << 8); + cells[1] = 0; + cells[2] = 0; + cells[3] = 0; + cells[4] = 0; + j = 5; + for (i = 0; i < PCI_NUM_REGIONS; i++) { + if (!d->io_regions[i].size) { + continue; + } + cells[j] = cpu_to_be32(d->devfn << 8 | (PCI_BASE_ADDRESS_0 + i * 4)); + if (d->io_regions[i].type & PCI_BASE_ADDRESS_SPACE_IO) { + cells[j] |= cpu_to_be32(1 << 24); + } else { + cells[j] |= cpu_to_be32(2 << 24); + if (d->io_regions[i].type & PCI_BASE_ADDRESS_MEM_PREFETCH) { + cells[j] |= cpu_to_be32(4 << 28); + } + } + cells[j + 1] = 0; + cells[j + 2] = 0; + cells[j + 3] = cpu_to_be32(d->io_regions[i].size >> 32); + cells[j + 4] = cpu_to_be32(d->io_regions[i].size); + j += 5; + } + qemu_fdt_setprop(fi->fdt, node->str, "reg", cells, j * sizeof(cells[0])); + qemu_fdt_setprop_string(fi->fdt, node->str, "name", name ?: pn); + if (pci_get_byte(&d->config[PCI_INTERRUPT_PIN])) { + qemu_fdt_setprop_cell(fi->fdt, node->str, "interrupts", + pci_get_byte(&d->config[PCI_INTERRUPT_PIN])); + } + /* Pegasos2 firmware has subsystem-id amd subsystem-vendor-id swapped */ + qemu_fdt_setprop_cell(fi->fdt, node->str, "subsystem-vendor-id", + pci_get_word(&d->config[PCI_SUBSYSTEM_ID])); + qemu_fdt_setprop_cell(fi->fdt, node->str, "subsystem-id", + pci_get_word(&d->config[PCI_SUBSYSTEM_VENDOR_ID])); + cells[0] = pci_get_long(&d->config[PCI_CLASS_REVISION]); + qemu_fdt_setprop_cell(fi->fdt, node->str, "class-code", cells[0] >> 8); + qemu_fdt_setprop_cell(fi->fdt, node->str, "revision-id", cells[0] & 0xff); + qemu_fdt_setprop_cell(fi->fdt, node->str, "device-id", + pci_get_word(&d->config[PCI_DEVICE_ID])); + qemu_fdt_setprop_cell(fi->fdt, node->str, "vendor-id", + pci_get_word(&d->config[PCI_VENDOR_ID])); + + g_string_free(node, TRUE); +} + +static void *build_fdt(MachineState *machine, int *fdt_size) +{ + Pegasos2MachineState *pm = PEGASOS2_MACHINE(machine); + PowerPCCPU *cpu = pm->cpu; + PCIBus *pci_bus; + FDTInfo fi; + uint32_t cells[16]; + void *fdt = create_device_tree(fdt_size); + + fi.fdt = fdt; + + /* root node */ + qemu_fdt_setprop_string(fdt, "/", "CODEGEN,description", + "Pegasos CHRP PowerPC System"); + qemu_fdt_setprop_string(fdt, "/", "CODEGEN,board", "Pegasos2"); + qemu_fdt_setprop_string(fdt, "/", "CODEGEN,vendor", "bplan GmbH"); + qemu_fdt_setprop_string(fdt, "/", "revision", "2B"); + qemu_fdt_setprop_string(fdt, "/", "model", "Pegasos2"); + qemu_fdt_setprop_string(fdt, "/", "device_type", "chrp"); + qemu_fdt_setprop_cell(fdt, "/", "#address-cells", 1); + qemu_fdt_setprop_string(fdt, "/", "name", "bplan,Pegasos2"); + + /* pci@c0000000 */ + qemu_fdt_add_subnode(fdt, "/pci@c0000000"); + cells[0] = 0; + cells[1] = 0; + qemu_fdt_setprop(fdt, "/pci@c0000000", "bus-range", + cells, 2 * sizeof(cells[0])); + qemu_fdt_setprop_cell(fdt, "/pci@c0000000", "pci-bridge-number", 1); + cells[0] = cpu_to_be32(PCI0_MEM_BASE); + cells[1] = cpu_to_be32(PCI0_MEM_SIZE); + qemu_fdt_setprop(fdt, "/pci@c0000000", "reg", cells, 2 * sizeof(cells[0])); + cells[0] = cpu_to_be32(0x01000000); + cells[1] = 0; + cells[2] = 0; + cells[3] = cpu_to_be32(PCI0_IO_BASE); + cells[4] = 0; + cells[5] = cpu_to_be32(PCI0_IO_SIZE); + cells[6] = cpu_to_be32(0x02000000); + cells[7] = 0; + cells[8] = cpu_to_be32(PCI0_MEM_BASE); + cells[9] = cpu_to_be32(PCI0_MEM_BASE); + cells[10] = 0; + cells[11] = cpu_to_be32(PCI0_MEM_SIZE); + qemu_fdt_setprop(fdt, "/pci@c0000000", "ranges", + cells, 12 * sizeof(cells[0])); + qemu_fdt_setprop_cell(fdt, "/pci@c0000000", "#size-cells", 2); + qemu_fdt_setprop_cell(fdt, "/pci@c0000000", "#address-cells", 3); + qemu_fdt_setprop_string(fdt, "/pci@c0000000", "device_type", "pci"); + qemu_fdt_setprop_string(fdt, "/pci@c0000000", "name", "pci"); + + fi.path = "/pci@c0000000"; + pci_bus = mv64361_get_pci_bus(pm->mv, 0); + pci_for_each_device_reverse(pci_bus, 0, add_pci_device, &fi); + + /* pci@80000000 */ + qemu_fdt_add_subnode(fdt, "/pci@80000000"); + cells[0] = 0; + cells[1] = 0; + qemu_fdt_setprop(fdt, "/pci@80000000", "bus-range", + cells, 2 * sizeof(cells[0])); + qemu_fdt_setprop_cell(fdt, "/pci@80000000", "pci-bridge-number", 0); + cells[0] = cpu_to_be32(PCI1_MEM_BASE); + cells[1] = cpu_to_be32(PCI1_MEM_SIZE); + qemu_fdt_setprop(fdt, "/pci@80000000", "reg", cells, 2 * sizeof(cells[0])); + qemu_fdt_setprop_cell(fdt, "/pci@80000000", "8259-interrupt-acknowledge", + 0xf1000cb4); + cells[0] = cpu_to_be32(0x01000000); + cells[1] = 0; + cells[2] = 0; + cells[3] = cpu_to_be32(PCI1_IO_BASE); + cells[4] = 0; + cells[5] = cpu_to_be32(PCI1_IO_SIZE); + cells[6] = cpu_to_be32(0x02000000); + cells[7] = 0; + cells[8] = cpu_to_be32(PCI1_MEM_BASE); + cells[9] = cpu_to_be32(PCI1_MEM_BASE); + cells[10] = 0; + cells[11] = cpu_to_be32(PCI1_MEM_SIZE); + qemu_fdt_setprop(fdt, "/pci@80000000", "ranges", + cells, 12 * sizeof(cells[0])); + qemu_fdt_setprop_cell(fdt, "/pci@80000000", "#size-cells", 2); + qemu_fdt_setprop_cell(fdt, "/pci@80000000", "#address-cells", 3); + qemu_fdt_setprop_string(fdt, "/pci@80000000", "device_type", "pci"); + qemu_fdt_setprop_string(fdt, "/pci@80000000", "name", "pci"); + + fi.path = "/pci@80000000"; + pci_bus = mv64361_get_pci_bus(pm->mv, 1); + pci_for_each_device_reverse(pci_bus, 0, add_pci_device, &fi); + + qemu_fdt_add_subnode(fdt, "/failsafe"); + qemu_fdt_setprop_string(fdt, "/failsafe", "device_type", "serial"); + qemu_fdt_setprop_string(fdt, "/failsafe", "name", "failsafe"); + + qemu_fdt_add_subnode(fdt, "/rtas"); + qemu_fdt_setprop_cell(fdt, "/rtas", "system-reboot", RTAS_SYSTEM_REBOOT); + qemu_fdt_setprop_cell(fdt, "/rtas", "hibernate", RTAS_HIBERNATE); + qemu_fdt_setprop_cell(fdt, "/rtas", "suspend", RTAS_SUSPEND); + qemu_fdt_setprop_cell(fdt, "/rtas", "power-off", RTAS_POWER_OFF); + qemu_fdt_setprop_cell(fdt, "/rtas", "set-indicator", RTAS_SET_INDICATOR); + qemu_fdt_setprop_cell(fdt, "/rtas", "display-character", + RTAS_DISPLAY_CHARACTER); + qemu_fdt_setprop_cell(fdt, "/rtas", "write-pci-config", + RTAS_WRITE_PCI_CONFIG); + qemu_fdt_setprop_cell(fdt, "/rtas", "read-pci-config", + RTAS_READ_PCI_CONFIG); + /* Pegasos2 firmware misspells check-exception and guests use that */ + qemu_fdt_setprop_cell(fdt, "/rtas", "check-execption", + RTAS_CHECK_EXCEPTION); + qemu_fdt_setprop_cell(fdt, "/rtas", "event-scan", RTAS_EVENT_SCAN); + qemu_fdt_setprop_cell(fdt, "/rtas", "set-time-of-day", + RTAS_SET_TIME_OF_DAY); + qemu_fdt_setprop_cell(fdt, "/rtas", "get-time-of-day", + RTAS_GET_TIME_OF_DAY); + qemu_fdt_setprop_cell(fdt, "/rtas", "nvram-store", RTAS_NVRAM_STORE); + qemu_fdt_setprop_cell(fdt, "/rtas", "nvram-fetch", RTAS_NVRAM_FETCH); + qemu_fdt_setprop_cell(fdt, "/rtas", "restart-rtas", RTAS_RESTART_RTAS); + qemu_fdt_setprop_cell(fdt, "/rtas", "rtas-error-log-max", 0); + qemu_fdt_setprop_cell(fdt, "/rtas", "rtas-event-scan-rate", 0); + qemu_fdt_setprop_cell(fdt, "/rtas", "rtas-display-device", 0); + qemu_fdt_setprop_cell(fdt, "/rtas", "rtas-size", 20); + qemu_fdt_setprop_cell(fdt, "/rtas", "rtas-version", 1); + + /* cpus */ + qemu_fdt_add_subnode(fdt, "/cpus"); + qemu_fdt_setprop_cell(fdt, "/cpus", "#cpus", 1); + qemu_fdt_setprop_cell(fdt, "/cpus", "#address-cells", 1); + qemu_fdt_setprop_cell(fdt, "/cpus", "#size-cells", 0); + qemu_fdt_setprop_string(fdt, "/cpus", "name", "cpus"); + + /* FIXME Get CPU name from CPU object */ + const char *cp = "/cpus/PowerPC,G4"; + qemu_fdt_add_subnode(fdt, cp); + qemu_fdt_setprop_cell(fdt, cp, "l2cr", 0); + qemu_fdt_setprop_cell(fdt, cp, "d-cache-size", 0x8000); + qemu_fdt_setprop_cell(fdt, cp, "d-cache-block-size", + cpu->env.dcache_line_size); + qemu_fdt_setprop_cell(fdt, cp, "d-cache-line-size", + cpu->env.dcache_line_size); + qemu_fdt_setprop_cell(fdt, cp, "i-cache-size", 0x8000); + qemu_fdt_setprop_cell(fdt, cp, "i-cache-block-size", + cpu->env.icache_line_size); + qemu_fdt_setprop_cell(fdt, cp, "i-cache-line-size", + cpu->env.icache_line_size); + if (cpu->env.id_tlbs) { + qemu_fdt_setprop_cell(fdt, cp, "i-tlb-sets", cpu->env.nb_ways); + qemu_fdt_setprop_cell(fdt, cp, "i-tlb-size", cpu->env.tlb_per_way); + qemu_fdt_setprop_cell(fdt, cp, "d-tlb-sets", cpu->env.nb_ways); + qemu_fdt_setprop_cell(fdt, cp, "d-tlb-size", cpu->env.tlb_per_way); + qemu_fdt_setprop_string(fdt, cp, "tlb-split", ""); + } + qemu_fdt_setprop_cell(fdt, cp, "tlb-sets", cpu->env.nb_ways); + qemu_fdt_setprop_cell(fdt, cp, "tlb-size", cpu->env.nb_tlb); + qemu_fdt_setprop_string(fdt, cp, "state", "running"); + if (cpu->env.insns_flags & PPC_ALTIVEC) { + qemu_fdt_setprop_string(fdt, cp, "altivec", ""); + qemu_fdt_setprop_string(fdt, cp, "data-streams", ""); + } + /* + * FIXME What flags do data-streams, external-control and + * performance-monitor depend on? + */ + qemu_fdt_setprop_string(fdt, cp, "external-control", ""); + if (cpu->env.insns_flags & PPC_FLOAT_FSQRT) { + qemu_fdt_setprop_string(fdt, cp, "general-purpose", ""); + } + qemu_fdt_setprop_string(fdt, cp, "performance-monitor", ""); + if (cpu->env.insns_flags & PPC_FLOAT_FRES) { + qemu_fdt_setprop_string(fdt, cp, "graphics", ""); + } + qemu_fdt_setprop_cell(fdt, cp, "reservation-granule-size", 4); + qemu_fdt_setprop_cell(fdt, cp, "timebase-frequency", + cpu->env.tb_env->tb_freq); + qemu_fdt_setprop_cell(fdt, cp, "bus-frequency", BUS_FREQ_HZ); + qemu_fdt_setprop_cell(fdt, cp, "clock-frequency", BUS_FREQ_HZ * 7.5); + qemu_fdt_setprop_cell(fdt, cp, "cpu-version", cpu->env.spr[SPR_PVR]); + cells[0] = 0; + cells[1] = 0; + qemu_fdt_setprop(fdt, cp, "reg", cells, 2 * sizeof(cells[0])); + qemu_fdt_setprop_string(fdt, cp, "device_type", "cpu"); + qemu_fdt_setprop_string(fdt, cp, "name", strrchr(cp, '/') + 1); + + /* memory */ + qemu_fdt_add_subnode(fdt, "/memory@0"); + cells[0] = 0; + cells[1] = cpu_to_be32(machine->ram_size); + qemu_fdt_setprop(fdt, "/memory@0", "reg", cells, 2 * sizeof(cells[0])); + qemu_fdt_setprop_string(fdt, "/memory@0", "device_type", "memory"); + qemu_fdt_setprop_string(fdt, "/memory@0", "name", "memory"); + + qemu_fdt_add_subnode(fdt, "/chosen"); + qemu_fdt_setprop_string(fdt, "/chosen", "bootargs", + machine->kernel_cmdline ?: ""); + qemu_fdt_setprop_string(fdt, "/chosen", "name", "chosen"); + + qemu_fdt_add_subnode(fdt, "/openprom"); + qemu_fdt_setprop_string(fdt, "/openprom", "model", "Pegasos2,1.1"); + + return fdt; +} diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c index 77af846cdf..d16dd2d080 100644 --- a/hw/ppc/pnv.c +++ b/hw/ppc/pnv.c @@ -32,14 +32,12 @@ #include "sysemu/device_tree.h" #include "sysemu/hw_accel.h" #include "target/ppc/cpu.h" -#include "qemu/log.h" #include "hw/ppc/fdt.h" #include "hw/ppc/ppc.h" #include "hw/ppc/pnv.h" #include "hw/ppc/pnv_core.h" #include "hw/loader.h" #include "hw/nmi.h" -#include "exec/address-spaces.h" #include "qapi/visitor.h" #include "monitor/monitor.h" #include "hw/intc/intc.h" @@ -53,7 +51,6 @@ #include "hw/ppc/pnv_pnor.h" #include "hw/isa/isa.h" -#include "hw/boards.h" #include "hw/char/serial.h" #include "hw/rtc/mc146818rtc.h" @@ -199,7 +196,7 @@ static void pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt) _FDT((fdt_setprop_string(fdt, offset, "status", "okay"))); _FDT((fdt_setprop(fdt, offset, "64-bit", NULL, 0))); - if (env->spr_cb[SPR_PURR].oea_read) { + if (ppc_has_spr(cpu, SPR_PURR)) { _FDT((fdt_setprop(fdt, offset, "ibm,purr", NULL, 0))); } diff --git a/hw/ppc/pnv_core.c b/hw/ppc/pnv_core.c index bd2bf2e044..8c2a15a0fb 100644 --- a/hw/ppc/pnv_core.c +++ b/hw/ppc/pnv_core.c @@ -29,6 +29,7 @@ #include "hw/ppc/pnv_xscom.h" #include "hw/ppc/xics.h" #include "hw/qdev-properties.h" +#include "helper_regs.h" static const char *pnv_core_cpu_typename(PnvCore *pc) { @@ -55,8 +56,8 @@ static void pnv_core_cpu_reset(PnvCore *pc, PowerPCCPU *cpu) env->gpr[3] = PNV_FDT_ADDR; env->nip = 0x10; env->msr |= MSR_HVB; /* Hypervisor mode */ - env->spr[SPR_HRMOR] = pc->hrmor; + hreg_compute_hflags(env); pcc->intc_reset(pc->chip, cpu); } diff --git a/hw/ppc/pnv_pnor.c b/hw/ppc/pnv_pnor.c index 4b455de1ea..5ef1cf2afb 100644 --- a/hw/ppc/pnv_pnor.c +++ b/hw/ppc/pnv_pnor.c @@ -10,7 +10,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu/error-report.h" -#include "qemu/log.h" #include "qemu/units.h" #include "sysemu/block-backend.h" #include "sysemu/blockdev.h" diff --git a/hw/ppc/pnv_psi.c b/hw/ppc/pnv_psi.c index 3e868c8c8d..cd9a2c5952 100644 --- a/hw/ppc/pnv_psi.c +++ b/hw/ppc/pnv_psi.c @@ -26,7 +26,6 @@ #include "qapi/error.h" #include "monitor/monitor.h" -#include "exec/address-spaces.h" #include "hw/ppc/fdt.h" #include "hw/ppc/pnv.h" @@ -466,7 +465,7 @@ static void pnv_psi_reset(DeviceState *dev) static void pnv_psi_reset_handler(void *dev) { - device_legacy_reset(DEVICE(dev)); + device_cold_reset(DEVICE(dev)); } static void pnv_psi_realize(DeviceState *dev, Error **errp) @@ -710,7 +709,7 @@ static void pnv_psi_p9_mmio_write(void *opaque, hwaddr addr, break; case PSIHB9_INTERRUPT_CONTROL: if (val & PSIHB9_IRQ_RESET) { - device_legacy_reset(DEVICE(&psi9->source)); + device_cold_reset(DEVICE(&psi9->source)); } psi->regs[reg] = val; break; diff --git a/hw/ppc/ppc.c b/hw/ppc/ppc.c index bf28d6bfc8..7375bf4fa9 100644 --- a/hw/ppc/ppc.c +++ b/hw/ppc/ppc.c @@ -23,7 +23,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "hw/irq.h" #include "hw/ppc/ppc.h" #include "hw/ppc/ppc_e500.h" diff --git a/hw/ppc/ppc405_boards.c b/hw/ppc/ppc405_boards.c index 8f77887fb1..972a7a4a3e 100644 --- a/hw/ppc/ppc405_boards.c +++ b/hw/ppc/ppc405_boards.c @@ -34,15 +34,12 @@ #include "ppc405.h" #include "hw/rtc/m48t59.h" #include "hw/block/flash.h" -#include "sysemu/sysemu.h" #include "sysemu/qtest.h" #include "sysemu/reset.h" #include "sysemu/block-backend.h" #include "hw/boards.h" -#include "qemu/log.h" #include "qemu/error-report.h" #include "hw/loader.h" -#include "exec/address-spaces.h" #include "qemu/cutils.h" #define BIOS_FILENAME "ppc405_rom.bin" diff --git a/hw/ppc/ppc405_uc.c b/hw/ppc/ppc405_uc.c index fe047074a1..e632c408bd 100644 --- a/hw/ppc/ppc405_uc.c +++ b/hw/ppc/ppc405_uc.c @@ -34,7 +34,6 @@ #include "qemu/timer.h" #include "sysemu/reset.h" #include "sysemu/sysemu.h" -#include "qemu/log.h" #include "exec/address-spaces.h" #include "hw/intc/ppc-uic.h" #include "hw/qdev-properties.h" diff --git a/hw/ppc/ppc440_bamboo.c b/hw/ppc/ppc440_bamboo.c index b7539aa721..7fb620b9a0 100644 --- a/hw/ppc/ppc440_bamboo.c +++ b/hw/ppc/ppc440_bamboo.c @@ -25,7 +25,6 @@ #include "sysemu/device_tree.h" #include "hw/loader.h" #include "elf.h" -#include "exec/address-spaces.h" #include "hw/char/serial.h" #include "hw/ppc/ppc.h" #include "ppc405.h" diff --git a/hw/ppc/ppc440_pcix.c b/hw/ppc/ppc440_pcix.c index 91cbcd0504..788d25514a 100644 --- a/hw/ppc/ppc440_pcix.c +++ b/hw/ppc/ppc440_pcix.c @@ -28,7 +28,6 @@ #include "hw/ppc/ppc4xx.h" #include "hw/pci/pci.h" #include "hw/pci/pci_host.h" -#include "exec/address-spaces.h" #include "trace.h" #include "qom/object.h" diff --git a/hw/ppc/ppc440_uc.c b/hw/ppc/ppc440_uc.c index f6f89058ab..993e3ba955 100644 --- a/hw/ppc/ppc440_uc.c +++ b/hw/ppc/ppc440_uc.c @@ -14,9 +14,7 @@ #include "qapi/error.h" #include "qemu/log.h" #include "qemu/module.h" -#include "cpu.h" #include "hw/irq.h" -#include "exec/address-spaces.h" #include "exec/memory.h" #include "hw/ppc/ppc.h" #include "hw/qdev-properties.h" diff --git a/hw/ppc/ppc4xx_devs.c b/hw/ppc/ppc4xx_devs.c index fe9d4f7155..980c48944f 100644 --- a/hw/ppc/ppc4xx_devs.c +++ b/hw/ppc/ppc4xx_devs.c @@ -29,7 +29,6 @@ #include "hw/irq.h" #include "hw/ppc/ppc.h" #include "hw/ppc/ppc4xx.h" -#include "hw/boards.h" #include "hw/intc/ppc-uic.h" #include "hw/qdev-properties.h" #include "qemu/log.h" diff --git a/hw/ppc/ppc4xx_pci.c b/hw/ppc/ppc4xx_pci.c index e8789f64e8..8147ba6f94 100644 --- a/hw/ppc/ppc4xx_pci.c +++ b/hw/ppc/ppc4xx_pci.c @@ -28,7 +28,6 @@ #include "sysemu/reset.h" #include "hw/pci/pci.h" #include "hw/pci/pci_host.h" -#include "exec/address-spaces.h" #include "trace.h" #include "qom/object.h" diff --git a/hw/ppc/ppc_booke.c b/hw/ppc/ppc_booke.c index 974c0c8a75..10b643861f 100644 --- a/hw/ppc/ppc_booke.c +++ b/hw/ppc/ppc_booke.c @@ -28,7 +28,6 @@ #include "qemu/timer.h" #include "sysemu/reset.h" #include "sysemu/runstate.h" -#include "qemu/log.h" #include "hw/loader.h" #include "kvm_ppc.h" diff --git a/hw/ppc/prep.c b/hw/ppc/prep.c index f1b1efdcef..acfc2a91d8 100644 --- a/hw/ppc/prep.c +++ b/hw/ppc/prep.c @@ -24,12 +24,10 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "hw/rtc/m48t59.h" #include "hw/char/serial.h" #include "hw/block/fdc.h" #include "net/net.h" -#include "sysemu/sysemu.h" #include "hw/isa/isa.h" #include "hw/pci/pci.h" #include "hw/pci/pci_host.h" @@ -38,7 +36,6 @@ #include "qapi/error.h" #include "qemu/error-report.h" #include "qemu/log.h" -#include "hw/irq.h" #include "hw/loader.h" #include "hw/rtc/mc146818rtc.h" #include "hw/isa/pc87312.h" @@ -46,7 +43,6 @@ #include "sysemu/arch_init.h" #include "sysemu/kvm.h" #include "sysemu/reset.h" -#include "exec/address-spaces.h" #include "trace.h" #include "elf.h" #include "qemu/units.h" diff --git a/hw/ppc/rs6000_mc.c b/hw/ppc/rs6000_mc.c index 4db5b51a2d..c0bc212e92 100644 --- a/hw/ppc/rs6000_mc.c +++ b/hw/ppc/rs6000_mc.c @@ -23,7 +23,6 @@ #include "hw/qdev-properties.h" #include "migration/vmstate.h" #include "exec/address-spaces.h" -#include "hw/boards.h" #include "qapi/error.h" #include "trace.h" #include "qom/object.h" diff --git a/hw/ppc/sam460ex.c b/hw/ppc/sam460ex.c index 0c6baf77e8..0737234d66 100644 --- a/hw/ppc/sam460ex.c +++ b/hw/ppc/sam460ex.c @@ -24,7 +24,6 @@ #include "sysemu/block-backend.h" #include "hw/loader.h" #include "elf.h" -#include "exec/address-spaces.h" #include "exec/memory.h" #include "ppc440.h" #include "ppc405.h" diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index e4be00b732..81699d4f8b 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -54,7 +54,6 @@ #include "cpu-models.h" #include "hw/core/cpu.h" -#include "hw/boards.h" #include "hw/ppc/ppc.h" #include "hw/loader.h" @@ -70,7 +69,6 @@ #include "hw/virtio/virtio-scsi.h" #include "hw/virtio/vhost-scsi-common.h" -#include "exec/address-spaces.h" #include "exec/ram_addr.h" #include "hw/usb.h" #include "qemu/config-file.h" @@ -100,9 +98,10 @@ * * We load our kernel at 4M, leaving space for SLOF initial image */ -#define RTAS_MAX_ADDR 0x80000000 /* RTAS must stay below that */ +#define FDT_MAX_ADDR 0x80000000 /* FDT must stay below that */ #define FW_MAX_SIZE 0x400000 #define FW_FILE_NAME "slof.bin" +#define FW_FILE_NAME_VOF "vof.bin" #define FW_OVERHEAD 0x2800000 #define KERNEL_LOAD_ADDR FW_MAX_SIZE @@ -705,10 +704,10 @@ static void spapr_dt_cpu(CPUState *cs, void *fdt, int offset, _FDT((fdt_setprop_string(fdt, offset, "status", "okay"))); _FDT((fdt_setprop(fdt, offset, "64-bit", NULL, 0))); - if (env->spr_cb[SPR_PURR].oea_read) { + if (ppc_has_spr(cpu, SPR_PURR)) { _FDT((fdt_setprop_cell(fdt, offset, "ibm,purr", 1))); } - if (env->spr_cb[SPR_SPURR].oea_read) { + if (ppc_has_spr(cpu, SPR_PURR)) { _FDT((fdt_setprop_cell(fdt, offset, "ibm,spurr", 1))); } @@ -882,6 +881,10 @@ static void spapr_dt_rtas(SpaprMachineState *spapr, void *fdt) add_str(hypertas, "hcall-copy"); add_str(hypertas, "hcall-debug"); add_str(hypertas, "hcall-vphn"); + if (spapr_get_cap(spapr, SPAPR_CAP_RPT_INVALIDATE) == SPAPR_CAP_ON) { + add_str(hypertas, "hcall-rpt-invalidate"); + } + add_str(qemu_hypertas, "hcall-memop1"); if (!kvm_enabled() || kvmppc_spapr_use_multitce()) { @@ -921,9 +924,13 @@ static void spapr_dt_rtas(SpaprMachineState *spapr, void *fdt) * * The extra 8 bytes is required because Linux's FWNMI error log check * is off-by-one. + * + * RTAS_MIN_SIZE is required for the RTAS blob itself. */ - _FDT(fdt_setprop_cell(fdt, rtas, "rtas-size", RTAS_ERROR_LOG_MAX + - ms->smp.max_cpus * sizeof(uint64_t)*2 + sizeof(uint64_t))); + _FDT(fdt_setprop_cell(fdt, rtas, "rtas-size", RTAS_MIN_SIZE + + RTAS_ERROR_LOG_MAX + + ms->smp.max_cpus * sizeof(uint64_t) * 2 + + sizeof(uint64_t))); _FDT(fdt_setprop_cell(fdt, rtas, "rtas-error-log-max", RTAS_ERROR_LOG_MAX)); _FDT(fdt_setprop_cell(fdt, rtas, "rtas-event-scan-rate", @@ -981,6 +988,7 @@ static void spapr_dt_ov5_platform_support(SpaprMachineState *spapr, void *fdt, */ val[1] = SPAPR_OV5_XIVE_LEGACY; /* XICS */ val[3] = 0x00; /* Hash */ + spapr_check_mmu_mode(false); } else if (kvm_enabled()) { if (kvmppc_has_cap_mmu_radix() && kvmppc_has_cap_mmu_hash_v3()) { val[3] = 0x80; /* OV5_MMU_BOTH */ @@ -1006,7 +1014,7 @@ static void spapr_dt_chosen(SpaprMachineState *spapr, void *fdt, bool reset) _FDT(chosen = fdt_add_subnode(fdt, 0, "chosen")); if (reset) { - const char *boot_device = machine->boot_order; + const char *boot_device = spapr->boot_device; char *stdout_path = spapr_vio_stdout_path(spapr->vio_bus); size_t cb = 0; char *bootlist = get_boot_devices_list(&cb); @@ -1558,6 +1566,22 @@ void spapr_setup_hpt(SpaprMachineState *spapr) } } +void spapr_check_mmu_mode(bool guest_radix) +{ + if (guest_radix) { + if (kvm_enabled() && !kvmppc_has_cap_mmu_radix()) { + error_report("Guest requested unavailable MMU mode (radix)."); + exit(EXIT_FAILURE); + } + } else { + if (kvm_enabled() && kvmppc_has_cap_mmu_radix() + && !kvmppc_has_cap_mmu_hash_v3()) { + error_report("Guest requested unavailable MMU mode (hash)."); + exit(EXIT_FAILURE); + } + } +} + static void spapr_machine_reset(MachineState *machine) { SpaprMachineState *spapr = SPAPR_MACHINE(machine); @@ -1617,29 +1641,36 @@ static void spapr_machine_reset(MachineState *machine) spapr_clear_pending_events(spapr); /* - * We place the device tree and RTAS just below either the top of the RMA, + * We place the device tree just below either the top of the RMA, * or just below 2GB, whichever is lower, so that it can be * processed with 32-bit real mode code if necessary */ - fdt_addr = MIN(spapr->rma_size, RTAS_MAX_ADDR) - FDT_MAX_SIZE; + fdt_addr = MIN(spapr->rma_size, FDT_MAX_ADDR) - FDT_MAX_SIZE; fdt = spapr_build_fdt(spapr, true, FDT_MAX_SIZE); + if (spapr->vof) { + spapr_vof_reset(spapr, fdt, &error_fatal); + /* + * Do not pack the FDT as the client may change properties. + * VOF client does not expect the FDT so we do not load it to the VM. + */ + } else { + rc = fdt_pack(fdt); + /* Should only fail if we've built a corrupted tree */ + assert(rc == 0); - rc = fdt_pack(fdt); - - /* Should only fail if we've built a corrupted tree */ - assert(rc == 0); - - /* Load the fdt */ + spapr_cpu_set_entry_state(first_ppc_cpu, SPAPR_ENTRY_POINT, + 0, fdt_addr, 0); + cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt)); + } qemu_fdt_dumpdtb(fdt, fdt_totalsize(fdt)); - cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt)); + g_free(spapr->fdt_blob); spapr->fdt_size = fdt_totalsize(fdt); spapr->fdt_initial_size = spapr->fdt_size; spapr->fdt_blob = fdt; /* Set up the entry state */ - spapr_cpu_set_entry_state(first_ppc_cpu, SPAPR_ENTRY_POINT, 0, fdt_addr, 0); first_ppc_cpu->env.gpr[5] = 0; spapr->fwnmi_system_reset_addr = -1; @@ -2003,6 +2034,7 @@ static const VMStateDescription vmstate_spapr = { &vmstate_spapr_cap_ccf_assist, &vmstate_spapr_cap_fwnmi, &vmstate_spapr_fwnmi, + &vmstate_spapr_cap_rpt_invalidate, NULL } }; @@ -2361,8 +2393,10 @@ static SaveVMHandlers savevm_htab_handlers = { static void spapr_boot_set(void *opaque, const char *boot_device, Error **errp) { - MachineState *machine = MACHINE(opaque); - machine->boot_order = g_strdup(boot_device); + SpaprMachineState *spapr = SPAPR_MACHINE(opaque); + + g_free(spapr->boot_device); + spapr->boot_device = g_strdup(boot_device); } static void spapr_create_lmb_dr_connectors(SpaprMachineState *spapr) @@ -2640,7 +2674,8 @@ static void spapr_machine_init(MachineState *machine) SpaprMachineState *spapr = SPAPR_MACHINE(machine); SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine); MachineClass *mc = MACHINE_GET_CLASS(machine); - const char *bios_name = machine->firmware ?: FW_FILE_NAME; + const char *bios_default = spapr->vof ? FW_FILE_NAME_VOF : FW_FILE_NAME; + const char *bios_name = machine->firmware ?: bios_default; const char *kernel_filename = machine->kernel_filename; const char *initrd_filename = machine->initrd_filename; PCIHostState *phb; @@ -2694,7 +2729,7 @@ static void spapr_machine_init(MachineState *machine) spapr->rma_size = spapr_rma_size(spapr, &error_fatal); /* Setup a load limit for the ramdisk leaving room for SLOF and FDT */ - load_limit = MIN(spapr->rma_size, RTAS_MAX_ADDR) - FW_OVERHEAD; + load_limit = MIN(spapr->rma_size, FDT_MAX_ADDR) - FW_OVERHEAD; /* * VSMT must be set in order to be able to compute VCPU ids, ie to @@ -2997,6 +3032,10 @@ static void spapr_machine_init(MachineState *machine) } qemu_cond_init(&spapr->fwnmi_machine_check_interlock_cond); + if (spapr->vof) { + spapr->vof->fw_size = fw_size; /* for claim() on itself */ + spapr_register_hypercall(KVMPPC_H_VOF_CLIENT, spapr_h_vof_client); + } } #define DEFAULT_KVM_TYPE "auto" @@ -3089,7 +3128,7 @@ static char *spapr_get_fw_dev_path(FWPathProvider *p, BusState *bus, */ if (strcmp("usb-host", qdev_fw_name(dev)) == 0) { USBDevice *usbdev = CAST(USBDevice, dev, TYPE_USB_DEVICE); - if (usb_host_dev_is_scsi_storage(usbdev)) { + if (usb_device_is_scsi_storage(usbdev)) { return g_strdup_printf("storage@%s/disk", usbdev->port->path); } } @@ -3187,6 +3226,28 @@ static void spapr_set_resize_hpt(Object *obj, const char *value, Error **errp) } } +static bool spapr_get_vof(Object *obj, Error **errp) +{ + SpaprMachineState *spapr = SPAPR_MACHINE(obj); + + return spapr->vof != NULL; +} + +static void spapr_set_vof(Object *obj, bool value, Error **errp) +{ + SpaprMachineState *spapr = SPAPR_MACHINE(obj); + + if (spapr->vof) { + vof_cleanup(spapr->vof); + g_free(spapr->vof); + spapr->vof = NULL; + } + if (!value) { + return; + } + spapr->vof = g_malloc0(sizeof(*spapr->vof)); +} + static char *spapr_get_ic_mode(Object *obj, Error **errp) { SpaprMachineState *spapr = SPAPR_MACHINE(obj); @@ -3312,6 +3373,11 @@ static void spapr_instance_init(Object *obj) stringify(KERNEL_LOAD_ADDR) " for -kernel is the default"); spapr->kernel_addr = KERNEL_LOAD_ADDR; + + object_property_add_bool(obj, "x-vof", spapr_get_vof, spapr_set_vof); + object_property_set_description(obj, "x-vof", + "Enable Virtual Open Firmware (experimental)"); + /* The machine class defines the default interrupt controller mode */ spapr->irq = smc->irq; object_property_add_str(obj, "ic-mode", spapr_get_ic_mode, @@ -4475,6 +4541,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) XICSFabricClass *xic = XICS_FABRIC_CLASS(oc); InterruptStatsProviderClass *ispc = INTERRUPT_STATS_PROVIDER_CLASS(oc); XiveFabricClass *xfc = XIVE_FABRIC_CLASS(oc); + VofMachineIfClass *vmc = VOF_MACHINE_CLASS(oc); mc->desc = "pSeries Logical Partition (PAPR compliant)"; mc->ignore_boot_device_suffixes = true; @@ -4487,7 +4554,16 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) mc->init = spapr_machine_init; mc->reset = spapr_machine_reset; mc->block_default_type = IF_SCSI; - mc->max_cpus = 1024; + + /* + * Setting max_cpus to INT32_MAX. Both KVM and TCG max_cpus values + * should be limited by the host capability instead of hardcoded. + * max_cpus for KVM guests will be checked in kvm_init(), and TCG + * guests are welcome to have as many CPUs as the host are capable + * of emulate. + */ + mc->max_cpus = INT32_MAX; + mc->no_parallel = 1; mc->default_boot_order = ""; mc->default_ram_size = 512 * MiB; @@ -4547,6 +4623,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) smc->default_caps.caps[SPAPR_CAP_LARGE_DECREMENTER] = SPAPR_CAP_ON; smc->default_caps.caps[SPAPR_CAP_CCF_ASSIST] = SPAPR_CAP_ON; smc->default_caps.caps[SPAPR_CAP_FWNMI] = SPAPR_CAP_ON; + smc->default_caps.caps[SPAPR_CAP_RPT_INVALIDATE] = SPAPR_CAP_OFF; spapr_caps_add_properties(smc); smc->irq = &spapr_irq_dual; smc->dr_phb_enabled = true; @@ -4554,6 +4631,9 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) smc->smp_threads_vsmt = true; smc->nr_xirqs = SPAPR_NR_XIRQS; xfc->match_nvt = spapr_match_nvt; + vmc->client_architecture_support = spapr_vof_client_architecture_support; + vmc->quiesce = spapr_vof_quiesce; + vmc->setprop = spapr_vof_setprop; } static const TypeInfo spapr_machine_info = { @@ -4573,6 +4653,7 @@ static const TypeInfo spapr_machine_info = { { TYPE_XICS_FABRIC }, { TYPE_INTERRUPT_STATS_PROVIDER }, { TYPE_XIVE_FABRIC }, + { TYPE_VOF_MACHINE_IF }, { } }, }; @@ -4605,14 +4686,25 @@ static void spapr_machine_latest_class_options(MachineClass *mc) type_init(spapr_machine_register_##suffix) /* - * pseries-6.0 + * pseries-6.1 */ -static void spapr_machine_6_0_class_options(MachineClass *mc) +static void spapr_machine_6_1_class_options(MachineClass *mc) { /* Defaults for the latest behaviour inherited from the base class */ } -DEFINE_SPAPR_MACHINE(6_0, "6.0", true); +DEFINE_SPAPR_MACHINE(6_1, "6.1", true); + +/* + * pseries-6.0 + */ +static void spapr_machine_6_0_class_options(MachineClass *mc) +{ + spapr_machine_6_1_class_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_0, hw_compat_6_0_len); +} + +DEFINE_SPAPR_MACHINE(6_0, "6.0", false); /* * pseries-5.2 diff --git a/hw/ppc/spapr_caps.c b/hw/ppc/spapr_caps.c index 9ea7ddd1e9..ed7c077a0d 100644 --- a/hw/ppc/spapr_caps.c +++ b/hw/ppc/spapr_caps.c @@ -371,6 +371,65 @@ static bool spapr_pagesize_cb(void *opaque, uint32_t seg_pshift, return true; } +static void ppc_hash64_filter_pagesizes(PowerPCCPU *cpu, + bool (*cb)(void *, uint32_t, uint32_t), + void *opaque) +{ + PPCHash64Options *opts = cpu->hash64_opts; + int i; + int n = 0; + bool ci_largepage = false; + + assert(opts); + + n = 0; + for (i = 0; i < ARRAY_SIZE(opts->sps); i++) { + PPCHash64SegmentPageSizes *sps = &opts->sps[i]; + int j; + int m = 0; + + assert(n <= i); + + if (!sps->page_shift) { + break; + } + + for (j = 0; j < ARRAY_SIZE(sps->enc); j++) { + PPCHash64PageSize *ps = &sps->enc[j]; + + assert(m <= j); + if (!ps->page_shift) { + break; + } + + if (cb(opaque, sps->page_shift, ps->page_shift)) { + if (ps->page_shift >= 16) { + ci_largepage = true; + } + sps->enc[m++] = *ps; + } + } + + /* Clear rest of the row */ + for (j = m; j < ARRAY_SIZE(sps->enc); j++) { + memset(&sps->enc[j], 0, sizeof(sps->enc[j])); + } + + if (m) { + n++; + } + } + + /* Clear the rest of the table */ + for (i = n; i < ARRAY_SIZE(opts->sps); i++) { + memset(&opts->sps[i], 0, sizeof(opts->sps[i])); + } + + if (!ci_largepage) { + opts->flags &= ~PPC_HASH64_CI_LARGEPAGE; + } +} + static void cap_hpt_maxpagesize_cpu_apply(SpaprMachineState *spapr, PowerPCCPU *cpu, uint8_t val, Error **errp) @@ -523,6 +582,37 @@ static void cap_fwnmi_apply(SpaprMachineState *spapr, uint8_t val, } } +static void cap_rpt_invalidate_apply(SpaprMachineState *spapr, + uint8_t val, Error **errp) +{ + ERRP_GUARD(); + + if (!val) { + /* capability disabled by default */ + return; + } + + if (tcg_enabled()) { + error_setg(errp, "No H_RPT_INVALIDATE support in TCG"); + error_append_hint(errp, + "Try appending -machine cap-rpt-invalidate=off\n"); + } else if (kvm_enabled()) { + if (!kvmppc_has_cap_mmu_radix()) { + error_setg(errp, "H_RPT_INVALIDATE only supported on Radix"); + return; + } + + if (!kvmppc_has_cap_rpt_invalidate()) { + error_setg(errp, + "KVM implementation does not support H_RPT_INVALIDATE"); + error_append_hint(errp, + "Try appending -machine cap-rpt-invalidate=off\n"); + } else { + kvmppc_enable_h_rpt_invalidate(); + } + } +} + SpaprCapabilityInfo capability_table[SPAPR_CAP_NUM] = { [SPAPR_CAP_HTM] = { .name = "htm", @@ -631,6 +721,15 @@ SpaprCapabilityInfo capability_table[SPAPR_CAP_NUM] = { .type = "bool", .apply = cap_fwnmi_apply, }, + [SPAPR_CAP_RPT_INVALIDATE] = { + .name = "rpt-invalidate", + .description = "Allow H_RPT_INVALIDATE", + .index = SPAPR_CAP_RPT_INVALIDATE, + .get = spapr_cap_get_bool, + .set = spapr_cap_set_bool, + .type = "bool", + .apply = cap_rpt_invalidate_apply, + }, }; static SpaprCapabilities default_caps_with_cpu(SpaprMachineState *spapr, @@ -771,6 +870,7 @@ SPAPR_CAP_MIG_STATE(nested_kvm_hv, SPAPR_CAP_NESTED_KVM_HV); SPAPR_CAP_MIG_STATE(large_decr, SPAPR_CAP_LARGE_DECREMENTER); SPAPR_CAP_MIG_STATE(ccf_assist, SPAPR_CAP_CCF_ASSIST); SPAPR_CAP_MIG_STATE(fwnmi, SPAPR_CAP_FWNMI); +SPAPR_CAP_MIG_STATE(rpt_invalidate, SPAPR_CAP_RPT_INVALIDATE); void spapr_caps_init(SpaprMachineState *spapr) { diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c index 9e16505fa1..a2f2634601 100644 --- a/hw/ppc/spapr_drc.c +++ b/hw/ppc/spapr_drc.c @@ -13,7 +13,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qapi/qmp/qnull.h" -#include "cpu.h" #include "qemu/cutils.h" #include "hw/ppc/spapr_drc.h" #include "qom/object.h" @@ -151,9 +150,32 @@ static uint32_t drc_isolate_logical(SpaprDrc *drc) static uint32_t drc_unisolate_logical(SpaprDrc *drc) { + SpaprMachineState *spapr = NULL; + switch (drc->state) { case SPAPR_DRC_STATE_LOGICAL_UNISOLATE: case SPAPR_DRC_STATE_LOGICAL_CONFIGURED: + /* + * Unisolating a logical DRC that was marked for unplug + * means that the kernel is refusing the removal. + */ + if (drc->unplug_requested && drc->dev) { + if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_LMB) { + spapr = SPAPR_MACHINE(qdev_get_machine()); + + spapr_memory_unplug_rollback(spapr, drc->dev); + } + + drc->unplug_requested = false; + error_report("Device hotunplug rejected by the guest " + "for device %s", drc->dev->id); + + /* + * TODO: send a QAPI DEVICE_UNPLUG_ERROR event when + * it is implemented. + */ + } + return RTAS_OUT_SUCCESS; /* Nothing to do */ case SPAPR_DRC_STATE_LOGICAL_AVAILABLE: break; /* see below */ diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c index d51daedfa6..23e2e2fff1 100644 --- a/hw/ppc/spapr_events.c +++ b/hw/ppc/spapr_events.c @@ -27,7 +27,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "sysemu/device_tree.h" #include "sysemu/runstate.h" @@ -935,7 +934,6 @@ static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t nret, target_ulong rets) { uint32_t mask, buf, len, event_len; - uint64_t xinfo; SpaprEventLogEntry *event; struct rtas_error_log header; int i; @@ -945,13 +943,9 @@ static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr, return; } - xinfo = rtas_ld(args, 1); mask = rtas_ld(args, 2); buf = rtas_ld(args, 4); len = rtas_ld(args, 5); - if (nargs == 7) { - xinfo |= (uint64_t)rtas_ld(args, 6) << 32; - } event = rtas_event_log_dequeue(spapr, mask); if (!event) { diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c index 7b5cd3553c..0e9a5b2e40 100644 --- a/hw/ppc/spapr_hcall.c +++ b/hw/ppc/spapr_hcall.c @@ -7,7 +7,6 @@ #include "qemu/main-loop.h" #include "qemu/module.h" #include "qemu/error-report.h" -#include "cpu.h" #include "exec/exec-all.h" #include "helper_regs.h" #include "hw/ppc/spapr.h" @@ -21,24 +20,7 @@ #include "mmu-book3s-v3.h" #include "hw/mem/memory-device.h" -static bool has_spr(PowerPCCPU *cpu, int spr) -{ - /* We can test whether the SPR is defined by checking for a valid name */ - return cpu->env.spr_cb[spr].name != NULL; -} - -static inline bool valid_ptex(PowerPCCPU *cpu, target_ulong ptex) -{ - /* - * hash value/pteg group index is normalized by HPT mask - */ - if (((ptex & ~7ULL) / HPTES_PER_GROUP) & ~ppc_hash64_hpt_mask(cpu)) { - return false; - } - return true; -} - -static bool is_ram_address(SpaprMachineState *spapr, hwaddr addr) +bool is_ram_address(SpaprMachineState *spapr, hwaddr addr) { MachineState *machine = MACHINE(spapr); DeviceMemoryState *dms = machine->device_memory; @@ -54,355 +36,6 @@ static bool is_ram_address(SpaprMachineState *spapr, hwaddr addr) return false; } -static target_ulong h_enter(PowerPCCPU *cpu, SpaprMachineState *spapr, - target_ulong opcode, target_ulong *args) -{ - target_ulong flags = args[0]; - target_ulong ptex = args[1]; - target_ulong pteh = args[2]; - target_ulong ptel = args[3]; - unsigned apshift; - target_ulong raddr; - target_ulong slot; - const ppc_hash_pte64_t *hptes; - - apshift = ppc_hash64_hpte_page_shift_noslb(cpu, pteh, ptel); - if (!apshift) { - /* Bad page size encoding */ - return H_PARAMETER; - } - - raddr = (ptel & HPTE64_R_RPN) & ~((1ULL << apshift) - 1); - - if (is_ram_address(spapr, raddr)) { - /* Regular RAM - should have WIMG=0010 */ - if ((ptel & HPTE64_R_WIMG) != HPTE64_R_M) { - return H_PARAMETER; - } - } else { - target_ulong wimg_flags; - /* Looks like an IO address */ - /* FIXME: What WIMG combinations could be sensible for IO? - * For now we allow WIMG=010x, but are there others? */ - /* FIXME: Should we check against registered IO addresses? */ - wimg_flags = (ptel & (HPTE64_R_W | HPTE64_R_I | HPTE64_R_M)); - - if (wimg_flags != HPTE64_R_I && - wimg_flags != (HPTE64_R_I | HPTE64_R_M)) { - return H_PARAMETER; - } - } - - pteh &= ~0x60ULL; - - if (!valid_ptex(cpu, ptex)) { - return H_PARAMETER; - } - - slot = ptex & 7ULL; - ptex = ptex & ~7ULL; - - if (likely((flags & H_EXACT) == 0)) { - hptes = ppc_hash64_map_hptes(cpu, ptex, HPTES_PER_GROUP); - for (slot = 0; slot < 8; slot++) { - if (!(ppc_hash64_hpte0(cpu, hptes, slot) & HPTE64_V_VALID)) { - break; - } - } - ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP); - if (slot == 8) { - return H_PTEG_FULL; - } - } else { - hptes = ppc_hash64_map_hptes(cpu, ptex + slot, 1); - if (ppc_hash64_hpte0(cpu, hptes, 0) & HPTE64_V_VALID) { - ppc_hash64_unmap_hptes(cpu, hptes, ptex + slot, 1); - return H_PTEG_FULL; - } - ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1); - } - - spapr_store_hpte(cpu, ptex + slot, pteh | HPTE64_V_HPTE_DIRTY, ptel); - - args[0] = ptex + slot; - return H_SUCCESS; -} - -typedef enum { - REMOVE_SUCCESS = 0, - REMOVE_NOT_FOUND = 1, - REMOVE_PARM = 2, - REMOVE_HW = 3, -} RemoveResult; - -static RemoveResult remove_hpte(PowerPCCPU *cpu - , target_ulong ptex, - target_ulong avpn, - target_ulong flags, - target_ulong *vp, target_ulong *rp) -{ - const ppc_hash_pte64_t *hptes; - target_ulong v, r; - - if (!valid_ptex(cpu, ptex)) { - return REMOVE_PARM; - } - - hptes = ppc_hash64_map_hptes(cpu, ptex, 1); - v = ppc_hash64_hpte0(cpu, hptes, 0); - r = ppc_hash64_hpte1(cpu, hptes, 0); - ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1); - - if ((v & HPTE64_V_VALID) == 0 || - ((flags & H_AVPN) && (v & ~0x7fULL) != avpn) || - ((flags & H_ANDCOND) && (v & avpn) != 0)) { - return REMOVE_NOT_FOUND; - } - *vp = v; - *rp = r; - spapr_store_hpte(cpu, ptex, HPTE64_V_HPTE_DIRTY, 0); - ppc_hash64_tlb_flush_hpte(cpu, ptex, v, r); - return REMOVE_SUCCESS; -} - -static target_ulong h_remove(PowerPCCPU *cpu, SpaprMachineState *spapr, - target_ulong opcode, target_ulong *args) -{ - CPUPPCState *env = &cpu->env; - target_ulong flags = args[0]; - target_ulong ptex = args[1]; - target_ulong avpn = args[2]; - RemoveResult ret; - - ret = remove_hpte(cpu, ptex, avpn, flags, - &args[0], &args[1]); - - switch (ret) { - case REMOVE_SUCCESS: - check_tlb_flush(env, true); - return H_SUCCESS; - - case REMOVE_NOT_FOUND: - return H_NOT_FOUND; - - case REMOVE_PARM: - return H_PARAMETER; - - case REMOVE_HW: - return H_HARDWARE; - } - - g_assert_not_reached(); -} - -#define H_BULK_REMOVE_TYPE 0xc000000000000000ULL -#define H_BULK_REMOVE_REQUEST 0x4000000000000000ULL -#define H_BULK_REMOVE_RESPONSE 0x8000000000000000ULL -#define H_BULK_REMOVE_END 0xc000000000000000ULL -#define H_BULK_REMOVE_CODE 0x3000000000000000ULL -#define H_BULK_REMOVE_SUCCESS 0x0000000000000000ULL -#define H_BULK_REMOVE_NOT_FOUND 0x1000000000000000ULL -#define H_BULK_REMOVE_PARM 0x2000000000000000ULL -#define H_BULK_REMOVE_HW 0x3000000000000000ULL -#define H_BULK_REMOVE_RC 0x0c00000000000000ULL -#define H_BULK_REMOVE_FLAGS 0x0300000000000000ULL -#define H_BULK_REMOVE_ABSOLUTE 0x0000000000000000ULL -#define H_BULK_REMOVE_ANDCOND 0x0100000000000000ULL -#define H_BULK_REMOVE_AVPN 0x0200000000000000ULL -#define H_BULK_REMOVE_PTEX 0x00ffffffffffffffULL - -#define H_BULK_REMOVE_MAX_BATCH 4 - -static target_ulong h_bulk_remove(PowerPCCPU *cpu, SpaprMachineState *spapr, - target_ulong opcode, target_ulong *args) -{ - CPUPPCState *env = &cpu->env; - int i; - target_ulong rc = H_SUCCESS; - - for (i = 0; i < H_BULK_REMOVE_MAX_BATCH; i++) { - target_ulong *tsh = &args[i*2]; - target_ulong tsl = args[i*2 + 1]; - target_ulong v, r, ret; - - if ((*tsh & H_BULK_REMOVE_TYPE) == H_BULK_REMOVE_END) { - break; - } else if ((*tsh & H_BULK_REMOVE_TYPE) != H_BULK_REMOVE_REQUEST) { - return H_PARAMETER; - } - - *tsh &= H_BULK_REMOVE_PTEX | H_BULK_REMOVE_FLAGS; - *tsh |= H_BULK_REMOVE_RESPONSE; - - if ((*tsh & H_BULK_REMOVE_ANDCOND) && (*tsh & H_BULK_REMOVE_AVPN)) { - *tsh |= H_BULK_REMOVE_PARM; - return H_PARAMETER; - } - - ret = remove_hpte(cpu, *tsh & H_BULK_REMOVE_PTEX, tsl, - (*tsh & H_BULK_REMOVE_FLAGS) >> 26, - &v, &r); - - *tsh |= ret << 60; - - switch (ret) { - case REMOVE_SUCCESS: - *tsh |= (r & (HPTE64_R_C | HPTE64_R_R)) << 43; - break; - - case REMOVE_PARM: - rc = H_PARAMETER; - goto exit; - - case REMOVE_HW: - rc = H_HARDWARE; - goto exit; - } - } - exit: - check_tlb_flush(env, true); - - return rc; -} - -static target_ulong h_protect(PowerPCCPU *cpu, SpaprMachineState *spapr, - target_ulong opcode, target_ulong *args) -{ - CPUPPCState *env = &cpu->env; - target_ulong flags = args[0]; - target_ulong ptex = args[1]; - target_ulong avpn = args[2]; - const ppc_hash_pte64_t *hptes; - target_ulong v, r; - - if (!valid_ptex(cpu, ptex)) { - return H_PARAMETER; - } - - hptes = ppc_hash64_map_hptes(cpu, ptex, 1); - v = ppc_hash64_hpte0(cpu, hptes, 0); - r = ppc_hash64_hpte1(cpu, hptes, 0); - ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1); - - if ((v & HPTE64_V_VALID) == 0 || - ((flags & H_AVPN) && (v & ~0x7fULL) != avpn)) { - return H_NOT_FOUND; - } - - r &= ~(HPTE64_R_PP0 | HPTE64_R_PP | HPTE64_R_N | - HPTE64_R_KEY_HI | HPTE64_R_KEY_LO); - r |= (flags << 55) & HPTE64_R_PP0; - r |= (flags << 48) & HPTE64_R_KEY_HI; - r |= flags & (HPTE64_R_PP | HPTE64_R_N | HPTE64_R_KEY_LO); - spapr_store_hpte(cpu, ptex, - (v & ~HPTE64_V_VALID) | HPTE64_V_HPTE_DIRTY, 0); - ppc_hash64_tlb_flush_hpte(cpu, ptex, v, r); - /* Flush the tlb */ - check_tlb_flush(env, true); - /* Don't need a memory barrier, due to qemu's global lock */ - spapr_store_hpte(cpu, ptex, v | HPTE64_V_HPTE_DIRTY, r); - return H_SUCCESS; -} - -static target_ulong h_read(PowerPCCPU *cpu, SpaprMachineState *spapr, - target_ulong opcode, target_ulong *args) -{ - target_ulong flags = args[0]; - target_ulong ptex = args[1]; - int i, ridx, n_entries = 1; - const ppc_hash_pte64_t *hptes; - - if (!valid_ptex(cpu, ptex)) { - return H_PARAMETER; - } - - if (flags & H_READ_4) { - /* Clear the two low order bits */ - ptex &= ~(3ULL); - n_entries = 4; - } - - hptes = ppc_hash64_map_hptes(cpu, ptex, n_entries); - for (i = 0, ridx = 0; i < n_entries; i++) { - args[ridx++] = ppc_hash64_hpte0(cpu, hptes, i); - args[ridx++] = ppc_hash64_hpte1(cpu, hptes, i); - } - ppc_hash64_unmap_hptes(cpu, hptes, ptex, n_entries); - - return H_SUCCESS; -} - -struct SpaprPendingHpt { - /* These fields are read-only after initialization */ - int shift; - QemuThread thread; - - /* These fields are protected by the BQL */ - bool complete; - - /* These fields are private to the preparation thread if - * !complete, otherwise protected by the BQL */ - int ret; - void *hpt; -}; - -static void free_pending_hpt(SpaprPendingHpt *pending) -{ - if (pending->hpt) { - qemu_vfree(pending->hpt); - } - - g_free(pending); -} - -static void *hpt_prepare_thread(void *opaque) -{ - SpaprPendingHpt *pending = opaque; - size_t size = 1ULL << pending->shift; - - pending->hpt = qemu_try_memalign(size, size); - if (pending->hpt) { - memset(pending->hpt, 0, size); - pending->ret = H_SUCCESS; - } else { - pending->ret = H_NO_MEM; - } - - qemu_mutex_lock_iothread(); - - if (SPAPR_MACHINE(qdev_get_machine())->pending_hpt == pending) { - /* Ready to go */ - pending->complete = true; - } else { - /* We've been cancelled, clean ourselves up */ - free_pending_hpt(pending); - } - - qemu_mutex_unlock_iothread(); - return NULL; -} - -/* Must be called with BQL held */ -static void cancel_hpt_prepare(SpaprMachineState *spapr) -{ - SpaprPendingHpt *pending = spapr->pending_hpt; - - /* Let the thread know it's cancelled */ - spapr->pending_hpt = NULL; - - if (!pending) { - /* Nothing to do */ - return; - } - - if (!pending->complete) { - /* thread will clean itself up */ - return; - } - - free_pending_hpt(pending); -} - /* Convert a return code from the KVM ioctl()s implementing resize HPT * into a PAPR hypercall return code */ static target_ulong resize_hpt_convert_rc(int ret) @@ -448,7 +81,6 @@ static target_ulong h_resize_hpt_prepare(PowerPCCPU *cpu, { target_ulong flags = args[0]; int shift = args[1]; - SpaprPendingHpt *pending = spapr->pending_hpt; uint64_t current_ram_size; int rc; @@ -485,182 +117,11 @@ static target_ulong h_resize_hpt_prepare(PowerPCCPU *cpu, return resize_hpt_convert_rc(rc); } - if (pending) { - /* something already in progress */ - if (pending->shift == shift) { - /* and it's suitable */ - if (pending->complete) { - return pending->ret; - } else { - return H_LONG_BUSY_ORDER_100_MSEC; - } - } - - /* not suitable, cancel and replace */ - cancel_hpt_prepare(spapr); - } - - if (!shift) { - /* nothing to do */ - return H_SUCCESS; - } - - /* start new prepare */ - - pending = g_new0(SpaprPendingHpt, 1); - pending->shift = shift; - pending->ret = H_HARDWARE; - - qemu_thread_create(&pending->thread, "sPAPR HPT prepare", - hpt_prepare_thread, pending, QEMU_THREAD_DETACHED); - - spapr->pending_hpt = pending; - - /* In theory we could estimate the time more accurately based on - * the new size, but there's not much point */ - return H_LONG_BUSY_ORDER_100_MSEC; -} - -static uint64_t new_hpte_load0(void *htab, uint64_t pteg, int slot) -{ - uint8_t *addr = htab; - - addr += pteg * HASH_PTEG_SIZE_64; - addr += slot * HASH_PTE_SIZE_64; - return ldq_p(addr); -} - -static void new_hpte_store(void *htab, uint64_t pteg, int slot, - uint64_t pte0, uint64_t pte1) -{ - uint8_t *addr = htab; - - addr += pteg * HASH_PTEG_SIZE_64; - addr += slot * HASH_PTE_SIZE_64; - - stq_p(addr, pte0); - stq_p(addr + HASH_PTE_SIZE_64 / 2, pte1); -} - -static int rehash_hpte(PowerPCCPU *cpu, - const ppc_hash_pte64_t *hptes, - void *old_hpt, uint64_t oldsize, - void *new_hpt, uint64_t newsize, - uint64_t pteg, int slot) -{ - uint64_t old_hash_mask = (oldsize >> 7) - 1; - uint64_t new_hash_mask = (newsize >> 7) - 1; - target_ulong pte0 = ppc_hash64_hpte0(cpu, hptes, slot); - target_ulong pte1; - uint64_t avpn; - unsigned base_pg_shift; - uint64_t hash, new_pteg, replace_pte0; - - if (!(pte0 & HPTE64_V_VALID) || !(pte0 & HPTE64_V_BOLTED)) { - return H_SUCCESS; - } - - pte1 = ppc_hash64_hpte1(cpu, hptes, slot); - - base_pg_shift = ppc_hash64_hpte_page_shift_noslb(cpu, pte0, pte1); - assert(base_pg_shift); /* H_ENTER shouldn't allow a bad encoding */ - avpn = HPTE64_V_AVPN_VAL(pte0) & ~(((1ULL << base_pg_shift) - 1) >> 23); - - if (pte0 & HPTE64_V_SECONDARY) { - pteg = ~pteg; - } - - if ((pte0 & HPTE64_V_SSIZE) == HPTE64_V_SSIZE_256M) { - uint64_t offset, vsid; - - /* We only have 28 - 23 bits of offset in avpn */ - offset = (avpn & 0x1f) << 23; - vsid = avpn >> 5; - /* We can find more bits from the pteg value */ - if (base_pg_shift < 23) { - offset |= ((vsid ^ pteg) & old_hash_mask) << base_pg_shift; - } - - hash = vsid ^ (offset >> base_pg_shift); - } else if ((pte0 & HPTE64_V_SSIZE) == HPTE64_V_SSIZE_1T) { - uint64_t offset, vsid; - - /* We only have 40 - 23 bits of seg_off in avpn */ - offset = (avpn & 0x1ffff) << 23; - vsid = avpn >> 17; - if (base_pg_shift < 23) { - offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) - << base_pg_shift; - } - - hash = vsid ^ (vsid << 25) ^ (offset >> base_pg_shift); - } else { - error_report("rehash_pte: Bad segment size in HPTE"); + if (kvm_enabled()) { return H_HARDWARE; } - new_pteg = hash & new_hash_mask; - if (pte0 & HPTE64_V_SECONDARY) { - assert(~pteg == (hash & old_hash_mask)); - new_pteg = ~new_pteg; - } else { - assert(pteg == (hash & old_hash_mask)); - } - assert((oldsize != newsize) || (pteg == new_pteg)); - replace_pte0 = new_hpte_load0(new_hpt, new_pteg, slot); - /* - * Strictly speaking, we don't need all these tests, since we only - * ever rehash bolted HPTEs. We might in future handle non-bolted - * HPTEs, though so make the logic correct for those cases as - * well. - */ - if (replace_pte0 & HPTE64_V_VALID) { - assert(newsize < oldsize); - if (replace_pte0 & HPTE64_V_BOLTED) { - if (pte0 & HPTE64_V_BOLTED) { - /* Bolted collision, nothing we can do */ - return H_PTEG_FULL; - } else { - /* Discard this hpte */ - return H_SUCCESS; - } - } - } - - new_hpte_store(new_hpt, new_pteg, slot, pte0, pte1); - return H_SUCCESS; -} - -static int rehash_hpt(PowerPCCPU *cpu, - void *old_hpt, uint64_t oldsize, - void *new_hpt, uint64_t newsize) -{ - uint64_t n_ptegs = oldsize >> 7; - uint64_t pteg; - int slot; - int rc; - - for (pteg = 0; pteg < n_ptegs; pteg++) { - hwaddr ptex = pteg * HPTES_PER_GROUP; - const ppc_hash_pte64_t *hptes - = ppc_hash64_map_hptes(cpu, ptex, HPTES_PER_GROUP); - - if (!hptes) { - return H_HARDWARE; - } - - for (slot = 0; slot < HPTES_PER_GROUP; slot++) { - rc = rehash_hpte(cpu, hptes, old_hpt, oldsize, new_hpt, newsize, - pteg, slot); - if (rc != H_SUCCESS) { - ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP); - return rc; - } - } - ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP); - } - - return H_SUCCESS; + return softmmu_resize_hpt_prepare(cpu, spapr, shift); } static void do_push_sregs_to_kvm_pr(CPUState *cs, run_on_cpu_data data) @@ -676,7 +137,7 @@ static void do_push_sregs_to_kvm_pr(CPUState *cs, run_on_cpu_data data) } } -static void push_sregs_to_kvm_pr(SpaprMachineState *spapr) +void push_sregs_to_kvm_pr(SpaprMachineState *spapr) { CPUState *cs; @@ -701,9 +162,7 @@ static target_ulong h_resize_hpt_commit(PowerPCCPU *cpu, { target_ulong flags = args[0]; target_ulong shift = args[1]; - SpaprPendingHpt *pending = spapr->pending_hpt; int rc; - size_t newsize; if (spapr->resize_hpt == SPAPR_RESIZE_HPT_DISABLED) { return H_AUTHORITY; @@ -726,43 +185,15 @@ static target_ulong h_resize_hpt_commit(PowerPCCPU *cpu, return rc; } - if (flags != 0) { - return H_PARAMETER; + if (kvm_enabled()) { + return H_HARDWARE; } - if (!pending || (pending->shift != shift)) { - /* no matching prepare */ - return H_CLOSED; - } - - if (!pending->complete) { - /* prepare has not completed */ - return H_BUSY; - } - - /* Shouldn't have got past PREPARE without an HPT */ - g_assert(spapr->htab_shift); - - newsize = 1ULL << pending->shift; - rc = rehash_hpt(cpu, spapr->htab, HTAB_SIZE(spapr), - pending->hpt, newsize); - if (rc == H_SUCCESS) { - qemu_vfree(spapr->htab); - spapr->htab = pending->hpt; - spapr->htab_shift = pending->shift; - - push_sregs_to_kvm_pr(spapr); - - pending->hpt = NULL; /* so it's not free()d */ - } - - /* Clean up */ - spapr->pending_hpt = NULL; - free_pending_hpt(pending); - - return rc; + return softmmu_resize_hpt_commit(cpu, spapr, flags, shift); } + + static target_ulong h_set_sprg0(PowerPCCPU *cpu, SpaprMachineState *spapr, target_ulong opcode, target_ulong *args) { @@ -775,12 +206,12 @@ static target_ulong h_set_sprg0(PowerPCCPU *cpu, SpaprMachineState *spapr, static target_ulong h_set_dabr(PowerPCCPU *cpu, SpaprMachineState *spapr, target_ulong opcode, target_ulong *args) { - if (!has_spr(cpu, SPR_DABR)) { + if (!ppc_has_spr(cpu, SPR_DABR)) { return H_HARDWARE; /* DABR register not available */ } cpu_synchronize_state(CPU(cpu)); - if (has_spr(cpu, SPR_DABRX)) { + if (ppc_has_spr(cpu, SPR_DABRX)) { cpu->env.spr[SPR_DABRX] = 0x3; /* Use Problem and Privileged state */ } else if (!(args[0] & 0x4)) { /* Breakpoint Translation set? */ return H_RESERVED_DABR; @@ -795,7 +226,7 @@ static target_ulong h_set_xdabr(PowerPCCPU *cpu, SpaprMachineState *spapr, { target_ulong dabrx = args[1]; - if (!has_spr(cpu, SPR_DABR) || !has_spr(cpu, SPR_DABRX)) { + if (!ppc_has_spr(cpu, SPR_DABR) || !ppc_has_spr(cpu, SPR_DABRX)) { return H_HARDWARE; } @@ -1395,7 +826,13 @@ static target_ulong h_set_mode_resource_addr_trans_mode(PowerPCCPU *cpu, return H_P4; } - if (mflags == AIL_RESERVED) { + if (mflags == 1) { + /* AIL=1 is reserved in POWER8/POWER9/POWER10 */ + return H_UNSUPPORTED_FLAG; + } + + if (mflags == 2 && (pcc->insns_flags2 & PPC2_ISA310)) { + /* AIL=2 is reserved in POWER10 (ISA v3.1) */ return H_UNSUPPORTED_FLAG; } @@ -1755,18 +1192,8 @@ target_ulong do_client_architecture_support(PowerPCCPU *cpu, spapr_ovec_intersect(spapr->ov5_cas, spapr->ov5, ov5_guest); spapr_ovec_cleanup(ov5_guest); - if (guest_radix) { - if (kvm_enabled() && !kvmppc_has_cap_mmu_radix()) { - error_report("Guest requested unavailable MMU mode (radix)."); - exit(EXIT_FAILURE); - } - } else { - if (kvm_enabled() && kvmppc_has_cap_mmu_radix() - && !kvmppc_has_cap_mmu_hash_v3()) { - error_report("Guest requested unavailable MMU mode (hash)."); - exit(EXIT_FAILURE); - } - } + spapr_check_mmu_mode(guest_radix); + spapr->cas_pre_isa3_guest = !spapr_ovec_test(ov1_guest, OV1_PPC_3_00); spapr_ovec_cleanup(ov1_guest); @@ -1806,8 +1233,7 @@ target_ulong do_client_architecture_support(PowerPCCPU *cpu, spapr_setup_hpt(spapr); } - fdt = spapr_build_fdt(spapr, false, fdt_bufsize); - + fdt = spapr_build_fdt(spapr, spapr->vof != NULL, fdt_bufsize); g_free(spapr->fdt_blob); spapr->fdt_size = fdt_totalsize(fdt); spapr->fdt_initial_size = spapr->fdt_size; @@ -1850,6 +1276,25 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu, return ret; } +target_ulong spapr_vof_client_architecture_support(MachineState *ms, + CPUState *cs, + target_ulong ovec_addr) +{ + SpaprMachineState *spapr = SPAPR_MACHINE(ms); + + target_ulong ret = do_client_architecture_support(POWERPC_CPU(cs), spapr, + ovec_addr, FDT_MAX_SIZE); + + /* + * This adds stdout and generates phandles for boottime and CAS FDTs. + * It is alright to update the FDT here as do_client_architecture_support() + * does not pack it. + */ + spapr_vof_client_dt_finalize(spapr, spapr->fdt_blob); + + return ret; +} + static target_ulong h_get_cpu_characteristics(PowerPCCPU *cpu, SpaprMachineState *spapr, target_ulong opcode, @@ -1872,6 +1317,8 @@ static target_ulong h_get_cpu_characteristics(PowerPCCPU *cpu, behaviour |= H_CPU_BEHAV_L1D_FLUSH_PR; break; case SPAPR_CAP_FIXED: + behaviour |= H_CPU_BEHAV_NO_L1D_FLUSH_ENTRY; + behaviour |= H_CPU_BEHAV_NO_L1D_FLUSH_UACCESS; break; default: /* broken */ assert(safe_cache == SPAPR_CAP_BROKEN); @@ -2018,16 +1465,34 @@ target_ulong spapr_hypercall(PowerPCCPU *cpu, target_ulong opcode, return H_FUNCTION; } -static void hypercall_register_types(void) +#ifndef CONFIG_TCG +static target_ulong h_softmmu(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + g_assert_not_reached(); +} + +static void hypercall_register_softmmu(void) { /* hcall-pft */ - spapr_register_hypercall(H_ENTER, h_enter); - spapr_register_hypercall(H_REMOVE, h_remove); - spapr_register_hypercall(H_PROTECT, h_protect); - spapr_register_hypercall(H_READ, h_read); + spapr_register_hypercall(H_ENTER, h_softmmu); + spapr_register_hypercall(H_REMOVE, h_softmmu); + spapr_register_hypercall(H_PROTECT, h_softmmu); + spapr_register_hypercall(H_READ, h_softmmu); /* hcall-bulk */ - spapr_register_hypercall(H_BULK_REMOVE, h_bulk_remove); + spapr_register_hypercall(H_BULK_REMOVE, h_softmmu); +} +#else +static void hypercall_register_softmmu(void) +{ + /* DO NOTHING */ +} +#endif + +static void hypercall_register_types(void) +{ + hypercall_register_softmmu(); /* hcall-hpt-resize */ spapr_register_hypercall(H_RESIZE_HPT_PREPARE, h_resize_hpt_prepare); diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c index 24537ffcbd..db01071858 100644 --- a/hw/ppc/spapr_iommu.c +++ b/hw/ppc/spapr_iommu.c @@ -25,7 +25,6 @@ #include "kvm_ppc.h" #include "migration/vmstate.h" #include "sysemu/dma.h" -#include "exec/address-spaces.h" #include "trace.h" #include "hw/ppc/spapr.h" diff --git a/hw/ppc/spapr_nvdimm.c b/hw/ppc/spapr_nvdimm.c index b46c36917c..91de1052f2 100644 --- a/hw/ppc/spapr_nvdimm.c +++ b/hw/ppc/spapr_nvdimm.c @@ -31,6 +31,22 @@ #include "qemu/range.h" #include "hw/ppc/spapr_numa.h" +/* DIMM health bitmap bitmap indicators. Taken from kernel's papr_scm.c */ +/* SCM device is unable to persist memory contents */ +#define PAPR_PMEM_UNARMED PPC_BIT(0) + +/* + * The nvdimm size should be aligned to SCM block size. + * The SCM block size should be aligned to SPAPR_MEMORY_BLOCK_SIZE + * in order to have SCM regions not to overlap with dimm memory regions. + * The SCM devices can have variable block sizes. For now, fixing the + * block size to the minimum value. + */ +#define SPAPR_MINIMUM_SCM_BLOCK_SIZE SPAPR_MEMORY_BLOCK_SIZE + +/* Have an explicit check for alignment */ +QEMU_BUILD_BUG_ON(SPAPR_MINIMUM_SCM_BLOCK_SIZE % SPAPR_MEMORY_BLOCK_SIZE); + bool spapr_nvdimm_validate(HotplugHandler *hotplug_dev, NVDIMMDevice *nvdimm, uint64_t size, Error **errp) { @@ -159,11 +175,11 @@ int spapr_pmem_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr, void spapr_dt_persistent_memory(SpaprMachineState *spapr, void *fdt) { - int offset = fdt_subnode_offset(fdt, 0, "persistent-memory"); + int offset = fdt_subnode_offset(fdt, 0, "ibm,persistent-memory"); GSList *iter, *nvdimms = nvdimm_get_device_list(); if (offset < 0) { - offset = fdt_add_subnode(fdt, 0, "persistent-memory"); + offset = fdt_add_subnode(fdt, 0, "ibm,persistent-memory"); _FDT(offset); _FDT((fdt_setprop_cell(fdt, offset, "#address-cells", 0x1))); _FDT((fdt_setprop_cell(fdt, offset, "#size-cells", 0x0))); @@ -467,6 +483,37 @@ static target_ulong h_scm_unbind_all(PowerPCCPU *cpu, SpaprMachineState *spapr, return H_SUCCESS; } +static target_ulong h_scm_health(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + + NVDIMMDevice *nvdimm; + uint64_t hbitmap = 0; + uint32_t drc_index = args[0]; + SpaprDrc *drc = spapr_drc_by_index(drc_index); + const uint64_t hbitmap_mask = PAPR_PMEM_UNARMED; + + + /* Ensure that the drc is valid & is valid PMEM dimm and is plugged in */ + if (!drc || !drc->dev || + spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PMEM) { + return H_PARAMETER; + } + + nvdimm = NVDIMM(drc->dev); + + /* Update if the nvdimm is unarmed and send its status via health bitmaps */ + if (object_property_get_bool(OBJECT(nvdimm), NVDIMM_UNARMED_PROP, NULL)) { + hbitmap |= PAPR_PMEM_UNARMED; + } + + /* Update the out args with health bitmap/mask */ + args[0] = hbitmap; + args[1] = hbitmap_mask; + + return H_SUCCESS; +} + static void spapr_scm_register_types(void) { /* qemu/scm specific hcalls */ @@ -475,6 +522,7 @@ static void spapr_scm_register_types(void) spapr_register_hypercall(H_SCM_BIND_MEM, h_scm_bind_mem); spapr_register_hypercall(H_SCM_UNBIND_MEM, h_scm_unbind_mem); spapr_register_hypercall(H_SCM_UNBIND_ALL, h_scm_unbind_all); + spapr_register_hypercall(H_SCM_HEALTH, h_scm_health); } type_init(spapr_scm_register_types) diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c index feba18cb12..7a725855f9 100644 --- a/hw/ppc/spapr_pci.c +++ b/hw/ppc/spapr_pci.c @@ -25,7 +25,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "hw/irq.h" #include "hw/sysbus.h" #include "migration/vmstate.h" @@ -35,7 +34,6 @@ #include "hw/pci/pci_host.h" #include "hw/ppc/spapr.h" #include "hw/pci-host/spapr.h" -#include "exec/address-spaces.h" #include "exec/ram_addr.h" #include #include "trace.h" diff --git a/hw/ppc/spapr_pci_vfio.c b/hw/ppc/spapr_pci_vfio.c index e0547b1740..f3b37df8ea 100644 --- a/hw/ppc/spapr_pci_vfio.c +++ b/hw/ppc/spapr_pci_vfio.c @@ -19,7 +19,6 @@ #include "qemu/osdep.h" #include -#include "cpu.h" #include "hw/ppc/spapr.h" #include "hw/pci-host/spapr.h" #include "hw/pci/msix.h" @@ -47,6 +46,16 @@ void spapr_phb_vfio_reset(DeviceState *qdev) spapr_phb_vfio_eeh_reenable(SPAPR_PCI_HOST_BRIDGE(qdev)); } +static void spapr_eeh_pci_find_device(PCIBus *bus, PCIDevice *pdev, + void *opaque) +{ + bool *found = opaque; + + if (object_dynamic_cast(OBJECT(pdev), "vfio-pci")) { + *found = true; + } +} + int spapr_phb_vfio_eeh_set_option(SpaprPhbState *sphb, unsigned int addr, int option) { @@ -59,17 +68,33 @@ int spapr_phb_vfio_eeh_set_option(SpaprPhbState *sphb, break; case RTAS_EEH_ENABLE: { PCIHostState *phb; - PCIDevice *pdev; + bool found = false; /* - * The EEH functionality is enabled on basis of PCI device, - * instead of PE. We need check the validity of the PCI - * device address. + * The EEH functionality is enabled per sphb level instead of + * per PCI device. We have already identified this specific sphb + * based on buid passed as argument to ibm,set-eeh-option rtas + * call. Now we just need to check the validity of the PCI + * pass-through devices (vfio-pci) under this sphb bus. + * We have already validated that all the devices under this sphb + * are from same iommu group (within same PE) before comming here. + * + * Prior to linux commit 98ba956f6a389 ("powerpc/pseries/eeh: + * Rework device EEH PE determination") kernel would call + * eeh-set-option for each device in the PE using the device's + * config_address as the argument rather than the PE address. + * Hence if we check validity of supplied config_addr whether + * it matches to this PHB will cause issues with older kernel + * versions v5.9 and older. If we return an error from + * eeh-set-option when the argument isn't a valid PE address + * then older kernels (v5.9 and older) will interpret that as + * EEH not being supported. */ phb = PCI_HOST_BRIDGE(sphb); - pdev = pci_find_device(phb->bus, - (addr >> 16) & 0xFF, (addr >> 8) & 0xFF); - if (!pdev || !object_dynamic_cast(OBJECT(pdev), "vfio-pci")) { + pci_for_each_device(phb->bus, (addr >> 16) & 0xFF, + spapr_eeh_pci_find_device, &found); + + if (!found) { return RTAS_OUT_PARAM_ERROR; } diff --git a/hw/ppc/spapr_rng.c b/hw/ppc/spapr_rng.c index d14800e9de..df5c4b9687 100644 --- a/hw/ppc/spapr_rng.c +++ b/hw/ppc/spapr_rng.c @@ -19,7 +19,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "qemu/error-report.h" #include "qemu/main-loop.h" #include "qemu/module.h" diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c index 8a79f9c628..b476382ae6 100644 --- a/hw/ppc/spapr_rtas.c +++ b/hw/ppc/spapr_rtas.c @@ -26,7 +26,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "qemu/log.h" #include "qemu/error-report.h" #include "sysemu/sysemu.h" @@ -41,7 +40,6 @@ #include "hw/ppc/spapr_rtas.h" #include "hw/ppc/spapr_cpu_core.h" #include "hw/ppc/ppc.h" -#include "hw/boards.h" #include #include "hw/ppc/spapr_drc.h" @@ -51,6 +49,7 @@ #include "target/ppc/mmu-hash64.h" #include "target/ppc/mmu-book3s-v3.h" #include "migration/blocker.h" +#include "helper_regs.h" static void rtas_display_character(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, @@ -133,8 +132,8 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, SpaprMachineState *spapr, target_ulong id, start, r3; PowerPCCPU *newcpu; CPUPPCState *env; - PowerPCCPUClass *pcc; target_ulong lpcr; + target_ulong caller_lpcr; if (nargs != 3 || nret != 1) { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); @@ -153,7 +152,6 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, SpaprMachineState *spapr, } env = &newcpu->env; - pcc = POWERPC_CPU_GET_CLASS(newcpu); if (!CPU(newcpu)->halted) { rtas_st(rets, 0, RTAS_OUT_HW_ERROR); @@ -163,12 +161,17 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, SpaprMachineState *spapr, cpu_synchronize_state(CPU(newcpu)); env->msr = (1ULL << MSR_SF) | (1ULL << MSR_ME); + hreg_compute_hflags(env); - /* Enable Power-saving mode Exit Cause exceptions for the new CPU */ + caller_lpcr = callcpu->env.spr[SPR_LPCR]; lpcr = env->spr[SPR_LPCR]; - if (!pcc->interrupts_big_endian(callcpu)) { - lpcr |= LPCR_ILE; - } + + /* Set ILE the same way */ + lpcr = (lpcr & ~LPCR_ILE) | (caller_lpcr & LPCR_ILE); + + /* Set AIL the same way */ + lpcr = (lpcr & ~LPCR_AIL) | (caller_lpcr & LPCR_AIL); + if (env->mmu_model == POWERPC_MMU_3_00) { /* * New cpus are expected to start in the same radix/hash mode diff --git a/hw/ppc/spapr_rtas_ddw.c b/hw/ppc/spapr_rtas_ddw.c index 3501b05819..3e826e1308 100644 --- a/hw/ppc/spapr_rtas_ddw.c +++ b/hw/ppc/spapr_rtas_ddw.c @@ -18,7 +18,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "qemu/error-report.h" #include "qemu/module.h" #include "hw/ppc/spapr.h" diff --git a/hw/ppc/spapr_rtc.c b/hw/ppc/spapr_rtc.c index 68cfc578a3..fba4dfca35 100644 --- a/hw/ppc/spapr_rtc.c +++ b/hw/ppc/spapr_rtc.c @@ -27,7 +27,6 @@ #include "qemu/osdep.h" #include "qemu-common.h" -#include "cpu.h" #include "qemu/timer.h" #include "sysemu/sysemu.h" #include "hw/ppc/spapr.h" diff --git a/hw/ppc/spapr_softmmu.c b/hw/ppc/spapr_softmmu.c new file mode 100644 index 0000000000..6c6b86dd3c --- /dev/null +++ b/hw/ppc/spapr_softmmu.c @@ -0,0 +1,627 @@ +#include "qemu/osdep.h" +#include "qemu/cutils.h" +#include "qapi/error.h" +#include "sysemu/hw_accel.h" +#include "sysemu/runstate.h" +#include "qemu/log.h" +#include "qemu/main-loop.h" +#include "qemu/module.h" +#include "qemu/error-report.h" +#include "cpu.h" +#include "exec/exec-all.h" +#include "helper_regs.h" +#include "hw/ppc/spapr.h" +#include "hw/ppc/spapr_cpu_core.h" +#include "mmu-hash64.h" +#include "cpu-models.h" +#include "trace.h" +#include "kvm_ppc.h" +#include "hw/ppc/fdt.h" +#include "hw/ppc/spapr_ovec.h" +#include "mmu-book3s-v3.h" +#include "hw/mem/memory-device.h" + +static inline bool valid_ptex(PowerPCCPU *cpu, target_ulong ptex) +{ + /* + * hash value/pteg group index is normalized by HPT mask + */ + if (((ptex & ~7ULL) / HPTES_PER_GROUP) & ~ppc_hash64_hpt_mask(cpu)) { + return false; + } + return true; +} + +static target_ulong h_enter(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + target_ulong flags = args[0]; + target_ulong ptex = args[1]; + target_ulong pteh = args[2]; + target_ulong ptel = args[3]; + unsigned apshift; + target_ulong raddr; + target_ulong slot; + const ppc_hash_pte64_t *hptes; + + apshift = ppc_hash64_hpte_page_shift_noslb(cpu, pteh, ptel); + if (!apshift) { + /* Bad page size encoding */ + return H_PARAMETER; + } + + raddr = (ptel & HPTE64_R_RPN) & ~((1ULL << apshift) - 1); + + if (is_ram_address(spapr, raddr)) { + /* Regular RAM - should have WIMG=0010 */ + if ((ptel & HPTE64_R_WIMG) != HPTE64_R_M) { + return H_PARAMETER; + } + } else { + target_ulong wimg_flags; + /* Looks like an IO address */ + /* FIXME: What WIMG combinations could be sensible for IO? + * For now we allow WIMG=010x, but are there others? */ + /* FIXME: Should we check against registered IO addresses? */ + wimg_flags = (ptel & (HPTE64_R_W | HPTE64_R_I | HPTE64_R_M)); + + if (wimg_flags != HPTE64_R_I && + wimg_flags != (HPTE64_R_I | HPTE64_R_M)) { + return H_PARAMETER; + } + } + + pteh &= ~0x60ULL; + + if (!valid_ptex(cpu, ptex)) { + return H_PARAMETER; + } + + slot = ptex & 7ULL; + ptex = ptex & ~7ULL; + + if (likely((flags & H_EXACT) == 0)) { + hptes = ppc_hash64_map_hptes(cpu, ptex, HPTES_PER_GROUP); + for (slot = 0; slot < 8; slot++) { + if (!(ppc_hash64_hpte0(cpu, hptes, slot) & HPTE64_V_VALID)) { + break; + } + } + ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP); + if (slot == 8) { + return H_PTEG_FULL; + } + } else { + hptes = ppc_hash64_map_hptes(cpu, ptex + slot, 1); + if (ppc_hash64_hpte0(cpu, hptes, 0) & HPTE64_V_VALID) { + ppc_hash64_unmap_hptes(cpu, hptes, ptex + slot, 1); + return H_PTEG_FULL; + } + ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1); + } + + spapr_store_hpte(cpu, ptex + slot, pteh | HPTE64_V_HPTE_DIRTY, ptel); + + args[0] = ptex + slot; + return H_SUCCESS; +} + +typedef enum { + REMOVE_SUCCESS = 0, + REMOVE_NOT_FOUND = 1, + REMOVE_PARM = 2, + REMOVE_HW = 3, +} RemoveResult; + +static RemoveResult remove_hpte(PowerPCCPU *cpu + , target_ulong ptex, + target_ulong avpn, + target_ulong flags, + target_ulong *vp, target_ulong *rp) +{ + const ppc_hash_pte64_t *hptes; + target_ulong v, r; + + if (!valid_ptex(cpu, ptex)) { + return REMOVE_PARM; + } + + hptes = ppc_hash64_map_hptes(cpu, ptex, 1); + v = ppc_hash64_hpte0(cpu, hptes, 0); + r = ppc_hash64_hpte1(cpu, hptes, 0); + ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1); + + if ((v & HPTE64_V_VALID) == 0 || + ((flags & H_AVPN) && (v & ~0x7fULL) != avpn) || + ((flags & H_ANDCOND) && (v & avpn) != 0)) { + return REMOVE_NOT_FOUND; + } + *vp = v; + *rp = r; + spapr_store_hpte(cpu, ptex, HPTE64_V_HPTE_DIRTY, 0); + ppc_hash64_tlb_flush_hpte(cpu, ptex, v, r); + return REMOVE_SUCCESS; +} + +static target_ulong h_remove(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + CPUPPCState *env = &cpu->env; + target_ulong flags = args[0]; + target_ulong ptex = args[1]; + target_ulong avpn = args[2]; + RemoveResult ret; + + ret = remove_hpte(cpu, ptex, avpn, flags, + &args[0], &args[1]); + + switch (ret) { + case REMOVE_SUCCESS: + check_tlb_flush(env, true); + return H_SUCCESS; + + case REMOVE_NOT_FOUND: + return H_NOT_FOUND; + + case REMOVE_PARM: + return H_PARAMETER; + + case REMOVE_HW: + return H_HARDWARE; + } + + g_assert_not_reached(); +} + +#define H_BULK_REMOVE_TYPE 0xc000000000000000ULL +#define H_BULK_REMOVE_REQUEST 0x4000000000000000ULL +#define H_BULK_REMOVE_RESPONSE 0x8000000000000000ULL +#define H_BULK_REMOVE_END 0xc000000000000000ULL +#define H_BULK_REMOVE_CODE 0x3000000000000000ULL +#define H_BULK_REMOVE_SUCCESS 0x0000000000000000ULL +#define H_BULK_REMOVE_NOT_FOUND 0x1000000000000000ULL +#define H_BULK_REMOVE_PARM 0x2000000000000000ULL +#define H_BULK_REMOVE_HW 0x3000000000000000ULL +#define H_BULK_REMOVE_RC 0x0c00000000000000ULL +#define H_BULK_REMOVE_FLAGS 0x0300000000000000ULL +#define H_BULK_REMOVE_ABSOLUTE 0x0000000000000000ULL +#define H_BULK_REMOVE_ANDCOND 0x0100000000000000ULL +#define H_BULK_REMOVE_AVPN 0x0200000000000000ULL +#define H_BULK_REMOVE_PTEX 0x00ffffffffffffffULL + +#define H_BULK_REMOVE_MAX_BATCH 4 + +static target_ulong h_bulk_remove(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + CPUPPCState *env = &cpu->env; + int i; + target_ulong rc = H_SUCCESS; + + for (i = 0; i < H_BULK_REMOVE_MAX_BATCH; i++) { + target_ulong *tsh = &args[i*2]; + target_ulong tsl = args[i*2 + 1]; + target_ulong v, r, ret; + + if ((*tsh & H_BULK_REMOVE_TYPE) == H_BULK_REMOVE_END) { + break; + } else if ((*tsh & H_BULK_REMOVE_TYPE) != H_BULK_REMOVE_REQUEST) { + return H_PARAMETER; + } + + *tsh &= H_BULK_REMOVE_PTEX | H_BULK_REMOVE_FLAGS; + *tsh |= H_BULK_REMOVE_RESPONSE; + + if ((*tsh & H_BULK_REMOVE_ANDCOND) && (*tsh & H_BULK_REMOVE_AVPN)) { + *tsh |= H_BULK_REMOVE_PARM; + return H_PARAMETER; + } + + ret = remove_hpte(cpu, *tsh & H_BULK_REMOVE_PTEX, tsl, + (*tsh & H_BULK_REMOVE_FLAGS) >> 26, + &v, &r); + + *tsh |= ret << 60; + + switch (ret) { + case REMOVE_SUCCESS: + *tsh |= (r & (HPTE64_R_C | HPTE64_R_R)) << 43; + break; + + case REMOVE_PARM: + rc = H_PARAMETER; + goto exit; + + case REMOVE_HW: + rc = H_HARDWARE; + goto exit; + } + } + exit: + check_tlb_flush(env, true); + + return rc; +} + +static target_ulong h_protect(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + CPUPPCState *env = &cpu->env; + target_ulong flags = args[0]; + target_ulong ptex = args[1]; + target_ulong avpn = args[2]; + const ppc_hash_pte64_t *hptes; + target_ulong v, r; + + if (!valid_ptex(cpu, ptex)) { + return H_PARAMETER; + } + + hptes = ppc_hash64_map_hptes(cpu, ptex, 1); + v = ppc_hash64_hpte0(cpu, hptes, 0); + r = ppc_hash64_hpte1(cpu, hptes, 0); + ppc_hash64_unmap_hptes(cpu, hptes, ptex, 1); + + if ((v & HPTE64_V_VALID) == 0 || + ((flags & H_AVPN) && (v & ~0x7fULL) != avpn)) { + return H_NOT_FOUND; + } + + r &= ~(HPTE64_R_PP0 | HPTE64_R_PP | HPTE64_R_N | + HPTE64_R_KEY_HI | HPTE64_R_KEY_LO); + r |= (flags << 55) & HPTE64_R_PP0; + r |= (flags << 48) & HPTE64_R_KEY_HI; + r |= flags & (HPTE64_R_PP | HPTE64_R_N | HPTE64_R_KEY_LO); + spapr_store_hpte(cpu, ptex, + (v & ~HPTE64_V_VALID) | HPTE64_V_HPTE_DIRTY, 0); + ppc_hash64_tlb_flush_hpte(cpu, ptex, v, r); + /* Flush the tlb */ + check_tlb_flush(env, true); + /* Don't need a memory barrier, due to qemu's global lock */ + spapr_store_hpte(cpu, ptex, v | HPTE64_V_HPTE_DIRTY, r); + return H_SUCCESS; +} + +static target_ulong h_read(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + target_ulong flags = args[0]; + target_ulong ptex = args[1]; + int i, ridx, n_entries = 1; + const ppc_hash_pte64_t *hptes; + + if (!valid_ptex(cpu, ptex)) { + return H_PARAMETER; + } + + if (flags & H_READ_4) { + /* Clear the two low order bits */ + ptex &= ~(3ULL); + n_entries = 4; + } + + hptes = ppc_hash64_map_hptes(cpu, ptex, n_entries); + for (i = 0, ridx = 0; i < n_entries; i++) { + args[ridx++] = ppc_hash64_hpte0(cpu, hptes, i); + args[ridx++] = ppc_hash64_hpte1(cpu, hptes, i); + } + ppc_hash64_unmap_hptes(cpu, hptes, ptex, n_entries); + + return H_SUCCESS; +} + +struct SpaprPendingHpt { + /* These fields are read-only after initialization */ + int shift; + QemuThread thread; + + /* These fields are protected by the BQL */ + bool complete; + + /* These fields are private to the preparation thread if + * !complete, otherwise protected by the BQL */ + int ret; + void *hpt; +}; + +static void free_pending_hpt(SpaprPendingHpt *pending) +{ + if (pending->hpt) { + qemu_vfree(pending->hpt); + } + + g_free(pending); +} + +static void *hpt_prepare_thread(void *opaque) +{ + SpaprPendingHpt *pending = opaque; + size_t size = 1ULL << pending->shift; + + pending->hpt = qemu_try_memalign(size, size); + if (pending->hpt) { + memset(pending->hpt, 0, size); + pending->ret = H_SUCCESS; + } else { + pending->ret = H_NO_MEM; + } + + qemu_mutex_lock_iothread(); + + if (SPAPR_MACHINE(qdev_get_machine())->pending_hpt == pending) { + /* Ready to go */ + pending->complete = true; + } else { + /* We've been cancelled, clean ourselves up */ + free_pending_hpt(pending); + } + + qemu_mutex_unlock_iothread(); + return NULL; +} + +/* Must be called with BQL held */ +static void cancel_hpt_prepare(SpaprMachineState *spapr) +{ + SpaprPendingHpt *pending = spapr->pending_hpt; + + /* Let the thread know it's cancelled */ + spapr->pending_hpt = NULL; + + if (!pending) { + /* Nothing to do */ + return; + } + + if (!pending->complete) { + /* thread will clean itself up */ + return; + } + + free_pending_hpt(pending); +} + +target_ulong softmmu_resize_hpt_prepare(PowerPCCPU *cpu, + SpaprMachineState *spapr, + target_ulong shift) +{ + SpaprPendingHpt *pending = spapr->pending_hpt; + + if (pending) { + /* something already in progress */ + if (pending->shift == shift) { + /* and it's suitable */ + if (pending->complete) { + return pending->ret; + } else { + return H_LONG_BUSY_ORDER_100_MSEC; + } + } + + /* not suitable, cancel and replace */ + cancel_hpt_prepare(spapr); + } + + if (!shift) { + /* nothing to do */ + return H_SUCCESS; + } + + /* start new prepare */ + + pending = g_new0(SpaprPendingHpt, 1); + pending->shift = shift; + pending->ret = H_HARDWARE; + + qemu_thread_create(&pending->thread, "sPAPR HPT prepare", + hpt_prepare_thread, pending, QEMU_THREAD_DETACHED); + + spapr->pending_hpt = pending; + + /* In theory we could estimate the time more accurately based on + * the new size, but there's not much point */ + return H_LONG_BUSY_ORDER_100_MSEC; +} + +static uint64_t new_hpte_load0(void *htab, uint64_t pteg, int slot) +{ + uint8_t *addr = htab; + + addr += pteg * HASH_PTEG_SIZE_64; + addr += slot * HASH_PTE_SIZE_64; + return ldq_p(addr); +} + +static void new_hpte_store(void *htab, uint64_t pteg, int slot, + uint64_t pte0, uint64_t pte1) +{ + uint8_t *addr = htab; + + addr += pteg * HASH_PTEG_SIZE_64; + addr += slot * HASH_PTE_SIZE_64; + + stq_p(addr, pte0); + stq_p(addr + HASH_PTE_SIZE_64 / 2, pte1); +} + +static int rehash_hpte(PowerPCCPU *cpu, + const ppc_hash_pte64_t *hptes, + void *old_hpt, uint64_t oldsize, + void *new_hpt, uint64_t newsize, + uint64_t pteg, int slot) +{ + uint64_t old_hash_mask = (oldsize >> 7) - 1; + uint64_t new_hash_mask = (newsize >> 7) - 1; + target_ulong pte0 = ppc_hash64_hpte0(cpu, hptes, slot); + target_ulong pte1; + uint64_t avpn; + unsigned base_pg_shift; + uint64_t hash, new_pteg, replace_pte0; + + if (!(pte0 & HPTE64_V_VALID) || !(pte0 & HPTE64_V_BOLTED)) { + return H_SUCCESS; + } + + pte1 = ppc_hash64_hpte1(cpu, hptes, slot); + + base_pg_shift = ppc_hash64_hpte_page_shift_noslb(cpu, pte0, pte1); + assert(base_pg_shift); /* H_ENTER shouldn't allow a bad encoding */ + avpn = HPTE64_V_AVPN_VAL(pte0) & ~(((1ULL << base_pg_shift) - 1) >> 23); + + if (pte0 & HPTE64_V_SECONDARY) { + pteg = ~pteg; + } + + if ((pte0 & HPTE64_V_SSIZE) == HPTE64_V_SSIZE_256M) { + uint64_t offset, vsid; + + /* We only have 28 - 23 bits of offset in avpn */ + offset = (avpn & 0x1f) << 23; + vsid = avpn >> 5; + /* We can find more bits from the pteg value */ + if (base_pg_shift < 23) { + offset |= ((vsid ^ pteg) & old_hash_mask) << base_pg_shift; + } + + hash = vsid ^ (offset >> base_pg_shift); + } else if ((pte0 & HPTE64_V_SSIZE) == HPTE64_V_SSIZE_1T) { + uint64_t offset, vsid; + + /* We only have 40 - 23 bits of seg_off in avpn */ + offset = (avpn & 0x1ffff) << 23; + vsid = avpn >> 17; + if (base_pg_shift < 23) { + offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) + << base_pg_shift; + } + + hash = vsid ^ (vsid << 25) ^ (offset >> base_pg_shift); + } else { + error_report("rehash_pte: Bad segment size in HPTE"); + return H_HARDWARE; + } + + new_pteg = hash & new_hash_mask; + if (pte0 & HPTE64_V_SECONDARY) { + assert(~pteg == (hash & old_hash_mask)); + new_pteg = ~new_pteg; + } else { + assert(pteg == (hash & old_hash_mask)); + } + assert((oldsize != newsize) || (pteg == new_pteg)); + replace_pte0 = new_hpte_load0(new_hpt, new_pteg, slot); + /* + * Strictly speaking, we don't need all these tests, since we only + * ever rehash bolted HPTEs. We might in future handle non-bolted + * HPTEs, though so make the logic correct for those cases as + * well. + */ + if (replace_pte0 & HPTE64_V_VALID) { + assert(newsize < oldsize); + if (replace_pte0 & HPTE64_V_BOLTED) { + if (pte0 & HPTE64_V_BOLTED) { + /* Bolted collision, nothing we can do */ + return H_PTEG_FULL; + } else { + /* Discard this hpte */ + return H_SUCCESS; + } + } + } + + new_hpte_store(new_hpt, new_pteg, slot, pte0, pte1); + return H_SUCCESS; +} + +static int rehash_hpt(PowerPCCPU *cpu, + void *old_hpt, uint64_t oldsize, + void *new_hpt, uint64_t newsize) +{ + uint64_t n_ptegs = oldsize >> 7; + uint64_t pteg; + int slot; + int rc; + + for (pteg = 0; pteg < n_ptegs; pteg++) { + hwaddr ptex = pteg * HPTES_PER_GROUP; + const ppc_hash_pte64_t *hptes + = ppc_hash64_map_hptes(cpu, ptex, HPTES_PER_GROUP); + + if (!hptes) { + return H_HARDWARE; + } + + for (slot = 0; slot < HPTES_PER_GROUP; slot++) { + rc = rehash_hpte(cpu, hptes, old_hpt, oldsize, new_hpt, newsize, + pteg, slot); + if (rc != H_SUCCESS) { + ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP); + return rc; + } + } + ppc_hash64_unmap_hptes(cpu, hptes, ptex, HPTES_PER_GROUP); + } + + return H_SUCCESS; +} + +target_ulong softmmu_resize_hpt_commit(PowerPCCPU *cpu, + SpaprMachineState *spapr, + target_ulong flags, + target_ulong shift) +{ + SpaprPendingHpt *pending = spapr->pending_hpt; + int rc; + size_t newsize; + + if (flags != 0) { + return H_PARAMETER; + } + + if (!pending || (pending->shift != shift)) { + /* no matching prepare */ + return H_CLOSED; + } + + if (!pending->complete) { + /* prepare has not completed */ + return H_BUSY; + } + + /* Shouldn't have got past PREPARE without an HPT */ + g_assert(spapr->htab_shift); + + newsize = 1ULL << pending->shift; + rc = rehash_hpt(cpu, spapr->htab, HTAB_SIZE(spapr), + pending->hpt, newsize); + if (rc == H_SUCCESS) { + qemu_vfree(spapr->htab); + spapr->htab = pending->hpt; + spapr->htab_shift = pending->shift; + + push_sregs_to_kvm_pr(spapr); + + pending->hpt = NULL; /* so it's not free()d */ + } + + /* Clean up */ + spapr->pending_hpt = NULL; + free_pending_hpt(pending); + + return rc; +} + +static void hypercall_register_types(void) +{ + /* hcall-pft */ + spapr_register_hypercall(H_ENTER, h_enter); + spapr_register_hypercall(H_REMOVE, h_remove); + spapr_register_hypercall(H_PROTECT, h_protect); + spapr_register_hypercall(H_READ, h_read); + + /* hcall-bulk */ + spapr_register_hypercall(H_BULK_REMOVE, h_bulk_remove); + +} + +type_init(hypercall_register_types) diff --git a/hw/ppc/spapr_tpm_proxy.c b/hw/ppc/spapr_tpm_proxy.c index a01f81f9e0..2454086744 100644 --- a/hw/ppc/spapr_tpm_proxy.c +++ b/hw/ppc/spapr_tpm_proxy.c @@ -15,7 +15,6 @@ #include "qapi/error.h" #include "qemu/error-report.h" #include "sysemu/reset.h" -#include "cpu.h" #include "hw/ppc/spapr.h" #include "hw/qdev-properties.h" #include "trace.h" diff --git a/hw/ppc/spapr_vio.c b/hw/ppc/spapr_vio.c index ef06e0362c..b59452bcd6 100644 --- a/hw/ppc/spapr_vio.c +++ b/hw/ppc/spapr_vio.c @@ -310,7 +310,7 @@ int spapr_vio_send_crq(SpaprVioDevice *dev, uint8_t *crq) static void spapr_vio_quiesce_one(SpaprVioDevice *dev) { if (dev->tcet) { - device_legacy_reset(DEVICE(dev->tcet)); + device_cold_reset(DEVICE(dev->tcet)); } free_crq(dev); } diff --git a/hw/ppc/spapr_vof.c b/hw/ppc/spapr_vof.c new file mode 100644 index 0000000000..40ce8fe003 --- /dev/null +++ b/hw/ppc/spapr_vof.c @@ -0,0 +1,167 @@ +/* + * SPAPR machine hooks to Virtual Open Firmware, + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qapi/error.h" +#include "hw/ppc/spapr.h" +#include "hw/ppc/spapr_vio.h" +#include "hw/ppc/spapr_cpu_core.h" +#include "hw/ppc/fdt.h" +#include "hw/ppc/vof.h" +#include "sysemu/sysemu.h" +#include "qom/qom-qobject.h" +#include "trace.h" + +target_ulong spapr_h_vof_client(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *_args) +{ + int ret = vof_client_call(MACHINE(spapr), spapr->vof, spapr->fdt_blob, + ppc64_phys_to_real(_args[0])); + + if (ret) { + return H_PARAMETER; + } + return H_SUCCESS; +} + +void spapr_vof_client_dt_finalize(SpaprMachineState *spapr, void *fdt) +{ + char *stdout_path = spapr_vio_stdout_path(spapr->vio_bus); + + vof_build_dt(fdt, spapr->vof); + + if (spapr->vof->bootargs) { + int chosen; + + _FDT(chosen = fdt_path_offset(fdt, "/chosen")); + /* + * If the client did not change "bootargs", spapr_dt_chosen() must have + * stored machine->kernel_cmdline in it before getting here. + */ + _FDT(fdt_setprop_string(fdt, chosen, "bootargs", spapr->vof->bootargs)); + } + + /* + * SLOF-less setup requires an open instance of stdout for early + * kernel printk. By now all phandles are settled so we can open + * the default serial console. + */ + if (stdout_path) { + _FDT(vof_client_open_store(fdt, spapr->vof, "/chosen", "stdout", + stdout_path)); + } +} + +void spapr_vof_reset(SpaprMachineState *spapr, void *fdt, Error **errp) +{ + target_ulong stack_ptr; + Vof *vof = spapr->vof; + PowerPCCPU *first_ppc_cpu = POWERPC_CPU(first_cpu); + + vof_init(vof, spapr->rma_size, errp); + + stack_ptr = vof_claim(vof, 0, VOF_STACK_SIZE, VOF_STACK_SIZE); + if (stack_ptr == -1) { + error_setg(errp, "Memory allocation for stack failed"); + return; + } + /* Stack grows downwards plus reserve space for the minimum stack frame */ + stack_ptr += VOF_STACK_SIZE - 0x20; + + if (spapr->kernel_size && + vof_claim(vof, spapr->kernel_addr, spapr->kernel_size, 0) == -1) { + error_setg(errp, "Memory for kernel is in use"); + return; + } + + if (spapr->initrd_size && + vof_claim(vof, spapr->initrd_base, spapr->initrd_size, 0) == -1) { + error_setg(errp, "Memory for initramdisk is in use"); + return; + } + + spapr_vof_client_dt_finalize(spapr, fdt); + + spapr_cpu_set_entry_state(first_ppc_cpu, SPAPR_ENTRY_POINT, + stack_ptr, spapr->initrd_base, + spapr->initrd_size); + /* VOF is 32bit BE so enforce MSR here */ + first_ppc_cpu->env.msr &= ~((1ULL << MSR_SF) | (1ULL << MSR_LE)); + + /* + * At this point the expected allocation map is: + * + * 0..c38 - the initial firmware + * 8000..10000 - stack + * 400000.. - kernel + * 3ea0000.. - initramdisk + * + * We skip writing FDT as nothing expects it; OF client interface is + * going to be used for reading the device tree. + */ +} + +void spapr_vof_quiesce(MachineState *ms) +{ + SpaprMachineState *spapr = SPAPR_MACHINE(ms); + + spapr->fdt_size = fdt_totalsize(spapr->fdt_blob); + spapr->fdt_initial_size = spapr->fdt_size; +} + +bool spapr_vof_setprop(MachineState *ms, const char *path, const char *propname, + void *val, int vallen) +{ + SpaprMachineState *spapr = SPAPR_MACHINE(ms); + + /* + * We only allow changing properties which we know how to update in QEMU + * OR + * the ones which we know that they need to survive during "quiesce". + */ + + if (strcmp(path, "/rtas") == 0) { + if (strcmp(propname, "linux,rtas-base") == 0 || + strcmp(propname, "linux,rtas-entry") == 0) { + /* These need to survive quiesce so let them store in the FDT */ + return true; + } + } + + if (strcmp(path, "/chosen") == 0) { + if (strcmp(propname, "bootargs") == 0) { + Vof *vof = spapr->vof; + + g_free(vof->bootargs); + vof->bootargs = g_strndup(val, vallen); + return true; + } + if (strcmp(propname, "linux,initrd-start") == 0) { + if (vallen == sizeof(uint32_t)) { + spapr->initrd_base = ldl_be_p(val); + return true; + } + if (vallen == sizeof(uint64_t)) { + spapr->initrd_base = ldq_be_p(val); + return true; + } + return false; + } + if (strcmp(propname, "linux,initrd-end") == 0) { + if (vallen == sizeof(uint32_t)) { + spapr->initrd_size = ldl_be_p(val) - spapr->initrd_base; + return true; + } + if (vallen == sizeof(uint64_t)) { + spapr->initrd_size = ldq_be_p(val) - spapr->initrd_base; + return true; + } + return false; + } + } + + return true; +} diff --git a/hw/ppc/trace-events b/hw/ppc/trace-events index b4bbfbb013..da6e74b80d 100644 --- a/hw/ppc/trace-events +++ b/hw/ppc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # spapr_pci.c spapr_pci_msi(const char *msg, uint32_t ca) "%s (cfg=0x%x)" @@ -71,6 +71,30 @@ spapr_rtas_ibm_configure_connector_invalid(uint32_t index) "DRC index: 0x%"PRIx3 spapr_vio_h_reg_crq(uint64_t reg, uint64_t queue_addr, uint64_t queue_len) "CRQ for dev 0x%" PRIx64 " registered at 0x%" PRIx64 "/0x%" PRIx64 spapr_vio_free_crq(uint32_t reg) "CRQ for dev 0x%" PRIx32 " freed" +# vof.c +vof_error_str_truncated(const char *s, int len) "%s truncated to %d" +vof_error_param(const char *method, int nargscheck, int nretcheck, int nargs, int nret) "%s takes/returns %d/%d, not %d/%d" +vof_error_unknown_service(const char *service, int nargs, int nret) "\"%s\" args=%d rets=%d" +vof_error_unknown_method(const char *method) "\"%s\"" +vof_error_unknown_ihandle_close(uint32_t ih) "ih=0x%x" +vof_error_unknown_path(const char *path) "\"%s\"" +vof_error_write(uint32_t ih) "ih=0x%x" +vof_finddevice(const char *path, uint32_t ph) "\"%s\" => ph=0x%x" +vof_claim(uint32_t virt, uint32_t size, uint32_t align, uint32_t ret) "virt=0x%x size=0x%x align=0x%x => 0x%x" +vof_release(uint32_t virt, uint32_t size, uint32_t ret) "virt=0x%x size=0x%x => 0x%x" +vof_method(uint32_t ihandle, const char *method, uint32_t param, uint32_t ret, uint32_t ret2) "ih=0x%x \"%s\"(0x%x) => 0x%x 0x%x" +vof_getprop(uint32_t ph, const char *prop, uint32_t ret, const char *val) "ph=0x%x \"%s\" => len=%d [%s]" +vof_getproplen(uint32_t ph, const char *prop, uint32_t ret) "ph=0x%x \"%s\" => len=%d" +vof_setprop(uint32_t ph, const char *prop, const char *val, uint32_t vallen, uint32_t ret) "ph=0x%x \"%s\" [%s] len=%d => ret=%d" +vof_open(const char *path, uint32_t ph, uint32_t ih) "%s ph=0x%x => ih=0x%x" +vof_interpret(const char *cmd, uint32_t param1, uint32_t param2, uint32_t ret, uint32_t ret2) "[%s] 0x%x 0x%x => 0x%x 0x%x" +vof_package_to_path(uint32_t ph, const char *tmp, int ret) "ph=0x%x => %s len=%d" +vof_instance_to_path(uint32_t ih, uint32_t ph, const char *tmp, int ret) "ih=0x%x ph=0x%x => %s len=%d" +vof_instance_to_package(uint32_t ih, uint32_t ph) "ih=0x%x => ph=0x%x" +vof_write(uint32_t ih, unsigned cb, const char *msg) "ih=0x%x [%u] \"%s\"" +vof_avail(uint64_t start, uint64_t end, uint64_t size) "0x%"PRIx64"..0x%"PRIx64" size=0x%"PRIx64 +vof_claimed(uint64_t start, uint64_t end, uint64_t size) "0x%"PRIx64"..0x%"PRIx64" size=0x%"PRIx64 + # ppc.c ppc_tb_adjust(uint64_t offs1, uint64_t offs2, int64_t diff, int64_t seconds) "adjusted from 0x%"PRIx64" to 0x%"PRIx64", diff %"PRId64" (%"PRId64"s)" diff --git a/hw/ppc/virtex_ml507.c b/hw/ppc/virtex_ml507.c index cb421570da..9c575403b8 100644 --- a/hw/ppc/virtex_ml507.c +++ b/hw/ppc/virtex_ml507.c @@ -38,9 +38,7 @@ #include "elf.h" #include "qapi/error.h" #include "qemu/error-report.h" -#include "qemu/log.h" #include "qemu/option.h" -#include "exec/address-spaces.h" #include "hw/intc/ppc-uic.h" #include "hw/ppc/ppc.h" diff --git a/hw/ppc/vof.c b/hw/ppc/vof.c new file mode 100644 index 0000000000..73adc44ec2 --- /dev/null +++ b/hw/ppc/vof.c @@ -0,0 +1,1062 @@ +/* + * QEMU PowerPC Virtual Open Firmware. + * + * This implements client interface from OpenFirmware IEEE1275 on the QEMU + * side to leave only a very basic firmware in the VM. + * + * Copyright (c) 2021 IBM Corporation. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/timer.h" +#include "qemu/range.h" +#include "qemu/units.h" +#include "qemu/log.h" +#include "qapi/error.h" +#include "exec/ram_addr.h" +#include "exec/address-spaces.h" +#include "hw/ppc/vof.h" +#include "hw/ppc/fdt.h" +#include "sysemu/runstate.h" +#include "qom/qom-qobject.h" +#include "trace.h" + +#include + +/* + * OF 1275 "nextprop" description suggests is it 32 bytes max but + * LoPAPR defines "ibm,query-interrupt-source-number" which is 33 chars long. + */ +#define OF_PROPNAME_LEN_MAX 64 + +#define VOF_MAX_PATH 256 +#define VOF_MAX_SETPROPLEN 2048 +#define VOF_MAX_METHODLEN 256 +#define VOF_MAX_FORTHCODE 256 +#define VOF_VTY_BUF_SIZE 256 + +typedef struct { + uint64_t start; + uint64_t size; +} OfClaimed; + +typedef struct { + char *path; /* the path used to open the instance */ + uint32_t phandle; +} OfInstance; + +static int readstr(hwaddr pa, char *buf, int size) +{ + if (VOF_MEM_READ(pa, buf, size) != MEMTX_OK) { + return -1; + } + if (strnlen(buf, size) == size) { + buf[size - 1] = '\0'; + trace_vof_error_str_truncated(buf, size); + return -1; + } + return 0; +} + +static bool cmpservice(const char *s, unsigned nargs, unsigned nret, + const char *s1, unsigned nargscheck, unsigned nretcheck) +{ + if (strcmp(s, s1)) { + return false; + } + if ((nargscheck && (nargs != nargscheck)) || + (nretcheck && (nret != nretcheck))) { + trace_vof_error_param(s, nargscheck, nretcheck, nargs, nret); + return false; + } + + return true; +} + +static void prop_format(char *tval, int tlen, const void *prop, int len) +{ + int i; + const unsigned char *c; + char *t; + const char bin[] = "..."; + + for (i = 0, c = prop; i < len; ++i, ++c) { + if (*c == '\0' && i == len - 1) { + strncpy(tval, prop, tlen - 1); + return; + } + if (*c < 0x20 || *c >= 0x80) { + break; + } + } + + for (i = 0, c = prop, t = tval; i < len; ++i, ++c) { + if (t >= tval + tlen - sizeof(bin) - 1 - 2 - 1) { + strcpy(t, bin); + return; + } + if (i && i % 4 == 0 && i != len - 1) { + strcat(t, " "); + ++t; + } + t += sprintf(t, "%02X", *c & 0xFF); + } +} + +static int get_path(const void *fdt, int offset, char *buf, int len) +{ + int ret; + + ret = fdt_get_path(fdt, offset, buf, len - 1); + if (ret < 0) { + return ret; + } + + buf[len - 1] = '\0'; + + return strlen(buf) + 1; +} + +static int phandle_to_path(const void *fdt, uint32_t ph, char *buf, int len) +{ + int ret; + + ret = fdt_node_offset_by_phandle(fdt, ph); + if (ret < 0) { + return ret; + } + + return get_path(fdt, ret, buf, len); +} + +static int path_offset(const void *fdt, const char *path) +{ + g_autofree char *p = NULL; + char *at; + + /* + * https://www.devicetree.org/open-firmware/bindings/ppc/release/ppc-2_1.html#HDR16 + * + * "Conversion from numeric representation to text representation shall use + * the lower case forms of the hexadecimal digits in the range a..f, + * suppressing leading zeros". + */ + p = g_strdup(path); + for (at = strchr(p, '@'); at && *at; ) { + if (*at == '/') { + at = strchr(at, '@'); + } else { + *at = tolower(*at); + ++at; + } + } + + return fdt_path_offset(fdt, p); +} + +static uint32_t vof_finddevice(const void *fdt, uint32_t nodeaddr) +{ + char fullnode[VOF_MAX_PATH]; + uint32_t ret = PROM_ERROR; + int offset; + + if (readstr(nodeaddr, fullnode, sizeof(fullnode))) { + return (uint32_t) ret; + } + + offset = path_offset(fdt, fullnode); + if (offset >= 0) { + ret = fdt_get_phandle(fdt, offset); + } + trace_vof_finddevice(fullnode, ret); + return ret; +} + +static const void *getprop(const void *fdt, int nodeoff, const char *propname, + int *proplen, bool *write0) +{ + const char *unit, *prop; + const void *ret = fdt_getprop(fdt, nodeoff, propname, proplen); + + if (ret) { + if (write0) { + *write0 = false; + } + return ret; + } + + if (strcmp(propname, "name")) { + return NULL; + } + /* + * We return a value for "name" from path if queried but property does not + * exist. @proplen does not include the unit part in this case. + */ + prop = fdt_get_name(fdt, nodeoff, proplen); + if (!prop) { + *proplen = 0; + return NULL; + } + + unit = memchr(prop, '@', *proplen); + if (unit) { + *proplen = unit - prop; + } + *proplen += 1; + + /* + * Since it might be cut at "@" and there will be no trailing zero + * in the prop buffer, tell the caller to write zero at the end. + */ + if (write0) { + *write0 = true; + } + return prop; +} + +static uint32_t vof_getprop(const void *fdt, uint32_t nodeph, uint32_t pname, + uint32_t valaddr, uint32_t vallen) +{ + char propname[OF_PROPNAME_LEN_MAX + 1]; + uint32_t ret = 0; + int proplen = 0; + const void *prop; + char trval[64] = ""; + int nodeoff = fdt_node_offset_by_phandle(fdt, nodeph); + bool write0; + + if (nodeoff < 0) { + return PROM_ERROR; + } + if (readstr(pname, propname, sizeof(propname))) { + return PROM_ERROR; + } + prop = getprop(fdt, nodeoff, propname, &proplen, &write0); + if (prop) { + const char zero = 0; + int cb = MIN(proplen, vallen); + + if (VOF_MEM_WRITE(valaddr, prop, cb) != MEMTX_OK || + /* if that was "name" with a unit address, overwrite '@' with '0' */ + (write0 && + cb == proplen && + VOF_MEM_WRITE(valaddr + cb - 1, &zero, 1) != MEMTX_OK)) { + ret = PROM_ERROR; + } else { + /* + * OF1275 says: + * "Size is either the actual size of the property, or -1 if name + * does not exist", hence returning proplen instead of cb. + */ + ret = proplen; + /* Do not format a value if tracepoint is silent, for performance */ + if (trace_event_get_state(TRACE_VOF_GETPROP) && + qemu_loglevel_mask(LOG_TRACE)) { + prop_format(trval, sizeof(trval), prop, ret); + } + } + } else { + ret = PROM_ERROR; + } + trace_vof_getprop(nodeph, propname, ret, trval); + + return ret; +} + +static uint32_t vof_getproplen(const void *fdt, uint32_t nodeph, uint32_t pname) +{ + char propname[OF_PROPNAME_LEN_MAX + 1]; + uint32_t ret = 0; + int proplen = 0; + const void *prop; + int nodeoff = fdt_node_offset_by_phandle(fdt, nodeph); + + if (nodeoff < 0) { + return PROM_ERROR; + } + if (readstr(pname, propname, sizeof(propname))) { + return PROM_ERROR; + } + prop = getprop(fdt, nodeoff, propname, &proplen, NULL); + if (prop) { + ret = proplen; + } else { + ret = PROM_ERROR; + } + trace_vof_getproplen(nodeph, propname, ret); + + return ret; +} + +static uint32_t vof_setprop(MachineState *ms, void *fdt, Vof *vof, + uint32_t nodeph, uint32_t pname, + uint32_t valaddr, uint32_t vallen) +{ + char propname[OF_PROPNAME_LEN_MAX + 1]; + uint32_t ret = PROM_ERROR; + int offset, rc; + char trval[64] = ""; + char nodepath[VOF_MAX_PATH] = ""; + Object *vmo = object_dynamic_cast(OBJECT(ms), TYPE_VOF_MACHINE_IF); + VofMachineIfClass *vmc; + g_autofree char *val = NULL; + + if (vallen > VOF_MAX_SETPROPLEN) { + goto trace_exit; + } + if (readstr(pname, propname, sizeof(propname))) { + goto trace_exit; + } + offset = fdt_node_offset_by_phandle(fdt, nodeph); + if (offset < 0) { + goto trace_exit; + } + rc = get_path(fdt, offset, nodepath, sizeof(nodepath)); + if (rc <= 0) { + goto trace_exit; + } + + val = g_malloc0(vallen); + if (VOF_MEM_READ(valaddr, val, vallen) != MEMTX_OK) { + goto trace_exit; + } + + if (!vmo) { + goto trace_exit; + } + + vmc = VOF_MACHINE_GET_CLASS(vmo); + if (!vmc->setprop || !vmc->setprop(ms, nodepath, propname, val, vallen)) { + goto trace_exit; + } + + rc = fdt_setprop(fdt, offset, propname, val, vallen); + if (rc) { + goto trace_exit; + } + + if (trace_event_get_state(TRACE_VOF_SETPROP) && + qemu_loglevel_mask(LOG_TRACE)) { + prop_format(trval, sizeof(trval), val, vallen); + } + ret = vallen; + +trace_exit: + trace_vof_setprop(nodeph, propname, trval, vallen, ret); + + return ret; +} + +static uint32_t vof_nextprop(const void *fdt, uint32_t phandle, + uint32_t prevaddr, uint32_t nameaddr) +{ + int offset, nodeoff = fdt_node_offset_by_phandle(fdt, phandle); + char prev[OF_PROPNAME_LEN_MAX + 1]; + const char *tmp; + + if (readstr(prevaddr, prev, sizeof(prev))) { + return PROM_ERROR; + } + + fdt_for_each_property_offset(offset, fdt, nodeoff) { + if (!fdt_getprop_by_offset(fdt, offset, &tmp, NULL)) { + return 0; + } + if (prev[0] == '\0' || strcmp(prev, tmp) == 0) { + if (prev[0] != '\0') { + offset = fdt_next_property_offset(fdt, offset); + if (offset < 0) { + return 0; + } + } + if (!fdt_getprop_by_offset(fdt, offset, &tmp, NULL)) { + return 0; + } + + if (VOF_MEM_WRITE(nameaddr, tmp, strlen(tmp) + 1) != MEMTX_OK) { + return PROM_ERROR; + } + return 1; + } + } + + return 0; +} + +static uint32_t vof_peer(const void *fdt, uint32_t phandle) +{ + uint32_t ret = 0; + int rc; + + if (phandle == 0) { + rc = fdt_path_offset(fdt, "/"); + } else { + rc = fdt_next_subnode(fdt, fdt_node_offset_by_phandle(fdt, phandle)); + } + + if (rc >= 0) { + ret = fdt_get_phandle(fdt, rc); + } + + return ret; +} + +static uint32_t vof_child(const void *fdt, uint32_t phandle) +{ + uint32_t ret = 0; + int rc = fdt_first_subnode(fdt, fdt_node_offset_by_phandle(fdt, phandle)); + + if (rc >= 0) { + ret = fdt_get_phandle(fdt, rc); + } + + return ret; +} + +static uint32_t vof_parent(const void *fdt, uint32_t phandle) +{ + uint32_t ret = 0; + int rc = fdt_parent_offset(fdt, fdt_node_offset_by_phandle(fdt, phandle)); + + if (rc >= 0) { + ret = fdt_get_phandle(fdt, rc); + } + + return ret; +} + +static uint32_t vof_do_open(void *fdt, Vof *vof, int offset, const char *path) +{ + uint32_t ret = PROM_ERROR; + OfInstance *inst = NULL; + + if (vof->of_instance_last == 0xFFFFFFFF) { + /* We do not recycle ihandles yet */ + goto trace_exit; + } + + inst = g_new0(OfInstance, 1); + inst->phandle = fdt_get_phandle(fdt, offset); + g_assert(inst->phandle); + ++vof->of_instance_last; + + inst->path = g_strdup(path); + g_hash_table_insert(vof->of_instances, + GINT_TO_POINTER(vof->of_instance_last), + inst); + ret = vof->of_instance_last; + +trace_exit: + trace_vof_open(path, inst ? inst->phandle : 0, ret); + + return ret; +} + +uint32_t vof_client_open_store(void *fdt, Vof *vof, const char *nodename, + const char *prop, const char *path) +{ + int offset, node = fdt_path_offset(fdt, nodename); + uint32_t inst; + + offset = fdt_path_offset(fdt, path); + if (offset < 0) { + trace_vof_error_unknown_path(path); + return PROM_ERROR; + } + + inst = vof_do_open(fdt, vof, offset, path); + + return fdt_setprop_cell(fdt, node, prop, inst) >= 0 ? 0 : PROM_ERROR; +} + +static uint32_t vof_open(void *fdt, Vof *vof, uint32_t pathaddr) +{ + char path[VOF_MAX_PATH]; + int offset; + + if (readstr(pathaddr, path, sizeof(path))) { + return PROM_ERROR; + } + + offset = path_offset(fdt, path); + if (offset < 0) { + trace_vof_error_unknown_path(path); + return PROM_ERROR; + } + + return vof_do_open(fdt, vof, offset, path); +} + +static void vof_close(Vof *vof, uint32_t ihandle) +{ + if (!g_hash_table_remove(vof->of_instances, GINT_TO_POINTER(ihandle))) { + trace_vof_error_unknown_ihandle_close(ihandle); + } +} + +static uint32_t vof_instance_to_package(Vof *vof, uint32_t ihandle) +{ + gpointer instp = g_hash_table_lookup(vof->of_instances, + GINT_TO_POINTER(ihandle)); + uint32_t ret = PROM_ERROR; + + if (instp) { + ret = ((OfInstance *)instp)->phandle; + } + trace_vof_instance_to_package(ihandle, ret); + + return ret; +} + +static uint32_t vof_package_to_path(const void *fdt, uint32_t phandle, + uint32_t buf, uint32_t len) +{ + int rc; + char tmp[VOF_MAX_PATH] = ""; + + rc = phandle_to_path(fdt, phandle, tmp, sizeof(tmp)); + if (rc > 0) { + if (VOF_MEM_WRITE(buf, tmp, rc) != MEMTX_OK) { + rc = -1; + } + } + + trace_vof_package_to_path(phandle, tmp, rc); + + return rc > 0 ? (uint32_t)rc : PROM_ERROR; +} + +static uint32_t vof_instance_to_path(void *fdt, Vof *vof, uint32_t ihandle, + uint32_t buf, uint32_t len) +{ + int rc = -1; + uint32_t phandle = vof_instance_to_package(vof, ihandle); + char tmp[VOF_MAX_PATH] = ""; + + if (phandle != -1) { + rc = phandle_to_path(fdt, phandle, tmp, sizeof(tmp)); + if (rc > 0) { + if (VOF_MEM_WRITE(buf, tmp, rc) != MEMTX_OK) { + rc = -1; + } + } + } + trace_vof_instance_to_path(ihandle, phandle, tmp, rc); + + return rc > 0 ? (uint32_t)rc : PROM_ERROR; +} + +static uint32_t vof_write(Vof *vof, uint32_t ihandle, uint32_t buf, + uint32_t len) +{ + char tmp[VOF_VTY_BUF_SIZE]; + unsigned cb; + OfInstance *inst = (OfInstance *) + g_hash_table_lookup(vof->of_instances, GINT_TO_POINTER(ihandle)); + + if (!inst) { + trace_vof_error_write(ihandle); + return PROM_ERROR; + } + + for ( ; len > 0; len -= cb) { + cb = MIN(len, sizeof(tmp) - 1); + if (VOF_MEM_READ(buf, tmp, cb) != MEMTX_OK) { + return PROM_ERROR; + } + + /* FIXME: there is no backend(s) yet so just call a trace */ + if (trace_event_get_state(TRACE_VOF_WRITE) && + qemu_loglevel_mask(LOG_TRACE)) { + tmp[cb] = '\0'; + trace_vof_write(ihandle, cb, tmp); + } + } + + return len; +} + +static void vof_claimed_dump(GArray *claimed) +{ + int i; + OfClaimed c; + + if (trace_event_get_state(TRACE_VOF_CLAIMED) && + qemu_loglevel_mask(LOG_TRACE)) { + + for (i = 0; i < claimed->len; ++i) { + c = g_array_index(claimed, OfClaimed, i); + trace_vof_claimed(c.start, c.start + c.size, c.size); + } + } +} + +static bool vof_claim_avail(GArray *claimed, uint64_t virt, uint64_t size) +{ + int i; + OfClaimed c; + + for (i = 0; i < claimed->len; ++i) { + c = g_array_index(claimed, OfClaimed, i); + if (ranges_overlap(c.start, c.size, virt, size)) { + return false; + } + } + + return true; +} + +static void vof_claim_add(GArray *claimed, uint64_t virt, uint64_t size) +{ + OfClaimed newclaim; + + newclaim.start = virt; + newclaim.size = size; + g_array_append_val(claimed, newclaim); +} + +static gint of_claimed_compare_func(gconstpointer a, gconstpointer b) +{ + return ((OfClaimed *)a)->start - ((OfClaimed *)b)->start; +} + +static void vof_dt_memory_available(void *fdt, GArray *claimed, uint64_t base) +{ + int i, n, offset, proplen = 0, sc, ac; + target_ulong mem0_end; + const uint8_t *mem0_reg; + g_autofree uint8_t *avail = NULL; + uint8_t *availcur; + + if (!fdt || !claimed) { + return; + } + + offset = fdt_path_offset(fdt, "/"); + _FDT(offset); + ac = fdt_address_cells(fdt, offset); + g_assert(ac == 1 || ac == 2); + sc = fdt_size_cells(fdt, offset); + g_assert(sc == 1 || sc == 2); + + offset = fdt_path_offset(fdt, "/memory@0"); + _FDT(offset); + + mem0_reg = fdt_getprop(fdt, offset, "reg", &proplen); + g_assert(mem0_reg && proplen == sizeof(uint32_t) * (ac + sc)); + if (sc == 2) { + mem0_end = be64_to_cpu(*(uint64_t *)(mem0_reg + sizeof(uint32_t) * ac)); + } else { + mem0_end = be32_to_cpu(*(uint32_t *)(mem0_reg + sizeof(uint32_t) * ac)); + } + + g_array_sort(claimed, of_claimed_compare_func); + vof_claimed_dump(claimed); + + /* + * VOF resides in the first page so we do not need to check if there is + * available memory before the first claimed block + */ + g_assert(claimed->len && (g_array_index(claimed, OfClaimed, 0).start == 0)); + + avail = g_malloc0(sizeof(uint32_t) * (ac + sc) * claimed->len); + for (i = 0, n = 0, availcur = avail; i < claimed->len; ++i) { + OfClaimed c = g_array_index(claimed, OfClaimed, i); + uint64_t start, size; + + start = c.start + c.size; + if (i < claimed->len - 1) { + OfClaimed cn = g_array_index(claimed, OfClaimed, i + 1); + + size = cn.start - start; + } else { + size = mem0_end - start; + } + + if (ac == 2) { + *(uint64_t *) availcur = cpu_to_be64(start); + } else { + *(uint32_t *) availcur = cpu_to_be32(start); + } + availcur += sizeof(uint32_t) * ac; + if (sc == 2) { + *(uint64_t *) availcur = cpu_to_be64(size); + } else { + *(uint32_t *) availcur = cpu_to_be32(size); + } + availcur += sizeof(uint32_t) * sc; + + if (size) { + trace_vof_avail(c.start + c.size, c.start + c.size + size, size); + ++n; + } + } + _FDT((fdt_setprop(fdt, offset, "available", avail, availcur - avail))); +} + +/* + * OF1275: + * "Allocates size bytes of memory. If align is zero, the allocated range + * begins at the virtual address virt. Otherwise, an aligned address is + * automatically chosen and the input argument virt is ignored". + * + * In other words, exactly one of @virt and @align is non-zero. + */ +uint64_t vof_claim(Vof *vof, uint64_t virt, uint64_t size, + uint64_t align) +{ + uint64_t ret; + + if (size == 0) { + ret = -1; + } else if (align == 0) { + if (!vof_claim_avail(vof->claimed, virt, size)) { + ret = -1; + } else { + ret = virt; + } + } else { + vof->claimed_base = QEMU_ALIGN_UP(vof->claimed_base, align); + while (1) { + if (vof->claimed_base >= vof->top_addr) { + error_report("Out of RMA memory for the OF client"); + return -1; + } + if (vof_claim_avail(vof->claimed, vof->claimed_base, size)) { + break; + } + vof->claimed_base += size; + } + ret = vof->claimed_base; + } + + if (ret != -1) { + vof->claimed_base = MAX(vof->claimed_base, ret + size); + vof_claim_add(vof->claimed, ret, size); + } + trace_vof_claim(virt, size, align, ret); + + return ret; +} + +static uint32_t vof_release(Vof *vof, uint64_t virt, uint64_t size) +{ + uint32_t ret = PROM_ERROR; + int i; + GArray *claimed = vof->claimed; + OfClaimed c; + + for (i = 0; i < claimed->len; ++i) { + c = g_array_index(claimed, OfClaimed, i); + if (c.start == virt && c.size == size) { + g_array_remove_index(claimed, i); + ret = 0; + break; + } + } + + trace_vof_release(virt, size, ret); + + return ret; +} + +static void vof_instantiate_rtas(Error **errp) +{ + error_setg(errp, "The firmware should have instantiated RTAS"); +} + +static uint32_t vof_call_method(MachineState *ms, Vof *vof, uint32_t methodaddr, + uint32_t ihandle, uint32_t param1, + uint32_t param2, uint32_t param3, + uint32_t param4, uint32_t *ret2) +{ + uint32_t ret = PROM_ERROR; + char method[VOF_MAX_METHODLEN] = ""; + OfInstance *inst; + + if (!ihandle) { + goto trace_exit; + } + + inst = (OfInstance *)g_hash_table_lookup(vof->of_instances, + GINT_TO_POINTER(ihandle)); + if (!inst) { + goto trace_exit; + } + + if (readstr(methodaddr, method, sizeof(method))) { + goto trace_exit; + } + + if (strcmp(inst->path, "/") == 0) { + if (strcmp(method, "ibm,client-architecture-support") == 0) { + Object *vmo = object_dynamic_cast(OBJECT(ms), TYPE_VOF_MACHINE_IF); + + if (vmo) { + VofMachineIfClass *vmc = VOF_MACHINE_GET_CLASS(vmo); + + g_assert(vmc->client_architecture_support); + ret = (uint32_t)vmc->client_architecture_support(ms, first_cpu, + param1); + } + + *ret2 = 0; + } + } else if (strcmp(inst->path, "/rtas") == 0) { + if (strcmp(method, "instantiate-rtas") == 0) { + vof_instantiate_rtas(&error_fatal); + ret = 0; + *ret2 = param1; /* rtas-base */ + } + } else { + trace_vof_error_unknown_method(method); + } + +trace_exit: + trace_vof_method(ihandle, method, param1, ret, *ret2); + + return ret; +} + +static uint32_t vof_call_interpret(uint32_t cmdaddr, uint32_t param1, + uint32_t param2, uint32_t *ret2) +{ + uint32_t ret = PROM_ERROR; + char cmd[VOF_MAX_FORTHCODE] = ""; + + /* No interpret implemented so just call a trace */ + readstr(cmdaddr, cmd, sizeof(cmd)); + trace_vof_interpret(cmd, param1, param2, ret, *ret2); + + return ret; +} + +static void vof_quiesce(MachineState *ms, void *fdt, Vof *vof) +{ + Object *vmo = object_dynamic_cast(OBJECT(ms), TYPE_VOF_MACHINE_IF); + /* After "quiesce", no change is expected to the FDT, pack FDT to ensure */ + int rc = fdt_pack(fdt); + + assert(rc == 0); + + if (vmo) { + VofMachineIfClass *vmc = VOF_MACHINE_GET_CLASS(vmo); + + if (vmc->quiesce) { + vmc->quiesce(ms); + } + } + + vof_claimed_dump(vof->claimed); +} + +static uint32_t vof_client_handle(MachineState *ms, void *fdt, Vof *vof, + const char *service, + uint32_t *args, unsigned nargs, + uint32_t *rets, unsigned nrets) +{ + uint32_t ret = 0; + + /* @nrets includes the value which this function returns */ +#define cmpserv(s, a, r) \ + cmpservice(service, nargs, nrets, (s), (a), (r)) + + if (cmpserv("finddevice", 1, 1)) { + ret = vof_finddevice(fdt, args[0]); + } else if (cmpserv("getprop", 4, 1)) { + ret = vof_getprop(fdt, args[0], args[1], args[2], args[3]); + } else if (cmpserv("getproplen", 2, 1)) { + ret = vof_getproplen(fdt, args[0], args[1]); + } else if (cmpserv("setprop", 4, 1)) { + ret = vof_setprop(ms, fdt, vof, args[0], args[1], args[2], args[3]); + } else if (cmpserv("nextprop", 3, 1)) { + ret = vof_nextprop(fdt, args[0], args[1], args[2]); + } else if (cmpserv("peer", 1, 1)) { + ret = vof_peer(fdt, args[0]); + } else if (cmpserv("child", 1, 1)) { + ret = vof_child(fdt, args[0]); + } else if (cmpserv("parent", 1, 1)) { + ret = vof_parent(fdt, args[0]); + } else if (cmpserv("open", 1, 1)) { + ret = vof_open(fdt, vof, args[0]); + } else if (cmpserv("close", 1, 0)) { + vof_close(vof, args[0]); + } else if (cmpserv("instance-to-package", 1, 1)) { + ret = vof_instance_to_package(vof, args[0]); + } else if (cmpserv("package-to-path", 3, 1)) { + ret = vof_package_to_path(fdt, args[0], args[1], args[2]); + } else if (cmpserv("instance-to-path", 3, 1)) { + ret = vof_instance_to_path(fdt, vof, args[0], args[1], args[2]); + } else if (cmpserv("write", 3, 1)) { + ret = vof_write(vof, args[0], args[1], args[2]); + } else if (cmpserv("claim", 3, 1)) { + uint64_t ret64 = vof_claim(vof, args[0], args[1], args[2]); + + if (ret64 < 0x100000000UL) { + vof_dt_memory_available(fdt, vof->claimed, vof->claimed_base); + ret = (uint32_t)ret64; + } else { + if (ret64 != -1) { + vof_release(vof, ret, args[1]); + } + ret = PROM_ERROR; + } + } else if (cmpserv("release", 2, 0)) { + ret = vof_release(vof, args[0], args[1]); + if (ret != PROM_ERROR) { + vof_dt_memory_available(fdt, vof->claimed, vof->claimed_base); + } + } else if (cmpserv("call-method", 0, 0)) { + ret = vof_call_method(ms, vof, args[0], args[1], args[2], args[3], + args[4], args[5], rets); + } else if (cmpserv("interpret", 0, 0)) { + ret = vof_call_interpret(args[0], args[1], args[2], rets); + } else if (cmpserv("milliseconds", 0, 1)) { + ret = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL); + } else if (cmpserv("quiesce", 0, 0)) { + vof_quiesce(ms, fdt, vof); + } else if (cmpserv("exit", 0, 0)) { + error_report("Stopped as the VM requested \"exit\""); + vm_stop(RUN_STATE_PAUSED); + } else { + trace_vof_error_unknown_service(service, nargs, nrets); + ret = -1; + } + +#undef cmpserv + + return ret; +} + +/* Defined as Big Endian */ +struct prom_args { + uint32_t service; + uint32_t nargs; + uint32_t nret; + uint32_t args[10]; +} QEMU_PACKED; + +int vof_client_call(MachineState *ms, Vof *vof, void *fdt, + target_ulong args_real) +{ + struct prom_args args_be; + uint32_t args[ARRAY_SIZE(args_be.args)]; + uint32_t rets[ARRAY_SIZE(args_be.args)] = { 0 }, ret; + char service[64]; + unsigned nargs, nret, i; + + if (VOF_MEM_READ(args_real, &args_be, sizeof(args_be)) != MEMTX_OK) { + return -EINVAL; + } + nargs = be32_to_cpu(args_be.nargs); + if (nargs >= ARRAY_SIZE(args_be.args)) { + return -EINVAL; + } + + if (VOF_MEM_READ(be32_to_cpu(args_be.service), service, sizeof(service)) != + MEMTX_OK) { + return -EINVAL; + } + if (strnlen(service, sizeof(service)) == sizeof(service)) { + /* Too long service name */ + return -EINVAL; + } + + for (i = 0; i < nargs; ++i) { + args[i] = be32_to_cpu(args_be.args[i]); + } + + nret = be32_to_cpu(args_be.nret); + if (nret > ARRAY_SIZE(args_be.args) - nargs) { + return -EINVAL; + } + ret = vof_client_handle(ms, fdt, vof, service, args, nargs, rets, nret); + if (!nret) { + return 0; + } + + /* @nrets includes the value which this function returns */ + args_be.args[nargs] = cpu_to_be32(ret); + for (i = 1; i < nret; ++i) { + args_be.args[nargs + i] = cpu_to_be32(rets[i - 1]); + } + + if (VOF_MEM_WRITE(args_real + offsetof(struct prom_args, args[nargs]), + args_be.args + nargs, sizeof(args_be.args[0]) * nret) != + MEMTX_OK) { + return -EINVAL; + } + + return 0; +} + +static void vof_instance_free(gpointer data) +{ + OfInstance *inst = (OfInstance *)data; + + g_free(inst->path); + g_free(inst); +} + +void vof_init(Vof *vof, uint64_t top_addr, Error **errp) +{ + vof_cleanup(vof); + + vof->of_instances = g_hash_table_new_full(g_direct_hash, g_direct_equal, + NULL, vof_instance_free); + vof->claimed = g_array_new(false, false, sizeof(OfClaimed)); + + /* Keep allocations in 32bit as CLI ABI can only return cells==32bit */ + vof->top_addr = MIN(top_addr, 4 * GiB); + if (vof_claim(vof, 0, vof->fw_size, 0) == -1) { + error_setg(errp, "Memory for firmware is in use"); + } +} + +void vof_cleanup(Vof *vof) +{ + if (vof->claimed) { + g_array_unref(vof->claimed); + } + if (vof->of_instances) { + g_hash_table_unref(vof->of_instances); + } + vof->claimed = NULL; + vof->of_instances = NULL; +} + +void vof_build_dt(void *fdt, Vof *vof) +{ + uint32_t phandle = fdt_get_max_phandle(fdt); + int offset, proplen = 0; + const void *prop; + + /* Assign phandles to nodes without predefined phandles (like XICS/XIVE) */ + for (offset = fdt_next_node(fdt, -1, NULL); + offset >= 0; + offset = fdt_next_node(fdt, offset, NULL)) { + prop = fdt_getprop(fdt, offset, "phandle", &proplen); + if (prop) { + continue; + } + ++phandle; + _FDT(fdt_setprop_cell(fdt, offset, "phandle", phandle)); + } + + vof_dt_memory_available(fdt, vof->claimed, vof->claimed_base); +} + +static const TypeInfo vof_machine_if_info = { + .name = TYPE_VOF_MACHINE_IF, + .parent = TYPE_INTERFACE, + .class_size = sizeof(VofMachineIfClass), +}; + +static void vof_machine_if_register_types(void) +{ + type_register_static(&vof_machine_if_info); +} +type_init(vof_machine_if_register_types) diff --git a/hw/rdma/trace-events b/hw/rdma/trace-events index 2022a820cb..9accb14973 100644 --- a/hw/rdma/trace-events +++ b/hw/rdma/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # rdma_backend.c rdma_check_dev_attr(const char *name, int max_bk, int max_fe) "%s: be=%d, fe=%d" diff --git a/hw/rdma/vmw/pvrdma_cmd.c b/hw/rdma/vmw/pvrdma_cmd.c index f59879e257..da7ddfa548 100644 --- a/hw/rdma/vmw/pvrdma_cmd.c +++ b/hw/rdma/vmw/pvrdma_cmd.c @@ -38,6 +38,13 @@ static void *pvrdma_map_to_pdir(PCIDevice *pdev, uint64_t pdir_dma, return NULL; } + length = ROUND_UP(length, TARGET_PAGE_SIZE); + if (nchunks * TARGET_PAGE_SIZE != length) { + rdma_error_report("Invalid nchunks/length (%u, %lu)", nchunks, + (unsigned long)length); + return NULL; + } + dir = rdma_pci_dma_map(pdev, pdir_dma, TARGET_PAGE_SIZE); if (!dir) { rdma_error_report("Failed to map to page directory"); diff --git a/hw/rdma/vmw/pvrdma_dev_ring.c b/hw/rdma/vmw/pvrdma_dev_ring.c index 074ac59b84..42130667a7 100644 --- a/hw/rdma/vmw/pvrdma_dev_ring.c +++ b/hw/rdma/vmw/pvrdma_dev_ring.c @@ -41,7 +41,7 @@ int pvrdma_ring_init(PvrdmaRing *ring, const char *name, PCIDevice *dev, qatomic_set(&ring->ring_state->cons_head, 0); */ ring->npages = npages; - ring->pages = g_malloc(npages * sizeof(void *)); + ring->pages = g_malloc0(npages * sizeof(void *)); for (i = 0; i < npages; i++) { if (!tbl[i]) { diff --git a/hw/rdma/vmw/pvrdma_main.c b/hw/rdma/vmw/pvrdma_main.c index 84ae8024fc..7c0c3551a8 100644 --- a/hw/rdma/vmw/pvrdma_main.c +++ b/hw/rdma/vmw/pvrdma_main.c @@ -92,6 +92,11 @@ static int init_dev_ring(PvrdmaRing *ring, PvrdmaRingState **ring_state, uint64_t *dir, *tbl; int rc = 0; + if (!num_pages) { + rdma_error_report("Ring pages count must be strictly positive"); + return -EINVAL; + } + dir = rdma_pci_dma_map(pci_dev, dir_addr, TARGET_PAGE_SIZE); if (!dir) { rdma_error_report("Failed to map to page directory (ring %s)", name); diff --git a/hw/rdma/vmw/trace-events b/hw/rdma/vmw/trace-events index 323fca8456..a6c77e1e10 100644 --- a/hw/rdma/vmw/trace-events +++ b/hw/rdma/vmw/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pvrdma_main.c pvrdma_regs_read(uint64_t addr, uint64_t val) "pvrdma.regs[0x%"PRIx64"]=0x%"PRIx64 diff --git a/hw/remote/iohub.c b/hw/remote/iohub.c index e4ff131a6b..547d597f0f 100644 --- a/hw/remote/iohub.c +++ b/hw/remote/iohub.c @@ -15,7 +15,6 @@ #include "hw/pci/pci_ids.h" #include "hw/pci/pci_bus.h" #include "qemu/thread.h" -#include "hw/boards.h" #include "hw/remote/machine.h" #include "hw/remote/iohub.h" #include "qemu/main-loop.h" diff --git a/hw/remote/machine.c b/hw/remote/machine.c index c0ab4f528a..952105eab5 100644 --- a/hw/remote/machine.c +++ b/hw/remote/machine.c @@ -17,7 +17,6 @@ #include "qemu-common.h" #include "hw/remote/machine.h" -#include "exec/address-spaces.h" #include "exec/memory.h" #include "qapi/error.h" #include "hw/pci/pci_host.h" diff --git a/hw/remote/memory.c b/hw/remote/memory.c index 32085b1e05..6e21ab1a45 100644 --- a/hw/remote/memory.c +++ b/hw/remote/memory.c @@ -12,7 +12,6 @@ #include "qemu-common.h" #include "hw/remote/memory.h" -#include "exec/address-spaces.h" #include "exec/ram_addr.h" #include "qapi/error.h" @@ -42,13 +41,12 @@ void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp) remote_sysmem_reset(); - for (region = 0; region < msg->num_fds; region++) { - g_autofree char *name; + for (region = 0; region < msg->num_fds; region++, suffix++) { + g_autofree char *name = g_strdup_printf("remote-mem-%u", suffix); subregion = g_new(MemoryRegion, 1); - name = g_strdup_printf("remote-mem-%u", suffix++); memory_region_init_ram_from_fd(subregion, NULL, name, sysmem_info->sizes[region], - true, msg->fds[region], + RAM_SHARED, msg->fds[region], sysmem_info->offsets[region], errp); diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index 9ce31526e8..e67a5de72c 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -218,7 +218,7 @@ uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev, bool mpqemu_msg_valid(MPQemuMsg *msg) { - if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) { + if (msg->cmd >= MPQEMU_CMD_MAX || msg->cmd < 0) { return false; } diff --git a/hw/remote/proxy-memory-listener.c b/hw/remote/proxy-memory-listener.c index af1fa6f5aa..901dbf1357 100644 --- a/hw/remote/proxy-memory-listener.c +++ b/hw/remote/proxy-memory-listener.c @@ -14,9 +14,7 @@ #include "qemu/range.h" #include "exec/memory.h" #include "exec/cpu-common.h" -#include "cpu.h" #include "exec/ram_addr.h" -#include "exec/address-spaces.h" #include "qapi/error.h" #include "hw/remote/mpqemu-link.h" #include "hw/remote/proxy-memory-listener.h" diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index 4fa4be079d..6dda705fc2 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -347,13 +347,12 @@ static void probe_pci_info(PCIDevice *dev, Error **errp) PCI_BASE_ADDRESS_SPACE_IO : PCI_BASE_ADDRESS_SPACE_MEMORY; if (size) { - g_autofree char *name; + g_autofree char *name = g_strdup_printf("bar-region-%d", i); pdev->region[i].dev = pdev; pdev->region[i].present = true; if (type == PCI_BASE_ADDRESS_SPACE_MEMORY) { pdev->region[i].memory = true; } - name = g_strdup_printf("bar-region-%d", i); memory_region_init_io(&pdev->region[i].mr, OBJECT(pdev), &proxy_mr_ops, &pdev->region[i], name, size); diff --git a/hw/riscv/Kconfig b/hw/riscv/Kconfig index 1de18cdcf1..0590f443fd 100644 --- a/hw/riscv/Kconfig +++ b/hw/riscv/Kconfig @@ -1,3 +1,6 @@ +config RISCV_NUMA + bool + config IBEX bool @@ -19,10 +22,22 @@ config OPENTITAN select IBEX select UNIMP +config SHAKTI + bool + +config SHAKTI_C + bool + select UNIMP + select SHAKTI + select SIFIVE_CLINT + select SIFIVE_PLIC + config RISCV_VIRT bool imply PCI_DEVICES + imply VIRTIO_VGA imply TEST_DEVICES + select RISCV_NUMA select GOLDFISH_RTC select MSI_NONBROKEN select PCI @@ -63,6 +78,7 @@ config SIFIVE_U config SPIKE bool + select RISCV_NUMA select HTIF select MSI_NONBROKEN select SIFIVE_CLINT diff --git a/hw/riscv/boot.c b/hw/riscv/boot.c index 0d38bb7426..993bf89064 100644 --- a/hw/riscv/boot.c +++ b/hw/riscv/boot.c @@ -182,7 +182,7 @@ uint32_t riscv_load_fdt(hwaddr dram_base, uint64_t mem_size, void *fdt) { uint32_t temp, fdt_addr; hwaddr dram_end = dram_base + mem_size; - int fdtsize = fdt_totalsize(fdt); + int ret, fdtsize = fdt_totalsize(fdt); if (fdtsize <= 0) { error_report("invalid device-tree"); @@ -198,7 +198,9 @@ uint32_t riscv_load_fdt(hwaddr dram_base, uint64_t mem_size, void *fdt) temp = MIN(dram_end, 3072 * MiB); fdt_addr = QEMU_ALIGN_DOWN(temp - fdtsize, 16 * MiB); - fdt_pack(fdt); + ret = fdt_pack(fdt); + /* Should only fail if we've built a corrupted tree */ + g_assert(ret == 0); /* copy in the device tree */ qemu_fdt_dumpdtb(fdt, fdtsize); diff --git a/hw/riscv/meson.build b/hw/riscv/meson.build index 275c0f7eb7..ab6cae57ea 100644 --- a/hw/riscv/meson.build +++ b/hw/riscv/meson.build @@ -1,9 +1,10 @@ riscv_ss = ss.source_set() riscv_ss.add(files('boot.c'), fdt) -riscv_ss.add(files('numa.c')) +riscv_ss.add(when: 'CONFIG_RISCV_NUMA', if_true: files('numa.c')) riscv_ss.add(files('riscv_hart.c')) riscv_ss.add(when: 'CONFIG_OPENTITAN', if_true: files('opentitan.c')) riscv_ss.add(when: 'CONFIG_RISCV_VIRT', if_true: files('virt.c')) +riscv_ss.add(when: 'CONFIG_SHAKTI_C', if_true: files('shakti_c.c')) riscv_ss.add(when: 'CONFIG_SIFIVE_E', if_true: files('sifive_e.c')) riscv_ss.add(when: 'CONFIG_SIFIVE_U', if_true: files('sifive_u.c')) riscv_ss.add(when: 'CONFIG_SPIKE', if_true: files('spike.c')) diff --git a/hw/riscv/microchip_pfsoc.c b/hw/riscv/microchip_pfsoc.c index c4146b7a6b..eb8e79e0a1 100644 --- a/hw/riscv/microchip_pfsoc.c +++ b/hw/riscv/microchip_pfsoc.c @@ -36,12 +36,10 @@ #include "qemu/osdep.h" #include "qemu/error-report.h" -#include "qemu/log.h" #include "qemu/units.h" #include "qemu/cutils.h" #include "qapi/error.h" #include "hw/boards.h" -#include "hw/irq.h" #include "hw/loader.h" #include "hw/sysbus.h" #include "chardev/char.h" @@ -53,6 +51,7 @@ #include "hw/riscv/microchip_pfsoc.h" #include "hw/intc/sifive_clint.h" #include "hw/intc/sifive_plic.h" +#include "sysemu/device_tree.h" #include "sysemu/sysemu.h" /* @@ -462,6 +461,12 @@ static void microchip_icicle_kit_machine_init(MachineState *machine) MemoryRegion *mem_high = g_new(MemoryRegion, 1); MemoryRegion *mem_high_alias = g_new(MemoryRegion, 1); uint64_t mem_high_size; + hwaddr firmware_load_addr; + const char *firmware_name; + bool kernel_as_payload = false; + target_ulong firmware_end_addr, kernel_start_addr; + uint64_t kernel_entry; + uint32_t fdt_load_addr; DriveInfo *dinfo = drive_get_next(IF_SD); /* Sanity check on RAM size */ @@ -506,9 +511,6 @@ static void microchip_icicle_kit_machine_init(MachineState *machine) memmap[MICROCHIP_PFSOC_DRAM_HI_ALIAS].base, mem_high_alias); - /* Load the firmware */ - riscv_find_and_load_firmware(machine, BIOS_FILENAME, RESET_VECTOR, NULL); - /* Attach an SD card */ if (dinfo) { CadenceSDHCIState *sdhci = &(s->soc.sdhci); @@ -518,6 +520,77 @@ static void microchip_icicle_kit_machine_init(MachineState *machine) &error_fatal); qdev_realize_and_unref(card, sdhci->bus, &error_fatal); } + + /* + * We follow the following table to select which payload we execute. + * + * -bios | -kernel | payload + * -------+------------+-------- + * N | N | HSS + * Y | don't care | HSS + * N | Y | kernel + * + * This ensures backwards compatibility with how we used to expose -bios + * to users but allows them to run through direct kernel booting as well. + * + * When -kernel is used for direct boot, -dtb must be present to provide + * a valid device tree for the board, as we don't generate device tree. + */ + + if (machine->kernel_filename && machine->dtb) { + int fdt_size; + machine->fdt = load_device_tree(machine->dtb, &fdt_size); + if (!machine->fdt) { + error_report("load_device_tree() failed"); + exit(1); + } + + firmware_name = RISCV64_BIOS_BIN; + firmware_load_addr = memmap[MICROCHIP_PFSOC_DRAM_LO].base; + kernel_as_payload = true; + } + + if (!kernel_as_payload) { + firmware_name = BIOS_FILENAME; + firmware_load_addr = RESET_VECTOR; + } + + /* Load the firmware */ + firmware_end_addr = riscv_find_and_load_firmware(machine, firmware_name, + firmware_load_addr, NULL); + + if (kernel_as_payload) { + kernel_start_addr = riscv_calc_kernel_start_addr(&s->soc.u_cpus, + firmware_end_addr); + + kernel_entry = riscv_load_kernel(machine->kernel_filename, + kernel_start_addr, NULL); + + if (machine->initrd_filename) { + hwaddr start; + hwaddr end = riscv_load_initrd(machine->initrd_filename, + machine->ram_size, kernel_entry, + &start); + qemu_fdt_setprop_cell(machine->fdt, "/chosen", + "linux,initrd-start", start); + qemu_fdt_setprop_cell(machine->fdt, "/chosen", + "linux,initrd-end", end); + } + + if (machine->kernel_cmdline) { + qemu_fdt_setprop_string(machine->fdt, "/chosen", + "bootargs", machine->kernel_cmdline); + } + + /* Compute the fdt load address in dram */ + fdt_load_addr = riscv_load_fdt(memmap[MICROCHIP_PFSOC_DRAM_LO].base, + machine->ram_size, machine->fdt); + /* Load the reset vector */ + riscv_setup_rom_reset_vec(machine, &s->soc.u_cpus, firmware_load_addr, + memmap[MICROCHIP_PFSOC_ENVM_DATA].base, + memmap[MICROCHIP_PFSOC_ENVM_DATA].size, + kernel_entry, fdt_load_addr, machine->fdt); + } } static void microchip_icicle_kit_machine_class_init(ObjectClass *oc, void *data) diff --git a/hw/riscv/numa.c b/hw/riscv/numa.c index 4f92307102..7fe92d402f 100644 --- a/hw/riscv/numa.c +++ b/hw/riscv/numa.c @@ -18,7 +18,6 @@ #include "qemu/osdep.h" #include "qemu/units.h" -#include "qemu/log.h" #include "qemu/error-report.h" #include "qapi/error.h" #include "hw/boards.h" diff --git a/hw/riscv/opentitan.c b/hw/riscv/opentitan.c index e168bffe69..36a41c8b5b 100644 --- a/hw/riscv/opentitan.c +++ b/hw/riscv/opentitan.c @@ -24,7 +24,6 @@ #include "hw/boards.h" #include "hw/misc/unimp.h" #include "hw/riscv/boot.h" -#include "exec/address-spaces.h" #include "qemu/units.h" #include "sysemu/sysemu.h" @@ -37,7 +36,7 @@ static const MemMapEntry ibex_memmap[] = { [IBEX_DEV_SPI] = { 0x40050000, 0x1000 }, [IBEX_DEV_I2C] = { 0x40080000, 0x1000 }, [IBEX_DEV_PATTGEN] = { 0x400e0000, 0x1000 }, - [IBEX_DEV_RV_TIMER] = { 0x40100000, 0x1000 }, + [IBEX_DEV_TIMER] = { 0x40100000, 0x1000 }, [IBEX_DEV_SENSOR_CTRL] = { 0x40110000, 0x1000 }, [IBEX_DEV_OTP_CTRL] = { 0x40130000, 0x4000 }, [IBEX_DEV_PWRMGR] = { 0x40400000, 0x1000 }, @@ -59,6 +58,8 @@ static const MemMapEntry ibex_memmap[] = { [IBEX_DEV_ALERT_HANDLER] = { 0x411b0000, 0x1000 }, [IBEX_DEV_NMI_GEN] = { 0x411c0000, 0x1000 }, [IBEX_DEV_OTBN] = { 0x411d0000, 0x10000 }, + [IBEX_DEV_PERI] = { 0x411f0000, 0x10000 }, + [IBEX_DEV_FLASH_VIRTUAL] = { 0x80000000, 0x80000 }, }; static void opentitan_board_init(MachineState *machine) @@ -107,6 +108,8 @@ static void lowrisc_ibex_soc_init(Object *obj) object_initialize_child(obj, "plic", &s->plic, TYPE_IBEX_PLIC); object_initialize_child(obj, "uart", &s->uart, TYPE_IBEX_UART); + + object_initialize_child(obj, "timer", &s->timer, TYPE_IBEX_TIMER); } static void lowrisc_ibex_soc_realize(DeviceState *dev_soc, Error **errp) @@ -120,7 +123,7 @@ static void lowrisc_ibex_soc_realize(DeviceState *dev_soc, Error **errp) &error_abort); object_property_set_int(OBJECT(&s->cpus), "num-harts", ms->smp.cpus, &error_abort); - object_property_set_int(OBJECT(&s->cpus), "resetvec", 0x8090, &error_abort); + object_property_set_int(OBJECT(&s->cpus), "resetvec", 0x8080, &error_abort); sysbus_realize(SYS_BUS_DEVICE(&s->cpus), &error_abort); /* Boot ROM */ @@ -132,8 +135,13 @@ static void lowrisc_ibex_soc_realize(DeviceState *dev_soc, Error **errp) /* Flash memory */ memory_region_init_rom(&s->flash_mem, OBJECT(dev_soc), "riscv.lowrisc.ibex.flash", memmap[IBEX_DEV_FLASH].size, &error_fatal); + memory_region_init_alias(&s->flash_alias, OBJECT(dev_soc), + "riscv.lowrisc.ibex.flash_virtual", &s->flash_mem, 0, + memmap[IBEX_DEV_FLASH_VIRTUAL].size); memory_region_add_subregion(sys_mem, memmap[IBEX_DEV_FLASH].base, &s->flash_mem); + memory_region_add_subregion(sys_mem, memmap[IBEX_DEV_FLASH_VIRTUAL].base, + &s->flash_alias); /* PLIC */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->plic), errp)) { @@ -149,16 +157,24 @@ static void lowrisc_ibex_soc_realize(DeviceState *dev_soc, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->uart), 0, memmap[IBEX_DEV_UART].base); sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart), 0, qdev_get_gpio_in(DEVICE(&s->plic), - IBEX_UART_TX_WATERMARK_IRQ)); + IBEX_UART0_TX_WATERMARK_IRQ)); sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart), 1, qdev_get_gpio_in(DEVICE(&s->plic), - IBEX_UART_RX_WATERMARK_IRQ)); + IBEX_UART0_RX_WATERMARK_IRQ)); sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart), 2, qdev_get_gpio_in(DEVICE(&s->plic), - IBEX_UART_TX_EMPTY_IRQ)); + IBEX_UART0_TX_EMPTY_IRQ)); sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart), 3, qdev_get_gpio_in(DEVICE(&s->plic), - IBEX_UART_RX_OVERFLOW_IRQ)); + IBEX_UART0_RX_OVERFLOW_IRQ)); + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->timer), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->timer), 0, memmap[IBEX_DEV_TIMER].base); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer), + 0, qdev_get_gpio_in(DEVICE(&s->plic), + IBEX_TIMER_TIMEREXPIRED0_0)); create_unimplemented_device("riscv.lowrisc.ibex.gpio", memmap[IBEX_DEV_GPIO].base, memmap[IBEX_DEV_GPIO].size); @@ -168,8 +184,6 @@ static void lowrisc_ibex_soc_realize(DeviceState *dev_soc, Error **errp) memmap[IBEX_DEV_I2C].base, memmap[IBEX_DEV_I2C].size); create_unimplemented_device("riscv.lowrisc.ibex.pattgen", memmap[IBEX_DEV_PATTGEN].base, memmap[IBEX_DEV_PATTGEN].size); - create_unimplemented_device("riscv.lowrisc.ibex.rv_timer", - memmap[IBEX_DEV_RV_TIMER].base, memmap[IBEX_DEV_RV_TIMER].size); create_unimplemented_device("riscv.lowrisc.ibex.sensor_ctrl", memmap[IBEX_DEV_SENSOR_CTRL].base, memmap[IBEX_DEV_SENSOR_CTRL].size); create_unimplemented_device("riscv.lowrisc.ibex.otp_ctrl", @@ -210,6 +224,8 @@ static void lowrisc_ibex_soc_realize(DeviceState *dev_soc, Error **errp) memmap[IBEX_DEV_NMI_GEN].base, memmap[IBEX_DEV_NMI_GEN].size); create_unimplemented_device("riscv.lowrisc.ibex.otbn", memmap[IBEX_DEV_OTBN].base, memmap[IBEX_DEV_OTBN].size); + create_unimplemented_device("riscv.lowrisc.ibex.peri", + memmap[IBEX_DEV_PERI].base, memmap[IBEX_DEV_PERI].size); } static void lowrisc_ibex_soc_class_init(ObjectClass *oc, void *data) diff --git a/hw/riscv/shakti_c.c b/hw/riscv/shakti_c.c new file mode 100644 index 0000000000..18f70fadaa --- /dev/null +++ b/hw/riscv/shakti_c.c @@ -0,0 +1,181 @@ +/* + * Shakti C-class SoC emulation + * + * Copyright (c) 2021 Vijai Kumar K + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see . + */ + +#include "qemu/osdep.h" +#include "hw/boards.h" +#include "hw/riscv/shakti_c.h" +#include "qapi/error.h" +#include "hw/intc/sifive_plic.h" +#include "hw/intc/sifive_clint.h" +#include "sysemu/sysemu.h" +#include "hw/qdev-properties.h" +#include "exec/address-spaces.h" +#include "hw/riscv/boot.h" + + +static const struct MemmapEntry { + hwaddr base; + hwaddr size; +} shakti_c_memmap[] = { + [SHAKTI_C_ROM] = { 0x00001000, 0x2000 }, + [SHAKTI_C_RAM] = { 0x80000000, 0x0 }, + [SHAKTI_C_UART] = { 0x00011300, 0x00040 }, + [SHAKTI_C_GPIO] = { 0x020d0000, 0x00100 }, + [SHAKTI_C_PLIC] = { 0x0c000000, 0x20000 }, + [SHAKTI_C_CLINT] = { 0x02000000, 0xc0000 }, + [SHAKTI_C_I2C] = { 0x20c00000, 0x00100 }, +}; + +static void shakti_c_machine_state_init(MachineState *mstate) +{ + ShaktiCMachineState *sms = RISCV_SHAKTI_MACHINE(mstate); + MemoryRegion *system_memory = get_system_memory(); + MemoryRegion *main_mem = g_new(MemoryRegion, 1); + + /* Allow only Shakti C CPU for this platform */ + if (strcmp(mstate->cpu_type, TYPE_RISCV_CPU_SHAKTI_C) != 0) { + error_report("This board can only be used with Shakti C CPU"); + exit(1); + } + + /* Initialize SoC */ + object_initialize_child(OBJECT(mstate), "soc", &sms->soc, + TYPE_RISCV_SHAKTI_SOC); + qdev_realize(DEVICE(&sms->soc), NULL, &error_abort); + + /* register RAM */ + memory_region_init_ram(main_mem, NULL, "riscv.shakti.c.ram", + mstate->ram_size, &error_fatal); + memory_region_add_subregion(system_memory, + shakti_c_memmap[SHAKTI_C_RAM].base, + main_mem); + + /* ROM reset vector */ + riscv_setup_rom_reset_vec(mstate, &sms->soc.cpus, + shakti_c_memmap[SHAKTI_C_RAM].base, + shakti_c_memmap[SHAKTI_C_ROM].base, + shakti_c_memmap[SHAKTI_C_ROM].size, 0, 0, + NULL); + if (mstate->firmware) { + riscv_load_firmware(mstate->firmware, + shakti_c_memmap[SHAKTI_C_RAM].base, + NULL); + } +} + +static void shakti_c_machine_instance_init(Object *obj) +{ +} + +static void shakti_c_machine_class_init(ObjectClass *klass, void *data) +{ + MachineClass *mc = MACHINE_CLASS(klass); + mc->desc = "RISC-V Board compatible with Shakti SDK"; + mc->init = shakti_c_machine_state_init; + mc->default_cpu_type = TYPE_RISCV_CPU_SHAKTI_C; +} + +static const TypeInfo shakti_c_machine_type_info = { + .name = TYPE_RISCV_SHAKTI_MACHINE, + .parent = TYPE_MACHINE, + .class_init = shakti_c_machine_class_init, + .instance_init = shakti_c_machine_instance_init, + .instance_size = sizeof(ShaktiCMachineState), +}; + +static void shakti_c_machine_type_info_register(void) +{ + type_register_static(&shakti_c_machine_type_info); +} +type_init(shakti_c_machine_type_info_register) + +static void shakti_c_soc_state_realize(DeviceState *dev, Error **errp) +{ + ShaktiCSoCState *sss = RISCV_SHAKTI_SOC(dev); + MemoryRegion *system_memory = get_system_memory(); + + sysbus_realize(SYS_BUS_DEVICE(&sss->cpus), &error_abort); + + sss->plic = sifive_plic_create(shakti_c_memmap[SHAKTI_C_PLIC].base, + (char *)SHAKTI_C_PLIC_HART_CONFIG, 0, + SHAKTI_C_PLIC_NUM_SOURCES, + SHAKTI_C_PLIC_NUM_PRIORITIES, + SHAKTI_C_PLIC_PRIORITY_BASE, + SHAKTI_C_PLIC_PENDING_BASE, + SHAKTI_C_PLIC_ENABLE_BASE, + SHAKTI_C_PLIC_ENABLE_STRIDE, + SHAKTI_C_PLIC_CONTEXT_BASE, + SHAKTI_C_PLIC_CONTEXT_STRIDE, + shakti_c_memmap[SHAKTI_C_PLIC].size); + + sifive_clint_create(shakti_c_memmap[SHAKTI_C_CLINT].base, + shakti_c_memmap[SHAKTI_C_CLINT].size, 0, 1, + SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, + SIFIVE_CLINT_TIMEBASE_FREQ, false); + + qdev_prop_set_chr(DEVICE(&(sss->uart)), "chardev", serial_hd(0)); + if (!sysbus_realize(SYS_BUS_DEVICE(&sss->uart), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&sss->uart), 0, + shakti_c_memmap[SHAKTI_C_UART].base); + + /* ROM */ + memory_region_init_rom(&sss->rom, OBJECT(dev), "riscv.shakti.c.rom", + shakti_c_memmap[SHAKTI_C_ROM].size, &error_fatal); + memory_region_add_subregion(system_memory, + shakti_c_memmap[SHAKTI_C_ROM].base, &sss->rom); +} + +static void shakti_c_soc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + dc->realize = shakti_c_soc_state_realize; +} + +static void shakti_c_soc_instance_init(Object *obj) +{ + ShaktiCSoCState *sss = RISCV_SHAKTI_SOC(obj); + + object_initialize_child(obj, "cpus", &sss->cpus, TYPE_RISCV_HART_ARRAY); + object_initialize_child(obj, "uart", &sss->uart, TYPE_SHAKTI_UART); + + /* + * CPU type is fixed and we are not supporting passing from commandline yet. + * So let it be in instance_init. When supported should use ms->cpu_type + * instead of TYPE_RISCV_CPU_SHAKTI_C + */ + object_property_set_str(OBJECT(&sss->cpus), "cpu-type", + TYPE_RISCV_CPU_SHAKTI_C, &error_abort); + object_property_set_int(OBJECT(&sss->cpus), "num-harts", 1, + &error_abort); +} + +static const TypeInfo shakti_c_type_info = { + .name = TYPE_RISCV_SHAKTI_SOC, + .parent = TYPE_DEVICE, + .class_init = shakti_c_soc_class_init, + .instance_init = shakti_c_soc_instance_init, + .instance_size = sizeof(ShaktiCSoCState), +}; + +static void shakti_c_type_info_register(void) +{ + type_register_static(&shakti_c_type_info); +} +type_init(shakti_c_type_info_register) diff --git a/hw/riscv/sifive_e.c b/hw/riscv/sifive_e.c index f939bcf9ea..ddc658c8d6 100644 --- a/hw/riscv/sifive_e.c +++ b/hw/riscv/sifive_e.c @@ -29,7 +29,6 @@ */ #include "qemu/osdep.h" -#include "qemu/log.h" #include "qemu/error-report.h" #include "qapi/error.h" #include "hw/boards.h" @@ -48,9 +47,8 @@ #include "chardev/char.h" #include "sysemu/arch_init.h" #include "sysemu/sysemu.h" -#include "exec/address-spaces.h" -static MemMapEntry sifive_e_memmap[] = { +static const MemMapEntry sifive_e_memmap[] = { [SIFIVE_E_DEV_DEBUG] = { 0x0, 0x1000 }, [SIFIVE_E_DEV_MROM] = { 0x1000, 0x2000 }, [SIFIVE_E_DEV_OTP] = { 0x20000, 0x2000 }, diff --git a/hw/riscv/sifive_u.c b/hw/riscv/sifive_u.c index 7b59942369..87bbd10b21 100644 --- a/hw/riscv/sifive_u.c +++ b/hw/riscv/sifive_u.c @@ -35,7 +35,6 @@ */ #include "qemu/osdep.h" -#include "qemu/log.h" #include "qemu/error-report.h" #include "qapi/error.h" #include "qapi/visitor.h" @@ -63,6 +62,9 @@ #include +/* CLINT timebase frequency */ +#define CLINT_TIMEBASE_FREQ 1000000 + static const MemMapEntry sifive_u_memmap[] = { [SIFIVE_U_DEV_DEBUG] = { 0x0, 0x100 }, [SIFIVE_U_DEV_MROM] = { 0x1000, 0xf000 }, @@ -96,9 +98,15 @@ static void create_fdt(SiFiveUState *s, const MemMapEntry *memmap, int cpu; uint32_t *cells; char *nodename; - char ethclk_names[] = "pclk\0hclk"; uint32_t plic_phandle, prci_phandle, gpio_phandle, phandle = 1; uint32_t hfclk_phandle, rtcclk_phandle, phy_phandle; + static const char * const ethclk_names[2] = { "pclk", "hclk" }; + static const char * const clint_compat[2] = { + "sifive,clint0", "riscv,clint0" + }; + static const char * const plic_compat[2] = { + "sifive,plic-1.0.0", "riscv,plic0" + }; if (ms->dtb) { fdt = s->fdt = load_device_tree(ms->dtb, &s->fdt_size); @@ -160,7 +168,7 @@ static void create_fdt(SiFiveUState *s, const MemMapEntry *memmap, qemu_fdt_add_subnode(fdt, "/cpus"); qemu_fdt_setprop_cell(fdt, "/cpus", "timebase-frequency", - SIFIVE_CLINT_TIMEBASE_FREQ); + CLINT_TIMEBASE_FREQ); qemu_fdt_setprop_cell(fdt, "/cpus", "#size-cells", 0x0); qemu_fdt_setprop_cell(fdt, "/cpus", "#address-cells", 0x1); @@ -210,7 +218,8 @@ static void create_fdt(SiFiveUState *s, const MemMapEntry *memmap, nodename = g_strdup_printf("/soc/clint@%lx", (long)memmap[SIFIVE_U_DEV_CLINT].base); qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "riscv,clint0"); + qemu_fdt_setprop_string_array(fdt, nodename, "compatible", + (char **)&clint_compat, ARRAY_SIZE(clint_compat)); qemu_fdt_setprop_cells(fdt, nodename, "reg", 0x0, memmap[SIFIVE_U_DEV_CLINT].base, 0x0, memmap[SIFIVE_U_DEV_CLINT].size); @@ -267,7 +276,8 @@ static void create_fdt(SiFiveUState *s, const MemMapEntry *memmap, (long)memmap[SIFIVE_U_DEV_PLIC].base); qemu_fdt_add_subnode(fdt, nodename); qemu_fdt_setprop_cell(fdt, nodename, "#interrupt-cells", 1); - qemu_fdt_setprop_string(fdt, nodename, "compatible", "riscv,plic0"); + qemu_fdt_setprop_string_array(fdt, nodename, "compatible", + (char **)&plic_compat, ARRAY_SIZE(plic_compat)); qemu_fdt_setprop(fdt, nodename, "interrupt-controller", NULL, 0); qemu_fdt_setprop(fdt, nodename, "interrupts-extended", cells, (ms->smp.cpus * 4 - 2) * sizeof(uint32_t)); @@ -413,8 +423,8 @@ static void create_fdt(SiFiveUState *s, const MemMapEntry *memmap, qemu_fdt_setprop_cell(fdt, nodename, "interrupts", SIFIVE_U_GEM_IRQ); qemu_fdt_setprop_cells(fdt, nodename, "clocks", prci_phandle, PRCI_CLK_GEMGXLPLL, prci_phandle, PRCI_CLK_GEMGXLPLL); - qemu_fdt_setprop(fdt, nodename, "clock-names", ethclk_names, - sizeof(ethclk_names)); + qemu_fdt_setprop_string_array(fdt, nodename, "clock-names", + (char **)ðclk_names, ARRAY_SIZE(ethclk_names)); qemu_fdt_setprop(fdt, nodename, "local-mac-address", s->soc.gem.conf.macaddr.a, ETH_ALEN); qemu_fdt_setprop_cell(fdt, nodename, "#address-cells", 1); @@ -553,12 +563,10 @@ static void sifive_u_machine_init(MachineState *machine) if (riscv_is_32bit(&s->soc.u_cpus)) { firmware_end_addr = riscv_find_and_load_firmware(machine, - "opensbi-riscv32-generic-fw_dynamic.bin", - start_addr, NULL); + RISCV32_BIOS_BIN, start_addr, NULL); } else { firmware_end_addr = riscv_find_and_load_firmware(machine, - "opensbi-riscv64-generic-fw_dynamic.bin", - start_addr, NULL); + RISCV64_BIOS_BIN, start_addr, NULL); } if (machine->kernel_filename) { @@ -594,10 +602,10 @@ static void sifive_u_machine_init(MachineState *machine) } /* reset vector */ - uint32_t reset_vec[11] = { + uint32_t reset_vec[12] = { s->msel, /* MSEL pin state */ 0x00000297, /* 1: auipc t0, %pcrel_hi(fw_dyn) */ - 0x02828613, /* addi a2, t0, %pcrel_lo(1b) */ + 0x02c28613, /* addi a2, t0, %pcrel_lo(1b) */ 0xf1402573, /* csrr a0, mhartid */ 0, 0, @@ -605,6 +613,7 @@ static void sifive_u_machine_init(MachineState *machine) start_addr, /* start: .dword */ start_addr_hi32, fdt_load_addr, /* fdt_laddr: .dword */ + 0x00000000, 0x00000000, /* fw_dyn: */ }; @@ -842,7 +851,7 @@ static void sifive_u_soc_realize(DeviceState *dev, Error **errp) sifive_clint_create(memmap[SIFIVE_U_DEV_CLINT].base, memmap[SIFIVE_U_DEV_CLINT].size, 0, ms->smp.cpus, SIFIVE_SIP_BASE, SIFIVE_TIMECMP_BASE, SIFIVE_TIME_BASE, - SIFIVE_CLINT_TIMEBASE_FREQ, false); + CLINT_TIMEBASE_FREQ, false); if (!sysbus_realize(SYS_BUS_DEVICE(&s->prci), errp)) { return; diff --git a/hw/riscv/spike.c b/hw/riscv/spike.c index ec7cb2f707..fead77f0c4 100644 --- a/hw/riscv/spike.c +++ b/hw/riscv/spike.c @@ -24,7 +24,6 @@ */ #include "qemu/osdep.h" -#include "qemu/log.h" #include "qemu/error-report.h" #include "qapi/error.h" #include "hw/boards.h" @@ -60,6 +59,9 @@ static void create_fdt(SpikeState *s, const MemMapEntry *memmap, uint32_t cpu_phandle, intc_phandle, phandle = 1; char *name, *mem_name, *clint_name, *clust_name; char *core_name, *cpu_name, *intc_name; + static const char * const clint_compat[2] = { + "sifive,clint0", "riscv,clint0" + }; fdt = s->fdt = create_device_tree(&s->fdt_size); if (!fdt) { @@ -153,7 +155,8 @@ static void create_fdt(SpikeState *s, const MemMapEntry *memmap, (memmap[SPIKE_CLINT].size * socket); clint_name = g_strdup_printf("/soc/clint@%lx", clint_addr); qemu_fdt_add_subnode(fdt, clint_name); - qemu_fdt_setprop_string(fdt, clint_name, "compatible", "riscv,clint0"); + qemu_fdt_setprop_string_array(fdt, clint_name, "compatible", + (char **)&clint_compat, ARRAY_SIZE(clint_compat)); qemu_fdt_setprop_cells(fdt, clint_name, "reg", 0x0, clint_addr, 0x0, memmap[SPIKE_CLINT].size); qemu_fdt_setprop(fdt, clint_name, "interrupts-extended", @@ -255,13 +258,11 @@ static void spike_board_init(MachineState *machine) */ if (riscv_is_32bit(&s->soc[0])) { firmware_end_addr = riscv_find_and_load_firmware(machine, - "opensbi-riscv32-generic-fw_dynamic.elf", - memmap[SPIKE_DRAM].base, + RISCV32_BIOS_ELF, memmap[SPIKE_DRAM].base, htif_symbol_callback); } else { firmware_end_addr = riscv_find_and_load_firmware(machine, - "opensbi-riscv64-generic-fw_dynamic.elf", - memmap[SPIKE_DRAM].base, + RISCV64_BIOS_ELF, memmap[SPIKE_DRAM].base, htif_symbol_callback); } diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c index c0dc69ff33..4a3cd2599a 100644 --- a/hw/riscv/virt.c +++ b/hw/riscv/virt.c @@ -20,7 +20,6 @@ #include "qemu/osdep.h" #include "qemu/units.h" -#include "qemu/log.h" #include "qemu/error-report.h" #include "qapi/error.h" #include "hw/boards.h" @@ -195,6 +194,12 @@ static void create_fdt(RISCVVirtState *s, const MemMapEntry *memmap, char *name, *clint_name, *plic_name, *clust_name; hwaddr flashsize = virt_memmap[VIRT_FLASH].size / 2; hwaddr flashbase = virt_memmap[VIRT_FLASH].base; + static const char * const clint_compat[2] = { + "sifive,clint0", "riscv,clint0" + }; + static const char * const plic_compat[2] = { + "sifive,plic-1.0.0", "riscv,plic0" + }; if (mc->dtb) { fdt = mc->fdt = load_device_tree(mc->dtb, &s->fdt_size); @@ -300,7 +305,8 @@ static void create_fdt(RISCVVirtState *s, const MemMapEntry *memmap, (memmap[VIRT_CLINT].size * socket); clint_name = g_strdup_printf("/soc/clint@%lx", clint_addr); qemu_fdt_add_subnode(fdt, clint_name); - qemu_fdt_setprop_string(fdt, clint_name, "compatible", "riscv,clint0"); + qemu_fdt_setprop_string_array(fdt, clint_name, "compatible", + (char **)&clint_compat, ARRAY_SIZE(clint_compat)); qemu_fdt_setprop_cells(fdt, clint_name, "reg", 0x0, clint_addr, 0x0, memmap[VIRT_CLINT].size); qemu_fdt_setprop(fdt, clint_name, "interrupts-extended", @@ -316,7 +322,8 @@ static void create_fdt(RISCVVirtState *s, const MemMapEntry *memmap, "#address-cells", FDT_PLIC_ADDR_CELLS); qemu_fdt_setprop_cell(fdt, plic_name, "#interrupt-cells", FDT_PLIC_INT_CELLS); - qemu_fdt_setprop_string(fdt, plic_name, "compatible", "riscv,plic0"); + qemu_fdt_setprop_string_array(fdt, plic_name, "compatible", + (char **)&plic_compat, ARRAY_SIZE(plic_compat)); qemu_fdt_setprop(fdt, plic_name, "interrupt-controller", NULL, 0); qemu_fdt_setprop(fdt, plic_name, "interrupts-extended", plic_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 4); @@ -395,8 +402,11 @@ static void create_fdt(RISCVVirtState *s, const MemMapEntry *memmap, (long)memmap[VIRT_TEST].base); qemu_fdt_add_subnode(fdt, name); { - const char compat[] = "sifive,test1\0sifive,test0\0syscon"; - qemu_fdt_setprop(fdt, name, "compatible", compat, sizeof(compat)); + static const char * const compat[3] = { + "sifive,test1", "sifive,test0", "syscon" + }; + qemu_fdt_setprop_string_array(fdt, name, "compatible", (char **)&compat, + ARRAY_SIZE(compat)); } qemu_fdt_setprop_cells(fdt, name, "reg", 0x0, memmap[VIRT_TEST].base, @@ -671,12 +681,10 @@ static void virt_machine_init(MachineState *machine) if (riscv_is_32bit(&s->soc[0])) { firmware_end_addr = riscv_find_and_load_firmware(machine, - "opensbi-riscv32-generic-fw_dynamic.bin", - start_addr, NULL); + RISCV32_BIOS_BIN, start_addr, NULL); } else { firmware_end_addr = riscv_find_and_load_firmware(machine, - "opensbi-riscv64-generic-fw_dynamic.bin", - start_addr, NULL); + RISCV64_BIOS_BIN, start_addr, NULL); } if (machine->kernel_filename) { diff --git a/hw/rtc/m48t59.c b/hw/rtc/m48t59.c index d54929e861..690f4e071a 100644 --- a/hw/rtc/m48t59.c +++ b/hw/rtc/m48t59.c @@ -32,7 +32,6 @@ #include "sysemu/runstate.h" #include "sysemu/sysemu.h" #include "hw/sysbus.h" -#include "exec/address-spaces.h" #include "qapi/error.h" #include "qemu/bcd.h" #include "qemu/module.h" diff --git a/hw/rtc/mc146818rtc.c b/hw/rtc/mc146818rtc.c index d08d2858b8..090a87b425 100644 --- a/hw/rtc/mc146818rtc.c +++ b/hw/rtc/mc146818rtc.c @@ -42,7 +42,6 @@ #include "qapi/error.h" #include "qapi/qapi-events-misc-target.h" #include "qapi/visitor.h" -#include "exec/address-spaces.h" #include "hw/rtc/mc146818rtc_regs.h" #ifdef TARGET_I386 @@ -890,22 +889,6 @@ static void rtc_notify_suspend(Notifier *notifier, void *data) rtc_set_memory(ISA_DEVICE(s), 0xF, 0xFE); } -static void rtc_reset(void *opaque) -{ - RTCState *s = opaque; - - s->cmos_data[RTC_REG_B] &= ~(REG_B_PIE | REG_B_AIE | REG_B_SQWE); - s->cmos_data[RTC_REG_C] &= ~(REG_C_UF | REG_C_IRQF | REG_C_PF | REG_C_AF); - check_update_timer(s); - - qemu_irq_lower(s->irq); - - if (s->lost_tick_policy == LOST_TICK_POLICY_SLEW) { - s->irq_coalesced = 0; - s->irq_reinject_on_ack_count = 0; - } -} - static const MemoryRegionOps cmos_ops = { .read = cmos_ioport_read, .write = cmos_ioport_write, @@ -980,7 +963,6 @@ static void rtc_realizefn(DeviceState *dev, Error **errp) memory_region_add_coalescing(&s->coalesced_io, 0, 1); qdev_set_legacy_instance_id(dev, RTC_ISA_BASE, 3); - qemu_register_reset(rtc_reset, s); object_property_add_tm(OBJECT(s), "date", rtc_get_date); @@ -1016,15 +998,32 @@ static Property mc146818rtc_properties[] = { DEFINE_PROP_END_OF_LIST(), }; -static void rtc_resetdev(DeviceState *d) +static void rtc_reset_enter(Object *obj, ResetType type) { - RTCState *s = MC146818_RTC(d); + RTCState *s = MC146818_RTC(obj); /* Reason: VM do suspend self will set 0xfe * Reset any values other than 0xfe(Guest suspend case) */ if (s->cmos_data[0x0f] != 0xfe) { s->cmos_data[0x0f] = 0x00; } + + s->cmos_data[RTC_REG_B] &= ~(REG_B_PIE | REG_B_AIE | REG_B_SQWE); + s->cmos_data[RTC_REG_C] &= ~(REG_C_UF | REG_C_IRQF | REG_C_PF | REG_C_AF); + check_update_timer(s); + + + if (s->lost_tick_policy == LOST_TICK_POLICY_SLEW) { + s->irq_coalesced = 0; + s->irq_reinject_on_ack_count = 0; + } +} + +static void rtc_reset_hold(Object *obj) +{ + RTCState *s = MC146818_RTC(obj); + + qemu_irq_lower(s->irq); } static void rtc_build_aml(ISADevice *isadev, Aml *scope) @@ -1051,13 +1050,16 @@ static void rtc_build_aml(ISADevice *isadev, Aml *scope) static void rtc_class_initfn(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); ISADeviceClass *isa = ISA_DEVICE_CLASS(klass); dc->realize = rtc_realizefn; - dc->reset = rtc_resetdev; dc->vmsd = &vmstate_rtc; + rc->phases.enter = rtc_reset_enter; + rc->phases.hold = rtc_reset_hold; isa->build_aml = rtc_build_aml; device_class_set_props(dc, mc146818rtc_properties); + set_bit(DEVICE_CATEGORY_MISC, dc->categories); } static const TypeInfo mc146818rtc_info = { diff --git a/hw/rtc/trace-events b/hw/rtc/trace-events index 8bdcf74264..ebb311a5b0 100644 --- a/hw/rtc/trace-events +++ b/hw/rtc/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # allwinner-rtc.c allwinner_rtc_read(uint64_t addr, uint64_t value) "addr 0x%" PRIx64 " value 0x%" PRIx64 diff --git a/hw/rx/rx-gdbsim.c b/hw/rx/rx-gdbsim.c index b1d7c2488f..75d1fec6ca 100644 --- a/hw/rx/rx-gdbsim.c +++ b/hw/rx/rx-gdbsim.c @@ -21,12 +21,8 @@ #include "qemu/error-report.h" #include "qapi/error.h" #include "qemu-common.h" -#include "cpu.h" -#include "hw/hw.h" -#include "hw/sysbus.h" #include "hw/loader.h" #include "hw/rx/rx62n.h" -#include "sysemu/sysemu.h" #include "sysemu/qtest.h" #include "sysemu/device_tree.h" #include "hw/boards.h" @@ -93,6 +89,7 @@ static void rx_gdbsim_init(MachineState *machine) char *sz = size_to_str(mc->default_ram_size); error_report("Invalid RAM size, should be more than %s", sz); g_free(sz); + exit(1); } /* Allocate memory space */ diff --git a/hw/rx/rx62n.c b/hw/rx/rx62n.c index 9c34ce14de..fa5add9f9d 100644 --- a/hw/rx/rx62n.c +++ b/hw/rx/rx62n.c @@ -23,13 +23,11 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu/error-report.h" -#include "hw/hw.h" #include "hw/rx/rx62n.h" #include "hw/loader.h" #include "hw/sysbus.h" #include "hw/qdev-properties.h" #include "sysemu/sysemu.h" -#include "cpu.h" #include "qom/object.h" /* diff --git a/hw/s390x/3270-ccw.c b/hw/s390x/3270-ccw.c index f3e7342b1e..69e6783ade 100644 --- a/hw/s390x/3270-ccw.c +++ b/hw/s390x/3270-ccw.c @@ -13,7 +13,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qemu/module.h" -#include "cpu.h" #include "hw/s390x/css.h" #include "hw/s390x/css-bridge.h" #include "hw/qdev-properties.h" @@ -130,6 +129,7 @@ static void emulated_ccw_3270_realize(DeviceState *ds, Error **errp) EMULATED_CCW_3270_CHPID_TYPE); sch->do_subchannel_work = do_subchannel_work_virtual; sch->ccw_cb = emulated_ccw_3270_cb; + sch->irb_cb = build_irb_virtual; ck->init(dev, &err); if (err) { @@ -159,7 +159,6 @@ static void emulated_ccw_3270_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); device_class_set_props(dc, emulated_ccw_3270_properties); - dc->bus_type = TYPE_VIRTUAL_CSS_BUS; dc->realize = emulated_ccw_3270_realize; dc->hotpluggable = false; set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories); diff --git a/hw/s390x/ccw-device.c b/hw/s390x/ccw-device.c index c9707110e9..95f269ab44 100644 --- a/hw/s390x/ccw-device.c +++ b/hw/s390x/ccw-device.c @@ -59,6 +59,7 @@ static void ccw_device_class_init(ObjectClass *klass, void *data) k->refill_ids = ccw_device_refill_ids; device_class_set_props(dc, ccw_device_properties); dc->reset = ccw_device_reset; + dc->bus_type = TYPE_VIRTUAL_CSS_BUS; } const VMStateDescription vmstate_ccw_dev = { diff --git a/hw/s390x/ccw-device.h b/hw/s390x/ccw-device.h index 832c78cd42..6dff95225d 100644 --- a/hw/s390x/ccw-device.h +++ b/hw/s390x/ccw-device.h @@ -14,6 +14,7 @@ #include "qom/object.h" #include "hw/qdev-core.h" #include "hw/s390x/css.h" +#include "hw/s390x/css-bridge.h" struct CcwDevice { DeviceState parent_obj; diff --git a/hw/s390x/css-bridge.c b/hw/s390x/css-bridge.c index 9d793d671e..191b29f077 100644 --- a/hw/s390x/css-bridge.c +++ b/hw/s390x/css-bridge.c @@ -20,7 +20,6 @@ #include "hw/s390x/css.h" #include "ccw-device.h" #include "hw/s390x/css-bridge.h" -#include "cpu.h" /* * Invoke device-specific unplug handler, disable the subchannel diff --git a/hw/s390x/css.c b/hw/s390x/css.c index 4149b8e5a7..133ddea575 100644 --- a/hw/s390x/css.c +++ b/hw/s390x/css.c @@ -15,7 +15,6 @@ #include "qemu/bitops.h" #include "qemu/error-report.h" #include "exec/address-spaces.h" -#include "cpu.h" #include "hw/s390x/ioinst.h" #include "hw/qdev-properties.h" #include "hw/s390x/css.h" @@ -1336,6 +1335,14 @@ static void copy_schib_to_guest(SCHIB *dest, const SCHIB *src) } } +void copy_esw_to_guest(ESW *dest, const ESW *src) +{ + dest->word0 = cpu_to_be32(src->word0); + dest->erw = cpu_to_be32(src->erw); + dest->word2 = cpu_to_be64(src->word2); + dest->word4 = cpu_to_be32(src->word4); +} + IOInstEnding css_do_stsch(SubchDev *sch, SCHIB *schib) { int ret; @@ -1605,9 +1612,8 @@ static void copy_irb_to_guest(IRB *dest, const IRB *src, const PMCW *pmcw, copy_scsw_to_guest(&dest->scsw, &src->scsw); - for (i = 0; i < ARRAY_SIZE(dest->esw); i++) { - dest->esw[i] = cpu_to_be32(src->esw[i]); - } + copy_esw_to_guest(&dest->esw, &src->esw); + for (i = 0; i < ARRAY_SIZE(dest->ecw); i++) { dest->ecw[i] = cpu_to_be32(src->ecw[i]); } @@ -1633,6 +1639,55 @@ static void copy_irb_to_guest(IRB *dest, const IRB *src, const PMCW *pmcw, *irb_len = sizeof(*dest); } +static void build_irb_sense_data(SubchDev *sch, IRB *irb) +{ + int i; + + /* Attention: sense_data is already BE! */ + memcpy(irb->ecw, sch->sense_data, sizeof(sch->sense_data)); + for (i = 0; i < ARRAY_SIZE(irb->ecw); i++) { + irb->ecw[i] = be32_to_cpu(irb->ecw[i]); + } +} + +void build_irb_passthrough(SubchDev *sch, IRB *irb) +{ + /* Copy ESW from hardware */ + irb->esw = sch->esw; + + /* + * If (irb->esw.erw & ESW_ERW_SENSE) is true, then the contents + * of the ECW is sense data. If false, then it is model-dependent + * information. Either way, copy it into the IRB for the guest to + * read/decide what to do with. + */ + build_irb_sense_data(sch, irb); +} + +void build_irb_virtual(SubchDev *sch, IRB *irb) +{ + SCHIB *schib = &sch->curr_status; + uint16_t stctl = schib->scsw.ctrl & SCSW_CTRL_MASK_STCTL; + + if (stctl & SCSW_STCTL_STATUS_PEND) { + if (schib->scsw.cstat & (SCSW_CSTAT_DATA_CHECK | + SCSW_CSTAT_CHN_CTRL_CHK | + SCSW_CSTAT_INTF_CTRL_CHK)) { + irb->scsw.flags |= SCSW_FLAGS_MASK_ESWF; + irb->esw.word0 = 0x04804000; + } else { + irb->esw.word0 = 0x00800000; + } + /* If a unit check is pending, copy sense data. */ + if ((schib->scsw.dstat & SCSW_DSTAT_UNIT_CHECK) && + (schib->pmcw.chars & PMCW_CHARS_MASK_CSENSE)) { + irb->scsw.flags |= SCSW_FLAGS_MASK_ESWF | SCSW_FLAGS_MASK_ECTL; + build_irb_sense_data(sch, irb); + irb->esw.erw = ESW_ERW_SENSE | (sizeof(sch->sense_data) << 8); + } + } +} + int css_do_tsch_get_irb(SubchDev *sch, IRB *target_irb, int *irb_len) { SCHIB *schib = &sch->curr_status; @@ -1651,29 +1706,12 @@ int css_do_tsch_get_irb(SubchDev *sch, IRB *target_irb, int *irb_len) /* Copy scsw from current status. */ irb.scsw = schib->scsw; - if (stctl & SCSW_STCTL_STATUS_PEND) { - if (schib->scsw.cstat & (SCSW_CSTAT_DATA_CHECK | - SCSW_CSTAT_CHN_CTRL_CHK | - SCSW_CSTAT_INTF_CTRL_CHK)) { - irb.scsw.flags |= SCSW_FLAGS_MASK_ESWF; - irb.esw[0] = 0x04804000; - } else { - irb.esw[0] = 0x00800000; - } - /* If a unit check is pending, copy sense data. */ - if ((schib->scsw.dstat & SCSW_DSTAT_UNIT_CHECK) && - (schib->pmcw.chars & PMCW_CHARS_MASK_CSENSE)) { - int i; - irb.scsw.flags |= SCSW_FLAGS_MASK_ESWF | SCSW_FLAGS_MASK_ECTL; - /* Attention: sense_data is already BE! */ - memcpy(irb.ecw, sch->sense_data, sizeof(sch->sense_data)); - for (i = 0; i < ARRAY_SIZE(irb.ecw); i++) { - irb.ecw[i] = be32_to_cpu(irb.ecw[i]); - } - irb.esw[1] = 0x01000000 | (sizeof(sch->sense_data) << 8); - } + /* Build other IRB data, if necessary */ + if (sch->irb_cb) { + sch->irb_cb(sch, &irb); } + /* Store the irb to the guest. */ p = schib->pmcw; copy_irb_to_guest(target_irb, &irb, &p, irb_len); diff --git a/hw/s390x/ipl.c b/hw/s390x/ipl.c index ff6b55e816..8c863cf386 100644 --- a/hw/s390x/ipl.c +++ b/hw/s390x/ipl.c @@ -18,9 +18,7 @@ #include "qapi/error.h" #include "sysemu/reset.h" #include "sysemu/runstate.h" -#include "sysemu/sysemu.h" #include "sysemu/tcg.h" -#include "cpu.h" #include "elf.h" #include "hw/loader.h" #include "hw/qdev-properties.h" diff --git a/hw/s390x/meson.build b/hw/s390x/meson.build index 327e9c93af..28484256ec 100644 --- a/hw/s390x/meson.build +++ b/hw/s390x/meson.build @@ -16,7 +16,6 @@ s390x_ss.add(files( 'sclp.c', 'sclpcpu.c', 'sclpquiesce.c', - 'tod-qemu.c', 'tod.c', )) s390x_ss.add(when: 'CONFIG_KVM', if_true: files( @@ -25,6 +24,9 @@ s390x_ss.add(when: 'CONFIG_KVM', if_true: files( 's390-stattrib-kvm.c', 'pv.c', )) +s390x_ss.add(when: 'CONFIG_TCG', if_true: files( + 'tod-tcg.c', +)) s390x_ss.add(when: 'CONFIG_S390_CCW_VIRTIO', if_true: files('s390-virtio-ccw.c')) s390x_ss.add(when: 'CONFIG_TERMINAL3270', if_true: files('3270-ccw.c')) s390x_ss.add(when: 'CONFIG_VFIO', if_true: files('s390-pci-vfio.c')) diff --git a/hw/s390x/pv.c b/hw/s390x/pv.c index 93eccfc05d..401b63d6cb 100644 --- a/hw/s390x/pv.c +++ b/hw/s390x/pv.c @@ -13,7 +13,6 @@ #include -#include "cpu.h" #include "qapi/error.h" #include "qemu/error-report.h" #include "sysemu/kvm.h" diff --git a/hw/s390x/s390-ccw.c b/hw/s390x/s390-ccw.c index b497571863..2fc8bb9c23 100644 --- a/hw/s390x/s390-ccw.c +++ b/hw/s390x/s390-ccw.c @@ -15,7 +15,6 @@ #include #include "qapi/error.h" #include "qemu/module.h" -#include "hw/sysbus.h" #include "hw/s390x/css.h" #include "hw/s390x/css-bridge.h" #include "hw/s390x/s390-ccw.h" @@ -125,6 +124,7 @@ static void s390_ccw_realize(S390CCWDevice *cdev, char *sysfsdev, Error **errp) } sch->driver_data = cdev; sch->do_subchannel_work = do_subchannel_work_passthrough; + sch->irb_cb = build_irb_passthrough; ccw_dev->sch = sch; ret = css_sch_build_schib(sch, &cdev->hostid); @@ -177,10 +177,8 @@ static void s390_ccw_instance_init(Object *obj) static void s390_ccw_class_init(ObjectClass *klass, void *data) { - DeviceClass *dc = DEVICE_CLASS(klass); S390CCWDeviceClass *cdc = S390_CCW_DEVICE_CLASS(klass); - dc->bus_type = TYPE_VIRTUAL_CSS_BUS; cdc->realize = s390_ccw_realize; cdc->unrealize = s390_ccw_unrealize; } diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c index dd138dae94..7db1c5943f 100644 --- a/hw/s390x/s390-pci-bus.c +++ b/hw/s390x/s390-pci-bus.c @@ -14,7 +14,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qapi/visitor.h" -#include "cpu.h" #include "hw/s390x/s390-pci-bus.h" #include "hw/s390x/s390-pci-inst.h" #include "hw/s390x/s390-pci-vfio.h" diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c index 4b8326afa4..9ec277d50e 100644 --- a/hw/s390x/s390-pci-inst.c +++ b/hw/s390x/s390-pci-inst.c @@ -12,7 +12,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include "exec/memop.h" #include "exec/memory-internal.h" #include "qemu/error-report.h" diff --git a/hw/s390x/s390-stattrib-kvm.c b/hw/s390x/s390-stattrib-kvm.c index f89d8d9d16..24cd01382e 100644 --- a/hw/s390x/s390-stattrib-kvm.c +++ b/hw/s390x/s390-stattrib-kvm.c @@ -16,8 +16,7 @@ #include "qemu/error-report.h" #include "sysemu/kvm.h" #include "exec/ram_addr.h" -#include "cpu.h" -#include "kvm_s390x.h" +#include "kvm/kvm_s390x.h" Object *kvm_s390_stattrib_create(void) { diff --git a/hw/s390x/s390-stattrib.c b/hw/s390x/s390-stattrib.c index 4441e1d331..9eda1c3b2a 100644 --- a/hw/s390x/s390-stattrib.c +++ b/hw/s390x/s390-stattrib.c @@ -11,7 +11,6 @@ #include "qemu/osdep.h" #include "qemu/units.h" -#include "cpu.h" #include "migration/qemu-file.h" #include "migration/register.h" #include "hw/s390x/storage-attributes.h" diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index 2972b607f3..e4b18aef49 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -13,11 +13,7 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" -#include "hw/boards.h" -#include "exec/address-spaces.h" #include "exec/ram_addr.h" -#include "hw/boards.h" #include "hw/s390x/s390-virtio-hcall.h" #include "hw/s390x/sclp.h" #include "hw/s390x/s390_flic.h" @@ -795,14 +791,29 @@ bool css_migration_enabled(void) } \ type_init(ccw_machine_register_##suffix) +static void ccw_machine_6_1_instance_options(MachineState *machine) +{ +} + +static void ccw_machine_6_1_class_options(MachineClass *mc) +{ +} +DEFINE_CCW_MACHINE(6_1, "6.1", true); + static void ccw_machine_6_0_instance_options(MachineState *machine) { + static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_0 }; + + ccw_machine_6_1_instance_options(machine); + s390_set_qemu_cpu_model(0x2964, 13, 2, qemu_cpu_feat); } static void ccw_machine_6_0_class_options(MachineClass *mc) { + ccw_machine_6_1_class_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_0, hw_compat_6_0_len); } -DEFINE_CCW_MACHINE(6_0, "6.0", true); +DEFINE_CCW_MACHINE(6_0, "6.0", false); static void ccw_machine_5_2_instance_options(MachineState *machine) { diff --git a/hw/s390x/sclp.c b/hw/s390x/sclp.c index 0cf2290826..edb6e3ea01 100644 --- a/hw/s390x/sclp.c +++ b/hw/s390x/sclp.c @@ -15,8 +15,6 @@ #include "qemu/osdep.h" #include "qemu/units.h" #include "qapi/error.h" -#include "cpu.h" -#include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/s390x/sclp.h" #include "hw/s390x/event-facility.h" diff --git a/hw/s390x/sclpcpu.c b/hw/s390x/sclpcpu.c index 62806d3273..f2b1a4b037 100644 --- a/hw/s390x/sclpcpu.c +++ b/hw/s390x/sclpcpu.c @@ -17,7 +17,6 @@ #include "hw/s390x/sclp.h" #include "qemu/module.h" #include "hw/s390x/event-facility.h" -#include "cpu.h" #include "sysemu/cpus.h" typedef struct ConfigMgtData { diff --git a/hw/s390x/tod-kvm.c b/hw/s390x/tod-kvm.c index 0b94477486..ec855811ae 100644 --- a/hw/s390x/tod-kvm.c +++ b/hw/s390x/tod-kvm.c @@ -13,7 +13,7 @@ #include "qemu/module.h" #include "sysemu/runstate.h" #include "hw/s390x/tod.h" -#include "kvm_s390x.h" +#include "kvm/kvm_s390x.h" static void kvm_s390_get_tod_raw(S390TOD *tod, Error **errp) { diff --git a/hw/s390x/tod-qemu.c b/hw/s390x/tod-tcg.c similarity index 96% rename from hw/s390x/tod-qemu.c rename to hw/s390x/tod-tcg.c index e91b9590f5..9bb94ff72b 100644 --- a/hw/s390x/tod-qemu.c +++ b/hw/s390x/tod-tcg.c @@ -1,5 +1,5 @@ /* - * TOD (Time Of Day) clock - QEMU implementation + * TOD (Time Of Day) clock - TCG implementation * * Copyright 2018 Red Hat, Inc. * Author(s): David Hildenbrand @@ -16,7 +16,7 @@ #include "qemu/cutils.h" #include "qemu/module.h" #include "cpu.h" -#include "tcg_s390x.h" +#include "tcg/tcg_s390x.h" static void qemu_s390_tod_get(const S390TODState *td, S390TOD *tod, Error **errp) diff --git a/hw/s390x/tod.c b/hw/s390x/tod.c index 3c2979175e..fd5a36bf24 100644 --- a/hw/s390x/tod.c +++ b/hw/s390x/tod.c @@ -14,6 +14,8 @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "sysemu/kvm.h" +#include "sysemu/tcg.h" +#include "sysemu/qtest.h" #include "migration/qemu-file-types.h" #include "migration/register.h" @@ -23,8 +25,13 @@ void s390_init_tod(void) if (kvm_enabled()) { obj = object_new(TYPE_KVM_S390_TOD); - } else { + } else if (tcg_enabled()) { obj = object_new(TYPE_QEMU_S390_TOD); + } else if (qtest_enabled()) { + return; + } else { + error_report("current accelerator not handled in s390_init_tod!"); + abort(); } object_property_add_child(qdev_get_machine(), TYPE_S390_TOD, obj); object_unref(obj); diff --git a/hw/s390x/trace-events b/hw/s390x/trace-events index 8156693749..8b9213eab9 100644 --- a/hw/s390x/trace-events +++ b/hw/s390x/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # css.c css_enable_facility(const char *facility) "CSS: enable %s" diff --git a/hw/s390x/virtio-ccw-gpu.c b/hw/s390x/virtio-ccw-gpu.c index 75a9e4bb39..5868a2a070 100644 --- a/hw/s390x/virtio-ccw-gpu.c +++ b/hw/s390x/virtio-ccw-gpu.c @@ -59,6 +59,7 @@ static const TypeInfo virtio_ccw_gpu = { .instance_init = virtio_ccw_gpu_instance_init, .class_init = virtio_ccw_gpu_class_init, }; +module_obj(TYPE_VIRTIO_GPU_CCW); static void virtio_ccw_gpu_register(void) { @@ -68,3 +69,5 @@ static void virtio_ccw_gpu_register(void) } type_init(virtio_ccw_gpu_register) + +module_arch("s390x"); diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c index 8195f3546e..6a2df1c1e9 100644 --- a/hw/s390x/virtio-ccw.c +++ b/hw/s390x/virtio-ccw.c @@ -17,7 +17,6 @@ #include "hw/virtio/virtio.h" #include "migration/qemu-file-types.h" #include "hw/virtio/virtio-net.h" -#include "hw/sysbus.h" #include "qemu/bitops.h" #include "qemu/error-report.h" #include "qemu/module.h" @@ -32,6 +31,7 @@ #include "trace.h" #include "hw/s390x/css-bridge.h" #include "hw/s390x/s390-virtio-ccw.h" +#include "sysemu/replay.h" #define NR_CLASSIC_INDICATOR_BITS 64 @@ -754,6 +754,7 @@ static void virtio_ccw_device_realize(VirtioCcwDevice *dev, Error **errp) sch->id.reserved = 0xff; sch->id.cu_type = VIRTIO_CCW_CU_TYPE; sch->do_subchannel_work = do_subchannel_work_virtual; + sch->irb_cb = build_irb_virtual; ccw_dev->sch = sch; dev->indicators = NULL; dev->revision = -1; @@ -770,6 +771,11 @@ static void virtio_ccw_device_realize(VirtioCcwDevice *dev, Error **errp) dev->flags &= ~VIRTIO_CCW_FLAG_USE_IOEVENTFD; } + /* fd-based ioevents can't be synchronized in record/replay */ + if (replay_mode != REPLAY_MODE_NONE) { + dev->flags &= ~VIRTIO_CCW_FLAG_USE_IOEVENTFD; + } + if (k->realize) { k->realize(dev, &err); if (err) { @@ -1235,7 +1241,6 @@ static void virtio_ccw_device_class_init(ObjectClass *klass, void *data) k->unplug = virtio_ccw_busdev_unplug; dc->realize = virtio_ccw_busdev_realize; dc->unrealize = virtio_ccw_busdev_unrealize; - dc->bus_type = TYPE_VIRTUAL_CSS_BUS; device_class_set_parent_reset(dc, virtio_ccw_reset, &vdc->parent_reset); } diff --git a/hw/scsi/esp.c b/hw/scsi/esp.c index b668acef82..4ac2114788 100644 --- a/hw/scsi/esp.c +++ b/hw/scsi/esp.c @@ -213,7 +213,7 @@ static int esp_select(ESPState *s) if (!s->current_dev) { /* No such drive */ s->rregs[ESP_RSTAT] = 0; - s->rregs[ESP_RINTR] |= INTR_DC; + s->rregs[ESP_RINTR] = INTR_DC; s->rregs[ESP_RSEQ] = SEQ_0; esp_raise_irq(s); return -1; @@ -221,7 +221,7 @@ static int esp_select(ESPState *s) /* * Note that we deliberately don't raise the IRQ here: this will be done - * either in do_busid_cmd() for DATA OUT transfers or by the deferred + * either in do_command_phase() for DATA OUT transfers or by the deferred * IRQ mechanism in esp_transfer_data() for DATA IN transfers */ s->rregs[ESP_RINTR] |= INTR_FC; @@ -260,9 +260,6 @@ static uint32_t get_cmd(ESPState *s, uint32_t maxlen) return 0; } n = esp_fifo_pop_buf(&s->fifo, buf, dmalen); - if (n >= 3) { - buf[0] = buf[2] >> 5; - } n = MIN(fifo8_num_free(&s->cmdfifo), n); fifo8_push_all(&s->cmdfifo, buf, n); } @@ -275,24 +272,22 @@ static uint32_t get_cmd(ESPState *s, uint32_t maxlen) return dmalen; } -static void do_busid_cmd(ESPState *s, uint8_t busid) +static void do_command_phase(ESPState *s) { uint32_t cmdlen; int32_t datalen; - int lun; SCSIDevice *current_lun; uint8_t buf[ESP_CMDFIFO_SZ]; - trace_esp_do_busid_cmd(busid); - lun = busid & 7; + trace_esp_do_command_phase(s->lun); cmdlen = fifo8_num_used(&s->cmdfifo); if (!cmdlen || !s->current_dev) { return; } esp_fifo_pop_buf(&s->cmdfifo, buf, cmdlen); - current_lun = scsi_device_find(&s->bus, 0, s->current_dev->id, lun); - s->current_req = scsi_req_new(current_lun, 0, lun, buf, s); + current_lun = scsi_device_find(&s->bus, 0, s->current_dev->id, s->lun); + s->current_req = scsi_req_new(current_lun, 0, s->lun, buf, s); datalen = scsi_req_enqueue(s->current_req); s->ti_size = datalen; fifo8_reset(&s->cmdfifo); @@ -319,28 +314,36 @@ static void do_busid_cmd(ESPState *s, uint8_t busid) } } -static void do_cmd(ESPState *s) +static void do_message_phase(ESPState *s) { - uint8_t busid = esp_fifo_pop(&s->cmdfifo); - int len; + if (s->cmdfifo_cdb_offset) { + uint8_t message = esp_fifo_pop(&s->cmdfifo); - s->cmdfifo_cdb_offset--; + trace_esp_do_identify(message); + s->lun = message & 7; + s->cmdfifo_cdb_offset--; + } /* Ignore extended messages for now */ if (s->cmdfifo_cdb_offset) { - len = MIN(s->cmdfifo_cdb_offset, fifo8_num_used(&s->cmdfifo)); + int len = MIN(s->cmdfifo_cdb_offset, fifo8_num_used(&s->cmdfifo)); esp_fifo_pop_buf(&s->cmdfifo, NULL, len); s->cmdfifo_cdb_offset = 0; } +} - do_busid_cmd(s, busid); +static void do_cmd(ESPState *s) +{ + do_message_phase(s); + assert(s->cmdfifo_cdb_offset == 0); + do_command_phase(s); } static void satn_pdma_cb(ESPState *s) { - s->do_cmd = 0; - if (!fifo8_is_empty(&s->cmdfifo)) { + if (!esp_get_tc(s) && !fifo8_is_empty(&s->cmdfifo)) { s->cmdfifo_cdb_offset = 1; + s->do_cmd = 0; do_cmd(s); } } @@ -369,13 +372,10 @@ static void handle_satn(ESPState *s) static void s_without_satn_pdma_cb(ESPState *s) { - uint32_t len; - - s->do_cmd = 0; - len = fifo8_num_used(&s->cmdfifo); - if (len) { + if (!esp_get_tc(s) && !fifo8_is_empty(&s->cmdfifo)) { s->cmdfifo_cdb_offset = 0; - do_busid_cmd(s, 0); + s->do_cmd = 0; + do_cmd(s); } } @@ -392,7 +392,7 @@ static void handle_s_without_atn(ESPState *s) if (cmdlen > 0) { s->cmdfifo_cdb_offset = 0; s->do_cmd = 0; - do_busid_cmd(s, 0); + do_cmd(s); } else if (cmdlen == 0) { s->do_cmd = 1; /* Target present, but no cmd yet - switch to command phase */ @@ -403,8 +403,7 @@ static void handle_s_without_atn(ESPState *s) static void satn_stop_pdma_cb(ESPState *s) { - s->do_cmd = 0; - if (!fifo8_is_empty(&s->cmdfifo)) { + if (!esp_get_tc(s) && !fifo8_is_empty(&s->cmdfifo)) { trace_esp_handle_satn_stop(fifo8_num_used(&s->cmdfifo)); s->do_cmd = 1; s->cmdfifo_cdb_offset = 1; @@ -481,7 +480,6 @@ static void esp_dma_done(ESPState *s) { s->rregs[ESP_RSTAT] |= STAT_TC; s->rregs[ESP_RINTR] |= INTR_BS; - s->rregs[ESP_RSEQ] = 0; s->rregs[ESP_RFLAGS] = 0; esp_set_tc(s, 0); esp_raise_irq(s); @@ -494,10 +492,32 @@ static void do_dma_pdma_cb(ESPState *s) uint32_t n; if (s->do_cmd) { + /* Ensure we have received complete command after SATN and stop */ + if (esp_get_tc(s) || fifo8_is_empty(&s->cmdfifo)) { + return; + } + s->ti_size = 0; - s->do_cmd = 0; - do_cmd(s); - esp_lower_drq(s); + if ((s->rregs[ESP_RSTAT] & 7) == STAT_CD) { + /* No command received */ + if (s->cmdfifo_cdb_offset == fifo8_num_used(&s->cmdfifo)) { + return; + } + + /* Command has been received */ + s->do_cmd = 0; + do_cmd(s); + } else { + /* + * Extra message out bytes received: update cmdfifo_cdb_offset + * and then switch to commmand phase + */ + s->cmdfifo_cdb_offset = fifo8_num_used(&s->cmdfifo); + s->rregs[ESP_RSTAT] = STAT_TC | STAT_CD; + s->rregs[ESP_RSEQ] = SEQ_CD; + s->rregs[ESP_RINTR] |= INTR_BS; + esp_raise_irq(s); + } return; } @@ -740,20 +760,17 @@ static void esp_do_nodma(ESPState *s) s->async_len -= len; s->ti_size += len; } else { - len = MIN(s->ti_size, s->async_len); - len = MIN(len, fifo8_num_free(&s->fifo)); - fifo8_push_all(&s->fifo, s->async_buf, len); - s->async_buf += len; - s->async_len -= len; - s->ti_size -= len; + if (fifo8_is_empty(&s->fifo)) { + fifo8_push(&s->fifo, s->async_buf[0]); + s->async_buf++; + s->async_len--; + s->ti_size--; + } } if (s->async_len == 0) { scsi_req_continue(s->current_req); - - if (to_device || s->ti_size == 0) { - return; - } + return; } s->rregs[ESP_RINTR] |= INTR_BS; @@ -763,20 +780,37 @@ static void esp_do_nodma(ESPState *s) void esp_command_complete(SCSIRequest *req, size_t resid) { ESPState *s = req->hba_private; + int to_device = ((s->rregs[ESP_RSTAT] & 7) == STAT_DO); trace_esp_command_complete(); - if (s->ti_size != 0) { - trace_esp_command_complete_unexpected(); + + /* + * Non-DMA transfers from the target will leave the last byte in + * the FIFO so don't reset ti_size in this case + */ + if (s->dma || to_device) { + if (s->ti_size != 0) { + trace_esp_command_complete_unexpected(); + } + s->ti_size = 0; } - s->ti_size = 0; + s->async_len = 0; if (req->status) { trace_esp_command_complete_fail(); } s->status = req->status; - s->rregs[ESP_RSTAT] = STAT_ST; - esp_dma_done(s); - esp_lower_drq(s); + + /* + * If the transfer is finished, switch to status phase. For non-DMA + * transfers from the target the last byte is still in the FIFO + */ + if (s->ti_size == 0) { + s->rregs[ESP_RSTAT] = STAT_TC | STAT_ST; + esp_dma_done(s); + esp_lower_drq(s); + } + if (s->current_req) { scsi_req_unref(s->current_req); s->current_req = NULL; @@ -804,16 +838,6 @@ void esp_transfer_data(SCSIRequest *req, uint32_t len) s->rregs[ESP_RSTAT] |= STAT_TC; s->rregs[ESP_RINTR] |= INTR_BS; esp_raise_irq(s); - - /* - * If data is ready to transfer and the TI command has already - * been executed, start DMA immediately. Otherwise DMA will start - * when host sends the TI command - */ - if (s->ti_size && (s->rregs[ESP_CMD] == (CMD_TI | CMD_DMA))) { - esp_do_dma(s); - } - return; } if (s->ti_cmd == 0) { @@ -827,7 +851,7 @@ void esp_transfer_data(SCSIRequest *req, uint32_t len) return; } - if (s->ti_cmd & CMD_DMA) { + if (s->ti_cmd == (CMD_TI | CMD_DMA)) { if (dmalen) { esp_do_dma(s); } else if (s->ti_size <= 0) { @@ -838,7 +862,7 @@ void esp_transfer_data(SCSIRequest *req, uint32_t len) esp_dma_done(s); esp_lower_drq(s); } - } else { + } else if (s->ti_cmd == CMD_TI) { esp_do_nodma(s); } } @@ -905,6 +929,17 @@ uint64_t esp_reg_read(ESPState *s, uint32_t saddr) qemu_log_mask(LOG_UNIMP, "esp: PIO data read not implemented\n"); s->rregs[ESP_FIFO] = 0; } else { + if ((s->rregs[ESP_RSTAT] & 0x7) == STAT_DI) { + if (s->ti_size) { + esp_do_nodma(s); + } else { + /* + * The last byte of a non-DMA transfer has been read out + * of the FIFO so switch to status phase + */ + s->rregs[ESP_RSTAT] = STAT_TC | STAT_ST; + } + } s->rregs[ESP_FIFO] = esp_fifo_pop(&s->fifo); } val = s->rregs[ESP_FIFO]; @@ -917,7 +952,15 @@ uint64_t esp_reg_read(ESPState *s, uint32_t saddr) val = s->rregs[ESP_RINTR]; s->rregs[ESP_RINTR] = 0; s->rregs[ESP_RSTAT] &= ~STAT_TC; - s->rregs[ESP_RSEQ] = SEQ_0; + /* + * According to the datasheet ESP_RSEQ should be cleared, but as the + * emulation currently defers information transfers to the next TI + * command leave it for now so that pedantic guests such as the old + * Linux 2.6 driver see the correct flags before the next SCSI phase + * transition. + * + * s->rregs[ESP_RSEQ] = SEQ_0; + */ esp_lower_irq(s); break; case ESP_TCHI: @@ -955,15 +998,18 @@ void esp_reg_write(ESPState *s, uint32_t saddr, uint64_t val) case ESP_FIFO: if (s->do_cmd) { esp_fifo_push(&s->cmdfifo, val); + + /* + * If any unexpected message out/command phase data is + * transferred using non-DMA, raise the interrupt + */ + if (s->rregs[ESP_CMD] == CMD_TI) { + s->rregs[ESP_RINTR] |= INTR_BS; + esp_raise_irq(s); + } } else { esp_fifo_push(&s->fifo, val); } - - /* Non-DMA transfers raise an interrupt after every byte */ - if (s->rregs[ESP_CMD] == CMD_TI) { - s->rregs[ESP_RINTR] |= INTR_FC | INTR_BS; - esp_raise_irq(s); - } break; case ESP_CMD: s->rregs[saddr] = val; @@ -1088,7 +1134,15 @@ static bool esp_is_version_5(void *opaque, int version_id) ESPState *s = ESP(opaque); version_id = MIN(version_id, s->mig_version_id); - return version_id == 5; + return version_id >= 5; +} + +static bool esp_is_version_6(void *opaque, int version_id) +{ + ESPState *s = ESP(opaque); + + version_id = MIN(version_id, s->mig_version_id); + return version_id >= 6; } int esp_pre_save(void *opaque) @@ -1128,7 +1182,7 @@ static int esp_post_load(void *opaque, int version_id) const VMStateDescription vmstate_esp = { .name = "esp", - .version_id = 5, + .version_id = 6, .minimum_version_id = 3, .post_load = esp_post_load, .fields = (VMStateField[]) { @@ -1157,6 +1211,7 @@ const VMStateDescription vmstate_esp = { VMSTATE_FIFO8_TEST(fifo, ESPState, esp_is_version_5), VMSTATE_FIFO8_TEST(cmdfifo, ESPState, esp_is_version_5), VMSTATE_UINT8_TEST(ti_cmd, ESPState, esp_is_version_5), + VMSTATE_UINT8_TEST(lun, ESPState, esp_is_version_6), VMSTATE_END_OF_LIST() }, }; @@ -1195,7 +1250,6 @@ static void sysbus_esp_pdma_write(void *opaque, hwaddr addr, { SysBusESPState *sysbus = opaque; ESPState *s = ESP(&sysbus->esp); - uint32_t dmalen; trace_esp_pdma_write(size); @@ -1208,10 +1262,7 @@ static void sysbus_esp_pdma_write(void *opaque, hwaddr addr, esp_pdma_write(s, val); break; } - dmalen = esp_get_tc(s); - if (dmalen == 0 || fifo8_num_free(&s->fifo) < 2) { - s->pdma_cb(s); - } + s->pdma_cb(s); } static uint64_t sysbus_esp_pdma_read(void *opaque, hwaddr addr, diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c index 3580e7ee61..e8a547dbb7 100644 --- a/hw/scsi/scsi-disk.c +++ b/hw/scsi/scsi-disk.c @@ -1582,6 +1582,7 @@ invalid_field: scsi_check_condition(r, SENSE_CODE(INVALID_FIELD)); } +/* sector_num and nb_sectors expected to be in qdev blocksize */ static inline bool check_lba_range(SCSIDiskState *s, uint64_t sector_num, uint32_t nb_sectors) { @@ -1614,11 +1615,12 @@ static void scsi_unmap_complete_noio(UnmapCBData *data, int ret) assert(r->req.aiocb == NULL); if (data->count > 0) { - r->sector = ldq_be_p(&data->inbuf[0]) - * (s->qdev.blocksize / BDRV_SECTOR_SIZE); - r->sector_count = (ldl_be_p(&data->inbuf[8]) & 0xffffffffULL) - * (s->qdev.blocksize / BDRV_SECTOR_SIZE); - if (!check_lba_range(s, r->sector, r->sector_count)) { + uint64_t sector_num = ldq_be_p(&data->inbuf[0]); + uint32_t nb_sectors = ldl_be_p(&data->inbuf[8]) & 0xffffffffULL; + r->sector = sector_num * (s->qdev.blocksize / BDRV_SECTOR_SIZE); + r->sector_count = nb_sectors * (s->qdev.blocksize / BDRV_SECTOR_SIZE); + + if (!check_lba_range(s, sector_num, nb_sectors)) { block_acct_invalid(blk_get_stats(s->qdev.conf.blk), BLOCK_ACCT_UNMAP); scsi_check_condition(r, SENSE_CODE(LBA_OUT_OF_RANGE)); diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c index 98c30c5d5c..665baf900e 100644 --- a/hw/scsi/scsi-generic.c +++ b/hw/scsi/scsi-generic.c @@ -147,7 +147,7 @@ static int execute_command(BlockBackend *blk, return 0; } -static void scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s) +static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len) { uint8_t page, page_idx; @@ -179,10 +179,12 @@ static void scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s) (r->req.cmd.buf[1] & 0x01)) { page = r->req.cmd.buf[2]; if (page == 0xb0) { - uint32_t max_transfer = - blk_get_max_transfer(s->conf.blk) / s->blocksize; + uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk); + uint32_t max_iov = blk_get_max_iov(s->conf.blk); assert(max_transfer); + max_transfer = MIN_NON_ZERO(max_transfer, max_iov * qemu_real_host_page_size) + / s->blocksize; stl_be_p(&r->buf[8], max_transfer); /* Also take care of the opt xfer len. */ stl_be_p(&r->buf[12], @@ -213,8 +215,13 @@ static void scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s) r->buf[page_idx] = 0xb0; } stw_be_p(r->buf + 2, lduw_be_p(r->buf + 2) + 1); + + if (len < r->buflen) { + len++; + } } } + return len; } static int scsi_generic_emulate_block_limits(SCSIGenericReq *r, SCSIDevice *s) @@ -332,7 +339,7 @@ static void scsi_read_complete(void * opaque, int ret) } } if (r->req.cmd.buf[0] == INQUIRY) { - scsi_handle_inquiry_reply(r, s); + len = scsi_handle_inquiry_reply(r, s, len); } req_complete: diff --git a/hw/scsi/spapr_vscsi.c b/hw/scsi/spapr_vscsi.c index ca5c13c4a8..c210262484 100644 --- a/hw/scsi/spapr_vscsi.c +++ b/hw/scsi/spapr_vscsi.c @@ -34,7 +34,6 @@ #include "qemu/osdep.h" #include "qemu/module.h" -#include "cpu.h" #include "hw/scsi/scsi.h" #include "migration/vmstate.h" #include "scsi/constants.h" diff --git a/hw/scsi/trace-events b/hw/scsi/trace-events index 1c331fb189..92d5b40f89 100644 --- a/hw/scsi/trace-events +++ b/hw/scsi/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # scsi-bus.c scsi_req_alloc(int target, int lun, int tag) "target %d lun %d tag %d" @@ -166,7 +166,8 @@ esp_dma_disable(void) "Lower enable" esp_pdma_read(int size) "pDMA read %u bytes" esp_pdma_write(int size) "pDMA write %u bytes" esp_get_cmd(uint32_t dmalen, int target) "len %d target %d" -esp_do_busid_cmd(uint8_t busid) "busid 0x%x" +esp_do_command_phase(uint8_t busid) "busid 0x%x" +esp_do_identify(uint8_t byte) "0x%x" esp_handle_satn_stop(uint32_t cmdlen) "cmdlen %d" esp_write_response(uint32_t status) "Transfer status (status=%d)" esp_do_dma(uint32_t cmdlen, uint32_t len) "command len %d + %d" diff --git a/hw/scsi/vhost-scsi.c b/hw/scsi/vhost-scsi.c index 4d70fa036b..8c611bfd2d 100644 --- a/hw/scsi/vhost-scsi.c +++ b/hw/scsi/vhost-scsi.c @@ -219,10 +219,8 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp) vsc->dev.backend_features = 0; ret = vhost_dev_init(&vsc->dev, (void *)(uintptr_t)vhostfd, - VHOST_BACKEND_TYPE_KERNEL, 0); + VHOST_BACKEND_TYPE_KERNEL, 0, errp); if (ret < 0) { - error_setg(errp, "vhost-scsi: vhost initialization failed: %s", - strerror(-ret)); goto free_vqs; } diff --git a/hw/scsi/vhost-user-scsi.c b/hw/scsi/vhost-user-scsi.c index 4666019442..1b2f7eed98 100644 --- a/hw/scsi/vhost-user-scsi.c +++ b/hw/scsi/vhost-user-scsi.c @@ -122,10 +122,8 @@ static void vhost_user_scsi_realize(DeviceState *dev, Error **errp) vqs = vsc->dev.vqs; ret = vhost_dev_init(&vsc->dev, &s->vhost_user, - VHOST_BACKEND_TYPE_USER, 0); + VHOST_BACKEND_TYPE_USER, 0, errp); if (ret < 0) { - error_setg(errp, "vhost-user-scsi: vhost initialization failed: %s", - strerror(-ret)); goto free_vhost; } diff --git a/hw/scsi/virtio-scsi-dataplane.c b/hw/scsi/virtio-scsi-dataplane.c index 4ad8793406..18eb824c97 100644 --- a/hw/scsi/virtio-scsi-dataplane.c +++ b/hw/scsi/virtio-scsi-dataplane.c @@ -94,8 +94,7 @@ static bool virtio_scsi_data_plane_handle_event(VirtIODevice *vdev, return progress; } -static int virtio_scsi_vring_init(VirtIOSCSI *s, VirtQueue *vq, int n, - VirtIOHandleAIOOutput fn) +static int virtio_scsi_set_host_notifier(VirtIOSCSI *s, VirtQueue *vq, int n) { BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s))); int rc; @@ -109,7 +108,6 @@ static int virtio_scsi_vring_init(VirtIOSCSI *s, VirtQueue *vq, int n, return rc; } - virtio_queue_aio_set_host_notifier_handler(vq, s->ctx, fn); return 0; } @@ -154,40 +152,63 @@ int virtio_scsi_dataplane_start(VirtIODevice *vdev) goto fail_guest_notifiers; } - aio_context_acquire(s->ctx); - rc = virtio_scsi_vring_init(s, vs->ctrl_vq, 0, - virtio_scsi_data_plane_handle_ctrl); - if (rc) { - goto fail_vrings; + /* + * Batch all the host notifiers in a single transaction to avoid + * quadratic time complexity in address_space_update_ioeventfds(). + */ + memory_region_transaction_begin(); + + rc = virtio_scsi_set_host_notifier(s, vs->ctrl_vq, 0); + if (rc != 0) { + goto fail_host_notifiers; } vq_init_count++; - rc = virtio_scsi_vring_init(s, vs->event_vq, 1, - virtio_scsi_data_plane_handle_event); - if (rc) { - goto fail_vrings; + rc = virtio_scsi_set_host_notifier(s, vs->event_vq, 1); + if (rc != 0) { + goto fail_host_notifiers; } vq_init_count++; + for (i = 0; i < vs->conf.num_queues; i++) { - rc = virtio_scsi_vring_init(s, vs->cmd_vqs[i], i + 2, - virtio_scsi_data_plane_handle_cmd); + rc = virtio_scsi_set_host_notifier(s, vs->cmd_vqs[i], i + 2); if (rc) { - goto fail_vrings; + goto fail_host_notifiers; } vq_init_count++; } + memory_region_transaction_commit(); + + aio_context_acquire(s->ctx); + virtio_queue_aio_set_host_notifier_handler(vs->ctrl_vq, s->ctx, + virtio_scsi_data_plane_handle_ctrl); + virtio_queue_aio_set_host_notifier_handler(vs->event_vq, s->ctx, + virtio_scsi_data_plane_handle_event); + + for (i = 0; i < vs->conf.num_queues; i++) { + virtio_queue_aio_set_host_notifier_handler(vs->cmd_vqs[i], s->ctx, + virtio_scsi_data_plane_handle_cmd); + } + s->dataplane_starting = false; s->dataplane_started = true; aio_context_release(s->ctx); return 0; -fail_vrings: - aio_wait_bh_oneshot(s->ctx, virtio_scsi_dataplane_stop_bh, s); - aio_context_release(s->ctx); +fail_host_notifiers: for (i = 0; i < vq_init_count; i++) { virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false); + } + + /* + * The transaction expects the ioeventfds to be open when it + * commits. Do it now, before the cleanup loop. + */ + memory_region_transaction_commit(); + + for (i = 0; i < vq_init_count; i++) { virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i); } k->set_guest_notifiers(qbus->parent, vs->conf.num_queues + 2, false); @@ -225,8 +246,23 @@ void virtio_scsi_dataplane_stop(VirtIODevice *vdev) blk_drain_all(); /* ensure there are no in-flight requests */ + /* + * Batch all the host notifiers in a single transaction to avoid + * quadratic time complexity in address_space_update_ioeventfds(). + */ + memory_region_transaction_begin(); + for (i = 0; i < vs->conf.num_queues + 2; i++) { virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false); + } + + /* + * The transaction expects the ioeventfds to be open when it + * commits. Do it now, before the cleanup loop. + */ + memory_region_transaction_commit(); + + for (i = 0; i < vs->conf.num_queues + 2; i++) { virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i); } diff --git a/hw/sd/cadence_sdhci.c b/hw/sd/cadence_sdhci.c index 0b371c843d..56b8bae1c3 100644 --- a/hw/sd/cadence_sdhci.c +++ b/hw/sd/cadence_sdhci.c @@ -23,10 +23,8 @@ #include "qemu/osdep.h" #include "qemu/bitops.h" #include "qemu/error-report.h" -#include "qemu/log.h" #include "qapi/error.h" #include "migration/vmstate.h" -#include "hw/irq.h" #include "hw/sd/cadence_sdhci.h" #include "sdhci-internal.h" diff --git a/hw/sd/meson.build b/hw/sd/meson.build index 9c29691e13..f1ce357a3b 100644 --- a/hw/sd/meson.build +++ b/hw/sd/meson.build @@ -4,7 +4,6 @@ softmmu_ss.add(when: 'CONFIG_SDHCI', if_true: files('sdhci.c')) softmmu_ss.add(when: 'CONFIG_SDHCI_PCI', if_true: files('sdhci-pci.c')) softmmu_ss.add(when: 'CONFIG_SSI_SD', if_true: files('ssi-sd.c')) -softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-memcard.c')) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_mmc.c')) softmmu_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_mmci.c')) softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_sdhost.c')) diff --git a/hw/sd/milkymist-memcard.c b/hw/sd/milkymist-memcard.c deleted file mode 100644 index a1235aa46c..0000000000 --- a/hw/sd/milkymist-memcard.c +++ /dev/null @@ -1,335 +0,0 @@ -/* - * QEMU model of the Milkymist SD Card Controller. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://milkymist.walle.cc/socdoc/memcard.pdf - */ - -#include "qemu/osdep.h" -#include "qemu/log.h" -#include "qemu/module.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "qapi/error.h" -#include "sysemu/block-backend.h" -#include "sysemu/blockdev.h" -#include "hw/qdev-properties.h" -#include "hw/sd/sd.h" -#include "qom/object.h" - -enum { - ENABLE_CMD_TX = (1<<0), - ENABLE_CMD_RX = (1<<1), - ENABLE_DAT_TX = (1<<2), - ENABLE_DAT_RX = (1<<3), -}; - -enum { - PENDING_CMD_TX = (1<<0), - PENDING_CMD_RX = (1<<1), - PENDING_DAT_TX = (1<<2), - PENDING_DAT_RX = (1<<3), -}; - -enum { - START_CMD_TX = (1<<0), - START_DAT_RX = (1<<1), -}; - -enum { - R_CLK2XDIV = 0, - R_ENABLE, - R_PENDING, - R_START, - R_CMD, - R_DAT, - R_MAX -}; - -#define TYPE_MILKYMIST_MEMCARD "milkymist-memcard" -OBJECT_DECLARE_SIMPLE_TYPE(MilkymistMemcardState, MILKYMIST_MEMCARD) - -#define TYPE_MILKYMIST_SDBUS "milkymist-sdbus" - -struct MilkymistMemcardState { - SysBusDevice parent_obj; - - MemoryRegion regs_region; - SDBus sdbus; - - int command_write_ptr; - int response_read_ptr; - int response_len; - int ignore_next_cmd; - int enabled; - uint8_t command[6]; - uint8_t response[17]; - uint32_t regs[R_MAX]; -}; - -static void update_pending_bits(MilkymistMemcardState *s) -{ - /* transmits are instantaneous, thus tx pending bits are never set */ - s->regs[R_PENDING] = 0; - /* if rx is enabled the corresponding pending bits are always set */ - if (s->regs[R_ENABLE] & ENABLE_CMD_RX) { - s->regs[R_PENDING] |= PENDING_CMD_RX; - } - if (s->regs[R_ENABLE] & ENABLE_DAT_RX) { - s->regs[R_PENDING] |= PENDING_DAT_RX; - } -} - -static void memcard_sd_command(MilkymistMemcardState *s) -{ - SDRequest req; - - req.cmd = s->command[0] & 0x3f; - req.arg = ldl_be_p(s->command + 1); - req.crc = s->command[5]; - - s->response[0] = req.cmd; - s->response_len = sdbus_do_command(&s->sdbus, &req, s->response + 1); - s->response_read_ptr = 0; - - if (s->response_len == 16) { - /* R2 response */ - s->response[0] = 0x3f; - s->response_len += 1; - } else if (s->response_len == 4) { - /* no crc calculation, insert dummy byte */ - s->response[5] = 0; - s->response_len += 2; - } - - if (req.cmd == 0) { - /* next write is a dummy byte to clock the initialization of the sd - * card */ - s->ignore_next_cmd = 1; - } -} - -static uint64_t memcard_read(void *opaque, hwaddr addr, - unsigned size) -{ - MilkymistMemcardState *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_CMD: - if (!s->enabled) { - r = 0xff; - } else { - r = s->response[s->response_read_ptr++]; - if (s->response_read_ptr > s->response_len) { - qemu_log_mask(LOG_GUEST_ERROR, "milkymist_memcard: " - "read more cmd bytes than available: clipping\n"); - s->response_read_ptr = 0; - } - } - break; - case R_DAT: - if (!s->enabled) { - r = 0xffffffff; - } else { - sdbus_read_data(&s->sdbus, &r, sizeof(r)); - be32_to_cpus(&r); - } - break; - case R_CLK2XDIV: - case R_ENABLE: - case R_PENDING: - case R_START: - r = s->regs[addr]; - break; - - default: - qemu_log_mask(LOG_UNIMP, "milkymist_memcard: " - "read access to unknown register 0x%" HWADDR_PRIx "\n", - addr << 2); - break; - } - - trace_milkymist_memcard_memory_read(addr << 2, r); - - return r; -} - -static void memcard_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - MilkymistMemcardState *s = opaque; - uint32_t val32; - - trace_milkymist_memcard_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_PENDING: - /* clear rx pending bits */ - s->regs[R_PENDING] &= ~(value & (PENDING_CMD_RX | PENDING_DAT_RX)); - update_pending_bits(s); - break; - case R_CMD: - if (!s->enabled) { - break; - } - if (s->ignore_next_cmd) { - s->ignore_next_cmd = 0; - break; - } - s->command[s->command_write_ptr] = value & 0xff; - s->command_write_ptr = (s->command_write_ptr + 1) % 6; - if (s->command_write_ptr == 0) { - memcard_sd_command(s); - } - break; - case R_DAT: - if (!s->enabled) { - break; - } - val32 = cpu_to_be32(value); - sdbus_write_data(&s->sdbus, &val32, sizeof(val32)); - break; - case R_ENABLE: - s->regs[addr] = value; - update_pending_bits(s); - break; - case R_CLK2XDIV: - case R_START: - s->regs[addr] = value; - break; - - default: - qemu_log_mask(LOG_UNIMP, "milkymist_memcard: " - "write access to unknown register 0x%" HWADDR_PRIx " " - "(value 0x%" PRIx64 ")\n", addr << 2, value); - break; - } -} - -static const MemoryRegionOps memcard_mmio_ops = { - .read = memcard_read, - .write = memcard_write, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void milkymist_memcard_reset(DeviceState *d) -{ - MilkymistMemcardState *s = MILKYMIST_MEMCARD(d); - int i; - - s->command_write_ptr = 0; - s->response_read_ptr = 0; - s->response_len = 0; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } -} - -static void milkymist_memcard_set_readonly(DeviceState *dev, bool level) -{ - qemu_log_mask(LOG_UNIMP, - "milkymist_memcard: read-only mode not supported\n"); -} - -static void milkymist_memcard_set_inserted(DeviceState *dev, bool level) -{ - MilkymistMemcardState *s = MILKYMIST_MEMCARD(dev); - - s->enabled = !!level; -} - -static void milkymist_memcard_init(Object *obj) -{ - MilkymistMemcardState *s = MILKYMIST_MEMCARD(obj); - SysBusDevice *dev = SYS_BUS_DEVICE(obj); - - memory_region_init_io(&s->regs_region, OBJECT(s), &memcard_mmio_ops, s, - "milkymist-memcard", R_MAX * 4); - sysbus_init_mmio(dev, &s->regs_region); - - qbus_create_inplace(&s->sdbus, sizeof(s->sdbus), TYPE_SD_BUS, - DEVICE(obj), "sd-bus"); -} - -static const VMStateDescription vmstate_milkymist_memcard = { - .name = "milkymist-memcard", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_INT32(command_write_ptr, MilkymistMemcardState), - VMSTATE_INT32(response_read_ptr, MilkymistMemcardState), - VMSTATE_INT32(response_len, MilkymistMemcardState), - VMSTATE_INT32(ignore_next_cmd, MilkymistMemcardState), - VMSTATE_INT32(enabled, MilkymistMemcardState), - VMSTATE_UINT8_ARRAY(command, MilkymistMemcardState, 6), - VMSTATE_UINT8_ARRAY(response, MilkymistMemcardState, 17), - VMSTATE_UINT32_ARRAY(regs, MilkymistMemcardState, R_MAX), - VMSTATE_END_OF_LIST() - } -}; - -static void milkymist_memcard_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->reset = milkymist_memcard_reset; - dc->vmsd = &vmstate_milkymist_memcard; - /* Reason: output IRQs should be wired up */ - dc->user_creatable = false; -} - -static const TypeInfo milkymist_memcard_info = { - .name = TYPE_MILKYMIST_MEMCARD, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(MilkymistMemcardState), - .instance_init = milkymist_memcard_init, - .class_init = milkymist_memcard_class_init, -}; - -static void milkymist_sdbus_class_init(ObjectClass *klass, void *data) -{ - SDBusClass *sbc = SD_BUS_CLASS(klass); - - sbc->set_inserted = milkymist_memcard_set_inserted; - sbc->set_readonly = milkymist_memcard_set_readonly; -} - -static const TypeInfo milkymist_sdbus_info = { - .name = TYPE_MILKYMIST_SDBUS, - .parent = TYPE_SD_BUS, - .instance_size = sizeof(SDBus), - .class_init = milkymist_sdbus_class_init, -}; - -static void milkymist_memcard_register_types(void) -{ - type_register_static(&milkymist_memcard_info); - type_register_static(&milkymist_sdbus_info); -} - -type_init(milkymist_memcard_register_types) diff --git a/hw/sd/omap_mmc.c b/hw/sd/omap_mmc.c index 1f946908fe..b67def6381 100644 --- a/hw/sd/omap_mmc.c +++ b/hw/sd/omap_mmc.c @@ -318,7 +318,7 @@ void omap_mmc_reset(struct omap_mmc_s *host) * into any bus, and we must reset it manually. When omap_mmc is * QOMified this must move into the QOM reset function. */ - device_legacy_reset(DEVICE(host->card)); + device_cold_reset(DEVICE(host->card)); } static uint64_t omap_mmc_read(void *opaque, hwaddr offset, diff --git a/hw/sd/sd.c b/hw/sd/sd.c index 282d39a704..bb5dbff68c 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -821,8 +821,15 @@ static uint32_t sd_wpbits(SDState *sd, uint64_t addr) wpnum = sd_addr_to_wpnum(addr); for (i = 0; i < 32; i++, wpnum++, addr += WPGROUP_SIZE) { + if (addr >= sd->size) { + /* + * If the addresses of the last groups are outside the valid range, + * then the corresponding write protection bits shall be set to 0. + */ + continue; + } assert(wpnum < sd->wpgrps_size); - if (addr < sd->size && test_bit(wpnum, sd->wp_groups)) { + if (test_bit(wpnum, sd->wp_groups)) { ret |= (1 << i); } } @@ -937,6 +944,19 @@ static void sd_lock_command(SDState *sd) sd->card_status &= ~CARD_IS_LOCKED; } +static bool address_in_range(SDState *sd, const char *desc, + uint64_t addr, uint32_t length) +{ + if (addr + length > sd->size) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s offset %"PRIu64" > card %"PRIu64" [%%%u]\n", + desc, addr, sd->size, length); + sd->card_status |= ADDRESS_ERROR; + return false; + } + return true; +} + static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) { uint32_t rca = 0x0000; @@ -1218,8 +1238,7 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) switch (sd->state) { case sd_transfer_state: - if (addr + sd->blk_len > sd->size) { - sd->card_status |= ADDRESS_ERROR; + if (!address_in_range(sd, "READ_BLOCK", addr, sd->blk_len)) { return sd_r1; } @@ -1264,8 +1283,7 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) switch (sd->state) { case sd_transfer_state: - if (addr + sd->blk_len > sd->size) { - sd->card_status |= ADDRESS_ERROR; + if (!address_in_range(sd, "WRITE_BLOCK", addr, sd->blk_len)) { return sd_r1; } @@ -1325,8 +1343,7 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) switch (sd->state) { case sd_transfer_state: - if (addr >= sd->size) { - sd->card_status |= ADDRESS_ERROR; + if (!address_in_range(sd, "SET_WRITE_PROT", addr, 1)) { return sd_r1b; } @@ -1348,8 +1365,7 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) switch (sd->state) { case sd_transfer_state: - if (addr >= sd->size) { - sd->card_status |= ADDRESS_ERROR; + if (!address_in_range(sd, "CLR_WRITE_PROT", addr, 1)) { return sd_r1b; } @@ -1371,6 +1387,11 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) switch (sd->state) { case sd_transfer_state: + if (!address_in_range(sd, "SEND_WRITE_PROT", + req.arg, sd->blk_len)) { + return sd_r1; + } + sd->state = sd_sendingdata_state; *(uint32_t *) sd->data = sd_wpbits(sd, req.arg); sd->data_start = addr; @@ -1504,7 +1525,8 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req) return sd_illegal; } - qemu_log_mask(LOG_GUEST_ERROR, "SD: CMD%i in a wrong state\n", req.cmd); + qemu_log_mask(LOG_GUEST_ERROR, "SD: CMD%i in a wrong state: %s\n", + req.cmd, sd_state_name(sd->state)); return sd_illegal; } @@ -1825,8 +1847,8 @@ void sd_write_byte(SDState *sd, uint8_t value) case 25: /* CMD25: WRITE_MULTIPLE_BLOCK */ if (sd->data_offset == 0) { /* Start of the block - let's check the address is valid */ - if (sd->data_start + sd->blk_len > sd->size) { - sd->card_status |= ADDRESS_ERROR; + if (!address_in_range(sd, "WRITE_MULTIPLE_BLOCK", + sd->data_start, sd->blk_len)) { break; } if (sd->size <= SDSC_MAX_CAPACITY) { @@ -1998,8 +2020,8 @@ uint8_t sd_read_byte(SDState *sd) case 18: /* CMD18: READ_MULTIPLE_BLOCK */ if (sd->data_offset == 0) { - if (sd->data_start + io_len > sd->size) { - sd->card_status |= ADDRESS_ERROR; + if (!address_in_range(sd, "READ_MULTIPLE_BLOCK", + sd->data_start, io_len)) { return 0x00; } BLK_READ_BLOCK(sd->data_start, io_len); diff --git a/hw/sd/trace-events b/hw/sd/trace-events index 4140e48540..3cc2ef89ba 100644 --- a/hw/sd/trace-events +++ b/hw/sd/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # allwinner-sdhost.c allwinner_sdhost_set_inserted(bool inserted) "inserted %u" @@ -55,10 +55,6 @@ sdcard_write_data(const char *proto, const char *cmd_desc, uint8_t cmd, uint8_t sdcard_read_data(const char *proto, const char *cmd_desc, uint8_t cmd, uint32_t length) "%s %20s/ CMD%02d len %" PRIu32 sdcard_set_voltage(uint16_t millivolts) "%u mV" -# milkymist-memcard.c -milkymist_memcard_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_memcard_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" - # pxa2xx_mmci.c pxa2xx_mmci_read(uint8_t size, uint32_t addr, uint32_t value) "size %d addr 0x%02x value 0x%08x" pxa2xx_mmci_write(uint8_t size, uint32_t addr, uint32_t value) "size %d addr 0x%02x value 0x%08x" diff --git a/hw/sensor/Kconfig b/hw/sensor/Kconfig new file mode 100644 index 0000000000..a2b55a4fdb --- /dev/null +++ b/hw/sensor/Kconfig @@ -0,0 +1,19 @@ +config TMP105 + bool + depends on I2C + +config TMP421 + bool + depends on I2C + +config EMC141X + bool + depends on I2C + +config ADM1272 + bool + depends on I2C + +config MAX34451 + bool + depends on I2C diff --git a/hw/sensor/adm1272.c b/hw/sensor/adm1272.c new file mode 100644 index 0000000000..7310c769be --- /dev/null +++ b/hw/sensor/adm1272.c @@ -0,0 +1,543 @@ +/* + * Analog Devices ADM1272 High Voltage Positive Hot Swap Controller and Digital + * Power Monitor with PMBus + * + * Copyright 2021 Google LLC + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include +#include "hw/i2c/pmbus_device.h" +#include "hw/irq.h" +#include "migration/vmstate.h" +#include "qapi/error.h" +#include "qapi/visitor.h" +#include "qemu/log.h" +#include "qemu/module.h" + +#define TYPE_ADM1272 "adm1272" +#define ADM1272(obj) OBJECT_CHECK(ADM1272State, (obj), TYPE_ADM1272) + +#define ADM1272_RESTART_TIME 0xCC +#define ADM1272_MFR_PEAK_IOUT 0xD0 +#define ADM1272_MFR_PEAK_VIN 0xD1 +#define ADM1272_MFR_PEAK_VOUT 0xD2 +#define ADM1272_MFR_PMON_CONTROL 0xD3 +#define ADM1272_MFR_PMON_CONFIG 0xD4 +#define ADM1272_MFR_ALERT1_CONFIG 0xD5 +#define ADM1272_MFR_ALERT2_CONFIG 0xD6 +#define ADM1272_MFR_PEAK_TEMPERATURE 0xD7 +#define ADM1272_MFR_DEVICE_CONFIG 0xD8 +#define ADM1272_MFR_POWER_CYCLE 0xD9 +#define ADM1272_MFR_PEAK_PIN 0xDA +#define ADM1272_MFR_READ_PIN_EXT 0xDB +#define ADM1272_MFR_READ_EIN_EXT 0xDC + +#define ADM1272_HYSTERESIS_LOW 0xF2 +#define ADM1272_HYSTERESIS_HIGH 0xF3 +#define ADM1272_STATUS_HYSTERESIS 0xF4 +#define ADM1272_STATUS_GPIO 0xF5 +#define ADM1272_STRT_UP_IOUT_LIM 0xF6 + +/* Defaults */ +#define ADM1272_OPERATION_DEFAULT 0x80 +#define ADM1272_CAPABILITY_DEFAULT 0xB0 +#define ADM1272_CAPABILITY_NO_PEC 0x30 +#define ADM1272_DIRECT_MODE 0x40 +#define ADM1272_HIGH_LIMIT_DEFAULT 0x0FFF +#define ADM1272_PIN_OP_DEFAULT 0x7FFF +#define ADM1272_PMBUS_REVISION_DEFAULT 0x22 +#define ADM1272_MFR_ID_DEFAULT "ADI" +#define ADM1272_MODEL_DEFAULT "ADM1272-A1" +#define ADM1272_MFR_DEFAULT_REVISION "25" +#define ADM1272_DEFAULT_DATE "160301" +#define ADM1272_RESTART_TIME_DEFAULT 0x64 +#define ADM1272_PMON_CONTROL_DEFAULT 0x1 +#define ADM1272_PMON_CONFIG_DEFAULT 0x3F35 +#define ADM1272_DEVICE_CONFIG_DEFAULT 0x8 +#define ADM1272_HYSTERESIS_HIGH_DEFAULT 0xFFFF +#define ADM1272_STRT_UP_IOUT_LIM_DEFAULT 0x000F +#define ADM1272_VOLT_DEFAULT 12000 +#define ADM1272_IOUT_DEFAULT 25000 +#define ADM1272_PWR_DEFAULT 300 /* 12V 25A */ +#define ADM1272_SHUNT 300 /* micro-ohms */ +#define ADM1272_VOLTAGE_COEFF_DEFAULT 1 +#define ADM1272_CURRENT_COEFF_DEFAULT 3 +#define ADM1272_PWR_COEFF_DEFAULT 7 +#define ADM1272_IOUT_OFFSET 0x5000 +#define ADM1272_IOUT_OFFSET 0x5000 + + +typedef struct ADM1272State { + PMBusDevice parent; + + uint64_t ein_ext; + uint32_t pin_ext; + uint8_t restart_time; + + uint16_t peak_vin; + uint16_t peak_vout; + uint16_t peak_iout; + uint16_t peak_temperature; + uint16_t peak_pin; + + uint8_t pmon_control; + uint16_t pmon_config; + uint16_t alert1_config; + uint16_t alert2_config; + uint16_t device_config; + + uint16_t hysteresis_low; + uint16_t hysteresis_high; + uint8_t status_hysteresis; + uint8_t status_gpio; + + uint16_t strt_up_iout_lim; + +} ADM1272State; + +static const PMBusCoefficients adm1272_coefficients[] = { + [0] = { 6770, 0, -2 }, /* voltage, vrange 60V */ + [1] = { 4062, 0, -2 }, /* voltage, vrange 100V */ + [2] = { 1326, 20480, -1 }, /* current, vsense range 15mV */ + [3] = { 663, 20480, -1 }, /* current, vsense range 30mV */ + [4] = { 3512, 0, -2 }, /* power, vrange 60V, irange 15mV */ + [5] = { 21071, 0, -3 }, /* power, vrange 100V, irange 15mV */ + [6] = { 17561, 0, -3 }, /* power, vrange 60V, irange 30mV */ + [7] = { 10535, 0, -3 }, /* power, vrange 100V, irange 30mV */ + [8] = { 42, 31871, -1 }, /* temperature */ +}; + +static void adm1272_check_limits(ADM1272State *s) +{ + PMBusDevice *pmdev = PMBUS_DEVICE(s); + + pmbus_check_limits(pmdev); + + if (pmdev->pages[0].read_vout > s->peak_vout) { + s->peak_vout = pmdev->pages[0].read_vout; + } + + if (pmdev->pages[0].read_vin > s->peak_vin) { + s->peak_vin = pmdev->pages[0].read_vin; + } + + if (pmdev->pages[0].read_iout > s->peak_iout) { + s->peak_iout = pmdev->pages[0].read_iout; + } + + if (pmdev->pages[0].read_temperature_1 > s->peak_temperature) { + s->peak_temperature = pmdev->pages[0].read_temperature_1; + } + + if (pmdev->pages[0].read_pin > s->peak_pin) { + s->peak_pin = pmdev->pages[0].read_pin; + } +} + +static uint16_t adm1272_millivolts_to_direct(uint32_t value) +{ + PMBusCoefficients c = adm1272_coefficients[ADM1272_VOLTAGE_COEFF_DEFAULT]; + c.b = c.b * 1000; + c.R = c.R - 3; + return pmbus_data2direct_mode(c, value); +} + +static uint32_t adm1272_direct_to_millivolts(uint16_t value) +{ + PMBusCoefficients c = adm1272_coefficients[ADM1272_VOLTAGE_COEFF_DEFAULT]; + c.b = c.b * 1000; + c.R = c.R - 3; + return pmbus_direct_mode2data(c, value); +} + +static uint16_t adm1272_milliamps_to_direct(uint32_t value) +{ + PMBusCoefficients c = adm1272_coefficients[ADM1272_CURRENT_COEFF_DEFAULT]; + /* Y = (m * r_sense * x - b) * 10^R */ + c.m = c.m * ADM1272_SHUNT / 1000; /* micro-ohms */ + c.b = c.b * 1000; + c.R = c.R - 3; + return pmbus_data2direct_mode(c, value); +} + +static uint32_t adm1272_direct_to_milliamps(uint16_t value) +{ + PMBusCoefficients c = adm1272_coefficients[ADM1272_CURRENT_COEFF_DEFAULT]; + c.m = c.m * ADM1272_SHUNT / 1000; + c.b = c.b * 1000; + c.R = c.R - 3; + return pmbus_direct_mode2data(c, value); +} + +static uint16_t adm1272_watts_to_direct(uint32_t value) +{ + PMBusCoefficients c = adm1272_coefficients[ADM1272_PWR_COEFF_DEFAULT]; + c.m = c.m * ADM1272_SHUNT / 1000; + return pmbus_data2direct_mode(c, value); +} + +static uint32_t adm1272_direct_to_watts(uint16_t value) +{ + PMBusCoefficients c = adm1272_coefficients[ADM1272_PWR_COEFF_DEFAULT]; + c.m = c.m * ADM1272_SHUNT / 1000; + return pmbus_direct_mode2data(c, value); +} + +static void adm1272_exit_reset(Object *obj) +{ + ADM1272State *s = ADM1272(obj); + PMBusDevice *pmdev = PMBUS_DEVICE(obj); + + pmdev->page = 0; + pmdev->pages[0].operation = ADM1272_OPERATION_DEFAULT; + + + pmdev->capability = ADM1272_CAPABILITY_NO_PEC; + pmdev->pages[0].revision = ADM1272_PMBUS_REVISION_DEFAULT; + pmdev->pages[0].vout_mode = ADM1272_DIRECT_MODE; + pmdev->pages[0].vout_ov_warn_limit = ADM1272_HIGH_LIMIT_DEFAULT; + pmdev->pages[0].vout_uv_warn_limit = 0; + pmdev->pages[0].iout_oc_warn_limit = ADM1272_HIGH_LIMIT_DEFAULT; + pmdev->pages[0].ot_fault_limit = ADM1272_HIGH_LIMIT_DEFAULT; + pmdev->pages[0].ot_warn_limit = ADM1272_HIGH_LIMIT_DEFAULT; + pmdev->pages[0].vin_ov_warn_limit = ADM1272_HIGH_LIMIT_DEFAULT; + pmdev->pages[0].vin_uv_warn_limit = 0; + pmdev->pages[0].pin_op_warn_limit = ADM1272_PIN_OP_DEFAULT; + + pmdev->pages[0].status_word = 0; + pmdev->pages[0].status_vout = 0; + pmdev->pages[0].status_iout = 0; + pmdev->pages[0].status_input = 0; + pmdev->pages[0].status_temperature = 0; + pmdev->pages[0].status_mfr_specific = 0; + + pmdev->pages[0].read_vin + = adm1272_millivolts_to_direct(ADM1272_VOLT_DEFAULT); + pmdev->pages[0].read_vout + = adm1272_millivolts_to_direct(ADM1272_VOLT_DEFAULT); + pmdev->pages[0].read_iout + = adm1272_milliamps_to_direct(ADM1272_IOUT_DEFAULT); + pmdev->pages[0].read_temperature_1 = 0; + pmdev->pages[0].read_pin = adm1272_watts_to_direct(ADM1272_PWR_DEFAULT); + pmdev->pages[0].revision = ADM1272_PMBUS_REVISION_DEFAULT; + pmdev->pages[0].mfr_id = ADM1272_MFR_ID_DEFAULT; + pmdev->pages[0].mfr_model = ADM1272_MODEL_DEFAULT; + pmdev->pages[0].mfr_revision = ADM1272_MFR_DEFAULT_REVISION; + pmdev->pages[0].mfr_date = ADM1272_DEFAULT_DATE; + + s->pin_ext = 0; + s->ein_ext = 0; + s->restart_time = ADM1272_RESTART_TIME_DEFAULT; + + s->peak_vin = 0; + s->peak_vout = 0; + s->peak_iout = 0; + s->peak_temperature = 0; + s->peak_pin = 0; + + s->pmon_control = ADM1272_PMON_CONTROL_DEFAULT; + s->pmon_config = ADM1272_PMON_CONFIG_DEFAULT; + s->alert1_config = 0; + s->alert2_config = 0; + s->device_config = ADM1272_DEVICE_CONFIG_DEFAULT; + + s->hysteresis_low = 0; + s->hysteresis_high = ADM1272_HYSTERESIS_HIGH_DEFAULT; + s->status_hysteresis = 0; + s->status_gpio = 0; + + s->strt_up_iout_lim = ADM1272_STRT_UP_IOUT_LIM_DEFAULT; +} + +static uint8_t adm1272_read_byte(PMBusDevice *pmdev) +{ + ADM1272State *s = ADM1272(pmdev); + + switch (pmdev->code) { + case ADM1272_RESTART_TIME: + pmbus_send8(pmdev, s->restart_time); + break; + + case ADM1272_MFR_PEAK_IOUT: + pmbus_send16(pmdev, s->peak_iout); + break; + + case ADM1272_MFR_PEAK_VIN: + pmbus_send16(pmdev, s->peak_vin); + break; + + case ADM1272_MFR_PEAK_VOUT: + pmbus_send16(pmdev, s->peak_vout); + break; + + case ADM1272_MFR_PMON_CONTROL: + pmbus_send8(pmdev, s->pmon_control); + break; + + case ADM1272_MFR_PMON_CONFIG: + pmbus_send16(pmdev, s->pmon_config); + break; + + case ADM1272_MFR_ALERT1_CONFIG: + pmbus_send16(pmdev, s->alert1_config); + break; + + case ADM1272_MFR_ALERT2_CONFIG: + pmbus_send16(pmdev, s->alert2_config); + break; + + case ADM1272_MFR_PEAK_TEMPERATURE: + pmbus_send16(pmdev, s->peak_temperature); + break; + + case ADM1272_MFR_DEVICE_CONFIG: + pmbus_send16(pmdev, s->device_config); + break; + + case ADM1272_MFR_PEAK_PIN: + pmbus_send16(pmdev, s->peak_pin); + break; + + case ADM1272_MFR_READ_PIN_EXT: + pmbus_send32(pmdev, s->pin_ext); + break; + + case ADM1272_MFR_READ_EIN_EXT: + pmbus_send64(pmdev, s->ein_ext); + break; + + case ADM1272_HYSTERESIS_LOW: + pmbus_send16(pmdev, s->hysteresis_low); + break; + + case ADM1272_HYSTERESIS_HIGH: + pmbus_send16(pmdev, s->hysteresis_high); + break; + + case ADM1272_STATUS_HYSTERESIS: + pmbus_send16(pmdev, s->status_hysteresis); + break; + + case ADM1272_STATUS_GPIO: + pmbus_send16(pmdev, s->status_gpio); + break; + + case ADM1272_STRT_UP_IOUT_LIM: + pmbus_send16(pmdev, s->strt_up_iout_lim); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: reading from unsupported register: 0x%02x\n", + __func__, pmdev->code); + return 0xFF; + break; + } + + return 0; +} + +static int adm1272_write_data(PMBusDevice *pmdev, const uint8_t *buf, + uint8_t len) +{ + ADM1272State *s = ADM1272(pmdev); + + if (len == 0) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: writing empty data\n", __func__); + return -1; + } + + pmdev->code = buf[0]; /* PMBus command code */ + + if (len == 1) { + return 0; + } + + /* Exclude command code from buffer */ + buf++; + len--; + + switch (pmdev->code) { + + case ADM1272_RESTART_TIME: + s->restart_time = pmbus_receive8(pmdev); + break; + + case ADM1272_MFR_PMON_CONTROL: + s->pmon_control = pmbus_receive8(pmdev); + break; + + case ADM1272_MFR_PMON_CONFIG: + s->pmon_config = pmbus_receive16(pmdev); + break; + + case ADM1272_MFR_ALERT1_CONFIG: + s->alert1_config = pmbus_receive16(pmdev); + break; + + case ADM1272_MFR_ALERT2_CONFIG: + s->alert2_config = pmbus_receive16(pmdev); + break; + + case ADM1272_MFR_DEVICE_CONFIG: + s->device_config = pmbus_receive16(pmdev); + break; + + case ADM1272_MFR_POWER_CYCLE: + adm1272_exit_reset((Object *)s); + break; + + case ADM1272_HYSTERESIS_LOW: + s->hysteresis_low = pmbus_receive16(pmdev); + break; + + case ADM1272_HYSTERESIS_HIGH: + s->hysteresis_high = pmbus_receive16(pmdev); + break; + + case ADM1272_STRT_UP_IOUT_LIM: + s->strt_up_iout_lim = pmbus_receive16(pmdev); + adm1272_check_limits(s); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: writing to unsupported register: 0x%02x\n", + __func__, pmdev->code); + break; + } + return 0; +} + +static void adm1272_get(Object *obj, Visitor *v, const char *name, void *opaque, + Error **errp) +{ + uint16_t value; + + if (strcmp(name, "vin") == 0 || strcmp(name, "vout") == 0) { + value = adm1272_direct_to_millivolts(*(uint16_t *)opaque); + } else if (strcmp(name, "iout") == 0) { + value = adm1272_direct_to_milliamps(*(uint16_t *)opaque); + } else if (strcmp(name, "pin") == 0) { + value = adm1272_direct_to_watts(*(uint16_t *)opaque); + } else { + value = *(uint16_t *)opaque; + } + + visit_type_uint16(v, name, &value, errp); +} + +static void adm1272_set(Object *obj, Visitor *v, const char *name, void *opaque, + Error **errp) +{ + ADM1272State *s = ADM1272(obj); + uint16_t *internal = opaque; + uint16_t value; + + if (!visit_type_uint16(v, name, &value, errp)) { + return; + } + + if (strcmp(name, "vin") == 0 || strcmp(name, "vout") == 0) { + *internal = adm1272_millivolts_to_direct(value); + } else if (strcmp(name, "iout") == 0) { + *internal = adm1272_milliamps_to_direct(value); + } else if (strcmp(name, "pin") == 0) { + *internal = adm1272_watts_to_direct(value); + } else { + *internal = value; + } + + adm1272_check_limits(s); +} + +static const VMStateDescription vmstate_adm1272 = { + .name = "ADM1272", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]){ + VMSTATE_PMBUS_DEVICE(parent, ADM1272State), + VMSTATE_UINT64(ein_ext, ADM1272State), + VMSTATE_UINT32(pin_ext, ADM1272State), + VMSTATE_UINT8(restart_time, ADM1272State), + + VMSTATE_UINT16(peak_vin, ADM1272State), + VMSTATE_UINT16(peak_vout, ADM1272State), + VMSTATE_UINT16(peak_iout, ADM1272State), + VMSTATE_UINT16(peak_temperature, ADM1272State), + VMSTATE_UINT16(peak_pin, ADM1272State), + + VMSTATE_UINT8(pmon_control, ADM1272State), + VMSTATE_UINT16(pmon_config, ADM1272State), + VMSTATE_UINT16(alert1_config, ADM1272State), + VMSTATE_UINT16(alert2_config, ADM1272State), + VMSTATE_UINT16(device_config, ADM1272State), + + VMSTATE_UINT16(hysteresis_low, ADM1272State), + VMSTATE_UINT16(hysteresis_high, ADM1272State), + VMSTATE_UINT8(status_hysteresis, ADM1272State), + VMSTATE_UINT8(status_gpio, ADM1272State), + + VMSTATE_UINT16(strt_up_iout_lim, ADM1272State), + VMSTATE_END_OF_LIST() + } +}; + +static void adm1272_init(Object *obj) +{ + PMBusDevice *pmdev = PMBUS_DEVICE(obj); + uint64_t flags = PB_HAS_VOUT_MODE | PB_HAS_VOUT | PB_HAS_VIN | PB_HAS_IOUT | + PB_HAS_PIN | PB_HAS_TEMPERATURE | PB_HAS_MFR_INFO; + + pmbus_page_config(pmdev, 0, flags); + + object_property_add(obj, "vin", "uint16", + adm1272_get, + adm1272_set, NULL, &pmdev->pages[0].read_vin); + + object_property_add(obj, "vout", "uint16", + adm1272_get, + adm1272_set, NULL, &pmdev->pages[0].read_vout); + + object_property_add(obj, "iout", "uint16", + adm1272_get, + adm1272_set, NULL, &pmdev->pages[0].read_iout); + + object_property_add(obj, "pin", "uint16", + adm1272_get, + adm1272_set, NULL, &pmdev->pages[0].read_pin); + +} + +static void adm1272_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + PMBusDeviceClass *k = PMBUS_DEVICE_CLASS(klass); + + dc->desc = "Analog Devices ADM1272 Hot Swap controller"; + dc->vmsd = &vmstate_adm1272; + k->write_data = adm1272_write_data; + k->receive_byte = adm1272_read_byte; + k->device_num_pages = 1; + + rc->phases.exit = adm1272_exit_reset; +} + +static const TypeInfo adm1272_info = { + .name = TYPE_ADM1272, + .parent = TYPE_PMBUS_DEVICE, + .instance_size = sizeof(ADM1272State), + .instance_init = adm1272_init, + .class_init = adm1272_class_init, +}; + +static void adm1272_register_types(void) +{ + type_register_static(&adm1272_info); +} + +type_init(adm1272_register_types) diff --git a/hw/misc/emc141x.c b/hw/sensor/emc141x.c similarity index 99% rename from hw/misc/emc141x.c rename to hw/sensor/emc141x.c index f7c53d48a4..7ce8f4e979 100644 --- a/hw/misc/emc141x.c +++ b/hw/sensor/emc141x.c @@ -25,7 +25,7 @@ #include "qapi/visitor.h" #include "qemu/module.h" #include "qom/object.h" -#include "hw/misc/emc141x_regs.h" +#include "hw/sensor/emc141x_regs.h" #define SENSORS_COUNT_MAX 4 diff --git a/hw/sensor/max34451.c b/hw/sensor/max34451.c new file mode 100644 index 0000000000..a91d8bd487 --- /dev/null +++ b/hw/sensor/max34451.c @@ -0,0 +1,775 @@ +/* + * Maxim MAX34451 PMBus 16-Channel V/I monitor and 12-Channel Sequencer/Marginer + * + * Copyright 2021 Google LLC + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "hw/i2c/pmbus_device.h" +#include "hw/irq.h" +#include "migration/vmstate.h" +#include "qapi/error.h" +#include "qapi/visitor.h" +#include "qemu/log.h" +#include "qemu/module.h" + +#define TYPE_MAX34451 "max34451" +#define MAX34451(obj) OBJECT_CHECK(MAX34451State, (obj), TYPE_MAX34451) + +#define MAX34451_MFR_MODE 0xD1 +#define MAX34451_MFR_PSEN_CONFIG 0xD2 +#define MAX34451_MFR_VOUT_PEAK 0xD4 +#define MAX34451_MFR_IOUT_PEAK 0xD5 +#define MAX34451_MFR_TEMPERATURE_PEAK 0xD6 +#define MAX34451_MFR_VOUT_MIN 0xD7 +#define MAX34451_MFR_NV_LOG_CONFIG 0xD8 +#define MAX34451_MFR_FAULT_RESPONSE 0xD9 +#define MAX34451_MFR_FAULT_RETRY 0xDA +#define MAX34451_MFR_NV_FAULT_LOG 0xDC +#define MAX34451_MFR_TIME_COUNT 0xDD +#define MAX34451_MFR_MARGIN_CONFIG 0xDF +#define MAX34451_MFR_FW_SERIAL 0xE0 +#define MAX34451_MFR_IOUT_AVG 0xE2 +#define MAX34451_MFR_CHANNEL_CONFIG 0xE4 +#define MAX34451_MFR_TON_SEQ_MAX 0xE6 +#define MAX34451_MFR_PWM_CONFIG 0xE7 +#define MAX34451_MFR_SEQ_CONFIG 0xE8 +#define MAX34451_MFR_STORE_ALL 0xEE +#define MAX34451_MFR_RESTORE_ALL 0xEF +#define MAX34451_MFR_TEMP_SENSOR_CONFIG 0xF0 +#define MAX34451_MFR_STORE_SINGLE 0xFC +#define MAX34451_MFR_CRC 0xFE + +#define MAX34451_NUM_MARGINED_PSU 12 +#define MAX34451_NUM_PWR_DEVICES 16 +#define MAX34451_NUM_TEMP_DEVICES 5 +#define MAX34451_NUM_PAGES 21 + +#define DEFAULT_OP_ON 0x80 +#define DEFAULT_CAPABILITY 0x20 +#define DEFAULT_ON_OFF_CONFIG 0x1a +#define DEFAULT_VOUT_MODE 0x40 +#define DEFAULT_TEMPERATURE 2500 +#define DEFAULT_SCALE 0x7FFF +#define DEFAULT_OV_LIMIT 0x7FFF +#define DEFAULT_OC_LIMIT 0x7FFF +#define DEFAULT_OT_LIMIT 0x7FFF +#define DEFAULT_VMIN 0x7FFF +#define DEFAULT_TON_FAULT_LIMIT 0xFFFF +#define DEFAULT_CHANNEL_CONFIG 0x20 +#define DEFAULT_TEXT 0x3130313031303130 + +/** + * MAX34451State: + * @code: The command code received + * @page: Each page corresponds to a device monitored by the Max 34451 + * The page register determines the available commands depending on device + ___________________________________________________________________________ + | 0 | Power supply monitored by RS0, controlled by PSEN0, and | + | | margined with PWM0. | + |_______|___________________________________________________________________| + | 1 | Power supply monitored by RS1, controlled by PSEN1, and | + | | margined with PWM1. | + |_______|___________________________________________________________________| + | 2 | Power supply monitored by RS2, controlled by PSEN2, and | + | | margined with PWM2. | + |_______|___________________________________________________________________| + | 3 | Power supply monitored by RS3, controlled by PSEN3, and | + | | margined with PWM3. | + |_______|___________________________________________________________________| + | 4 | Power supply monitored by RS4, controlled by PSEN4, and | + | | margined with PWM4. | + |_______|___________________________________________________________________| + | 5 | Power supply monitored by RS5, controlled by PSEN5, and | + | | margined with PWM5. | + |_______|___________________________________________________________________| + | 6 | Power supply monitored by RS6, controlled by PSEN6, and | + | | margined with PWM6. | + |_______|___________________________________________________________________| + | 7 | Power supply monitored by RS7, controlled by PSEN7, and | + | | margined with PWM7. | + |_______|___________________________________________________________________| + | 8 | Power supply monitored by RS8, controlled by PSEN8, and | + | | optionally margined by OUT0 of external DS4424 at I2C address A0h.| + |_______|___________________________________________________________________| + | 9 | Power supply monitored by RS9, controlled by PSEN9, and | + | | optionally margined by OUT1 of external DS4424 at I2C address A0h.| + |_______|___________________________________________________________________| + | 10 | Power supply monitored by RS10, controlled by PSEN10, and | + | | optionally margined by OUT2 of external DS4424 at I2C address A0h.| + |_______|___________________________________________________________________| + | 11 | Power supply monitored by RS11, controlled by PSEN11, and | + | | optionally margined by OUT3 of external DS4424 at I2C address A0h.| + |_______|___________________________________________________________________| + | 12 | ADC channel 12 (monitors voltage or current) or GPI. | + |_______|___________________________________________________________________| + | 13 | ADC channel 13 (monitors voltage or current) or GPI. | + |_______|___________________________________________________________________| + | 14 | ADC channel 14 (monitors voltage or current) or GPI. | + |_______|___________________________________________________________________| + | 15 | ADC channel 15 (monitors voltage or current) or GPI. | + |_______|___________________________________________________________________| + | 16 | Internal temperature sensor. | + |_______|___________________________________________________________________| + | 17 | External DS75LV temperature sensor with I2C address 90h. | + |_______|___________________________________________________________________| + | 18 | External DS75LV temperature sensor with I2C address 92h. | + |_______|___________________________________________________________________| + | 19 | External DS75LV temperature sensor with I2C address 94h. | + |_______|___________________________________________________________________| + | 20 | External DS75LV temperature sensor with I2C address 96h. | + |_______|___________________________________________________________________| + | 21=E2=80=93254| Reserved. | + |_______|___________________________________________________________________| + | 255 | Applies to all pages. | + |_______|___________________________________________________________________| + * + * @operation: Turn on and off power supplies + * @on_off_config: Configure the power supply on and off transition behaviour + * @write_protect: protect against changes to the device's memory + * @vout_margin_high: the voltage when OPERATION is set to margin high + * @vout_margin_low: the voltage when OPERATION is set to margin low + * @vout_scale: scale ADC reading to actual device reading if different + * @iout_cal_gain: set ratio of the voltage at the ADC input to sensed current + */ +typedef struct MAX34451State { + PMBusDevice parent; + + uint16_t power_good_on[MAX34451_NUM_PWR_DEVICES]; + uint16_t power_good_off[MAX34451_NUM_PWR_DEVICES]; + uint16_t ton_delay[MAX34451_NUM_MARGINED_PSU]; + uint16_t ton_max_fault_limit[MAX34451_NUM_MARGINED_PSU]; + uint16_t toff_delay[MAX34451_NUM_MARGINED_PSU]; + uint8_t status_mfr_specific[MAX34451_NUM_PWR_DEVICES]; + /* Manufacturer specific function */ + uint64_t mfr_location; + uint64_t mfr_date; + uint64_t mfr_serial; + uint16_t mfr_mode; + uint32_t psen_config[MAX34451_NUM_MARGINED_PSU]; + uint16_t vout_peak[MAX34451_NUM_PWR_DEVICES]; + uint16_t iout_peak[MAX34451_NUM_PWR_DEVICES]; + uint16_t temperature_peak[MAX34451_NUM_TEMP_DEVICES]; + uint16_t vout_min[MAX34451_NUM_PWR_DEVICES]; + uint16_t nv_log_config; + uint32_t fault_response[MAX34451_NUM_PWR_DEVICES]; + uint16_t fault_retry; + uint32_t fault_log; + uint32_t time_count; + uint16_t margin_config[MAX34451_NUM_MARGINED_PSU]; + uint16_t fw_serial; + uint16_t iout_avg[MAX34451_NUM_PWR_DEVICES]; + uint16_t channel_config[MAX34451_NUM_PWR_DEVICES]; + uint16_t ton_seq_max[MAX34451_NUM_MARGINED_PSU]; + uint32_t pwm_config[MAX34451_NUM_MARGINED_PSU]; + uint32_t seq_config[MAX34451_NUM_MARGINED_PSU]; + uint16_t temp_sensor_config[MAX34451_NUM_TEMP_DEVICES]; + uint16_t store_single; + uint16_t crc; +} MAX34451State; + + +static void max34451_check_limits(MAX34451State *s) +{ + PMBusDevice *pmdev = PMBUS_DEVICE(s); + + pmbus_check_limits(pmdev); + + for (int i = 0; i < MAX34451_NUM_PWR_DEVICES; i++) { + if (pmdev->pages[i].read_vout == 0) { /* PSU disabled */ + continue; + } + + if (pmdev->pages[i].read_vout > s->vout_peak[i]) { + s->vout_peak[i] = pmdev->pages[i].read_vout; + } + + if (pmdev->pages[i].read_vout < s->vout_min[i]) { + s->vout_min[i] = pmdev->pages[i].read_vout; + } + + if (pmdev->pages[i].read_iout > s->iout_peak[i]) { + s->iout_peak[i] = pmdev->pages[i].read_iout; + } + } + + for (int i = 0; i < MAX34451_NUM_TEMP_DEVICES; i++) { + if (pmdev->pages[i + 16].read_temperature_1 > s->temperature_peak[i]) { + s->temperature_peak[i] = pmdev->pages[i + 16].read_temperature_1; + } + } +} + +static uint8_t max34451_read_byte(PMBusDevice *pmdev) +{ + MAX34451State *s = MAX34451(pmdev); + switch (pmdev->code) { + + case PMBUS_POWER_GOOD_ON: + if (pmdev->page < 16) { + pmbus_send16(pmdev, s->power_good_on[pmdev->page]); + } + break; + + case PMBUS_POWER_GOOD_OFF: + if (pmdev->page < 16) { + pmbus_send16(pmdev, s->power_good_off[pmdev->page]); + } + break; + + case PMBUS_TON_DELAY: + if (pmdev->page < 12) { + pmbus_send16(pmdev, s->ton_delay[pmdev->page]); + } + break; + + case PMBUS_TON_MAX_FAULT_LIMIT: + if (pmdev->page < 12) { + pmbus_send16(pmdev, s->ton_max_fault_limit[pmdev->page]); + } + break; + + case PMBUS_TOFF_DELAY: + if (pmdev->page < 12) { + pmbus_send16(pmdev, s->toff_delay[pmdev->page]); + } + break; + + case PMBUS_STATUS_MFR_SPECIFIC: + if (pmdev->page < 16) { + pmbus_send8(pmdev, s->status_mfr_specific[pmdev->page]); + } + break; + + case PMBUS_MFR_ID: + pmbus_send8(pmdev, 0x4d); /* Maxim */ + break; + + case PMBUS_MFR_MODEL: + pmbus_send8(pmdev, 0x59); + break; + + case PMBUS_MFR_LOCATION: + pmbus_send64(pmdev, s->mfr_location); + break; + + case PMBUS_MFR_DATE: + pmbus_send64(pmdev, s->mfr_date); + break; + + case PMBUS_MFR_SERIAL: + pmbus_send64(pmdev, s->mfr_serial); + break; + + case MAX34451_MFR_MODE: + pmbus_send16(pmdev, s->mfr_mode); + break; + + case MAX34451_MFR_PSEN_CONFIG: + if (pmdev->page < 12) { + pmbus_send32(pmdev, s->psen_config[pmdev->page]); + } + break; + + case MAX34451_MFR_VOUT_PEAK: + if (pmdev->page < 16) { + pmbus_send16(pmdev, s->vout_peak[pmdev->page]); + } + break; + + case MAX34451_MFR_IOUT_PEAK: + if (pmdev->page < 16) { + pmbus_send16(pmdev, s->iout_peak[pmdev->page]); + } + break; + + case MAX34451_MFR_TEMPERATURE_PEAK: + if (15 < pmdev->page && pmdev->page < 21) { + pmbus_send16(pmdev, s->temperature_peak[pmdev->page % 16]); + } else { + pmbus_send16(pmdev, s->temperature_peak[0]); + } + break; + + case MAX34451_MFR_VOUT_MIN: + if (pmdev->page < 16) { + pmbus_send16(pmdev, s->vout_min[pmdev->page]); + } + break; + + case MAX34451_MFR_NV_LOG_CONFIG: + pmbus_send16(pmdev, s->nv_log_config); + break; + + case MAX34451_MFR_FAULT_RESPONSE: + if (pmdev->page < 16) { + pmbus_send32(pmdev, s->fault_response[pmdev->page]); + } + break; + + case MAX34451_MFR_FAULT_RETRY: + pmbus_send32(pmdev, s->fault_retry); + break; + + case MAX34451_MFR_NV_FAULT_LOG: + pmbus_send32(pmdev, s->fault_log); + break; + + case MAX34451_MFR_TIME_COUNT: + pmbus_send32(pmdev, s->time_count); + break; + + case MAX34451_MFR_MARGIN_CONFIG: + if (pmdev->page < 12) { + pmbus_send16(pmdev, s->margin_config[pmdev->page]); + } + break; + + case MAX34451_MFR_FW_SERIAL: + if (pmdev->page == 255) { + pmbus_send16(pmdev, 1); /* Firmware revision */ + } + break; + + case MAX34451_MFR_IOUT_AVG: + if (pmdev->page < 16) { + pmbus_send16(pmdev, s->iout_avg[pmdev->page]); + } + break; + + case MAX34451_MFR_CHANNEL_CONFIG: + if (pmdev->page < 16) { + pmbus_send16(pmdev, s->channel_config[pmdev->page]); + } + break; + + case MAX34451_MFR_TON_SEQ_MAX: + if (pmdev->page < 12) { + pmbus_send16(pmdev, s->ton_seq_max[pmdev->page]); + } + break; + + case MAX34451_MFR_PWM_CONFIG: + if (pmdev->page < 12) { + pmbus_send32(pmdev, s->pwm_config[pmdev->page]); + } + break; + + case MAX34451_MFR_SEQ_CONFIG: + if (pmdev->page < 12) { + pmbus_send32(pmdev, s->seq_config[pmdev->page]); + } + break; + + case MAX34451_MFR_TEMP_SENSOR_CONFIG: + if (15 < pmdev->page && pmdev->page < 21) { + pmbus_send32(pmdev, s->temp_sensor_config[pmdev->page % 16]); + } + break; + + case MAX34451_MFR_STORE_SINGLE: + pmbus_send32(pmdev, s->store_single); + break; + + case MAX34451_MFR_CRC: + pmbus_send32(pmdev, s->crc); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: reading from unsupported register: 0x%02x\n", + __func__, pmdev->code); + break; + } + return 0xFF; +} + +static int max34451_write_data(PMBusDevice *pmdev, const uint8_t *buf, + uint8_t len) +{ + MAX34451State *s = MAX34451(pmdev); + + if (len == 0) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: writing empty data\n", __func__); + return -1; + } + + pmdev->code = buf[0]; /* PMBus command code */ + + if (len == 1) { + return 0; + } + + /* Exclude command code from buffer */ + buf++; + len--; + uint8_t index = pmdev->page; + + switch (pmdev->code) { + case MAX34451_MFR_STORE_ALL: + case MAX34451_MFR_RESTORE_ALL: + case MAX34451_MFR_STORE_SINGLE: + /* + * TODO: hardware behaviour is to move the contents of volatile + * memory to non-volatile memory. + */ + break; + + case PMBUS_POWER_GOOD_ON: /* R/W word */ + if (pmdev->page < MAX34451_NUM_PWR_DEVICES) { + s->power_good_on[pmdev->page] = pmbus_receive16(pmdev); + } + break; + + case PMBUS_POWER_GOOD_OFF: /* R/W word */ + if (pmdev->page < MAX34451_NUM_PWR_DEVICES) { + s->power_good_off[pmdev->page] = pmbus_receive16(pmdev); + } + break; + + case PMBUS_TON_DELAY: /* R/W word */ + if (pmdev->page < 12) { + s->ton_delay[pmdev->page] = pmbus_receive16(pmdev); + } + break; + + case PMBUS_TON_MAX_FAULT_LIMIT: /* R/W word */ + if (pmdev->page < 12) { + s->ton_max_fault_limit[pmdev->page] + = pmbus_receive16(pmdev); + } + break; + + case PMBUS_TOFF_DELAY: /* R/W word */ + if (pmdev->page < 12) { + s->toff_delay[pmdev->page] = pmbus_receive16(pmdev); + } + break; + + case PMBUS_MFR_LOCATION: /* R/W 64 */ + s->mfr_location = pmbus_receive64(pmdev); + break; + + case PMBUS_MFR_DATE: /* R/W 64 */ + s->mfr_date = pmbus_receive64(pmdev); + break; + + case PMBUS_MFR_SERIAL: /* R/W 64 */ + s->mfr_serial = pmbus_receive64(pmdev); + break; + + case MAX34451_MFR_MODE: /* R/W word */ + s->mfr_mode = pmbus_receive16(pmdev); + break; + + case MAX34451_MFR_PSEN_CONFIG: /* R/W 32 */ + if (pmdev->page < 12) { + s->psen_config[pmdev->page] = pmbus_receive32(pmdev); + } + break; + + case MAX34451_MFR_VOUT_PEAK: /* R/W word */ + if (pmdev->page < 16) { + s->vout_peak[pmdev->page] = pmbus_receive16(pmdev); + } + break; + + case MAX34451_MFR_IOUT_PEAK: /* R/W word */ + if (pmdev->page < 16) { + s->iout_peak[pmdev->page] = pmbus_receive16(pmdev); + } + break; + + case MAX34451_MFR_TEMPERATURE_PEAK: /* R/W word */ + if (15 < pmdev->page && pmdev->page < 21) { + s->temperature_peak[pmdev->page % 16] + = pmbus_receive16(pmdev); + } + break; + + case MAX34451_MFR_VOUT_MIN: /* R/W word */ + if (pmdev->page < 16) { + s->vout_min[pmdev->page] = pmbus_receive16(pmdev); + } + break; + + case MAX34451_MFR_NV_LOG_CONFIG: /* R/W word */ + s->nv_log_config = pmbus_receive16(pmdev); + break; + + case MAX34451_MFR_FAULT_RESPONSE: /* R/W 32 */ + if (pmdev->page < 16) { + s->fault_response[pmdev->page] = pmbus_receive32(pmdev); + } + break; + + case MAX34451_MFR_FAULT_RETRY: /* R/W word */ + s->fault_retry = pmbus_receive16(pmdev); + break; + + case MAX34451_MFR_TIME_COUNT: /* R/W 32 */ + s->time_count = pmbus_receive32(pmdev); + break; + + case MAX34451_MFR_MARGIN_CONFIG: /* R/W word */ + if (pmdev->page < 12) { + s->margin_config[pmdev->page] = pmbus_receive16(pmdev); + } + break; + + case MAX34451_MFR_CHANNEL_CONFIG: /* R/W word */ + if (pmdev->page < 16) { + s->channel_config[pmdev->page] = pmbus_receive16(pmdev); + } + break; + + case MAX34451_MFR_TON_SEQ_MAX: /* R/W word */ + if (pmdev->page < 12) { + s->ton_seq_max[pmdev->page] = pmbus_receive16(pmdev); + } + break; + + case MAX34451_MFR_PWM_CONFIG: /* R/W 32 */ + if (pmdev->page < 12) { + s->pwm_config[pmdev->page] = pmbus_receive32(pmdev); + } + break; + + case MAX34451_MFR_SEQ_CONFIG: /* R/W 32 */ + if (pmdev->page < 12) { + s->seq_config[pmdev->page] = pmbus_receive32(pmdev); + } + break; + + case MAX34451_MFR_TEMP_SENSOR_CONFIG: /* R/W word */ + if (15 < pmdev->page && pmdev->page < 21) { + s->temp_sensor_config[pmdev->page % 16] + = pmbus_receive16(pmdev); + } + break; + + case MAX34451_MFR_CRC: /* R/W word */ + s->crc = pmbus_receive16(pmdev); + break; + + case MAX34451_MFR_NV_FAULT_LOG: + case MAX34451_MFR_FW_SERIAL: + case MAX34451_MFR_IOUT_AVG: + /* Read only commands */ + pmdev->pages[index].status_word |= PMBUS_STATUS_CML; + pmdev->pages[index].status_cml |= PB_CML_FAULT_INVALID_DATA; + qemu_log_mask(LOG_GUEST_ERROR, + "%s: writing to read-only register 0x%02x\n", + __func__, pmdev->code); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: writing to unsupported register: 0x%02x\n", + __func__, pmdev->code); + break; + } + + return 0; +} + +static void max34451_get(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + visit_type_uint16(v, name, (uint16_t *)opaque, errp); +} + +static void max34451_set(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + MAX34451State *s = MAX34451(obj); + uint16_t *internal = opaque; + uint16_t value; + if (!visit_type_uint16(v, name, &value, errp)) { + return; + } + + *internal = value; + max34451_check_limits(s); +} + +/* used to init uint16_t arrays */ +static inline void *memset_word(void *s, uint16_t c, size_t n) +{ + size_t i; + uint16_t *p = s; + + for (i = 0; i < n; i++) { + p[i] = c; + } + + return s; +} + +static void max34451_exit_reset(Object *obj) +{ + PMBusDevice *pmdev = PMBUS_DEVICE(obj); + MAX34451State *s = MAX34451(obj); + pmdev->capability = DEFAULT_CAPABILITY; + + for (int i = 0; i < MAX34451_NUM_PAGES; i++) { + pmdev->pages[i].operation = DEFAULT_OP_ON; + pmdev->pages[i].on_off_config = DEFAULT_ON_OFF_CONFIG; + pmdev->pages[i].revision = 0x11; + pmdev->pages[i].vout_mode = DEFAULT_VOUT_MODE; + } + + for (int i = 0; i < MAX34451_NUM_PWR_DEVICES; i++) { + pmdev->pages[i].vout_scale_monitor = DEFAULT_SCALE; + pmdev->pages[i].vout_ov_fault_limit = DEFAULT_OV_LIMIT; + pmdev->pages[i].vout_ov_warn_limit = DEFAULT_OV_LIMIT; + pmdev->pages[i].iout_oc_warn_limit = DEFAULT_OC_LIMIT; + pmdev->pages[i].iout_oc_fault_limit = DEFAULT_OC_LIMIT; + } + + for (int i = 0; i < MAX34451_NUM_MARGINED_PSU; i++) { + pmdev->pages[i].ton_max_fault_limit = DEFAULT_TON_FAULT_LIMIT; + } + + for (int i = 16; i < MAX34451_NUM_TEMP_DEVICES + 16; i++) { + pmdev->pages[i].read_temperature_1 = DEFAULT_TEMPERATURE; + pmdev->pages[i].ot_warn_limit = DEFAULT_OT_LIMIT; + pmdev->pages[i].ot_fault_limit = DEFAULT_OT_LIMIT; + } + + memset_word(s->ton_max_fault_limit, DEFAULT_TON_FAULT_LIMIT, + MAX34451_NUM_MARGINED_PSU); + memset_word(s->channel_config, DEFAULT_CHANNEL_CONFIG, + MAX34451_NUM_PWR_DEVICES); + memset_word(s->vout_min, DEFAULT_VMIN, MAX34451_NUM_PWR_DEVICES); + + s->mfr_location = DEFAULT_TEXT; + s->mfr_date = DEFAULT_TEXT; + s->mfr_serial = DEFAULT_TEXT; +} + +static const VMStateDescription vmstate_max34451 = { + .name = TYPE_MAX34451, + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]){ + VMSTATE_PMBUS_DEVICE(parent, MAX34451State), + VMSTATE_UINT16_ARRAY(power_good_on, MAX34451State, + MAX34451_NUM_PWR_DEVICES), + VMSTATE_UINT16_ARRAY(power_good_off, MAX34451State, + MAX34451_NUM_PWR_DEVICES), + VMSTATE_UINT16_ARRAY(ton_delay, MAX34451State, + MAX34451_NUM_MARGINED_PSU), + VMSTATE_UINT16_ARRAY(ton_max_fault_limit, MAX34451State, + MAX34451_NUM_MARGINED_PSU), + VMSTATE_UINT16_ARRAY(toff_delay, MAX34451State, + MAX34451_NUM_MARGINED_PSU), + VMSTATE_UINT8_ARRAY(status_mfr_specific, MAX34451State, + MAX34451_NUM_PWR_DEVICES), + VMSTATE_UINT64(mfr_location, MAX34451State), + VMSTATE_UINT64(mfr_date, MAX34451State), + VMSTATE_UINT64(mfr_serial, MAX34451State), + VMSTATE_UINT16(mfr_mode, MAX34451State), + VMSTATE_UINT32_ARRAY(psen_config, MAX34451State, + MAX34451_NUM_MARGINED_PSU), + VMSTATE_UINT16_ARRAY(vout_peak, MAX34451State, + MAX34451_NUM_PWR_DEVICES), + VMSTATE_UINT16_ARRAY(iout_peak, MAX34451State, + MAX34451_NUM_PWR_DEVICES), + VMSTATE_UINT16_ARRAY(temperature_peak, MAX34451State, + MAX34451_NUM_TEMP_DEVICES), + VMSTATE_UINT16_ARRAY(vout_min, MAX34451State, MAX34451_NUM_PWR_DEVICES), + VMSTATE_UINT16(nv_log_config, MAX34451State), + VMSTATE_UINT32_ARRAY(fault_response, MAX34451State, + MAX34451_NUM_PWR_DEVICES), + VMSTATE_UINT16(fault_retry, MAX34451State), + VMSTATE_UINT32(fault_log, MAX34451State), + VMSTATE_UINT32(time_count, MAX34451State), + VMSTATE_UINT16_ARRAY(margin_config, MAX34451State, + MAX34451_NUM_MARGINED_PSU), + VMSTATE_UINT16(fw_serial, MAX34451State), + VMSTATE_UINT16_ARRAY(iout_avg, MAX34451State, MAX34451_NUM_PWR_DEVICES), + VMSTATE_UINT16_ARRAY(channel_config, MAX34451State, + MAX34451_NUM_PWR_DEVICES), + VMSTATE_UINT16_ARRAY(ton_seq_max, MAX34451State, + MAX34451_NUM_MARGINED_PSU), + VMSTATE_UINT32_ARRAY(pwm_config, MAX34451State, + MAX34451_NUM_MARGINED_PSU), + VMSTATE_UINT32_ARRAY(seq_config, MAX34451State, + MAX34451_NUM_MARGINED_PSU), + VMSTATE_UINT16_ARRAY(temp_sensor_config, MAX34451State, + MAX34451_NUM_TEMP_DEVICES), + VMSTATE_UINT16(store_single, MAX34451State), + VMSTATE_UINT16(crc, MAX34451State), + VMSTATE_END_OF_LIST() + } +}; + +static void max34451_init(Object *obj) +{ + PMBusDevice *pmdev = PMBUS_DEVICE(obj); + uint64_t psu_flags = PB_HAS_VOUT | PB_HAS_IOUT | PB_HAS_VOUT_MODE | + PB_HAS_IOUT_GAIN; + + for (int i = 0; i < MAX34451_NUM_PWR_DEVICES; i++) { + pmbus_page_config(pmdev, i, psu_flags); + } + + for (int i = 0; i < MAX34451_NUM_MARGINED_PSU; i++) { + pmbus_page_config(pmdev, i, psu_flags | PB_HAS_VOUT_MARGIN); + } + + for (int i = 16; i < MAX34451_NUM_TEMP_DEVICES + 16; i++) { + pmbus_page_config(pmdev, i, PB_HAS_TEMPERATURE | PB_HAS_VOUT_MODE); + } + + /* get and set the voltage in millivolts, max is 32767 mV */ + for (int i = 0; i < MAX34451_NUM_PWR_DEVICES; i++) { + object_property_add(obj, "vout[*]", "uint16", + max34451_get, + max34451_set, NULL, &pmdev->pages[i].read_vout); + } + + /* + * get and set the temperature of the internal temperature sensor in + * centidegrees Celcius i.e.: 2500 -> 25.00 C, max is 327.67 C + */ + for (int i = 0; i < MAX34451_NUM_TEMP_DEVICES; i++) { + object_property_add(obj, "temperature[*]", "uint16", + max34451_get, + max34451_set, + NULL, + &pmdev->pages[i + 16].read_temperature_1); + } + +} + +static void max34451_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + PMBusDeviceClass *k = PMBUS_DEVICE_CLASS(klass); + dc->desc = "Maxim MAX34451 16-Channel V/I monitor"; + dc->vmsd = &vmstate_max34451; + k->write_data = max34451_write_data; + k->receive_byte = max34451_read_byte; + k->device_num_pages = MAX34451_NUM_PAGES; + rc->phases.exit = max34451_exit_reset; +} + +static const TypeInfo max34451_info = { + .name = TYPE_MAX34451, + .parent = TYPE_PMBUS_DEVICE, + .instance_size = sizeof(MAX34451State), + .instance_init = max34451_init, + .class_init = max34451_class_init, +}; + +static void max34451_register_types(void) +{ + type_register_static(&max34451_info); +} + +type_init(max34451_register_types) diff --git a/hw/sensor/meson.build b/hw/sensor/meson.build new file mode 100644 index 0000000000..034e3e0207 --- /dev/null +++ b/hw/sensor/meson.build @@ -0,0 +1,5 @@ +softmmu_ss.add(when: 'CONFIG_TMP105', if_true: files('tmp105.c')) +softmmu_ss.add(when: 'CONFIG_TMP421', if_true: files('tmp421.c')) +softmmu_ss.add(when: 'CONFIG_EMC141X', if_true: files('emc141x.c')) +softmmu_ss.add(when: 'CONFIG_ADM1272', if_true: files('adm1272.c')) +softmmu_ss.add(when: 'CONFIG_MAX34451', if_true: files('max34451.c')) diff --git a/hw/misc/tmp105.c b/hw/sensor/tmp105.c similarity index 99% rename from hw/misc/tmp105.c rename to hw/sensor/tmp105.c index d299d9b21b..2056449489 100644 --- a/hw/misc/tmp105.c +++ b/hw/sensor/tmp105.c @@ -22,7 +22,7 @@ #include "hw/i2c/i2c.h" #include "hw/irq.h" #include "migration/vmstate.h" -#include "tmp105.h" +#include "hw/sensor/tmp105.h" #include "qapi/error.h" #include "qapi/visitor.h" #include "qemu/module.h" diff --git a/hw/misc/tmp421.c b/hw/sensor/tmp421.c similarity index 100% rename from hw/misc/tmp421.c rename to hw/sensor/tmp421.c diff --git a/hw/sh4/r2d.c b/hw/sh4/r2d.c index 443820901d..006010f30a 100644 --- a/hw/sh4/r2d.c +++ b/hw/sh4/r2d.c @@ -42,7 +42,6 @@ #include "hw/loader.h" #include "hw/usb.h" #include "hw/block/flash.h" -#include "exec/address-spaces.h" #define FLASH_BASE 0x00000000 #define FLASH_SIZE (16 * MiB) diff --git a/hw/sh4/sh7750.c b/hw/sh4/sh7750.c index f8ac3ec6e3..d53a436d8c 100644 --- a/hw/sh4/sh7750.c +++ b/hw/sh4/sh7750.c @@ -31,7 +31,6 @@ #include "sh7750_regnames.h" #include "hw/sh4/sh_intc.h" #include "hw/timer/tmu012.h" -#include "cpu.h" #include "exec/exec-all.h" #define NB_DEVICES 4 diff --git a/hw/sh4/shix.c b/hw/sh4/shix.c index d9a9fcbc59..b0579aa0f1 100644 --- a/hw/sh4/shix.c +++ b/hw/sh4/shix.c @@ -31,11 +31,9 @@ #include "qapi/error.h" #include "cpu.h" #include "hw/sh4/sh.h" -#include "sysemu/sysemu.h" #include "sysemu/qtest.h" #include "hw/boards.h" #include "hw/loader.h" -#include "exec/address-spaces.h" #include "qemu/error-report.h" #define BIOS_FILENAME "shix_bios.bin" diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c index f22c4f5b73..7397e56737 100644 --- a/hw/smbios/smbios.c +++ b/hw/smbios/smbios.c @@ -27,6 +27,7 @@ #include "hw/firmware/smbios.h" #include "hw/loader.h" #include "hw/boards.h" +#include "hw/pci/pci_bus.h" #include "smbios_build.h" /* legacy structures and constants for <= 2.0 machines */ @@ -118,6 +119,28 @@ static struct { uint16_t speed; } type17; +static QEnumLookup type41_kind_lookup = { + .array = (const char *const[]) { + "other", + "unknown", + "video", + "scsi", + "ethernet", + "tokenring", + "sound", + "pata", + "sata", + "sas", + }, + .size = 10 +}; +struct type41_instance { + const char *designation, *pcidev; + uint8_t instance, kind; + QTAILQ_ENTRY(type41_instance) next; +}; +static QTAILQ_HEAD(, type41_instance) type41 = QTAILQ_HEAD_INITIALIZER(type41); + static QemuOptsList qemu_smbios_opts = { .name = "smbios", .head = QTAILQ_HEAD_INITIALIZER(qemu_smbios_opts.head), @@ -358,6 +381,32 @@ static const QemuOptDesc qemu_smbios_type17_opts[] = { { /* end of list */ } }; +static const QemuOptDesc qemu_smbios_type41_opts[] = { + { + .name = "type", + .type = QEMU_OPT_NUMBER, + .help = "SMBIOS element type", + },{ + .name = "designation", + .type = QEMU_OPT_STRING, + .help = "reference designation string", + },{ + .name = "kind", + .type = QEMU_OPT_STRING, + .help = "device type", + .def_value_str = "other", + },{ + .name = "instance", + .type = QEMU_OPT_NUMBER, + .help = "device type instance", + },{ + .name = "pcidev", + .type = QEMU_OPT_STRING, + .help = "PCI device", + }, + { /* end of list */ } +}; + static void smbios_register_config(void) { qemu_add_opts(&qemu_smbios_opts); @@ -773,6 +822,53 @@ static void smbios_build_type_32_table(void) SMBIOS_BUILD_TABLE_POST; } +static void smbios_build_type_41_table(Error **errp) +{ + unsigned instance = 0; + struct type41_instance *t41; + + QTAILQ_FOREACH(t41, &type41, next) { + SMBIOS_BUILD_TABLE_PRE(41, 0x2900 + instance, true); + + SMBIOS_TABLE_SET_STR(41, reference_designation_str, t41->designation); + t->device_type = t41->kind; + t->device_type_instance = t41->instance; + t->segment_group_number = cpu_to_le16(0); + t->bus_number = 0; + t->device_number = 0; + + if (t41->pcidev) { + PCIDevice *pdev = NULL; + int rc = pci_qdev_find_device(t41->pcidev, &pdev); + if (rc != 0) { + error_setg(errp, + "No PCI device %s for SMBIOS type 41 entry %s", + t41->pcidev, t41->designation); + return; + } + /* + * We only handle the case were the device is attached to + * the PCI root bus. The general case is more complex as + * bridges are enumerated later and the table would need + * to be updated at this moment. + */ + if (!pci_bus_is_root(pci_get_bus(pdev))) { + error_setg(errp, + "Cannot create type 41 entry for PCI device %s: " + "not attached to the root bus", + t41->pcidev); + return; + } + t->segment_group_number = cpu_to_le16(0); + t->bus_number = pci_dev_bus_num(pdev); + t->device_number = pdev->devfn; + } + + SMBIOS_BUILD_TABLE_POST; + instance++; + } +} + static void smbios_build_type_127_table(void) { SMBIOS_BUILD_TABLE_PRE(127, 0x7F00, true); /* required */ @@ -883,7 +979,8 @@ void smbios_get_tables(MachineState *ms, const struct smbios_phys_mem_area *mem_array, const unsigned int mem_array_size, uint8_t **tables, size_t *tables_len, - uint8_t **anchor, size_t *anchor_len) + uint8_t **anchor, size_t *anchor_len, + Error **errp) { unsigned i, dimm_cnt; @@ -928,6 +1025,7 @@ void smbios_get_tables(MachineState *ms, smbios_build_type_32_table(); smbios_build_type_38_table(); + smbios_build_type_41_table(errp); smbios_build_type_127_table(); smbios_validate_table(ms); @@ -1224,6 +1322,30 @@ void smbios_entry_add(QemuOpts *opts, Error **errp) save_opt(&type17.part, opts, "part"); type17.speed = qemu_opt_get_number(opts, "speed", 0); return; + case 41: { + struct type41_instance *t; + Error *local_err = NULL; + + if (!qemu_opts_validate(opts, qemu_smbios_type41_opts, errp)) { + return; + } + t = g_new0(struct type41_instance, 1); + save_opt(&t->designation, opts, "designation"); + t->kind = qapi_enum_parse(&type41_kind_lookup, + qemu_opt_get(opts, "kind"), + 0, &local_err) + 1; + t->kind |= 0x80; /* enabled */ + if (local_err != NULL) { + error_propagate(errp, local_err); + g_free(t); + return; + } + t->instance = qemu_opt_get_number(opts, "instance", 1); + save_opt(&t->pcidev, opts, "pcidev"); + + QTAILQ_INSERT_TAIL(&type41, t, next); + return; + } default: error_setg(errp, "Don't know how to build fields for SMBIOS type %ld", diff --git a/hw/sparc/Kconfig b/hw/sparc/Kconfig index 8dcb10086f..79d58beb7a 100644 --- a/hw/sparc/Kconfig +++ b/hw/sparc/Kconfig @@ -8,7 +8,7 @@ config SUN4M select UNIMP select ESCC select ESP - select FDC + select FDC_SYSBUS select SLAVIO select LANCE select M48T59 diff --git a/hw/sparc/leon3.c b/hw/sparc/leon3.c index 7e16eea9e6..7b4dec1721 100644 --- a/hw/sparc/leon3.c +++ b/hw/sparc/leon3.c @@ -40,7 +40,6 @@ #include "hw/loader.h" #include "elf.h" #include "trace.h" -#include "exec/address-spaces.h" #include "hw/sparc/grlib.h" #include "hw/misc/grlib_ahb_apb_pnp.h" @@ -137,7 +136,36 @@ static void main_cpu_reset(void *opaque) env->regbase[6] = s->sp; } -void leon3_irq_ack(void *irq_manager, int intno) +static void leon3_cache_control_int(CPUSPARCState *env) +{ + uint32_t state = 0; + + if (env->cache_control & CACHE_CTRL_IF) { + /* Instruction cache state */ + state = env->cache_control & CACHE_STATE_MASK; + if (state == CACHE_ENABLED) { + state = CACHE_FROZEN; + trace_int_helper_icache_freeze(); + } + + env->cache_control &= ~CACHE_STATE_MASK; + env->cache_control |= state; + } + + if (env->cache_control & CACHE_CTRL_DF) { + /* Data cache state */ + state = (env->cache_control >> 2) & CACHE_STATE_MASK; + if (state == CACHE_ENABLED) { + state = CACHE_FROZEN; + trace_int_helper_dcache_freeze(); + } + + env->cache_control &= ~(CACHE_STATE_MASK << 2); + env->cache_control |= (state << 2); + } +} + +static void leon3_irq_ack(void *irq_manager, int intno) { grlib_irqmp_ack((DeviceState *)irq_manager, intno); } @@ -181,6 +209,12 @@ static void leon3_set_pil_in(void *opaque, int n, int level) } } +static void leon3_irq_manager(CPUSPARCState *env, void *irq_manager, int intno) +{ + leon3_irq_ack(irq_manager, intno); + leon3_cache_control_int(env); +} + static void leon3_generic_hw_init(MachineState *machine) { ram_addr_t ram_size = machine->ram_size; diff --git a/hw/sparc/sun4m.c b/hw/sparc/sun4m.c index 1a00816d9a..42e139849e 100644 --- a/hw/sparc/sun4m.c +++ b/hw/sparc/sun4m.c @@ -107,6 +107,17 @@ struct sun4m_hwdef { uint8_t nvram_machine_id; }; +struct Sun4mMachineClass { + /*< private >*/ + MachineClass parent_obj; + /*< public >*/ + const struct sun4m_hwdef *hwdef; +}; +typedef struct Sun4mMachineClass Sun4mMachineClass; + +#define TYPE_SUN4M_MACHINE MACHINE_TYPE_NAME("sun4m-common") +DECLARE_CLASS_CHECKERS(Sun4mMachineClass, SUN4M_MACHINE, TYPE_SUN4M_MACHINE) + const char *fw_cfg_arch_key_name(uint16_t key) { static const struct { @@ -159,38 +170,6 @@ static void nvram_init(Nvram *nvram, uint8_t *macaddr, } } -void cpu_check_irqs(CPUSPARCState *env) -{ - CPUState *cs; - - /* We should be holding the BQL before we mess with IRQs */ - g_assert(qemu_mutex_iothread_locked()); - - if (env->pil_in && (env->interrupt_index == 0 || - (env->interrupt_index & ~15) == TT_EXTINT)) { - unsigned int i; - - for (i = 15; i > 0; i--) { - if (env->pil_in & (1 << i)) { - int old_interrupt = env->interrupt_index; - - env->interrupt_index = TT_EXTINT | i; - if (old_interrupt != env->interrupt_index) { - cs = env_cpu(env); - trace_sun4m_cpu_interrupt(i); - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } - break; - } - } - } else if (!env->pil_in && (env->interrupt_index & ~15) == TT_EXTINT) { - cs = env_cpu(env); - trace_sun4m_cpu_reset_interrupt(env->interrupt_index & 15); - env->interrupt_index = 0; - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } -} - static void cpu_kick_irq(SPARCCPU *cpu) { CPUSPARCState *env = &cpu->env; @@ -837,9 +816,9 @@ static void dummy_fdc_tc(void *opaque, int irq, int level) { } -static void sun4m_hw_init(const struct sun4m_hwdef *hwdef, - MachineState *machine) +static void sun4m_hw_init(MachineState *machine) { + const struct sun4m_hwdef *hwdef = SUN4M_MACHINE_GET_CLASS(machine)->hwdef; DeviceState *slavio_intctl; unsigned int i; Nvram *nvram; @@ -1127,9 +1106,22 @@ enum { ss600mp_id, }; -static const struct sun4m_hwdef sun4m_hwdefs[] = { - /* SS-5 */ - { +static void sun4m_machine_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->init = sun4m_hw_init; + mc->block_default_type = IF_SCSI; + mc->default_boot_order = "c"; + mc->default_display = "tcx"; + mc->default_ram_id = "sun4m.ram"; +} + +static void ss5_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + Sun4mMachineClass *smc = SUN4M_MACHINE_CLASS(mc); + static const struct sun4m_hwdef ss5_hwdef = { .iommu_base = 0x10000000, .iommu_pad_base = 0x10004000, .iommu_pad_len = 0x0fffb000, @@ -1154,9 +1146,19 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { .machine_id = ss5_id, .iommu_version = 0x05000000, .max_mem = 0x10000000, - }, - /* SS-10 */ - { + }; + + mc->desc = "Sun4m platform, SPARCstation 5"; + mc->is_default = true; + mc->default_cpu_type = SPARC_CPU_TYPE_NAME("Fujitsu-MB86904"); + smc->hwdef = &ss5_hwdef; +} + +static void ss10_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + Sun4mMachineClass *smc = SUN4M_MACHINE_CLASS(mc); + static const struct sun4m_hwdef ss10_hwdef = { .iommu_base = 0xfe0000000ULL, .tcx_base = 0xe20000000ULL, .slavio_base = 0xff0000000ULL, @@ -1170,18 +1172,28 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { .dma_base = 0xef0400000ULL, .esp_base = 0xef0800000ULL, .le_base = 0xef0c00000ULL, - .apc_base = 0xefa000000ULL, // XXX should not exist + .apc_base = 0xefa000000ULL, /* XXX should not exist */ .aux1_base = 0xff1800000ULL, .aux2_base = 0xff1a01000ULL, .ecc_base = 0xf00000000ULL, - .ecc_version = 0x10000000, // version 0, implementation 1 + .ecc_version = 0x10000000, /* version 0, implementation 1 */ .nvram_machine_id = 0x72, .machine_id = ss10_id, .iommu_version = 0x03000000, .max_mem = 0xf00000000ULL, - }, - /* SS-600MP */ - { + }; + + mc->desc = "Sun4m platform, SPARCstation 10"; + mc->max_cpus = 4; + mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-SuperSparc-II"); + smc->hwdef = &ss10_hwdef; +} + +static void ss600mp_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + Sun4mMachineClass *smc = SUN4M_MACHINE_CLASS(mc); + static const struct sun4m_hwdef ss600mp_hwdef = { .iommu_base = 0xfe0000000ULL, .tcx_base = 0xe20000000ULL, .slavio_base = 0xff0000000ULL, @@ -1193,18 +1205,28 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { .dma_base = 0xef0081000ULL, .esp_base = 0xef0080000ULL, .le_base = 0xef0060000ULL, - .apc_base = 0xefa000000ULL, // XXX should not exist + .apc_base = 0xefa000000ULL, /* XXX should not exist */ .aux1_base = 0xff1800000ULL, - .aux2_base = 0xff1a01000ULL, // XXX should not exist + .aux2_base = 0xff1a01000ULL, /* XXX should not exist */ .ecc_base = 0xf00000000ULL, - .ecc_version = 0x00000000, // version 0, implementation 0 + .ecc_version = 0x00000000, /* version 0, implementation 0 */ .nvram_machine_id = 0x71, .machine_id = ss600mp_id, .iommu_version = 0x01000000, .max_mem = 0xf00000000ULL, - }, - /* SS-20 */ - { + }; + + mc->desc = "Sun4m platform, SPARCserver 600MP"; + mc->max_cpus = 4; + mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-SuperSparc-II"); + smc->hwdef = &ss600mp_hwdef; +} + +static void ss20_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + Sun4mMachineClass *smc = SUN4M_MACHINE_CLASS(mc); + static const struct sun4m_hwdef ss20_hwdef = { .iommu_base = 0xfe0000000ULL, .tcx_base = 0xe20000000ULL, .slavio_base = 0xff0000000ULL, @@ -1219,7 +1241,7 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { .esp_base = 0xef0800000ULL, .le_base = 0xef0c00000ULL, .bpp_base = 0xef4800000ULL, - .apc_base = 0xefa000000ULL, // XXX should not exist + .apc_base = 0xefa000000ULL, /* XXX should not exist */ .aux1_base = 0xff1800000ULL, .aux2_base = 0xff1a01000ULL, .dbri_base = 0xee0000000ULL, @@ -1238,14 +1260,24 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { } }, .ecc_base = 0xf00000000ULL, - .ecc_version = 0x20000000, // version 0, implementation 2 + .ecc_version = 0x20000000, /* version 0, implementation 2 */ .nvram_machine_id = 0x72, .machine_id = ss20_id, .iommu_version = 0x13000000, .max_mem = 0xf00000000ULL, - }, - /* Voyager */ - { + }; + + mc->desc = "Sun4m platform, SPARCstation 20"; + mc->max_cpus = 4; + mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-SuperSparc-II"); + smc->hwdef = &ss20_hwdef; +} + +static void voyager_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + Sun4mMachineClass *smc = SUN4M_MACHINE_CLASS(mc); + static const struct sun4m_hwdef voyager_hwdef = { .iommu_base = 0x10000000, .tcx_base = 0x50000000, .slavio_base = 0x70000000, @@ -1259,16 +1291,25 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { .dma_base = 0x78400000, .esp_base = 0x78800000, .le_base = 0x78c00000, - .apc_base = 0x71300000, // pmc + .apc_base = 0x71300000, /* pmc */ .aux1_base = 0x71900000, .aux2_base = 0x71910000, .nvram_machine_id = 0x80, .machine_id = vger_id, .iommu_version = 0x05000000, .max_mem = 0x10000000, - }, - /* LX */ - { + }; + + mc->desc = "Sun4m platform, SPARCstation Voyager"; + mc->default_cpu_type = SPARC_CPU_TYPE_NAME("Fujitsu-MB86904"); + smc->hwdef = &voyager_hwdef; +} + +static void ss_lx_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + Sun4mMachineClass *smc = SUN4M_MACHINE_CLASS(mc); + static const struct sun4m_hwdef ss_lx_hwdef = { .iommu_base = 0x10000000, .iommu_pad_base = 0x10004000, .iommu_pad_len = 0x0fffb000, @@ -1290,9 +1331,18 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { .machine_id = lx_id, .iommu_version = 0x04000000, .max_mem = 0x10000000, - }, - /* SS-4 */ - { + }; + + mc->desc = "Sun4m platform, SPARCstation LX"; + mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-MicroSparc-I"); + smc->hwdef = &ss_lx_hwdef; +} + +static void ss4_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + Sun4mMachineClass *smc = SUN4M_MACHINE_CLASS(mc); + static const struct sun4m_hwdef ss4_hwdef = { .iommu_base = 0x10000000, .tcx_base = 0x50000000, .cs_base = 0x6c000000, @@ -1314,9 +1364,18 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { .machine_id = ss4_id, .iommu_version = 0x05000000, .max_mem = 0x10000000, - }, - /* SPARCClassic */ - { + }; + + mc->desc = "Sun4m platform, SPARCstation 4"; + mc->default_cpu_type = SPARC_CPU_TYPE_NAME("Fujitsu-MB86904"); + smc->hwdef = &ss4_hwdef; +} + +static void scls_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + Sun4mMachineClass *smc = SUN4M_MACHINE_CLASS(mc); + static const struct sun4m_hwdef scls_hwdef = { .iommu_base = 0x10000000, .tcx_base = 0x50000000, .slavio_base = 0x70000000, @@ -1337,11 +1396,20 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { .machine_id = scls_id, .iommu_version = 0x05000000, .max_mem = 0x10000000, - }, - /* SPARCbook */ - { + }; + + mc->desc = "Sun4m platform, SPARCClassic"; + mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-MicroSparc-I"); + smc->hwdef = &scls_hwdef; +} + +static void sbook_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + Sun4mMachineClass *smc = SUN4M_MACHINE_CLASS(mc); + static const struct sun4m_hwdef sbook_hwdef = { .iommu_base = 0x10000000, - .tcx_base = 0x50000000, // XXX + .tcx_base = 0x50000000, /* XXX */ .slavio_base = 0x70000000, .ms_kb_base = 0x71000000, .serial_base = 0x71100000, @@ -1360,254 +1428,67 @@ static const struct sun4m_hwdef sun4m_hwdefs[] = { .machine_id = sbook_id, .iommu_version = 0x05000000, .max_mem = 0x10000000, - }, -}; - -/* SPARCstation 5 hardware initialisation */ -static void ss5_init(MachineState *machine) -{ - sun4m_hw_init(&sun4m_hwdefs[0], machine); -} - -/* SPARCstation 10 hardware initialisation */ -static void ss10_init(MachineState *machine) -{ - sun4m_hw_init(&sun4m_hwdefs[1], machine); -} - -/* SPARCserver 600MP hardware initialisation */ -static void ss600mp_init(MachineState *machine) -{ - sun4m_hw_init(&sun4m_hwdefs[2], machine); -} - -/* SPARCstation 20 hardware initialisation */ -static void ss20_init(MachineState *machine) -{ - sun4m_hw_init(&sun4m_hwdefs[3], machine); -} - -/* SPARCstation Voyager hardware initialisation */ -static void vger_init(MachineState *machine) -{ - sun4m_hw_init(&sun4m_hwdefs[4], machine); -} - -/* SPARCstation LX hardware initialisation */ -static void ss_lx_init(MachineState *machine) -{ - sun4m_hw_init(&sun4m_hwdefs[5], machine); -} - -/* SPARCstation 4 hardware initialisation */ -static void ss4_init(MachineState *machine) -{ - sun4m_hw_init(&sun4m_hwdefs[6], machine); -} - -/* SPARCClassic hardware initialisation */ -static void scls_init(MachineState *machine) -{ - sun4m_hw_init(&sun4m_hwdefs[7], machine); -} - -/* SPARCbook hardware initialisation */ -static void sbook_init(MachineState *machine) -{ - sun4m_hw_init(&sun4m_hwdefs[8], machine); -} - -static void ss5_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Sun4m platform, SPARCstation 5"; - mc->init = ss5_init; - mc->block_default_type = IF_SCSI; - mc->is_default = true; - mc->default_boot_order = "c"; - mc->default_cpu_type = SPARC_CPU_TYPE_NAME("Fujitsu-MB86904"); - mc->default_display = "tcx"; - mc->default_ram_id = "sun4m.ram"; -} - -static const TypeInfo ss5_type = { - .name = MACHINE_TYPE_NAME("SS-5"), - .parent = TYPE_MACHINE, - .class_init = ss5_class_init, -}; - -static void ss10_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Sun4m platform, SPARCstation 10"; - mc->init = ss10_init; - mc->block_default_type = IF_SCSI; - mc->max_cpus = 4; - mc->default_boot_order = "c"; - mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-SuperSparc-II"); - mc->default_display = "tcx"; - mc->default_ram_id = "sun4m.ram"; -} - -static const TypeInfo ss10_type = { - .name = MACHINE_TYPE_NAME("SS-10"), - .parent = TYPE_MACHINE, - .class_init = ss10_class_init, -}; - -static void ss600mp_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Sun4m platform, SPARCserver 600MP"; - mc->init = ss600mp_init; - mc->block_default_type = IF_SCSI; - mc->max_cpus = 4; - mc->default_boot_order = "c"; - mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-SuperSparc-II"); - mc->default_display = "tcx"; - mc->default_ram_id = "sun4m.ram"; -} - -static const TypeInfo ss600mp_type = { - .name = MACHINE_TYPE_NAME("SS-600MP"), - .parent = TYPE_MACHINE, - .class_init = ss600mp_class_init, -}; - -static void ss20_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Sun4m platform, SPARCstation 20"; - mc->init = ss20_init; - mc->block_default_type = IF_SCSI; - mc->max_cpus = 4; - mc->default_boot_order = "c"; - mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-SuperSparc-II"); - mc->default_display = "tcx"; - mc->default_ram_id = "sun4m.ram"; -} - -static const TypeInfo ss20_type = { - .name = MACHINE_TYPE_NAME("SS-20"), - .parent = TYPE_MACHINE, - .class_init = ss20_class_init, -}; - -static void voyager_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Sun4m platform, SPARCstation Voyager"; - mc->init = vger_init; - mc->block_default_type = IF_SCSI; - mc->default_boot_order = "c"; - mc->default_cpu_type = SPARC_CPU_TYPE_NAME("Fujitsu-MB86904"); - mc->default_display = "tcx"; - mc->default_ram_id = "sun4m.ram"; -} - -static const TypeInfo voyager_type = { - .name = MACHINE_TYPE_NAME("Voyager"), - .parent = TYPE_MACHINE, - .class_init = voyager_class_init, -}; - -static void ss_lx_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Sun4m platform, SPARCstation LX"; - mc->init = ss_lx_init; - mc->block_default_type = IF_SCSI; - mc->default_boot_order = "c"; - mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-MicroSparc-I"); - mc->default_display = "tcx"; - mc->default_ram_id = "sun4m.ram"; -} - -static const TypeInfo ss_lx_type = { - .name = MACHINE_TYPE_NAME("LX"), - .parent = TYPE_MACHINE, - .class_init = ss_lx_class_init, -}; - -static void ss4_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Sun4m platform, SPARCstation 4"; - mc->init = ss4_init; - mc->block_default_type = IF_SCSI; - mc->default_boot_order = "c"; - mc->default_cpu_type = SPARC_CPU_TYPE_NAME("Fujitsu-MB86904"); - mc->default_display = "tcx"; - mc->default_ram_id = "sun4m.ram"; -} - -static const TypeInfo ss4_type = { - .name = MACHINE_TYPE_NAME("SS-4"), - .parent = TYPE_MACHINE, - .class_init = ss4_class_init, -}; - -static void scls_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); - - mc->desc = "Sun4m platform, SPARCClassic"; - mc->init = scls_init; - mc->block_default_type = IF_SCSI; - mc->default_boot_order = "c"; - mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-MicroSparc-I"); - mc->default_display = "tcx"; - mc->default_ram_id = "sun4m.ram"; -} - -static const TypeInfo scls_type = { - .name = MACHINE_TYPE_NAME("SPARCClassic"), - .parent = TYPE_MACHINE, - .class_init = scls_class_init, -}; - -static void sbook_class_init(ObjectClass *oc, void *data) -{ - MachineClass *mc = MACHINE_CLASS(oc); + }; mc->desc = "Sun4m platform, SPARCbook"; - mc->init = sbook_init; - mc->block_default_type = IF_SCSI; - mc->default_boot_order = "c"; mc->default_cpu_type = SPARC_CPU_TYPE_NAME("TI-MicroSparc-I"); - mc->default_display = "tcx"; - mc->default_ram_id = "sun4m.ram"; + smc->hwdef = &sbook_hwdef; } -static const TypeInfo sbook_type = { - .name = MACHINE_TYPE_NAME("SPARCbook"), - .parent = TYPE_MACHINE, - .class_init = sbook_class_init, +static const TypeInfo sun4m_machine_types[] = { + { + .name = MACHINE_TYPE_NAME("SS-5"), + .parent = TYPE_SUN4M_MACHINE, + .class_init = ss5_class_init, + }, { + .name = MACHINE_TYPE_NAME("SS-10"), + .parent = TYPE_SUN4M_MACHINE, + .class_init = ss10_class_init, + }, { + .name = MACHINE_TYPE_NAME("SS-600MP"), + .parent = TYPE_SUN4M_MACHINE, + .class_init = ss600mp_class_init, + }, { + .name = MACHINE_TYPE_NAME("SS-20"), + .parent = TYPE_SUN4M_MACHINE, + .class_init = ss20_class_init, + }, { + .name = MACHINE_TYPE_NAME("Voyager"), + .parent = TYPE_SUN4M_MACHINE, + .class_init = voyager_class_init, + }, { + .name = MACHINE_TYPE_NAME("LX"), + .parent = TYPE_SUN4M_MACHINE, + .class_init = ss_lx_class_init, + }, { + .name = MACHINE_TYPE_NAME("SS-4"), + .parent = TYPE_SUN4M_MACHINE, + .class_init = ss4_class_init, + }, { + .name = MACHINE_TYPE_NAME("SPARCClassic"), + .parent = TYPE_SUN4M_MACHINE, + .class_init = scls_class_init, + }, { + .name = MACHINE_TYPE_NAME("SPARCbook"), + .parent = TYPE_SUN4M_MACHINE, + .class_init = sbook_class_init, + }, { + .name = TYPE_SUN4M_MACHINE, + .parent = TYPE_MACHINE, + .class_size = sizeof(Sun4mMachineClass), + .class_init = sun4m_machine_class_init, + .abstract = true, + } }; +DEFINE_TYPES(sun4m_machine_types) + static void sun4m_register_types(void) { type_register_static(&idreg_info); type_register_static(&afx_info); type_register_static(&prom_info); type_register_static(&ram_info); - - type_register_static(&ss5_type); - type_register_static(&ss10_type); - type_register_static(&ss600mp_type); - type_register_static(&ss20_type); - type_register_static(&voyager_type); - type_register_static(&ss_lx_type); - type_register_static(&ss4_type); - type_register_static(&scls_type); - type_register_static(&sbook_type); } type_init(sun4m_register_types) diff --git a/hw/sparc/trace-events b/hw/sparc/trace-events index 355b07ae05..00b0212c3b 100644 --- a/hw/sparc/trace-events +++ b/hw/sparc/trace-events @@ -1,8 +1,6 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # sun4m.c -sun4m_cpu_interrupt(unsigned int level) "Set CPU IRQ %d" -sun4m_cpu_reset_interrupt(unsigned int level) "Reset CPU IRQ %d" sun4m_cpu_set_irq_raise(int level) "Raise CPU IRQ %d" sun4m_cpu_set_irq_lower(int level) "Lower CPU IRQ %d" @@ -19,3 +17,5 @@ sun4m_iommu_bad_addr(uint64_t addr) "bad addr 0x%"PRIx64 # leon3.c leon3_set_irq(int intno) "Set CPU IRQ %d" leon3_reset_irq(int intno) "Reset CPU IRQ %d" +int_helper_icache_freeze(void) "Instruction cache: freeze" +int_helper_dcache_freeze(void) "Data cache: freeze" diff --git a/hw/sparc64/Kconfig b/hw/sparc64/Kconfig index 980a201bb7..7e557ad17b 100644 --- a/hw/sparc64/Kconfig +++ b/hw/sparc64/Kconfig @@ -6,7 +6,7 @@ config SUN4U imply PARALLEL select M48T59 select ISA_BUS - select FDC + select FDC_ISA select SERIAL_ISA select PCI_SABRE select IDE_CMD646 diff --git a/hw/sparc64/niagara.c b/hw/sparc64/niagara.c index a87d55f6bb..f3e42d0326 100644 --- a/hw/sparc64/niagara.c +++ b/hw/sparc64/niagara.c @@ -31,7 +31,6 @@ #include "hw/loader.h" #include "hw/sparc/sparc64.h" #include "hw/rtc/sun4v-rtc.h" -#include "exec/address-spaces.h" #include "sysemu/block-backend.h" #include "qemu/error-report.h" #include "sysemu/qtest.h" diff --git a/hw/sparc64/sparc64.c b/hw/sparc64/sparc64.c index e3f9219a10..8654e955eb 100644 --- a/hw/sparc64/sparc64.c +++ b/hw/sparc64/sparc64.c @@ -26,7 +26,6 @@ #include "qemu/osdep.h" #include "cpu.h" #include "hw/boards.h" -#include "hw/char/serial.h" #include "hw/sparc/sparc64.h" #include "qemu/timer.h" #include "sysemu/reset.h" @@ -35,68 +34,6 @@ #define TICK_MAX 0x7fffffffffffffffULL -void cpu_check_irqs(CPUSPARCState *env) -{ - CPUState *cs; - uint32_t pil = env->pil_in | - (env->softint & ~(SOFTINT_TIMER | SOFTINT_STIMER)); - - /* We should be holding the BQL before we mess with IRQs */ - g_assert(qemu_mutex_iothread_locked()); - - /* TT_IVEC has a higher priority (16) than TT_EXTINT (31..17) */ - if (env->ivec_status & 0x20) { - return; - } - cs = env_cpu(env); - /* check if TM or SM in SOFTINT are set - setting these also causes interrupt 14 */ - if (env->softint & (SOFTINT_TIMER | SOFTINT_STIMER)) { - pil |= 1 << 14; - } - - /* The bit corresponding to psrpil is (1<< psrpil), the next bit - is (2 << psrpil). */ - if (pil < (2 << env->psrpil)) { - if (cs->interrupt_request & CPU_INTERRUPT_HARD) { - trace_sparc64_cpu_check_irqs_reset_irq(env->interrupt_index); - env->interrupt_index = 0; - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } - return; - } - - if (cpu_interrupts_enabled(env)) { - - unsigned int i; - - for (i = 15; i > env->psrpil; i--) { - if (pil & (1 << i)) { - int old_interrupt = env->interrupt_index; - int new_interrupt = TT_EXTINT | i; - - if (unlikely(env->tl > 0 && cpu_tsptr(env)->tt > new_interrupt - && ((cpu_tsptr(env)->tt & 0x1f0) == TT_EXTINT))) { - trace_sparc64_cpu_check_irqs_noset_irq(env->tl, - cpu_tsptr(env)->tt, - new_interrupt); - } else if (old_interrupt != new_interrupt) { - env->interrupt_index = new_interrupt; - trace_sparc64_cpu_check_irqs_set_irq(i, old_interrupt, - new_interrupt); - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } - break; - } - } - } else if (cs->interrupt_request & CPU_INTERRUPT_HARD) { - trace_sparc64_cpu_check_irqs_disabled(pil, env->pil_in, env->softint, - env->interrupt_index); - env->interrupt_index = 0; - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } -} - static void cpu_kick_irq(SPARCCPU *cpu) { CPUState *cs = CPU(cpu); diff --git a/hw/sparc64/trace-events b/hw/sparc64/trace-events index a0b29987d2..3eb4bacf79 100644 --- a/hw/sparc64/trace-events +++ b/hw/sparc64/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # sun4u.c ebus_isa_irq_handler(int n, int level) "Set ISA IRQ %d level %d" @@ -9,10 +9,6 @@ sun4u_iommu_mem_write(uint64_t addr, uint64_t val, int size) "addr: 0x%"PRIx64" sun4u_iommu_translate(uint64_t addr, uint64_t trans_addr, uint64_t tte) "xlate 0x%"PRIx64" => pa 0x%"PRIx64" tte: 0x%"PRIx64 # sparc64.c -sparc64_cpu_check_irqs_reset_irq(int intno) "Reset CPU IRQ (current interrupt 0x%x)" -sparc64_cpu_check_irqs_noset_irq(uint32_t tl, uint32_t tt, int intno) "Not setting CPU IRQ: TL=%d current 0x%x >= pending 0x%x" -sparc64_cpu_check_irqs_set_irq(unsigned int i, int old, int new) "Set CPU IRQ %d old=0x%x new=0x%x" -sparc64_cpu_check_irqs_disabled(uint32_t pil, uint32_t pil_in, uint32_t softint, int intno) "Interrupts disabled, pil=0x%08x pil_in=0x%08x softint=0x%08x current interrupt 0x%x" sparc64_cpu_ivec_raise_irq(int irq) "Raise IVEC IRQ %d" sparc64_cpu_ivec_lower_irq(int irq) "Lower IVEC IRQ %d" sparc64_cpu_tick_irq_disabled(void) "tick_irq: softint disabled" diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c index 16addee4dc..331a2c5446 100644 --- a/hw/ssi/aspeed_smc.c +++ b/hw/ssi/aspeed_smc.c @@ -29,7 +29,6 @@ #include "qemu/module.h" #include "qemu/error-report.h" #include "qapi/error.h" -#include "exec/address-spaces.h" #include "qemu/units.h" #include "trace.h" @@ -127,6 +126,8 @@ /* DMA Control/Status Register */ #define R_DMA_CTRL (0x80 / 4) +#define DMA_CTRL_REQUEST (1 << 31) +#define DMA_CTRL_GRANT (1 << 30) #define DMA_CTRL_DELAY_MASK 0xf #define DMA_CTRL_DELAY_SHIFT 8 #define DMA_CTRL_FREQ_MASK 0xf @@ -178,10 +179,8 @@ * 0: 4 bytes * 0x7FFFFF: 32M bytes */ -#define DMA_DRAM_ADDR(s, val) ((s)->sdram_base | \ - ((val) & (s)->ctrl->dma_dram_mask)) -#define DMA_FLASH_ADDR(s, val) ((s)->ctrl->flash_window_base | \ - ((val) & (s)->ctrl->dma_flash_mask)) +#define DMA_DRAM_ADDR(s, val) ((val) & (s)->ctrl->dma_dram_mask) +#define DMA_FLASH_ADDR(s, val) ((val) & (s)->ctrl->dma_flash_mask) #define DMA_LENGTH(val) ((val) & 0x01FFFFFC) /* Flash opcodes. */ @@ -230,6 +229,7 @@ static uint32_t aspeed_smc_segment_to_reg(const AspeedSMCState *s, const AspeedSegments *seg); static void aspeed_smc_reg_to_segment(const AspeedSMCState *s, uint32_t reg, AspeedSegments *seg); +static void aspeed_smc_dma_ctrl(AspeedSMCState *s, uint32_t value); /* * AST2600 definitions @@ -259,6 +259,15 @@ static uint32_t aspeed_2600_smc_segment_to_reg(const AspeedSMCState *s, const AspeedSegments *seg); static void aspeed_2600_smc_reg_to_segment(const AspeedSMCState *s, uint32_t reg, AspeedSegments *seg); +static void aspeed_2600_smc_dma_ctrl(AspeedSMCState *s, uint32_t value); + +#define ASPEED_SMC_FEATURE_DMA 0x1 +#define ASPEED_SMC_FEATURE_DMA_GRANT 0x2 + +static inline bool aspeed_smc_has_dma(const AspeedSMCState *s) +{ + return !!(s->ctrl->features & ASPEED_SMC_FEATURE_DMA); +} static const AspeedSMCController controllers[] = { { @@ -273,10 +282,11 @@ static const AspeedSMCController controllers[] = { .segments = aspeed_segments_legacy, .flash_window_base = ASPEED_SOC_SMC_FLASH_BASE, .flash_window_size = 0x6000000, - .has_dma = false, + .features = 0x0, .nregs = ASPEED_SMC_R_SMC_MAX, .segment_to_reg = aspeed_smc_segment_to_reg, .reg_to_segment = aspeed_smc_reg_to_segment, + .dma_ctrl = aspeed_smc_dma_ctrl, }, { .name = "aspeed.fmc-ast2400", .r_conf = R_CONF, @@ -289,12 +299,13 @@ static const AspeedSMCController controllers[] = { .segments = aspeed_segments_fmc, .flash_window_base = ASPEED_SOC_FMC_FLASH_BASE, .flash_window_size = 0x10000000, - .has_dma = true, + .features = ASPEED_SMC_FEATURE_DMA, .dma_flash_mask = 0x0FFFFFFC, .dma_dram_mask = 0x1FFFFFFC, .nregs = ASPEED_SMC_R_MAX, .segment_to_reg = aspeed_smc_segment_to_reg, .reg_to_segment = aspeed_smc_reg_to_segment, + .dma_ctrl = aspeed_smc_dma_ctrl, }, { .name = "aspeed.spi1-ast2400", .r_conf = R_SPI_CONF, @@ -307,10 +318,11 @@ static const AspeedSMCController controllers[] = { .segments = aspeed_segments_spi, .flash_window_base = ASPEED_SOC_SPI_FLASH_BASE, .flash_window_size = 0x10000000, - .has_dma = false, + .features = 0x0, .nregs = ASPEED_SMC_R_SPI_MAX, .segment_to_reg = aspeed_smc_segment_to_reg, .reg_to_segment = aspeed_smc_reg_to_segment, + .dma_ctrl = aspeed_smc_dma_ctrl, }, { .name = "aspeed.fmc-ast2500", .r_conf = R_CONF, @@ -323,12 +335,13 @@ static const AspeedSMCController controllers[] = { .segments = aspeed_segments_ast2500_fmc, .flash_window_base = ASPEED_SOC_FMC_FLASH_BASE, .flash_window_size = 0x10000000, - .has_dma = true, + .features = ASPEED_SMC_FEATURE_DMA, .dma_flash_mask = 0x0FFFFFFC, .dma_dram_mask = 0x3FFFFFFC, .nregs = ASPEED_SMC_R_MAX, .segment_to_reg = aspeed_smc_segment_to_reg, .reg_to_segment = aspeed_smc_reg_to_segment, + .dma_ctrl = aspeed_smc_dma_ctrl, }, { .name = "aspeed.spi1-ast2500", .r_conf = R_CONF, @@ -341,10 +354,11 @@ static const AspeedSMCController controllers[] = { .segments = aspeed_segments_ast2500_spi1, .flash_window_base = ASPEED_SOC_SPI_FLASH_BASE, .flash_window_size = 0x8000000, - .has_dma = false, + .features = 0x0, .nregs = ASPEED_SMC_R_MAX, .segment_to_reg = aspeed_smc_segment_to_reg, .reg_to_segment = aspeed_smc_reg_to_segment, + .dma_ctrl = aspeed_smc_dma_ctrl, }, { .name = "aspeed.spi2-ast2500", .r_conf = R_CONF, @@ -357,10 +371,11 @@ static const AspeedSMCController controllers[] = { .segments = aspeed_segments_ast2500_spi2, .flash_window_base = ASPEED_SOC_SPI2_FLASH_BASE, .flash_window_size = 0x8000000, - .has_dma = false, + .features = 0x0, .nregs = ASPEED_SMC_R_MAX, .segment_to_reg = aspeed_smc_segment_to_reg, .reg_to_segment = aspeed_smc_reg_to_segment, + .dma_ctrl = aspeed_smc_dma_ctrl, }, { .name = "aspeed.fmc-ast2600", .r_conf = R_CONF, @@ -373,12 +388,13 @@ static const AspeedSMCController controllers[] = { .segments = aspeed_segments_ast2600_fmc, .flash_window_base = ASPEED26_SOC_FMC_FLASH_BASE, .flash_window_size = 0x10000000, - .has_dma = true, + .features = ASPEED_SMC_FEATURE_DMA, .dma_flash_mask = 0x0FFFFFFC, .dma_dram_mask = 0x3FFFFFFC, .nregs = ASPEED_SMC_R_MAX, .segment_to_reg = aspeed_2600_smc_segment_to_reg, .reg_to_segment = aspeed_2600_smc_reg_to_segment, + .dma_ctrl = aspeed_2600_smc_dma_ctrl, }, { .name = "aspeed.spi1-ast2600", .r_conf = R_CONF, @@ -391,12 +407,14 @@ static const AspeedSMCController controllers[] = { .segments = aspeed_segments_ast2600_spi1, .flash_window_base = ASPEED26_SOC_SPI_FLASH_BASE, .flash_window_size = 0x10000000, - .has_dma = true, + .features = ASPEED_SMC_FEATURE_DMA | + ASPEED_SMC_FEATURE_DMA_GRANT, .dma_flash_mask = 0x0FFFFFFC, .dma_dram_mask = 0x3FFFFFFC, .nregs = ASPEED_SMC_R_MAX, .segment_to_reg = aspeed_2600_smc_segment_to_reg, .reg_to_segment = aspeed_2600_smc_reg_to_segment, + .dma_ctrl = aspeed_2600_smc_dma_ctrl, }, { .name = "aspeed.spi2-ast2600", .r_conf = R_CONF, @@ -409,12 +427,14 @@ static const AspeedSMCController controllers[] = { .segments = aspeed_segments_ast2600_spi2, .flash_window_base = ASPEED26_SOC_SPI2_FLASH_BASE, .flash_window_size = 0x10000000, - .has_dma = true, + .features = ASPEED_SMC_FEATURE_DMA | + ASPEED_SMC_FEATURE_DMA_GRANT, .dma_flash_mask = 0x0FFFFFFC, .dma_dram_mask = 0x3FFFFFFC, .nregs = ASPEED_SMC_R_MAX, .segment_to_reg = aspeed_2600_smc_segment_to_reg, .reg_to_segment = aspeed_2600_smc_reg_to_segment, + .dma_ctrl = aspeed_2600_smc_dma_ctrl, }, }; @@ -999,11 +1019,11 @@ static uint64_t aspeed_smc_read(void *opaque, hwaddr addr, unsigned int size) addr == R_CE_CMD_CTRL || addr == R_INTR_CTRL || addr == R_DUMMY_DATA || - (s->ctrl->has_dma && addr == R_DMA_CTRL) || - (s->ctrl->has_dma && addr == R_DMA_FLASH_ADDR) || - (s->ctrl->has_dma && addr == R_DMA_DRAM_ADDR) || - (s->ctrl->has_dma && addr == R_DMA_LEN) || - (s->ctrl->has_dma && addr == R_DMA_CHECKSUM) || + (aspeed_smc_has_dma(s) && addr == R_DMA_CTRL) || + (aspeed_smc_has_dma(s) && addr == R_DMA_FLASH_ADDR) || + (aspeed_smc_has_dma(s) && addr == R_DMA_DRAM_ADDR) || + (aspeed_smc_has_dma(s) && addr == R_DMA_LEN) || + (aspeed_smc_has_dma(s) && addr == R_DMA_CHECKSUM) || (addr >= R_SEG_ADDR0 && addr < R_SEG_ADDR0 + s->ctrl->max_peripherals) || (addr >= s->r_ctrl0 && addr < s->r_ctrl0 + s->ctrl->max_peripherals)) { @@ -1236,7 +1256,7 @@ static void aspeed_smc_dma_done(AspeedSMCState *s) } } -static void aspeed_smc_dma_ctrl(AspeedSMCState *s, uint64_t dma_ctrl) +static void aspeed_smc_dma_ctrl(AspeedSMCState *s, uint32_t dma_ctrl) { if (!(dma_ctrl & DMA_CTRL_ENABLE)) { s->regs[R_DMA_CTRL] = dma_ctrl; @@ -1261,6 +1281,46 @@ static void aspeed_smc_dma_ctrl(AspeedSMCState *s, uint64_t dma_ctrl) aspeed_smc_dma_done(s); } +static inline bool aspeed_smc_dma_granted(AspeedSMCState *s) +{ + if (!(s->ctrl->features & ASPEED_SMC_FEATURE_DMA_GRANT)) { + return true; + } + + if (!(s->regs[R_DMA_CTRL] & DMA_CTRL_GRANT)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: DMA not granted\n", __func__); + return false; + } + + return true; +} + +static void aspeed_2600_smc_dma_ctrl(AspeedSMCState *s, uint32_t dma_ctrl) +{ + /* Preserve DMA bits */ + dma_ctrl |= s->regs[R_DMA_CTRL] & (DMA_CTRL_REQUEST | DMA_CTRL_GRANT); + + if (dma_ctrl == 0xAEED0000) { + /* automatically grant request */ + s->regs[R_DMA_CTRL] |= (DMA_CTRL_REQUEST | DMA_CTRL_GRANT); + return; + } + + /* clear request */ + if (dma_ctrl == 0xDEEA0000) { + s->regs[R_DMA_CTRL] &= ~(DMA_CTRL_REQUEST | DMA_CTRL_GRANT); + return; + } + + if (!aspeed_smc_dma_granted(s)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: DMA not granted\n", __func__); + return; + } + + aspeed_smc_dma_ctrl(s, dma_ctrl); + s->regs[R_DMA_CTRL] &= ~(DMA_CTRL_REQUEST | DMA_CTRL_GRANT); +} + static void aspeed_smc_write(void *opaque, hwaddr addr, uint64_t data, unsigned int size) { @@ -1292,13 +1352,16 @@ static void aspeed_smc_write(void *opaque, hwaddr addr, uint64_t data, s->regs[addr] = value & 0xff; } else if (addr == R_INTR_CTRL) { s->regs[addr] = value; - } else if (s->ctrl->has_dma && addr == R_DMA_CTRL) { - aspeed_smc_dma_ctrl(s, value); - } else if (s->ctrl->has_dma && addr == R_DMA_DRAM_ADDR) { + } else if (aspeed_smc_has_dma(s) && addr == R_DMA_CTRL) { + s->ctrl->dma_ctrl(s, value); + } else if (aspeed_smc_has_dma(s) && addr == R_DMA_DRAM_ADDR && + aspeed_smc_dma_granted(s)) { s->regs[addr] = DMA_DRAM_ADDR(s, value); - } else if (s->ctrl->has_dma && addr == R_DMA_FLASH_ADDR) { + } else if (aspeed_smc_has_dma(s) && addr == R_DMA_FLASH_ADDR && + aspeed_smc_dma_granted(s)) { s->regs[addr] = DMA_FLASH_ADDR(s, value); - } else if (s->ctrl->has_dma && addr == R_DMA_LEN) { + } else if (aspeed_smc_has_dma(s) && addr == R_DMA_LEN && + aspeed_smc_dma_granted(s)) { s->regs[addr] = DMA_LENGTH(value); } else { qemu_log_mask(LOG_UNIMP, "%s: not implemented: 0x%" HWADDR_PRIx "\n", @@ -1386,7 +1449,9 @@ static void aspeed_smc_realize(DeviceState *dev, Error **errp) memory_region_init_io(&s->mmio_flash, OBJECT(s), &aspeed_smc_flash_default_ops, s, name, s->ctrl->flash_window_size); - sysbus_init_mmio(sbd, &s->mmio_flash); + memory_region_init_alias(&s->mmio_flash_alias, OBJECT(s), name, + &s->mmio_flash, 0, s->ctrl->flash_window_size); + sysbus_init_mmio(sbd, &s->mmio_flash_alias); s->flashes = g_new0(AspeedSMCFlash, s->ctrl->max_peripherals); @@ -1412,7 +1477,7 @@ static void aspeed_smc_realize(DeviceState *dev, Error **errp) } /* DMA support */ - if (s->ctrl->has_dma) { + if (aspeed_smc_has_dma(s)) { aspeed_smc_dma_setup(s, errp); } } @@ -1432,7 +1497,6 @@ static const VMStateDescription vmstate_aspeed_smc = { static Property aspeed_smc_properties[] = { DEFINE_PROP_UINT32("num-cs", AspeedSMCState, num_cs, 1), DEFINE_PROP_BOOL("inject-failure", AspeedSMCState, inject_failure, false), - DEFINE_PROP_UINT64("sdram-base", AspeedSMCState, sdram_base, 0), DEFINE_PROP_LINK("dram", AspeedSMCState, dram_mr, TYPE_MEMORY_REGION, MemoryRegion *), DEFINE_PROP_END_OF_LIST(), diff --git a/hw/ssi/sifive_spi.c b/hw/ssi/sifive_spi.c index 0c9ebca3c8..03540cf5ca 100644 --- a/hw/ssi/sifive_spi.c +++ b/hw/ssi/sifive_spi.c @@ -24,7 +24,6 @@ #include "hw/qdev-properties.h" #include "hw/sysbus.h" #include "hw/ssi/ssi.h" -#include "sysemu/sysemu.h" #include "qemu/fifo8.h" #include "qemu/log.h" #include "qemu/module.h" diff --git a/hw/ssi/xilinx_spi.c b/hw/ssi/xilinx_spi.c index 49ff275593..b2819a7ff0 100644 --- a/hw/ssi/xilinx_spi.c +++ b/hw/ssi/xilinx_spi.c @@ -27,7 +27,6 @@ #include "qemu/osdep.h" #include "hw/sysbus.h" #include "migration/vmstate.h" -#include "qemu/log.h" #include "qemu/module.h" #include "qemu/fifo8.h" diff --git a/hw/timer/etraxfs_timer.c b/hw/timer/etraxfs_timer.c index 5379006086..4ba662190d 100644 --- a/hw/timer/etraxfs_timer.c +++ b/hw/timer/etraxfs_timer.c @@ -309,9 +309,9 @@ static const MemoryRegionOps timer_ops = { } }; -static void etraxfs_timer_reset(void *opaque) +static void etraxfs_timer_reset_enter(Object *obj, ResetType type) { - ETRAXTimerState *t = opaque; + ETRAXTimerState *t = ETRAX_TIMER(obj); ptimer_transaction_begin(t->ptimer_t0); ptimer_stop(t->ptimer_t0); @@ -325,6 +325,12 @@ static void etraxfs_timer_reset(void *opaque) t->rw_wd_ctrl = 0; t->r_intr = 0; t->rw_intr_mask = 0; +} + +static void etraxfs_timer_reset_hold(Object *obj) +{ + ETRAXTimerState *t = ETRAX_TIMER(obj); + qemu_irq_lower(t->irq); } @@ -343,14 +349,16 @@ static void etraxfs_timer_realize(DeviceState *dev, Error **errp) memory_region_init_io(&t->mmio, OBJECT(t), &timer_ops, t, "etraxfs-timer", 0x5c); sysbus_init_mmio(sbd, &t->mmio); - qemu_register_reset(etraxfs_timer_reset, t); } static void etraxfs_timer_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); dc->realize = etraxfs_timer_realize; + rc->phases.enter = etraxfs_timer_reset_enter; + rc->phases.hold = etraxfs_timer_reset_hold; } static const TypeInfo etraxfs_timer_info = { diff --git a/hw/timer/ibex_timer.c b/hw/timer/ibex_timer.c new file mode 100644 index 0000000000..5befb53506 --- /dev/null +++ b/hw/timer/ibex_timer.c @@ -0,0 +1,305 @@ +/* + * QEMU lowRISC Ibex Timer device + * + * Copyright (c) 2021 Western Digital + * + * For details check the documentation here: + * https://docs.opentitan.org/hw/ip/rv_timer/doc/ + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/timer.h" +#include "hw/timer/ibex_timer.h" +#include "hw/irq.h" +#include "hw/qdev-properties.h" +#include "target/riscv/cpu.h" +#include "migration/vmstate.h" + +REG32(CTRL, 0x00) + FIELD(CTRL, ACTIVE, 0, 1) +REG32(CFG0, 0x100) + FIELD(CFG0, PRESCALE, 0, 12) + FIELD(CFG0, STEP, 16, 8) +REG32(LOWER0, 0x104) +REG32(UPPER0, 0x108) +REG32(COMPARE_LOWER0, 0x10C) +REG32(COMPARE_UPPER0, 0x110) +REG32(INTR_ENABLE, 0x114) + FIELD(INTR_ENABLE, IE_0, 0, 1) +REG32(INTR_STATE, 0x118) + FIELD(INTR_STATE, IS_0, 0, 1) +REG32(INTR_TEST, 0x11C) + FIELD(INTR_TEST, T_0, 0, 1) + +static uint64_t cpu_riscv_read_rtc(uint32_t timebase_freq) +{ + return muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), + timebase_freq, NANOSECONDS_PER_SECOND); +} + +static void ibex_timer_update_irqs(IbexTimerState *s) +{ + CPUState *cs = qemu_get_cpu(0); + RISCVCPU *cpu = RISCV_CPU(cs); + uint64_t value = s->timer_compare_lower0 | + ((uint64_t)s->timer_compare_upper0 << 32); + uint64_t next, diff; + uint64_t now = cpu_riscv_read_rtc(s->timebase_freq); + + if (!(s->timer_ctrl & R_CTRL_ACTIVE_MASK)) { + /* Timer isn't active */ + return; + } + + /* Update the CPUs mtimecmp */ + cpu->env.timecmp = value; + + if (cpu->env.timecmp <= now) { + /* + * If the mtimecmp was in the past raise the interrupt now. + */ + riscv_cpu_update_mip(cpu, MIP_MTIP, BOOL_TO_MASK(1)); + if (s->timer_intr_enable & R_INTR_ENABLE_IE_0_MASK) { + s->timer_intr_state |= R_INTR_STATE_IS_0_MASK; + qemu_set_irq(s->irq, true); + } + return; + } + + /* Setup a timer to trigger the interrupt in the future */ + riscv_cpu_update_mip(cpu, MIP_MTIP, BOOL_TO_MASK(0)); + qemu_set_irq(s->irq, false); + + diff = cpu->env.timecmp - now; + next = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + + muldiv64(diff, + NANOSECONDS_PER_SECOND, + s->timebase_freq); + + if (next < qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL)) { + /* We overflowed the timer, just set it as large as we can */ + timer_mod(cpu->env.timer, 0x7FFFFFFFFFFFFFFF); + } else { + timer_mod(cpu->env.timer, next); + } +} + +static void ibex_timer_cb(void *opaque) +{ + IbexTimerState *s = opaque; + CPUState *cs = qemu_get_cpu(0); + RISCVCPU *cpu = RISCV_CPU(cs); + + riscv_cpu_update_mip(cpu, MIP_MTIP, BOOL_TO_MASK(1)); + if (s->timer_intr_enable & R_INTR_ENABLE_IE_0_MASK) { + s->timer_intr_state |= R_INTR_STATE_IS_0_MASK; + qemu_set_irq(s->irq, true); + } +} + +static void ibex_timer_reset(DeviceState *dev) +{ + IbexTimerState *s = IBEX_TIMER(dev); + + CPUState *cpu = qemu_get_cpu(0); + CPURISCVState *env = cpu->env_ptr; + env->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, + &ibex_timer_cb, s); + env->timecmp = 0; + + s->timer_ctrl = 0x00000000; + s->timer_cfg0 = 0x00010000; + s->timer_compare_lower0 = 0xFFFFFFFF; + s->timer_compare_upper0 = 0xFFFFFFFF; + s->timer_intr_enable = 0x00000000; + s->timer_intr_state = 0x00000000; + s->timer_intr_test = 0x00000000; + + ibex_timer_update_irqs(s); +} + +static uint64_t ibex_timer_read(void *opaque, hwaddr addr, + unsigned int size) +{ + IbexTimerState *s = opaque; + uint64_t now = cpu_riscv_read_rtc(s->timebase_freq); + uint64_t retvalue = 0; + + switch (addr >> 2) { + case R_CTRL: + retvalue = s->timer_ctrl; + break; + case R_CFG0: + retvalue = s->timer_cfg0; + break; + case R_LOWER0: + retvalue = now; + break; + case R_UPPER0: + retvalue = now >> 32; + break; + case R_COMPARE_LOWER0: + retvalue = s->timer_compare_lower0; + break; + case R_COMPARE_UPPER0: + retvalue = s->timer_compare_upper0; + break; + case R_INTR_ENABLE: + retvalue = s->timer_intr_enable; + break; + case R_INTR_STATE: + retvalue = s->timer_intr_state; + break; + case R_INTR_TEST: + retvalue = s->timer_intr_test; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%"HWADDR_PRIx"\n", __func__, addr); + return 0; + } + + return retvalue; +} + +static void ibex_timer_write(void *opaque, hwaddr addr, + uint64_t val64, unsigned int size) +{ + IbexTimerState *s = opaque; + uint32_t val = val64; + + switch (addr >> 2) { + case R_CTRL: + s->timer_ctrl = val; + break; + case R_CFG0: + qemu_log_mask(LOG_UNIMP, "Changing prescale or step not supported"); + s->timer_cfg0 = val; + break; + case R_LOWER0: + qemu_log_mask(LOG_UNIMP, "Changing timer value is not supported"); + break; + case R_UPPER0: + qemu_log_mask(LOG_UNIMP, "Changing timer value is not supported"); + break; + case R_COMPARE_LOWER0: + s->timer_compare_lower0 = val; + ibex_timer_update_irqs(s); + break; + case R_COMPARE_UPPER0: + s->timer_compare_upper0 = val; + ibex_timer_update_irqs(s); + break; + case R_INTR_ENABLE: + s->timer_intr_enable = val; + break; + case R_INTR_STATE: + /* Write 1 to clear */ + s->timer_intr_state &= ~val; + break; + case R_INTR_TEST: + s->timer_intr_test = val; + if (s->timer_intr_enable & + s->timer_intr_test & + R_INTR_ENABLE_IE_0_MASK) { + s->timer_intr_state |= R_INTR_STATE_IS_0_MASK; + qemu_set_irq(s->irq, true); + } + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%"HWADDR_PRIx"\n", __func__, addr); + } +} + +static const MemoryRegionOps ibex_timer_ops = { + .read = ibex_timer_read, + .write = ibex_timer_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl.min_access_size = 4, + .impl.max_access_size = 4, +}; + +static int ibex_timer_post_load(void *opaque, int version_id) +{ + IbexTimerState *s = opaque; + + ibex_timer_update_irqs(s); + return 0; +} + +static const VMStateDescription vmstate_ibex_timer = { + .name = TYPE_IBEX_TIMER, + .version_id = 1, + .minimum_version_id = 1, + .post_load = ibex_timer_post_load, + .fields = (VMStateField[]) { + VMSTATE_UINT32(timer_ctrl, IbexTimerState), + VMSTATE_UINT32(timer_cfg0, IbexTimerState), + VMSTATE_UINT32(timer_compare_lower0, IbexTimerState), + VMSTATE_UINT32(timer_compare_upper0, IbexTimerState), + VMSTATE_UINT32(timer_intr_enable, IbexTimerState), + VMSTATE_UINT32(timer_intr_state, IbexTimerState), + VMSTATE_UINT32(timer_intr_test, IbexTimerState), + VMSTATE_END_OF_LIST() + } +}; + +static Property ibex_timer_properties[] = { + DEFINE_PROP_UINT32("timebase-freq", IbexTimerState, timebase_freq, 10000), + DEFINE_PROP_END_OF_LIST(), +}; + +static void ibex_timer_init(Object *obj) +{ + IbexTimerState *s = IBEX_TIMER(obj); + + sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); + + memory_region_init_io(&s->mmio, obj, &ibex_timer_ops, s, + TYPE_IBEX_TIMER, 0x400); + sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->mmio); +} + +static void ibex_timer_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = ibex_timer_reset; + dc->vmsd = &vmstate_ibex_timer; + device_class_set_props(dc, ibex_timer_properties); +} + +static const TypeInfo ibex_timer_info = { + .name = TYPE_IBEX_TIMER, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(IbexTimerState), + .instance_init = ibex_timer_init, + .class_init = ibex_timer_class_init, +}; + +static void ibex_timer_register_types(void) +{ + type_register_static(&ibex_timer_info); +} + +type_init(ibex_timer_register_types) diff --git a/hw/timer/lm32_timer.c b/hw/timer/lm32_timer.c deleted file mode 100644 index eeaf0ada5f..0000000000 --- a/hw/timer/lm32_timer.c +++ /dev/null @@ -1,249 +0,0 @@ -/* - * QEMU model of the LatticeMico32 timer block. - * - * Copyright (c) 2010 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://www.latticesemi.com/documents/mico32timer.pdf - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "qemu/timer.h" -#include "hw/ptimer.h" -#include "hw/qdev-properties.h" -#include "qemu/error-report.h" -#include "qemu/module.h" -#include "qom/object.h" - -#define DEFAULT_FREQUENCY (50*1000000) - -enum { - R_SR = 0, - R_CR, - R_PERIOD, - R_SNAPSHOT, - R_MAX -}; - -enum { - SR_TO = (1 << 0), - SR_RUN = (1 << 1), -}; - -enum { - CR_ITO = (1 << 0), - CR_CONT = (1 << 1), - CR_START = (1 << 2), - CR_STOP = (1 << 3), -}; - -#define TYPE_LM32_TIMER "lm32-timer" -OBJECT_DECLARE_SIMPLE_TYPE(LM32TimerState, LM32_TIMER) - -struct LM32TimerState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - - ptimer_state *ptimer; - - qemu_irq irq; - uint32_t freq_hz; - - uint32_t regs[R_MAX]; -}; - -static void timer_update_irq(LM32TimerState *s) -{ - int state = (s->regs[R_SR] & SR_TO) && (s->regs[R_CR] & CR_ITO); - - trace_lm32_timer_irq_state(state); - qemu_set_irq(s->irq, state); -} - -static uint64_t timer_read(void *opaque, hwaddr addr, unsigned size) -{ - LM32TimerState *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_SR: - case R_CR: - case R_PERIOD: - r = s->regs[addr]; - break; - case R_SNAPSHOT: - r = (uint32_t)ptimer_get_count(s->ptimer); - break; - default: - error_report("lm32_timer: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - trace_lm32_timer_memory_read(addr << 2, r); - return r; -} - -static void timer_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size) -{ - LM32TimerState *s = opaque; - - trace_lm32_timer_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_SR: - s->regs[R_SR] &= ~SR_TO; - break; - case R_CR: - ptimer_transaction_begin(s->ptimer); - s->regs[R_CR] = value; - if (s->regs[R_CR] & CR_START) { - ptimer_run(s->ptimer, 1); - } - if (s->regs[R_CR] & CR_STOP) { - ptimer_stop(s->ptimer); - } - ptimer_transaction_commit(s->ptimer); - break; - case R_PERIOD: - s->regs[R_PERIOD] = value; - ptimer_transaction_begin(s->ptimer); - ptimer_set_count(s->ptimer, value); - ptimer_transaction_commit(s->ptimer); - break; - case R_SNAPSHOT: - error_report("lm32_timer: write access to read only register 0x" - TARGET_FMT_plx, addr << 2); - break; - default: - error_report("lm32_timer: write access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - timer_update_irq(s); -} - -static const MemoryRegionOps timer_ops = { - .read = timer_read, - .write = timer_write, - .endianness = DEVICE_NATIVE_ENDIAN, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, -}; - -static void timer_hit(void *opaque) -{ - LM32TimerState *s = opaque; - - trace_lm32_timer_hit(); - - s->regs[R_SR] |= SR_TO; - - if (s->regs[R_CR] & CR_CONT) { - ptimer_set_count(s->ptimer, s->regs[R_PERIOD]); - ptimer_run(s->ptimer, 1); - } - timer_update_irq(s); -} - -static void timer_reset(DeviceState *d) -{ - LM32TimerState *s = LM32_TIMER(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } - ptimer_transaction_begin(s->ptimer); - ptimer_stop(s->ptimer); - ptimer_transaction_commit(s->ptimer); -} - -static void lm32_timer_init(Object *obj) -{ - LM32TimerState *s = LM32_TIMER(obj); - SysBusDevice *dev = SYS_BUS_DEVICE(obj); - - sysbus_init_irq(dev, &s->irq); - - memory_region_init_io(&s->iomem, obj, &timer_ops, s, - "timer", R_MAX * 4); - sysbus_init_mmio(dev, &s->iomem); -} - -static void lm32_timer_realize(DeviceState *dev, Error **errp) -{ - LM32TimerState *s = LM32_TIMER(dev); - - s->ptimer = ptimer_init(timer_hit, s, PTIMER_POLICY_DEFAULT); - - ptimer_transaction_begin(s->ptimer); - ptimer_set_freq(s->ptimer, s->freq_hz); - ptimer_transaction_commit(s->ptimer); -} - -static const VMStateDescription vmstate_lm32_timer = { - .name = "lm32-timer", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_PTIMER(ptimer, LM32TimerState), - VMSTATE_UINT32(freq_hz, LM32TimerState), - VMSTATE_UINT32_ARRAY(regs, LM32TimerState, R_MAX), - VMSTATE_END_OF_LIST() - } -}; - -static Property lm32_timer_properties[] = { - DEFINE_PROP_UINT32("frequency", LM32TimerState, freq_hz, DEFAULT_FREQUENCY), - DEFINE_PROP_END_OF_LIST(), -}; - -static void lm32_timer_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = lm32_timer_realize; - dc->reset = timer_reset; - dc->vmsd = &vmstate_lm32_timer; - device_class_set_props(dc, lm32_timer_properties); -} - -static const TypeInfo lm32_timer_info = { - .name = TYPE_LM32_TIMER, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(LM32TimerState), - .instance_init = lm32_timer_init, - .class_init = lm32_timer_class_init, -}; - -static void lm32_timer_register_types(void) -{ - type_register_static(&lm32_timer_info); -} - -type_init(lm32_timer_register_types) diff --git a/hw/timer/meson.build b/hw/timer/meson.build index 598d058506..1aa3cd2284 100644 --- a/hw/timer/meson.build +++ b/hw/timer/meson.build @@ -19,15 +19,12 @@ softmmu_ss.add(when: 'CONFIG_HPET', if_true: files('hpet.c')) softmmu_ss.add(when: 'CONFIG_I8254', if_true: files('i8254_common.c', 'i8254.c')) softmmu_ss.add(when: 'CONFIG_IMX', if_true: files('imx_epit.c')) softmmu_ss.add(when: 'CONFIG_IMX', if_true: files('imx_gpt.c')) -softmmu_ss.add(when: 'CONFIG_LM32_DEVICES', if_true: files('lm32_timer.c')) -softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-sysctl.c')) softmmu_ss.add(when: 'CONFIG_MIPS_CPS', if_true: files('mips_gictimer.c')) softmmu_ss.add(when: 'CONFIG_MSF2', if_true: files('mss-timer.c')) softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_timer.c')) softmmu_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_timer.c')) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_gptimer.c')) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_synctimer.c')) -softmmu_ss.add(when: 'CONFIG_PUV3', if_true: files('puv3_ost.c')) softmmu_ss.add(when: 'CONFIG_PXA2XX', if_true: files('pxa2xx_timer.c')) softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_systmr.c')) softmmu_ss.add(when: 'CONFIG_SH_TIMER', if_true: files('sh_timer.c')) @@ -36,5 +33,6 @@ softmmu_ss.add(when: 'CONFIG_SSE_COUNTER', if_true: files('sse-counter.c')) softmmu_ss.add(when: 'CONFIG_SSE_TIMER', if_true: files('sse-timer.c')) softmmu_ss.add(when: 'CONFIG_STM32F2XX_TIMER', if_true: files('stm32f2xx_timer.c')) softmmu_ss.add(when: 'CONFIG_XILINX', if_true: files('xilinx_timer.c')) +specific_ss.add(when: 'CONFIG_IBEX', if_true: files('ibex_timer.c')) specific_ss.add(when: 'CONFIG_AVR_TIMER16', if_true: files('avr_timer16.c')) diff --git a/hw/timer/milkymist-sysctl.c b/hw/timer/milkymist-sysctl.c deleted file mode 100644 index 9ecea63861..0000000000 --- a/hw/timer/milkymist-sysctl.c +++ /dev/null @@ -1,361 +0,0 @@ -/* - * QEMU model of the Milkymist System Controller. - * - * Copyright (c) 2010-2012 Michael Walle - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://milkymist.walle.cc/socdoc/sysctl.pdf - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "migration/vmstate.h" -#include "trace.h" -#include "qemu/timer.h" -#include "sysemu/runstate.h" -#include "hw/ptimer.h" -#include "hw/qdev-properties.h" -#include "qemu/error-report.h" -#include "qemu/module.h" -#include "qom/object.h" - -enum { - CTRL_ENABLE = (1<<0), - CTRL_AUTORESTART = (1<<1), -}; - -enum { - ICAP_READY = (1<<0), -}; - -enum { - R_GPIO_IN = 0, - R_GPIO_OUT, - R_GPIO_INTEN, - R_TIMER0_CONTROL = 4, - R_TIMER0_COMPARE, - R_TIMER0_COUNTER, - R_TIMER1_CONTROL = 8, - R_TIMER1_COMPARE, - R_TIMER1_COUNTER, - R_ICAP = 16, - R_DBG_SCRATCHPAD = 20, - R_DBG_WRITE_LOCK, - R_CLK_FREQUENCY = 29, - R_CAPABILITIES, - R_SYSTEM_ID, - R_MAX -}; - -#define TYPE_MILKYMIST_SYSCTL "milkymist-sysctl" -OBJECT_DECLARE_SIMPLE_TYPE(MilkymistSysctlState, MILKYMIST_SYSCTL) - -struct MilkymistSysctlState { - SysBusDevice parent_obj; - - MemoryRegion regs_region; - - ptimer_state *ptimer0; - ptimer_state *ptimer1; - - uint32_t freq_hz; - uint32_t capabilities; - uint32_t systemid; - uint32_t strappings; - - uint32_t regs[R_MAX]; - - qemu_irq gpio_irq; - qemu_irq timer0_irq; - qemu_irq timer1_irq; -}; - -static void sysctl_icap_write(MilkymistSysctlState *s, uint32_t value) -{ - trace_milkymist_sysctl_icap_write(value); - switch (value & 0xffff) { - case 0x000e: - qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); - break; - } -} - -static uint64_t sysctl_read(void *opaque, hwaddr addr, - unsigned size) -{ - MilkymistSysctlState *s = opaque; - uint32_t r = 0; - - addr >>= 2; - switch (addr) { - case R_TIMER0_COUNTER: - r = (uint32_t)ptimer_get_count(s->ptimer0); - /* milkymist timer counts up */ - r = s->regs[R_TIMER0_COMPARE] - r; - break; - case R_TIMER1_COUNTER: - r = (uint32_t)ptimer_get_count(s->ptimer1); - /* milkymist timer counts up */ - r = s->regs[R_TIMER1_COMPARE] - r; - break; - case R_GPIO_IN: - case R_GPIO_OUT: - case R_GPIO_INTEN: - case R_TIMER0_CONTROL: - case R_TIMER0_COMPARE: - case R_TIMER1_CONTROL: - case R_TIMER1_COMPARE: - case R_ICAP: - case R_DBG_SCRATCHPAD: - case R_DBG_WRITE_LOCK: - case R_CLK_FREQUENCY: - case R_CAPABILITIES: - case R_SYSTEM_ID: - r = s->regs[addr]; - break; - - default: - error_report("milkymist_sysctl: read access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } - - trace_milkymist_sysctl_memory_read(addr << 2, r); - - return r; -} - -static void sysctl_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - MilkymistSysctlState *s = opaque; - - trace_milkymist_sysctl_memory_write(addr, value); - - addr >>= 2; - switch (addr) { - case R_GPIO_OUT: - case R_GPIO_INTEN: - case R_TIMER0_COUNTER: - case R_TIMER1_COUNTER: - case R_DBG_SCRATCHPAD: - s->regs[addr] = value; - break; - case R_TIMER0_COMPARE: - ptimer_transaction_begin(s->ptimer0); - ptimer_set_limit(s->ptimer0, value, 0); - s->regs[addr] = value; - ptimer_transaction_commit(s->ptimer0); - break; - case R_TIMER1_COMPARE: - ptimer_transaction_begin(s->ptimer1); - ptimer_set_limit(s->ptimer1, value, 0); - s->regs[addr] = value; - ptimer_transaction_commit(s->ptimer1); - break; - case R_TIMER0_CONTROL: - ptimer_transaction_begin(s->ptimer0); - s->regs[addr] = value; - if (s->regs[R_TIMER0_CONTROL] & CTRL_ENABLE) { - trace_milkymist_sysctl_start_timer0(); - ptimer_set_count(s->ptimer0, - s->regs[R_TIMER0_COMPARE] - s->regs[R_TIMER0_COUNTER]); - ptimer_run(s->ptimer0, 0); - } else { - trace_milkymist_sysctl_stop_timer0(); - ptimer_stop(s->ptimer0); - } - ptimer_transaction_commit(s->ptimer0); - break; - case R_TIMER1_CONTROL: - ptimer_transaction_begin(s->ptimer1); - s->regs[addr] = value; - if (s->regs[R_TIMER1_CONTROL] & CTRL_ENABLE) { - trace_milkymist_sysctl_start_timer1(); - ptimer_set_count(s->ptimer1, - s->regs[R_TIMER1_COMPARE] - s->regs[R_TIMER1_COUNTER]); - ptimer_run(s->ptimer1, 0); - } else { - trace_milkymist_sysctl_stop_timer1(); - ptimer_stop(s->ptimer1); - } - ptimer_transaction_commit(s->ptimer1); - break; - case R_ICAP: - sysctl_icap_write(s, value); - break; - case R_DBG_WRITE_LOCK: - s->regs[addr] = 1; - break; - case R_SYSTEM_ID: - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); - break; - - case R_GPIO_IN: - case R_CLK_FREQUENCY: - case R_CAPABILITIES: - error_report("milkymist_sysctl: write to read-only register 0x" - TARGET_FMT_plx, addr << 2); - break; - - default: - error_report("milkymist_sysctl: write access to unknown register 0x" - TARGET_FMT_plx, addr << 2); - break; - } -} - -static const MemoryRegionOps sysctl_mmio_ops = { - .read = sysctl_read, - .write = sysctl_write, - .valid = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void timer0_hit(void *opaque) -{ - MilkymistSysctlState *s = opaque; - - if (!(s->regs[R_TIMER0_CONTROL] & CTRL_AUTORESTART)) { - s->regs[R_TIMER0_CONTROL] &= ~CTRL_ENABLE; - trace_milkymist_sysctl_stop_timer0(); - ptimer_stop(s->ptimer0); - } - - trace_milkymist_sysctl_pulse_irq_timer0(); - qemu_irq_pulse(s->timer0_irq); -} - -static void timer1_hit(void *opaque) -{ - MilkymistSysctlState *s = opaque; - - if (!(s->regs[R_TIMER1_CONTROL] & CTRL_AUTORESTART)) { - s->regs[R_TIMER1_CONTROL] &= ~CTRL_ENABLE; - trace_milkymist_sysctl_stop_timer1(); - ptimer_stop(s->ptimer1); - } - - trace_milkymist_sysctl_pulse_irq_timer1(); - qemu_irq_pulse(s->timer1_irq); -} - -static void milkymist_sysctl_reset(DeviceState *d) -{ - MilkymistSysctlState *s = MILKYMIST_SYSCTL(d); - int i; - - for (i = 0; i < R_MAX; i++) { - s->regs[i] = 0; - } - - ptimer_transaction_begin(s->ptimer0); - ptimer_stop(s->ptimer0); - ptimer_transaction_commit(s->ptimer0); - ptimer_transaction_begin(s->ptimer1); - ptimer_stop(s->ptimer1); - ptimer_transaction_commit(s->ptimer1); - - /* defaults */ - s->regs[R_ICAP] = ICAP_READY; - s->regs[R_SYSTEM_ID] = s->systemid; - s->regs[R_CLK_FREQUENCY] = s->freq_hz; - s->regs[R_CAPABILITIES] = s->capabilities; - s->regs[R_GPIO_IN] = s->strappings; -} - -static void milkymist_sysctl_init(Object *obj) -{ - MilkymistSysctlState *s = MILKYMIST_SYSCTL(obj); - SysBusDevice *dev = SYS_BUS_DEVICE(obj); - - sysbus_init_irq(dev, &s->gpio_irq); - sysbus_init_irq(dev, &s->timer0_irq); - sysbus_init_irq(dev, &s->timer1_irq); - - memory_region_init_io(&s->regs_region, obj, &sysctl_mmio_ops, s, - "milkymist-sysctl", R_MAX * 4); - sysbus_init_mmio(dev, &s->regs_region); -} - -static void milkymist_sysctl_realize(DeviceState *dev, Error **errp) -{ - MilkymistSysctlState *s = MILKYMIST_SYSCTL(dev); - - s->ptimer0 = ptimer_init(timer0_hit, s, PTIMER_POLICY_DEFAULT); - s->ptimer1 = ptimer_init(timer1_hit, s, PTIMER_POLICY_DEFAULT); - - ptimer_transaction_begin(s->ptimer0); - ptimer_set_freq(s->ptimer0, s->freq_hz); - ptimer_transaction_commit(s->ptimer0); - ptimer_transaction_begin(s->ptimer1); - ptimer_set_freq(s->ptimer1, s->freq_hz); - ptimer_transaction_commit(s->ptimer1); -} - -static const VMStateDescription vmstate_milkymist_sysctl = { - .name = "milkymist-sysctl", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, MilkymistSysctlState, R_MAX), - VMSTATE_PTIMER(ptimer0, MilkymistSysctlState), - VMSTATE_PTIMER(ptimer1, MilkymistSysctlState), - VMSTATE_END_OF_LIST() - } -}; - -static Property milkymist_sysctl_properties[] = { - DEFINE_PROP_UINT32("frequency", MilkymistSysctlState, - freq_hz, 80000000), - DEFINE_PROP_UINT32("capabilities", MilkymistSysctlState, - capabilities, 0x00000000), - DEFINE_PROP_UINT32("systemid", MilkymistSysctlState, - systemid, 0x10014d31), - DEFINE_PROP_UINT32("gpio_strappings", MilkymistSysctlState, - strappings, 0x00000001), - DEFINE_PROP_END_OF_LIST(), -}; - -static void milkymist_sysctl_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = milkymist_sysctl_realize; - dc->reset = milkymist_sysctl_reset; - dc->vmsd = &vmstate_milkymist_sysctl; - device_class_set_props(dc, milkymist_sysctl_properties); -} - -static const TypeInfo milkymist_sysctl_info = { - .name = TYPE_MILKYMIST_SYSCTL, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(MilkymistSysctlState), - .instance_init = milkymist_sysctl_init, - .class_init = milkymist_sysctl_class_init, -}; - -static void milkymist_sysctl_register_types(void) -{ - type_register_static(&milkymist_sysctl_info); -} - -type_init(milkymist_sysctl_register_types) diff --git a/hw/timer/mips_gictimer.c b/hw/timer/mips_gictimer.c index bc44cd934e..2b0696d4ac 100644 --- a/hw/timer/mips_gictimer.c +++ b/hw/timer/mips_gictimer.c @@ -7,7 +7,6 @@ */ #include "qemu/osdep.h" -#include "hw/sysbus.h" #include "qemu/timer.h" #include "hw/timer/mips_gictimer.h" diff --git a/hw/timer/puv3_ost.c b/hw/timer/puv3_ost.c deleted file mode 100644 index d5bf26b56b..0000000000 --- a/hw/timer/puv3_ost.c +++ /dev/null @@ -1,166 +0,0 @@ -/* - * OSTimer device simulation in PKUnity SoC - * - * Copyright (C) 2010-2012 Guan Xuetao - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation, or any later version. - * See the COPYING file in the top-level directory. - */ - -#include "qemu/osdep.h" -#include "hw/sysbus.h" -#include "hw/irq.h" -#include "hw/ptimer.h" -#include "qemu/module.h" -#include "qemu/log.h" -#include "qom/object.h" - -#undef DEBUG_PUV3 -#include "hw/unicore32/puv3.h" - -#define TYPE_PUV3_OST "puv3_ost" -OBJECT_DECLARE_SIMPLE_TYPE(PUV3OSTState, PUV3_OST) - -/* puv3 ostimer implementation. */ -struct PUV3OSTState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - qemu_irq irq; - ptimer_state *ptimer; - - uint32_t reg_OSMR0; - uint32_t reg_OSCR; - uint32_t reg_OSSR; - uint32_t reg_OIER; -}; - -static uint64_t puv3_ost_read(void *opaque, hwaddr offset, - unsigned size) -{ - PUV3OSTState *s = opaque; - uint32_t ret = 0; - - switch (offset) { - case 0x10: /* Counter Register */ - ret = s->reg_OSMR0 - (uint32_t)ptimer_get_count(s->ptimer); - break; - case 0x14: /* Status Register */ - ret = s->reg_OSSR; - break; - case 0x1c: /* Interrupt Enable Register */ - ret = s->reg_OIER; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad read offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } - DPRINTF("offset 0x%x, value 0x%x\n", offset, ret); - return ret; -} - -static void puv3_ost_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - PUV3OSTState *s = opaque; - - DPRINTF("offset 0x%x, value 0x%x\n", offset, value); - switch (offset) { - case 0x00: /* Match Register 0 */ - ptimer_transaction_begin(s->ptimer); - s->reg_OSMR0 = value; - if (s->reg_OSMR0 > s->reg_OSCR) { - ptimer_set_count(s->ptimer, s->reg_OSMR0 - s->reg_OSCR); - } else { - ptimer_set_count(s->ptimer, s->reg_OSMR0 + - (0xffffffff - s->reg_OSCR)); - } - ptimer_run(s->ptimer, 2); - ptimer_transaction_commit(s->ptimer); - break; - case 0x14: /* Status Register */ - assert(value == 0); - if (s->reg_OSSR) { - s->reg_OSSR = value; - qemu_irq_lower(s->irq); - } - break; - case 0x1c: /* Interrupt Enable Register */ - s->reg_OIER = value; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Bad write offset 0x%"HWADDR_PRIx"\n", - __func__, offset); - } -} - -static const MemoryRegionOps puv3_ost_ops = { - .read = puv3_ost_read, - .write = puv3_ost_write, - .impl = { - .min_access_size = 4, - .max_access_size = 4, - }, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static void puv3_ost_tick(void *opaque) -{ - PUV3OSTState *s = opaque; - - DPRINTF("ost hit when ptimer counter from 0x%x to 0x%x!\n", - s->reg_OSCR, s->reg_OSMR0); - - s->reg_OSCR = s->reg_OSMR0; - if (s->reg_OIER) { - s->reg_OSSR = 1; - qemu_irq_raise(s->irq); - } -} - -static void puv3_ost_realize(DeviceState *dev, Error **errp) -{ - PUV3OSTState *s = PUV3_OST(dev); - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - - s->reg_OIER = 0; - s->reg_OSSR = 0; - s->reg_OSMR0 = 0; - s->reg_OSCR = 0; - - sysbus_init_irq(sbd, &s->irq); - - s->ptimer = ptimer_init(puv3_ost_tick, s, PTIMER_POLICY_DEFAULT); - ptimer_transaction_begin(s->ptimer); - ptimer_set_freq(s->ptimer, 50 * 1000 * 1000); - ptimer_transaction_commit(s->ptimer); - - memory_region_init_io(&s->iomem, OBJECT(s), &puv3_ost_ops, s, "puv3_ost", - PUV3_REGS_OFFSET); - sysbus_init_mmio(sbd, &s->iomem); -} - -static void puv3_ost_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->realize = puv3_ost_realize; -} - -static const TypeInfo puv3_ost_info = { - .name = TYPE_PUV3_OST, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(PUV3OSTState), - .class_init = puv3_ost_class_init, -}; - -static void puv3_ost_register_type(void) -{ - type_register_static(&puv3_ost_info); -} - -type_init(puv3_ost_register_type) diff --git a/hw/timer/sse-counter.c b/hw/timer/sse-counter.c index 0384051f15..16c0e8ad15 100644 --- a/hw/timer/sse-counter.c +++ b/hw/timer/sse-counter.c @@ -33,7 +33,6 @@ #include "trace.h" #include "hw/timer/sse-counter.h" #include "hw/sysbus.h" -#include "hw/irq.h" #include "hw/registerfields.h" #include "hw/clock.h" #include "hw/qdev-clock.h" diff --git a/hw/timer/trace-events b/hw/timer/trace-events index f8b9db25c2..5234c0ea9e 100644 --- a/hw/timer/trace-events +++ b/hw/timer/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # slavio_timer.c slavio_timer_get_out(uint64_t limit, uint32_t counthigh, uint32_t count) "limit 0x%"PRIx64" count 0x%x0x%08x" @@ -24,23 +24,6 @@ grlib_gptimer_hit(int id) "timer:%d HIT" grlib_gptimer_readl(int id, uint64_t addr, uint32_t val) "timer:%d addr 0x%"PRIx64" 0x%x" grlib_gptimer_writel(int id, uint64_t addr, uint32_t val) "timer:%d addr 0x%"PRIx64" 0x%x" -# lm32_timer.c -lm32_timer_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -lm32_timer_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -lm32_timer_hit(void) "timer hit" -lm32_timer_irq_state(int level) "irq state %d" - -# milkymist-sysctl.c -milkymist_sysctl_memory_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_sysctl_memory_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" -milkymist_sysctl_icap_write(uint32_t value) "value 0x%08x" -milkymist_sysctl_start_timer0(void) "Start timer0" -milkymist_sysctl_stop_timer0(void) "Stop timer0" -milkymist_sysctl_start_timer1(void) "Start timer1" -milkymist_sysctl_stop_timer1(void) "Stop timer1" -milkymist_sysctl_pulse_irq_timer0(void) "Pulse IRQ Timer0" -milkymist_sysctl_pulse_irq_timer1(void) "Pulse IRQ Timer1" - # aspeed_timer.c aspeed_timer_ctrl_enable(uint8_t i, bool enable) "Timer %" PRIu8 ": %d" aspeed_timer_ctrl_external_clock(uint8_t i, bool enable) "Timer %" PRIu8 ": %d" diff --git a/hw/tpm/tpm_crb.c b/hw/tpm/tpm_crb.c index aa9c00aad3..58ebd1469c 100644 --- a/hw/tpm/tpm_crb.c +++ b/hw/tpm/tpm_crb.c @@ -18,7 +18,6 @@ #include "qemu/module.h" #include "qapi/error.h" -#include "exec/address-spaces.h" #include "hw/qdev-properties.h" #include "hw/pci/pci_ids.h" #include "hw/acpi/tpm.h" diff --git a/hw/tpm/tpm_ppi.c b/hw/tpm/tpm_ppi.c index 72d7a3d926..362edcc5c9 100644 --- a/hw/tpm/tpm_ppi.c +++ b/hw/tpm/tpm_ppi.c @@ -23,7 +23,7 @@ void tpm_ppi_reset(TPMPPI *tpmppi) { - if (tpmppi->buf[0x15a /* movv, docs/specs/tpm.txt */] & 0x1) { + if (tpmppi->buf[0x15a /* movv, docs/specs/tpm.rst */] & 0x1) { GuestPhysBlockList guest_phys_blocks; GuestPhysBlock *block; diff --git a/hw/tpm/trace-events b/hw/tpm/trace-events index 6005ecb5da..f17110458e 100644 --- a/hw/tpm/trace-events +++ b/hw/tpm/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # tpm_crb.c tpm_crb_mmio_read(uint64_t addr, unsigned size, uint32_t val) "CRB read 0x%016" PRIx64 " len:%u val: 0x%" PRIx32 diff --git a/hw/tricore/Kconfig b/hw/tricore/Kconfig index 506e6183c1..33c1e852c3 100644 --- a/hw/tricore/Kconfig +++ b/hw/tricore/Kconfig @@ -1,9 +1,8 @@ -config TRICORE +config TRICORE_TESTBOARD bool config TRIBOARD bool - select TRICORE select TC27X_SOC config TC27X_SOC diff --git a/hw/tricore/meson.build b/hw/tricore/meson.build index 77ff6fd137..7e3585daf8 100644 --- a/hw/tricore/meson.build +++ b/hw/tricore/meson.build @@ -1,5 +1,6 @@ tricore_ss = ss.source_set() -tricore_ss.add(when: 'CONFIG_TRICORE', if_true: files('tricore_testboard.c')) +tricore_ss.add(when: 'CONFIG_TRICORE_TESTBOARD', if_true: files('tricore_testboard.c')) +tricore_ss.add(when: 'CONFIG_TRICORE_TESTBOARD', if_true: files('tricore_testdevice.c')) tricore_ss.add(when: 'CONFIG_TRIBOARD', if_true: files('triboard.c')) tricore_ss.add(when: 'CONFIG_TC27X_SOC', if_true: files('tc27x_soc.c')) diff --git a/hw/tricore/tc27x_soc.c b/hw/tricore/tc27x_soc.c index 8af079e6b2..ecd92717b5 100644 --- a/hw/tricore/tc27x_soc.c +++ b/hw/tricore/tc27x_soc.c @@ -21,13 +21,9 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/sysbus.h" -#include "hw/boards.h" #include "hw/loader.h" #include "qemu/units.h" #include "hw/misc/unimp.h" -#include "exec/address-spaces.h" -#include "qemu/log.h" -#include "cpu.h" #include "hw/tricore/tc27x_soc.h" #include "hw/tricore/triboard.h" diff --git a/hw/tricore/triboard.c b/hw/tricore/triboard.c index 16e2fd7e27..4dba0259cd 100644 --- a/hw/tricore/triboard.c +++ b/hw/tricore/triboard.c @@ -22,11 +22,8 @@ #include "qemu/units.h" #include "qapi/error.h" #include "hw/qdev-properties.h" -#include "cpu.h" #include "net/net.h" -#include "hw/boards.h" #include "hw/loader.h" -#include "exec/address-spaces.h" #include "elf.h" #include "hw/tricore/tricore.h" #include "qemu/error-report.h" diff --git a/hw/tricore/tricore_testboard.c b/hw/tricore/tricore_testboard.c index 12ea1490fd..b6810e3be0 100644 --- a/hw/tricore/tricore_testboard.c +++ b/hw/tricore/tricore_testboard.c @@ -25,9 +25,9 @@ #include "net/net.h" #include "hw/boards.h" #include "hw/loader.h" -#include "exec/address-spaces.h" #include "elf.h" #include "hw/tricore/tricore.h" +#include "hw/tricore/tricore_testdevice.h" #include "qemu/error-report.h" @@ -57,6 +57,7 @@ static void tricore_testboard_init(MachineState *machine, int board_id) { TriCoreCPU *cpu; CPUTriCoreState *env; + TriCoreTestDeviceState *test_dev; MemoryRegion *sysmem = get_system_memory(); MemoryRegion *ext_cram = g_new(MemoryRegion, 1); @@ -88,6 +89,12 @@ static void tricore_testboard_init(MachineState *machine, int board_id) memory_region_add_subregion(sysmem, 0xf0050000, pcp_data); memory_region_add_subregion(sysmem, 0xf0060000, pcp_text); + test_dev = g_new(TriCoreTestDeviceState, 1); + object_initialize(test_dev, sizeof(TriCoreTestDeviceState), + TYPE_TRICORE_TESTDEVICE); + memory_region_add_subregion(sysmem, 0xf0000000, &test_dev->iomem); + + tricoretb_binfo.ram_size = machine->ram_size; tricoretb_binfo.kernel_filename = machine->kernel_filename; diff --git a/hw/tricore/tricore_testdevice.c b/hw/tricore/tricore_testdevice.c new file mode 100644 index 0000000000..a1563aa568 --- /dev/null +++ b/hw/tricore/tricore_testdevice.c @@ -0,0 +1,82 @@ +/* + * Copyright (c) 2018-2021 Bastian Koppelmann Paderborn University + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see . + */ + +#include "qemu/osdep.h" +#include "hw/sysbus.h" +#include "hw/qdev-properties.h" +#include "hw/tricore/tricore_testdevice.h" + +static void tricore_testdevice_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + exit(value); +} + +static uint64_t tricore_testdevice_read(void *opaque, hwaddr offset, + unsigned size) +{ + return 0xdeadbeef; +} + +static void tricore_testdevice_reset(DeviceState *dev) +{ +} + +static const MemoryRegionOps tricore_testdevice_ops = { + .read = tricore_testdevice_read, + .write = tricore_testdevice_write, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static void tricore_testdevice_init(Object *obj) +{ + TriCoreTestDeviceState *s = TRICORE_TESTDEVICE(obj); + /* map memory */ + memory_region_init_io(&s->iomem, OBJECT(s), &tricore_testdevice_ops, s, + "tricore_testdevice", 0x4); +} + +static Property tricore_testdevice_properties[] = { + DEFINE_PROP_END_OF_LIST() +}; + +static void tricore_testdevice_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + device_class_set_props(dc, tricore_testdevice_properties); + dc->reset = tricore_testdevice_reset; +} + +static const TypeInfo tricore_testdevice_info = { + .name = TYPE_TRICORE_TESTDEVICE, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(TriCoreTestDeviceState), + .instance_init = tricore_testdevice_init, + .class_init = tricore_testdevice_class_init, +}; + +static void tricore_testdevice_register_types(void) +{ + type_register_static(&tricore_testdevice_info); +} + +type_init(tricore_testdevice_register_types) diff --git a/hw/unicore32/Kconfig b/hw/unicore32/Kconfig deleted file mode 100644 index 4443a29dd2..0000000000 --- a/hw/unicore32/Kconfig +++ /dev/null @@ -1,5 +0,0 @@ -config PUV3 - bool - select ISA_BUS - select PCKBD - select PTIMER diff --git a/hw/unicore32/meson.build b/hw/unicore32/meson.build deleted file mode 100644 index fc26d6bcab..0000000000 --- a/hw/unicore32/meson.build +++ /dev/null @@ -1,5 +0,0 @@ -unicore32_ss = ss.source_set() -# PKUnity-v3 SoC and board information -unicore32_ss.add(when: 'CONFIG_PUV3', if_true: files('puv3.c')) - -hw_arch += {'unicore32': unicore32_ss} diff --git a/hw/unicore32/puv3.c b/hw/unicore32/puv3.c deleted file mode 100644 index eacacb4249..0000000000 --- a/hw/unicore32/puv3.c +++ /dev/null @@ -1,145 +0,0 @@ -/* - * Generic PKUnity SoC machine and board descriptor - * - * Copyright (C) 2010-2012 Guan Xuetao - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation, or any later version. - * See the COPYING file in the top-level directory. - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "cpu.h" -#include "ui/console.h" -#include "hw/boards.h" -#include "hw/loader.h" -#include "sysemu/qtest.h" -#include "hw/unicore32/puv3.h" -#include "hw/input/i8042.h" -#include "hw/irq.h" - -#define KERNEL_LOAD_ADDR 0x03000000 -#define KERNEL_MAX_SIZE 0x00800000 /* Just a guess */ - -/* PKUnity System bus (AHB): 0xc0000000 - 0xedffffff (640MB) */ -#define PUV3_DMA_BASE (0xc0200000) /* AHB-4 */ - -/* PKUnity Peripheral bus (APB): 0xee000000 - 0xefffffff (128MB) */ -#define PUV3_GPIO_BASE (0xee500000) /* APB-5 */ -#define PUV3_INTC_BASE (0xee600000) /* APB-6 */ -#define PUV3_OST_BASE (0xee800000) /* APB-8 */ -#define PUV3_PM_BASE (0xeea00000) /* APB-10 */ -#define PUV3_PS2_BASE (0xeeb00000) /* APB-11 */ - -static void puv3_intc_cpu_handler(void *opaque, int irq, int level) -{ - UniCore32CPU *cpu = opaque; - CPUState *cs = CPU(cpu); - - assert(irq == 0); - if (level) { - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } else { - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } -} - -static void puv3_soc_init(CPUUniCore32State *env) -{ - qemu_irq cpu_intc, irqs[PUV3_IRQS_NR]; - DeviceState *dev; - MemoryRegion *i8042 = g_new(MemoryRegion, 1); - int i; - - /* Initialize interrupt controller */ - cpu_intc = qemu_allocate_irq(puv3_intc_cpu_handler, - env_archcpu(env), 0); - dev = sysbus_create_simple("puv3_intc", PUV3_INTC_BASE, cpu_intc); - for (i = 0; i < PUV3_IRQS_NR; i++) { - irqs[i] = qdev_get_gpio_in(dev, i); - } - - /* Initialize minimal necessary devices for kernel booting */ - sysbus_create_simple("puv3_pm", PUV3_PM_BASE, NULL); - sysbus_create_simple("puv3_dma", PUV3_DMA_BASE, NULL); - sysbus_create_simple("puv3_ost", PUV3_OST_BASE, irqs[PUV3_IRQS_OST0]); - sysbus_create_varargs("puv3_gpio", PUV3_GPIO_BASE, - irqs[PUV3_IRQS_GPIOLOW0], irqs[PUV3_IRQS_GPIOLOW1], - irqs[PUV3_IRQS_GPIOLOW2], irqs[PUV3_IRQS_GPIOLOW3], - irqs[PUV3_IRQS_GPIOLOW4], irqs[PUV3_IRQS_GPIOLOW5], - irqs[PUV3_IRQS_GPIOLOW6], irqs[PUV3_IRQS_GPIOLOW7], - irqs[PUV3_IRQS_GPIOHIGH], NULL); - - /* Keyboard (i8042), mouse disabled for nographic */ - i8042_mm_init(irqs[PUV3_IRQS_PS2_KBD], NULL, i8042, PUV3_REGS_OFFSET, 4); - memory_region_add_subregion(get_system_memory(), PUV3_PS2_BASE, i8042); -} - -static void puv3_board_init(CPUUniCore32State *env, ram_addr_t ram_size) -{ - MemoryRegion *ram_memory = g_new(MemoryRegion, 1); - - /* SDRAM at address zero. */ - memory_region_init_ram(ram_memory, NULL, "puv3.ram", ram_size, - &error_fatal); - memory_region_add_subregion(get_system_memory(), 0, ram_memory); -} - -static const GraphicHwOps no_ops; - -static void puv3_load_kernel(const char *kernel_filename) -{ - int size; - - if (kernel_filename == NULL && qtest_enabled()) { - return; - } - if (kernel_filename == NULL) { - error_report("kernel parameter cannot be empty"); - exit(1); - } - - /* only zImage format supported */ - size = load_image_targphys(kernel_filename, KERNEL_LOAD_ADDR, - KERNEL_MAX_SIZE); - if (size < 0) { - error_report("Load kernel error: '%s'", kernel_filename); - exit(1); - } - - /* cheat curses that we have a graphic console, only under ocd console */ - graphic_console_init(NULL, 0, &no_ops, NULL); -} - -static void puv3_init(MachineState *machine) -{ - ram_addr_t ram_size = machine->ram_size; - const char *kernel_filename = machine->kernel_filename; - const char *initrd_filename = machine->initrd_filename; - CPUUniCore32State *env; - UniCore32CPU *cpu; - - if (initrd_filename) { - error_report("Please use kernel built-in initramdisk"); - exit(1); - } - - cpu = UNICORE32_CPU(cpu_create(machine->cpu_type)); - env = &cpu->env; - - puv3_soc_init(env); - puv3_board_init(env, ram_size); - puv3_load_kernel(kernel_filename); -} - -static void puv3_machine_init(MachineClass *mc) -{ - mc->desc = "PKUnity Version-3 based on UniCore32"; - mc->init = puv3_init; - mc->is_default = true; - mc->default_cpu_type = UNICORE32_CPU_TYPE_NAME("UniCore-II"); -} - -DEFINE_MACHINE("puv3", puv3_machine_init) diff --git a/hw/usb/ccid-card-emulated.c b/hw/usb/ccid-card-emulated.c index 5c76bed77a..6c8c0355e0 100644 --- a/hw/usb/ccid-card-emulated.c +++ b/hw/usb/ccid-card-emulated.c @@ -612,6 +612,7 @@ static const TypeInfo emulated_card_info = { .instance_size = sizeof(EmulatedState), .class_init = emulated_class_initfn, }; +module_obj(TYPE_EMULATED_CCID); static void ccid_card_emulated_register_types(void) { diff --git a/hw/usb/ccid-card-passthru.c b/hw/usb/ccid-card-passthru.c index c1a90fcc7a..fa3040fb71 100644 --- a/hw/usb/ccid-card-passthru.c +++ b/hw/usb/ccid-card-passthru.c @@ -374,7 +374,7 @@ static void passthru_realize(CCIDCardState *base, Error **errp) card->atr_length = sizeof(DEFAULT_ATR); } -static VMStateDescription passthru_vmstate = { +static const VMStateDescription passthru_vmstate = { .name = "ccid-card-passthru", .version_id = 1, .minimum_version_id = 1, @@ -414,6 +414,7 @@ static const TypeInfo passthru_card_info = { .instance_size = sizeof(PassthruState), .class_init = passthru_class_initfn, }; +module_obj(TYPE_CCID_PASSTHRU); static void ccid_card_passthru_register_types(void) { diff --git a/hw/usb/chipidea.c b/hw/usb/chipidea.c index 3dcd22ccba..b1c85404d6 100644 --- a/hw/usb/chipidea.c +++ b/hw/usb/chipidea.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" #include "hw/usb/hcd-ehci.h" #include "hw/usb/chipidea.h" -#include "qemu/log.h" #include "qemu/module.h" enum { diff --git a/hw/usb/combined-packet.c b/hw/usb/combined-packet.c index 5d57e883dc..e56802f89a 100644 --- a/hw/usb/combined-packet.c +++ b/hw/usb/combined-packet.c @@ -171,7 +171,9 @@ void usb_ep_combine_input_packets(USBEndpoint *ep) if ((p->iov.size % ep->max_packet_size) != 0 || !p->short_not_ok || next == NULL || /* Work around for Linux usbfs bulk splitting + migration */ - (totalsize == (16 * KiB - 36) && p->int_req)) { + (totalsize == (16 * KiB - 36) && p->int_req) || + /* Next package may grow combined package over 1MiB */ + totalsize > 1 * MiB - ep->max_packet_size) { usb_device_handle_data(ep->dev, first); assert(first->status == USB_RET_ASYNC); if (first->combined) { diff --git a/hw/usb/desc-msos.c b/hw/usb/desc-msos.c index 3a5ad7c8d0..836e38c67e 100644 --- a/hw/usb/desc-msos.c +++ b/hw/usb/desc-msos.c @@ -181,7 +181,7 @@ static int usb_desc_msos_prop(const USBDesc *desc, uint8_t *dest) if (desc->msos->Label) { /* - * Given as example in the specs. Havn't figured yet where + * Given as example in the specs. Haven't figured yet where * this label shows up in the windows gui. */ length += usb_desc_msos_prop_str(dest+length, MSOS_REG_SZ, diff --git a/hw/usb/dev-hid.c b/hw/usb/dev-hid.c index fc39bab79f..1c7ae97c30 100644 --- a/hw/usb/dev-hid.c +++ b/hw/usb/dev-hid.c @@ -656,7 +656,7 @@ static void usb_hid_handle_data(USBDevice *dev, USBPacket *p) { USBHIDState *us = USB_HID(dev); HIDState *hs = &us->hid; - uint8_t buf[p->iov.size]; + g_autofree uint8_t *buf = g_malloc(p->iov.size); int len = 0; switch (p->pid) { diff --git a/hw/usb/dev-mtp.c b/hw/usb/dev-mtp.c index bbb8274344..c1d1694fd0 100644 --- a/hw/usb/dev-mtp.c +++ b/hw/usb/dev-mtp.c @@ -772,12 +772,9 @@ static void usb_mtp_add_str(MTPData *data, const char *str) static void usb_mtp_add_time(MTPData *data, time_t time) { - char buf[16]; - struct tm tm; - - gmtime_r(&time, &tm); - strftime(buf, sizeof(buf), "%Y%m%dT%H%M%S", &tm); - usb_mtp_add_str(data, buf); + g_autoptr(GDateTime) then = g_date_time_new_from_unix_utc(time); + g_autofree char *thenstr = g_date_time_format(then, "%Y%m%dT%H%M%S"); + usb_mtp_add_str(data, thenstr); } /* ----------------------------------------------------------------------- */ @@ -907,7 +904,8 @@ static MTPData *usb_mtp_get_object_handles(MTPState *s, MTPControl *c, MTPObject *o) { MTPData *d = usb_mtp_data_alloc(c); - uint32_t i = 0, handles[o->nchildren]; + uint32_t i = 0; + g_autofree uint32_t *handles = g_new(uint32_t, o->nchildren); MTPObject *iter; trace_usb_mtp_op_get_object_handles(s->dev.addr, o->handle, o->path); diff --git a/hw/usb/dev-smartcard-reader.c b/hw/usb/dev-smartcard-reader.c index bc3d94092a..f7043075be 100644 --- a/hw/usb/dev-smartcard-reader.c +++ b/hw/usb/dev-smartcard-reader.c @@ -1365,7 +1365,7 @@ static int ccid_pre_save(void *opaque) return 0; } -static VMStateDescription bulk_in_vmstate = { +static const VMStateDescription bulk_in_vmstate = { .name = "CCID BulkIn state", .version_id = 1, .minimum_version_id = 1, @@ -1377,7 +1377,7 @@ static VMStateDescription bulk_in_vmstate = { } }; -static VMStateDescription answer_vmstate = { +static const VMStateDescription answer_vmstate = { .name = "CCID Answer state", .version_id = 1, .minimum_version_id = 1, @@ -1388,7 +1388,7 @@ static VMStateDescription answer_vmstate = { } }; -static VMStateDescription usb_device_vmstate = { +static const VMStateDescription usb_device_vmstate = { .name = "usb_device", .version_id = 1, .minimum_version_id = 1, @@ -1400,7 +1400,7 @@ static VMStateDescription usb_device_vmstate = { } }; -static VMStateDescription ccid_vmstate = { +static const VMStateDescription ccid_vmstate = { .name = "usb-ccid", .version_id = 1, .minimum_version_id = 1, diff --git a/hw/usb/dev-storage-bot.c b/hw/usb/dev-storage-bot.c index 6aad026d11..68ebaca10c 100644 --- a/hw/usb/dev-storage-bot.c +++ b/hw/usb/dev-storage-bot.c @@ -32,6 +32,7 @@ static void usb_msd_bot_realize(USBDevice *dev, Error **errp) usb_desc_create_serial(dev); usb_desc_init(dev); + dev->flags |= (1 << USB_DEV_FLAG_IS_SCSI_STORAGE); if (d->hotplugged) { s->dev.auto_attach = 0; } diff --git a/hw/usb/dev-storage-classic.c b/hw/usb/dev-storage-classic.c index 00cb34b22f..3d017a4e67 100644 --- a/hw/usb/dev-storage-classic.c +++ b/hw/usb/dev-storage-classic.c @@ -64,6 +64,7 @@ static void usb_msd_storage_realize(USBDevice *dev, Error **errp) usb_desc_create_serial(dev); usb_desc_init(dev); + dev->flags |= (1 << USB_DEV_FLAG_IS_SCSI_STORAGE); scsi_bus_new(&s->bus, sizeof(s->bus), DEVICE(dev), &usb_msd_scsi_info_storage, NULL); scsi_dev = scsi_bus_legacy_add_drive(&s->bus, blk, 0, !!s->removable, diff --git a/hw/usb/dev-uas.c b/hw/usb/dev-uas.c index d2bd85d3f6..263056231c 100644 --- a/hw/usb/dev-uas.c +++ b/hw/usb/dev-uas.c @@ -926,6 +926,7 @@ static void usb_uas_realize(USBDevice *dev, Error **errp) QTAILQ_INIT(&uas->requests); uas->status_bh = qemu_bh_new(usb_uas_send_status_bh, uas); + dev->flags |= (1 << USB_DEV_FLAG_IS_SCSI_STORAGE); scsi_bus_new(&uas->bus, sizeof(uas->bus), DEVICE(dev), &usb_uas_scsi_info, NULL); } diff --git a/hw/usb/dev-wacom.c b/hw/usb/dev-wacom.c index b595048635..ed687bc9f1 100644 --- a/hw/usb/dev-wacom.c +++ b/hw/usb/dev-wacom.c @@ -301,7 +301,7 @@ static void usb_wacom_handle_control(USBDevice *dev, USBPacket *p, static void usb_wacom_handle_data(USBDevice *dev, USBPacket *p) { USBWacomState *s = (USBWacomState *) dev; - uint8_t buf[p->iov.size]; + g_autofree uint8_t *buf = g_malloc(p->iov.size); int len = 0; switch (p->pid) { diff --git a/hw/usb/hcd-dwc3.c b/hw/usb/hcd-dwc3.c index d547d0538d..279263489e 100644 --- a/hw/usb/hcd-dwc3.c +++ b/hw/usb/hcd-dwc3.c @@ -31,7 +31,6 @@ #include "hw/sysbus.h" #include "hw/register.h" #include "qemu/bitops.h" -#include "qemu/log.h" #include "qom/object.h" #include "migration/vmstate.h" #include "hw/qdev-properties.h" diff --git a/hw/usb/hcd-xhci-pci.c b/hw/usb/hcd-xhci-pci.c index 9421734d0f..e934b1a5b1 100644 --- a/hw/usb/hcd-xhci-pci.c +++ b/hw/usb/hcd-xhci-pci.c @@ -57,7 +57,7 @@ static void xhci_pci_intr_update(XHCIState *xhci, int n, bool enable) } } -static void xhci_pci_intr_raise(XHCIState *xhci, int n, bool level) +static bool xhci_pci_intr_raise(XHCIState *xhci, int n, bool level) { XHCIPciState *s = container_of(xhci, XHCIPciState, xhci); PCIDevice *pci_dev = PCI_DEVICE(s); @@ -67,15 +67,18 @@ static void xhci_pci_intr_raise(XHCIState *xhci, int n, bool level) msi_enabled(pci_dev))) { pci_set_irq(pci_dev, level); } - if (msix_enabled(pci_dev)) { + + if (msix_enabled(pci_dev) && level) { msix_notify(pci_dev, n); - return; + return true; } - if (msi_enabled(pci_dev)) { + if (msi_enabled(pci_dev) && level) { msi_notify(pci_dev, n); - return; + return true; } + + return false; } static void xhci_pci_reset(DeviceState *dev) diff --git a/hw/usb/hcd-xhci-sysbus.c b/hw/usb/hcd-xhci-sysbus.c index 42e2574c82..a14e438196 100644 --- a/hw/usb/hcd-xhci-sysbus.c +++ b/hw/usb/hcd-xhci-sysbus.c @@ -16,11 +16,13 @@ #include "hw/acpi/aml-build.h" #include "hw/irq.h" -static void xhci_sysbus_intr_raise(XHCIState *xhci, int n, bool level) +static bool xhci_sysbus_intr_raise(XHCIState *xhci, int n, bool level) { XHCISysbusState *s = container_of(xhci, XHCISysbusState, xhci); qemu_set_irq(s->irq[n], level); + + return false; } void xhci_sysbus_reset(DeviceState *dev) diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c index 46212b1e69..e01700039b 100644 --- a/hw/usb/hcd-xhci.c +++ b/hw/usb/hcd-xhci.c @@ -551,7 +551,9 @@ static void xhci_intr_update(XHCIState *xhci, int v) level = 1; } if (xhci->intr_raise) { - xhci->intr_raise(xhci, 0, level); + if (xhci->intr_raise(xhci, 0, level)) { + xhci->intr[0].iman &= ~IMAN_IP; + } } } if (xhci->intr_update) { @@ -579,7 +581,9 @@ static void xhci_intr_raise(XHCIState *xhci, int v) return; } if (xhci->intr_raise) { - xhci->intr_raise(xhci, v, true); + if (xhci->intr_raise(xhci, v, true)) { + xhci->intr[v].iman &= ~IMAN_IP; + } } } diff --git a/hw/usb/hcd-xhci.h b/hw/usb/hcd-xhci.h index 7bba361f3b..98f598382a 100644 --- a/hw/usb/hcd-xhci.h +++ b/hw/usb/hcd-xhci.h @@ -194,7 +194,7 @@ typedef struct XHCIState { uint32_t flags; uint32_t max_pstreams_mask; void (*intr_update)(XHCIState *s, int n, bool enable); - void (*intr_raise)(XHCIState *s, int n, bool level); + bool (*intr_raise)(XHCIState *s, int n, bool level); DeviceState *hostOpaque; /* Operational Registers */ diff --git a/hw/usb/host-libusb.c b/hw/usb/host-libusb.c index 2518306f52..00f6fbb29b 100644 --- a/hw/usb/host-libusb.c +++ b/hw/usb/host-libusb.c @@ -254,6 +254,29 @@ static void usb_host_del_fd(int fd, void *user_data) qemu_set_fd_handler(fd, NULL, NULL, NULL); } +#else + +static QEMUTimer *poll_timer; +static uint32_t request_count; + +static void usb_host_timer_kick(void) +{ + int64_t delay_ns; + + delay_ns = request_count + ? (NANOSECONDS_PER_SECOND / 100) /* 10 ms interval with active req */ + : (NANOSECONDS_PER_SECOND); /* 1 sec interval otherwise */ + timer_mod(poll_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + delay_ns); +} + +static void usb_host_timer(void *opaque) +{ + struct timeval tv = { 0, 0 }; + + libusb_handle_events_timeout(ctx, &tv); + usb_host_timer_kick(); +} + #endif /* !CONFIG_WIN32 */ static int usb_host_init(void) @@ -276,7 +299,8 @@ static int usb_host_init(void) libusb_set_debug(ctx, loglevel); #endif #ifdef CONFIG_WIN32 - /* FIXME: add support for Windows. */ + poll_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, usb_host_timer, NULL); + usb_host_timer_kick(); #else libusb_set_pollfd_notifiers(ctx, usb_host_add_fd, usb_host_del_fd, @@ -364,11 +388,18 @@ static USBHostRequest *usb_host_req_alloc(USBHostDevice *s, USBPacket *p, r->buffer = g_malloc(bufsize); } QTAILQ_INSERT_TAIL(&s->requests, r, next); +#ifdef CONFIG_WIN32 + request_count++; + usb_host_timer_kick(); +#endif return r; } static void usb_host_req_free(USBHostRequest *r) { +#ifdef CONFIG_WIN32 + request_count--; +#endif QTAILQ_REMOVE(&r->host->requests, r, next); libusb_free_transfer(r->xfer); g_free(r->buffer); @@ -770,6 +801,13 @@ static void usb_host_speed_compat(USBHostDevice *s) for (i = 0; i < conf->bNumInterfaces; i++) { for (a = 0; a < conf->interface[i].num_altsetting; a++) { intf = &conf->interface[i].altsetting[a]; + + if (intf->bInterfaceClass == LIBUSB_CLASS_MASS_STORAGE && + intf->bInterfaceSubClass == 6) { /* SCSI */ + udev->flags |= (1 << USB_DEV_FLAG_IS_SCSI_STORAGE); + break; + } + for (e = 0; e < intf->bNumEndpoints; e++) { endp = &intf->endpoint[e]; type = endp->bmAttributes & 0x3; @@ -1770,10 +1808,12 @@ static TypeInfo usb_host_dev_info = { .class_init = usb_host_class_initfn, .instance_init = usb_host_instance_init, }; +module_obj(TYPE_USB_HOST_DEVICE); static void usb_host_register_types(void) { type_register_static(&usb_host_dev_info); + monitor_register_hmp("usbhost", true, hmp_info_usbhost); } type_init(usb_host_register_types) @@ -1893,35 +1933,6 @@ static void usb_host_auto_check(void *unused) timer_mod(usb_auto_timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + 2000); } -/** - * Check whether USB host device has a USB mass storage SCSI interface - */ -bool usb_host_dev_is_scsi_storage(USBDevice *ud) -{ - USBHostDevice *uhd = USB_HOST_DEVICE(ud); - struct libusb_config_descriptor *conf; - const struct libusb_interface_descriptor *intf; - bool is_scsi_storage = false; - int i; - - if (!uhd || libusb_get_active_config_descriptor(uhd->dev, &conf) != 0) { - return false; - } - - for (i = 0; i < conf->bNumInterfaces; i++) { - intf = &conf->interface[i].altsetting[ud->altsetting[i]]; - if (intf->bInterfaceClass == LIBUSB_CLASS_MASS_STORAGE && - intf->bInterfaceSubClass == 6) { /* 6 means SCSI */ - is_scsi_storage = true; - break; - } - } - - libusb_free_config_descriptor(conf); - - return is_scsi_storage; -} - void hmp_info_usbhost(Monitor *mon, const QDict *qdict) { libusb_device **devs = NULL; diff --git a/hw/usb/imx-usb-phy.c b/hw/usb/imx-usb-phy.c index e705a03a1f..5d7a549e34 100644 --- a/hw/usb/imx-usb-phy.c +++ b/hw/usb/imx-usb-phy.c @@ -13,7 +13,6 @@ #include "qemu/osdep.h" #include "hw/usb/imx-usb-phy.h" #include "migration/vmstate.h" -#include "qemu/log.h" #include "qemu/module.h" static const VMStateDescription vmstate_imx_usbphy = { diff --git a/hw/usb/meson.build b/hw/usb/meson.build index fb7a74e73a..de853d780d 100644 --- a/hw/usb/meson.build +++ b/hw/usb/meson.build @@ -1,17 +1,14 @@ hw_usb_modules = {} # usb subsystem core -softmmu_ss.add(files( +softmmu_ss.add(when: 'CONFIG_USB', if_true: files( 'bus.c', 'combined-packet.c', 'core.c', - 'pcap.c', - 'libhw.c' -)) - -softmmu_ss.add(when: 'CONFIG_USB', if_true: files( 'desc.c', 'desc-msos.c', + 'libhw.c', + 'pcap.c', )) # usb host adapters @@ -52,7 +49,7 @@ softmmu_ss.add(when: ['CONFIG_POSIX', 'CONFIG_USB_STORAGE_MTP'], if_true: files( # smartcard softmmu_ss.add(when: 'CONFIG_USB_SMARTCARD', if_true: files('dev-smartcard-reader.c')) -if config_host.has_key('CONFIG_SMARTCARD') +if cacard.found() usbsmartcard_ss = ss.source_set() usbsmartcard_ss.add(when: 'CONFIG_USB_SMARTCARD', if_true: [cacard, files('ccid-card-emulated.c', 'ccid-card-passthru.c')]) @@ -67,7 +64,7 @@ if u2f.found() endif # usb redirect -if config_host.has_key('CONFIG_USB_REDIR') +if usbredir.found() usbredir_ss = ss.source_set() usbredir_ss.add(when: 'CONFIG_USB', if_true: [usbredir, files('redirect.c', 'quirks.c')]) @@ -75,10 +72,12 @@ if config_host.has_key('CONFIG_USB_REDIR') endif # usb pass-through -softmmu_ss.add(when: ['CONFIG_USB', 'CONFIG_USB_LIBUSB', libusb], - if_true: files('host-libusb.c'), - if_false: files('host-stub.c')) -softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('host-stub.c')) +if libusb.found() + usbhost_ss = ss.source_set() + usbhost_ss.add(when: ['CONFIG_USB', libusb], + if_true: files('host-libusb.c')) + hw_usb_modules += {'host': usbhost_ss} +endif softmmu_ss.add(when: ['CONFIG_USB', 'CONFIG_XEN', libusb], if_true: files('xen-usb.c')) diff --git a/hw/usb/quirks-ftdi-ids.h b/hw/usb/quirks-ftdi-ids.h index 57c12ef662..01aca55ca7 100644 --- a/hw/usb/quirks-ftdi-ids.h +++ b/hw/usb/quirks-ftdi-ids.h @@ -1221,12 +1221,6 @@ #define FTDI_SCIENCESCOPE_LS_LOGBOOK_PID 0xFF1C #define FTDI_SCIENCESCOPE_HS_LOGBOOK_PID 0xFF1D -/* - * Milkymist One JTAG/Serial - */ -#define QIHARDWARE_VID 0x20B7 -#define MILKYMISTONE_JTAGSERIAL_PID 0x0713 - /* * CTI GmbH RS485 Converter http://www.cti-lean.com/ */ diff --git a/hw/usb/quirks.h b/hw/usb/quirks.h index 50ef2f9c2e..c3e595f40b 100644 --- a/hw/usb/quirks.h +++ b/hw/usb/quirks.h @@ -904,7 +904,6 @@ static const struct usb_device_id usbredir_ftdi_serial_ids[] = { { USB_DEVICE(FTDI_VID, FTDI_SCIENCESCOPE_HS_LOGBOOK_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CINTERION_MC55I_PID) }, { USB_DEVICE(FTDI_VID, FTDI_DOTEC_PID) }, - { USB_DEVICE(QIHARDWARE_VID, MILKYMISTONE_JTAGSERIAL_PID) }, { USB_DEVICE(ST_VID, ST_STMCLT1030_PID) }, { USB_DEVICE(FTDI_VID, FTDI_RF_R106) }, { USB_DEVICE(FTDI_VID, FTDI_DISTORTEC_JTAG_LOCK_PICK_PID) }, diff --git a/hw/usb/redirect.c b/hw/usb/redirect.c index 17f06f3417..5f0ef9cb3b 100644 --- a/hw/usb/redirect.c +++ b/hw/usb/redirect.c @@ -270,7 +270,7 @@ static int usbredir_read(void *priv, uint8_t *data, int count) return count; } -static gboolean usbredir_write_unblocked(GIOChannel *chan, GIOCondition cond, +static gboolean usbredir_write_unblocked(void *do_not_use, GIOCondition cond, void *opaque) { USBRedirDevice *dev = opaque; @@ -476,7 +476,7 @@ static int bufp_alloc(USBRedirDevice *dev, uint8_t *data, uint16_t len, if (dev->endpoint[EP2I(ep)].bufpq_dropping_packets) { if (dev->endpoint[EP2I(ep)].bufpq_size > dev->endpoint[EP2I(ep)].bufpq_target_size) { - free(data); + free(free_on_destroy); return -1; } dev->endpoint[EP2I(ep)].bufpq_dropping_packets = 0; @@ -620,7 +620,7 @@ static void usbredir_handle_iso_data(USBRedirDevice *dev, USBPacket *p, .endpoint = ep, .length = p->iov.size }; - uint8_t buf[p->iov.size]; + g_autofree uint8_t *buf = g_malloc(p->iov.size); /* No id, we look at the ep when receiving a status back */ usb_packet_copy(p, buf, p->iov.size); usbredirparser_send_iso_packet(dev->parser, 0, &iso_packet, @@ -818,7 +818,7 @@ static void usbredir_handle_bulk_data(USBRedirDevice *dev, USBPacket *p, usbredirparser_send_bulk_packet(dev->parser, p->id, &bulk_packet, NULL, 0); } else { - uint8_t buf[size]; + g_autofree uint8_t *buf = g_malloc(size); usb_packet_copy(p, buf, size); usbredir_log_data(dev, "bulk data out:", buf, size); usbredirparser_send_bulk_packet(dev->parser, p->id, @@ -923,7 +923,7 @@ static void usbredir_handle_interrupt_out_data(USBRedirDevice *dev, USBPacket *p, uint8_t ep) { struct usb_redir_interrupt_packet_header interrupt_packet; - uint8_t buf[p->iov.size]; + g_autofree uint8_t *buf = g_malloc(p->iov.size); DPRINTF("interrupt-out ep %02X len %zd id %"PRIu64"\n", ep, p->iov.size, p->id); @@ -2608,6 +2608,7 @@ static const TypeInfo usbredir_dev_info = { .class_init = usbredir_class_initfn, .instance_init = usbredir_instance_init, }; +module_obj(TYPE_USB_REDIR); static void usbredir_register_types(void) { diff --git a/hw/usb/trace-events b/hw/usb/trace-events index 38e05fc7f4..b8287b63f1 100644 --- a/hw/usb/trace-events +++ b/hw/usb/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # core.c usb_packet_state_change(int bus, const char *port, int ep, void *p, const char *o, const char *n) "bus %d, port %s, ep %d, packet %p, state %s -> %s" diff --git a/hw/usb/xen-usb.c b/hw/usb/xen-usb.c index 4d266d7bb4..0f7369e7ed 100644 --- a/hw/usb/xen-usb.c +++ b/hw/usb/xen-usb.c @@ -26,7 +26,6 @@ #include "qemu/config-file.h" #include "qemu/main-loop.h" #include "qemu/option.h" -#include "hw/sysbus.h" #include "hw/usb.h" #include "hw/xen/xen-legacy-backend.h" #include "monitor/qdev.h" diff --git a/hw/usb/xlnx-usb-subsystem.c b/hw/usb/xlnx-usb-subsystem.c index 568257370c..d8deeb6ced 100644 --- a/hw/usb/xlnx-usb-subsystem.c +++ b/hw/usb/xlnx-usb-subsystem.c @@ -24,10 +24,8 @@ #include "qemu/osdep.h" #include "hw/sysbus.h" -#include "hw/irq.h" #include "hw/register.h" #include "qemu/bitops.h" -#include "qemu/log.h" #include "qom/object.h" #include "qapi/error.h" #include "hw/qdev-properties.h" diff --git a/hw/usb/xlnx-versal-usb2-ctrl-regs.c b/hw/usb/xlnx-versal-usb2-ctrl-regs.c index 9eaa59ebb8..1c094aa1a6 100644 --- a/hw/usb/xlnx-versal-usb2-ctrl-regs.c +++ b/hw/usb/xlnx-versal-usb2-ctrl-regs.c @@ -32,7 +32,6 @@ #include "hw/irq.h" #include "hw/register.h" #include "qemu/bitops.h" -#include "qemu/log.h" #include "qom/object.h" #include "migration/vmstate.h" #include "hw/usb/xlnx-versal-usb2-ctrl-regs.h" diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c index 9571c2f91f..e0dd561e85 100644 --- a/hw/vfio/ap.c +++ b/hw/vfio/ap.c @@ -14,7 +14,6 @@ #include #include #include "qapi/error.h" -#include "hw/sysbus.h" #include "hw/vfio/vfio.h" #include "hw/vfio/vfio-common.h" #include "hw/s390x/ap-device.h" @@ -22,8 +21,7 @@ #include "qemu/module.h" #include "qemu/option.h" #include "qemu/config-file.h" -#include "cpu.h" -#include "kvm_s390x.h" +#include "kvm/kvm_s390x.h" #include "migration/vmstate.h" #include "hw/qdev-properties.h" #include "hw/s390x/ap-bridge.h" diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index b2df708e4b..000992fb9f 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -20,7 +20,6 @@ #include #include "qapi/error.h" -#include "hw/sysbus.h" #include "hw/vfio/vfio.h" #include "hw/vfio/vfio-common.h" #include "hw/s390x/s390-ccw.h" @@ -322,6 +321,7 @@ static void vfio_ccw_io_notifier_handler(void *opaque) SCHIB *schib = &sch->curr_status; SCSW s; IRB irb; + ESW esw; int size; if (!event_notifier_test_and_clear(&vcdev->io_notifier)) { @@ -372,6 +372,9 @@ static void vfio_ccw_io_notifier_handler(void *opaque) copy_scsw_to_guest(&s, &irb.scsw); schib->scsw = s; + copy_esw_to_guest(&esw, &irb.esw); + sch->esw = esw; + /* If a uint check is pending, copy sense data. */ if ((schib->scsw.dstat & SCSW_DSTAT_UNIT_CHECK) && (schib->pmcw.chars & PMCW_CHARS_MASK_CSENSE)) { @@ -412,8 +415,8 @@ static void vfio_ccw_register_irq_notifier(VFIOCCWDevice *vcdev, } if (vdev->num_irqs < irq + 1) { - error_setg(errp, "vfio: unexpected number of irqs %u", - vdev->num_irqs); + error_setg(errp, "vfio: IRQ %u not available (number of irqs %u)", + irq, vdev->num_irqs); return; } @@ -470,7 +473,7 @@ static void vfio_ccw_unregister_irq_notifier(VFIOCCWDevice *vcdev, if (vfio_set_irq_signaling(&vcdev->vdev, irq, 0, VFIO_IRQ_SET_ACTION_TRIGGER, -1, &err)) { - error_reportf_err(err, VFIO_MSG_PREFIX, vcdev->vdev.name); + warn_reportf_err(err, VFIO_MSG_PREFIX, vcdev->vdev.name); } qemu_set_fd_handler(event_notifier_get_fd(notifier), @@ -690,20 +693,24 @@ static void vfio_ccw_realize(DeviceState *dev, Error **errp) if (vcdev->crw_region) { vfio_ccw_register_irq_notifier(vcdev, VFIO_CCW_CRW_IRQ_INDEX, &err); if (err) { - goto out_crw_notifier_err; + goto out_irq_notifier_err; } } vfio_ccw_register_irq_notifier(vcdev, VFIO_CCW_REQ_IRQ_INDEX, &err); if (err) { - goto out_req_notifier_err; + /* + * Report this error, but do not make it a failing condition. + * Lack of this IRQ in the host does not prevent normal operation. + */ + error_report_err(err); } return; -out_req_notifier_err: +out_irq_notifier_err: + vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_REQ_IRQ_INDEX); vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_CRW_IRQ_INDEX); -out_crw_notifier_err: vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_IO_IRQ_INDEX); out_io_notifier_err: vfio_ccw_put_region(vcdev); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index ae5654fcdb..8728d4d5c2 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -36,6 +36,7 @@ #include "qemu/range.h" #include "sysemu/kvm.h" #include "sysemu/reset.h" +#include "sysemu/runstate.h" #include "trace.h" #include "qapi/error.h" #include "migration/migration.h" @@ -134,6 +135,29 @@ static const char *index_to_str(VFIODevice *vbasedev, int index) } } +static int vfio_ram_block_discard_disable(VFIOContainer *container, bool state) +{ + switch (container->iommu_type) { + case VFIO_TYPE1v2_IOMMU: + case VFIO_TYPE1_IOMMU: + /* + * We support coordinated discarding of RAM via the RamDiscardManager. + */ + return ram_block_uncoordinated_discard_disable(state); + default: + /* + * VFIO_SPAPR_TCE_IOMMU most probably works just fine with + * RamDiscardManager, however, it is completely untested. + * + * VFIO_SPAPR_TCE_v2_IOMMU with "DMA memory preregistering" does + * completely the opposite of managing mapping/pinning dynamically as + * required by RamDiscardManager. We would have to special-case sections + * with a RamDiscardManager. + */ + return ram_block_discard_disable(state); + } +} + int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, int action, int fd, Error **errp) { @@ -569,6 +593,44 @@ static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr, error_report("iommu map to non memory area %"HWADDR_PRIx"", xlat); return false; + } else if (memory_region_has_ram_discard_manager(mr)) { + RamDiscardManager *rdm = memory_region_get_ram_discard_manager(mr); + MemoryRegionSection tmp = { + .mr = mr, + .offset_within_region = xlat, + .size = int128_make64(len), + }; + + /* + * Malicious VMs can map memory into the IOMMU, which is expected + * to remain discarded. vfio will pin all pages, populating memory. + * Disallow that. vmstate priorities make sure any RamDiscardManager + * were already restored before IOMMUs are restored. + */ + if (!ram_discard_manager_is_populated(rdm, &tmp)) { + error_report("iommu map to discarded memory (e.g., unplugged via" + " virtio-mem): %"HWADDR_PRIx"", + iotlb->translated_addr); + return false; + } + + /* + * Malicious VMs might trigger discarding of IOMMU-mapped memory. The + * pages will remain pinned inside vfio until unmapped, resulting in a + * higher memory consumption than expected. If memory would get + * populated again later, there would be an inconsistency between pages + * pinned by vfio and pages seen by QEMU. This is the case until + * unmapped from the IOMMU (e.g., during device reset). + * + * With malicious guests, we really only care about pinning more memory + * than expected. RLIMIT_MEMLOCK set for the user/process can never be + * exceeded and can be used to mitigate this problem. + */ + warn_report_once("Using vfio with vIOMMUs and coordinated discarding of" + " RAM (e.g., virtio-mem) works, however, malicious" + " guests can trigger pinning of more memory than" + " intended via an IOMMU. It's possible to mitigate " + " by setting/adjusting RLIMIT_MEMLOCK."); } /* @@ -649,6 +711,154 @@ out: rcu_read_unlock(); } +static void vfio_ram_discard_notify_discard(RamDiscardListener *rdl, + MemoryRegionSection *section) +{ + VFIORamDiscardListener *vrdl = container_of(rdl, VFIORamDiscardListener, + listener); + const hwaddr size = int128_get64(section->size); + const hwaddr iova = section->offset_within_address_space; + int ret; + + /* Unmap with a single call. */ + ret = vfio_dma_unmap(vrdl->container, iova, size , NULL); + if (ret) { + error_report("%s: vfio_dma_unmap() failed: %s", __func__, + strerror(-ret)); + } +} + +static int vfio_ram_discard_notify_populate(RamDiscardListener *rdl, + MemoryRegionSection *section) +{ + VFIORamDiscardListener *vrdl = container_of(rdl, VFIORamDiscardListener, + listener); + const hwaddr end = section->offset_within_region + + int128_get64(section->size); + hwaddr start, next, iova; + void *vaddr; + int ret; + + /* + * Map in (aligned within memory region) minimum granularity, so we can + * unmap in minimum granularity later. + */ + for (start = section->offset_within_region; start < end; start = next) { + next = ROUND_UP(start + 1, vrdl->granularity); + next = MIN(next, end); + + iova = start - section->offset_within_region + + section->offset_within_address_space; + vaddr = memory_region_get_ram_ptr(section->mr) + start; + + ret = vfio_dma_map(vrdl->container, iova, next - start, + vaddr, section->readonly); + if (ret) { + /* Rollback */ + vfio_ram_discard_notify_discard(rdl, section); + return ret; + } + } + return 0; +} + +static void vfio_register_ram_discard_listener(VFIOContainer *container, + MemoryRegionSection *section) +{ + RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr); + VFIORamDiscardListener *vrdl; + + /* Ignore some corner cases not relevant in practice. */ + g_assert(QEMU_IS_ALIGNED(section->offset_within_region, TARGET_PAGE_SIZE)); + g_assert(QEMU_IS_ALIGNED(section->offset_within_address_space, + TARGET_PAGE_SIZE)); + g_assert(QEMU_IS_ALIGNED(int128_get64(section->size), TARGET_PAGE_SIZE)); + + vrdl = g_new0(VFIORamDiscardListener, 1); + vrdl->container = container; + vrdl->mr = section->mr; + vrdl->offset_within_address_space = section->offset_within_address_space; + vrdl->size = int128_get64(section->size); + vrdl->granularity = ram_discard_manager_get_min_granularity(rdm, + section->mr); + + g_assert(vrdl->granularity && is_power_of_2(vrdl->granularity)); + g_assert(container->pgsizes && + vrdl->granularity >= 1ULL << ctz64(container->pgsizes)); + + ram_discard_listener_init(&vrdl->listener, + vfio_ram_discard_notify_populate, + vfio_ram_discard_notify_discard, true); + ram_discard_manager_register_listener(rdm, &vrdl->listener, section); + QLIST_INSERT_HEAD(&container->vrdl_list, vrdl, next); + + /* + * Sanity-check if we have a theoretically problematic setup where we could + * exceed the maximum number of possible DMA mappings over time. We assume + * that each mapped section in the same address space as a RamDiscardManager + * section consumes exactly one DMA mapping, with the exception of + * RamDiscardManager sections; i.e., we don't expect to have gIOMMU sections + * in the same address space as RamDiscardManager sections. + * + * We assume that each section in the address space consumes one memslot. + * We take the number of KVM memory slots as a best guess for the maximum + * number of sections in the address space we could have over time, + * also consuming DMA mappings. + */ + if (container->dma_max_mappings) { + unsigned int vrdl_count = 0, vrdl_mappings = 0, max_memslots = 512; + +#ifdef CONFIG_KVM + if (kvm_enabled()) { + max_memslots = kvm_get_max_memslots(); + } +#endif + + QLIST_FOREACH(vrdl, &container->vrdl_list, next) { + hwaddr start, end; + + start = QEMU_ALIGN_DOWN(vrdl->offset_within_address_space, + vrdl->granularity); + end = ROUND_UP(vrdl->offset_within_address_space + vrdl->size, + vrdl->granularity); + vrdl_mappings += (end - start) / vrdl->granularity; + vrdl_count++; + } + + if (vrdl_mappings + max_memslots - vrdl_count > + container->dma_max_mappings) { + warn_report("%s: possibly running out of DMA mappings. E.g., try" + " increasing the 'block-size' of virtio-mem devies." + " Maximum possible DMA mappings: %d, Maximum possible" + " memslots: %d", __func__, container->dma_max_mappings, + max_memslots); + } + } +} + +static void vfio_unregister_ram_discard_listener(VFIOContainer *container, + MemoryRegionSection *section) +{ + RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr); + VFIORamDiscardListener *vrdl = NULL; + + QLIST_FOREACH(vrdl, &container->vrdl_list, next) { + if (vrdl->mr == section->mr && + vrdl->offset_within_address_space == + section->offset_within_address_space) { + break; + } + } + + if (!vrdl) { + hw_error("vfio: Trying to unregister missing RAM discard listener"); + } + + ram_discard_manager_unregister_listener(rdm, &vrdl->listener); + QLIST_REMOVE(vrdl, next); + g_free(vrdl); +} + static void vfio_listener_region_add(MemoryListener *listener, MemoryRegionSection *section) { @@ -810,6 +1020,16 @@ static void vfio_listener_region_add(MemoryListener *listener, /* Here we assume that memory_region_is_ram(section->mr)==true */ + /* + * For RAM memory regions with a RamDiscardManager, we only want to map the + * actually populated parts - and update the mapping whenever we're notified + * about changes. + */ + if (memory_region_has_ram_discard_manager(section->mr)) { + vfio_register_ram_discard_listener(container, section); + return; + } + vaddr = memory_region_get_ram_ptr(section->mr) + section->offset_within_region + (iova - section->offset_within_address_space); @@ -947,6 +1167,10 @@ static void vfio_listener_region_del(MemoryListener *listener, pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1; try_unmap = !((iova & pgmask) || (int128_get64(llsize) & pgmask)); + } else if (memory_region_has_ram_discard_manager(section->mr)) { + vfio_unregister_ram_discard_listener(container, section); + /* Unregistering will trigger an unmap. */ + try_unmap = false; } if (try_unmap) { @@ -1108,6 +1332,49 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) rcu_read_unlock(); } +static int vfio_ram_discard_get_dirty_bitmap(MemoryRegionSection *section, + void *opaque) +{ + const hwaddr size = int128_get64(section->size); + const hwaddr iova = section->offset_within_address_space; + const ram_addr_t ram_addr = memory_region_get_ram_addr(section->mr) + + section->offset_within_region; + VFIORamDiscardListener *vrdl = opaque; + + /* + * Sync the whole mapped region (spanning multiple individual mappings) + * in one go. + */ + return vfio_get_dirty_bitmap(vrdl->container, iova, size, ram_addr); +} + +static int vfio_sync_ram_discard_listener_dirty_bitmap(VFIOContainer *container, + MemoryRegionSection *section) +{ + RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr); + VFIORamDiscardListener *vrdl = NULL; + + QLIST_FOREACH(vrdl, &container->vrdl_list, next) { + if (vrdl->mr == section->mr && + vrdl->offset_within_address_space == + section->offset_within_address_space) { + break; + } + } + + if (!vrdl) { + hw_error("vfio: Trying to sync missing RAM discard listener"); + } + + /* + * We only want/can synchronize the bitmap for actually mapped parts - + * which correspond to populated parts. Replay all populated parts. + */ + return ram_discard_manager_replay_populated(rdm, section, + vfio_ram_discard_get_dirty_bitmap, + &vrdl); +} + static int vfio_sync_dirty_bitmap(VFIOContainer *container, MemoryRegionSection *section) { @@ -1139,6 +1406,8 @@ static int vfio_sync_dirty_bitmap(VFIOContainer *container, } } return 0; + } else if (memory_region_has_ram_discard_manager(section->mr)) { + return vfio_sync_ram_discard_listener_dirty_bitmap(container, section); } ram_addr = memory_region_get_ram_addr(section->mr) + @@ -1732,15 +2001,25 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, * new memory, it will not yet set ram_block_discard_set_required() and * therefore, neither stops us here or deals with the sudden memory * consumption of inflated memory. + * + * We do support discarding of memory coordinated via the RamDiscardManager + * with some IOMMU types. vfio_ram_block_discard_disable() handles the + * details once we know which type of IOMMU we are using. */ - ret = ram_block_discard_disable(true); - if (ret) { - error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"); - return ret; - } QLIST_FOREACH(container, &space->containers, next) { if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { + ret = vfio_ram_block_discard_disable(container, true); + if (ret) { + error_setg_errno(errp, -ret, + "Cannot set discarding of RAM broken"); + if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, + &container->fd)) { + error_report("vfio: error disconnecting group %d from" + " container", group->groupid); + } + return ret; + } group->container = container; QLIST_INSERT_HEAD(&container->group_list, group, container_next); vfio_kvm_device_add_group(group); @@ -1768,14 +2047,22 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, container->fd = fd; container->error = NULL; container->dirty_pages_supported = false; + container->dma_max_mappings = 0; QLIST_INIT(&container->giommu_list); QLIST_INIT(&container->hostwin_list); + QLIST_INIT(&container->vrdl_list); ret = vfio_init_container(container, group->fd, errp); if (ret) { goto free_container_exit; } + ret = vfio_ram_block_discard_disable(container, true); + if (ret) { + error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"); + goto free_container_exit; + } + switch (container->iommu_type) { case VFIO_TYPE1v2_IOMMU: case VFIO_TYPE1_IOMMU: @@ -1798,7 +2085,10 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, vfio_host_win_add(container, 0, (hwaddr)-1, info->iova_pgsizes); container->pgsizes = info->iova_pgsizes; + /* The default in the kernel ("dma_entry_limit") is 65535. */ + container->dma_max_mappings = 65535; if (!ret) { + vfio_get_info_dma_avail(info, &container->dma_max_mappings); vfio_get_iommu_info_migration(container, info); } g_free(info); @@ -1820,7 +2110,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, if (ret) { error_setg_errno(errp, errno, "failed to enable container"); ret = -errno; - goto free_container_exit; + goto enable_discards_exit; } } else { container->prereg_listener = vfio_prereg_listener; @@ -1832,7 +2122,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, ret = -1; error_propagate_prepend(errp, container->error, "RAM memory listener initialization failed: "); - goto free_container_exit; + goto enable_discards_exit; } } @@ -1845,7 +2135,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, if (v2) { memory_listener_unregister(&container->prereg_listener); } - goto free_container_exit; + goto enable_discards_exit; } if (v2) { @@ -1860,7 +2150,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, if (ret) { error_setg_errno(errp, -ret, "failed to remove existing window"); - goto free_container_exit; + goto enable_discards_exit; } } else { /* The default table uses 4K pages */ @@ -1901,6 +2191,9 @@ listener_release_exit: vfio_kvm_device_del_group(group); vfio_listener_release(container); +enable_discards_exit: + vfio_ram_block_discard_disable(container, false); + free_container_exit: g_free(container); @@ -1908,7 +2201,6 @@ close_fd_exit: close(fd); put_space_exit: - ram_block_discard_disable(false); vfio_put_address_space(space); return ret; @@ -2030,7 +2322,7 @@ void vfio_put_group(VFIOGroup *group) } if (!group->ram_block_discard_allowed) { - ram_block_discard_disable(false); + vfio_ram_block_discard_disable(group->container, false); } vfio_kvm_device_del_group(group); vfio_disconnect_container(group); @@ -2084,7 +2376,7 @@ int vfio_get_device(VFIOGroup *group, const char *name, if (!group->ram_block_discard_allowed) { group->ram_block_discard_allowed = true; - ram_block_discard_disable(false); + vfio_ram_block_discard_disable(group->container, false); } } diff --git a/hw/vfio/display.c b/hw/vfio/display.c index f04473e3ce..89bc90508f 100644 --- a/hw/vfio/display.c +++ b/hw/vfio/display.c @@ -14,7 +14,6 @@ #include #include -#include "sysemu/sysemu.h" #include "hw/display/edid.h" #include "ui/console.h" #include "qapi/error.h" diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c index 384576cfc0..82f654afb6 100644 --- a/hw/vfio/migration.c +++ b/hw/vfio/migration.c @@ -15,7 +15,6 @@ #include "sysemu/runstate.h" #include "hw/vfio/vfio-common.h" -#include "cpu.h" #include "migration/migration.h" #include "migration/vmstate.h" #include "migration/qemu-file.h" @@ -725,7 +724,16 @@ static void vfio_vmstate_change(void *opaque, bool running, RunState state) * _RUNNING bit */ mask = ~VFIO_DEVICE_STATE_RUNNING; - value = 0; + + /* + * When VM state transition to stop for savevm command, device should + * start saving data. + */ + if (state == RUN_STATE_SAVE_VM) { + value = VFIO_DEVICE_STATE_SAVING; + } else { + value = 0; + } } ret = vfio_migration_set_state(vbasedev, mask, value); @@ -893,6 +901,7 @@ void vfio_migration_finalize(VFIODevice *vbasedev) remove_migration_state_change_notifier(&migration->migration_state); qemu_del_vm_change_state_handler(migration->vm_state); + unregister_savevm(VMSTATE_IF(vbasedev->dev), "vfio", vbasedev); vfio_migration_exit(vbasedev); } diff --git a/hw/vfio/pci-quirks.c b/hw/vfio/pci-quirks.c index b90cf3d37c..e21a6ede11 100644 --- a/hw/vfio/pci-quirks.c +++ b/hw/vfio/pci-quirks.c @@ -22,7 +22,6 @@ #include "qapi/error.h" #include "qapi/visitor.h" #include -#include "hw/hw.h" #include "hw/nvram/fw_cfg.h" #include "hw/qdev-properties.h" #include "pci.h" diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 5c65aa0a98..e1ea1d8a23 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -37,7 +37,6 @@ #include "qemu/units.h" #include "sysemu/kvm.h" #include "sysemu/runstate.h" -#include "sysemu/sysemu.h" #include "pci.h" #include "trace.h" #include "qapi/error.h" @@ -1500,6 +1499,14 @@ static void vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp) if (vdev->vendor_id == PCI_VENDOR_ID_CHELSIO && (vdev->device_id & 0xff00) == 0x5800) { msix->pba_offset = 0x1000; + /* + * BAIDU KUNLUN Virtual Function devices for KUNLUN AI processor + * return an incorrect value of 0x460000 for the VF PBA offset while + * the BAR itself is only 0x10000. The correct value is 0xb400. + */ + } else if (vfio_pci_is(vdev, PCI_VENDOR_ID_BAIDU, + PCI_DEVICE_ID_KUNLUN_VF)) { + msix->pba_offset = 0xb400; } else if (vdev->msix_relo == OFF_AUTOPCIBAR_OFF) { error_setg(errp, "hardware reports invalid configuration, " "MSIX PBA outside of specified BAR"); @@ -3059,14 +3066,14 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } } - if (vdev->vendor_id == PCI_VENDOR_ID_NVIDIA) { + if (vfio_pci_is(vdev, PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID)) { ret = vfio_pci_nvidia_v100_ram_init(vdev, errp); if (ret && ret != -ENODEV) { error_report("Failed to setup NVIDIA V100 GPU RAM"); } } - if (vdev->vendor_id == PCI_VENDOR_ID_IBM) { + if (vfio_pci_is(vdev, PCI_VENDOR_ID_IBM, PCI_ANY_ID)) { ret = vfio_pci_nvlink2_init(vdev, errp); if (ret && ret != -ENODEV) { error_report("Failed to setup NVlink2 bridge"); diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c index 2900bd1941..ea3f70bd2f 100644 --- a/hw/vfio/spapr.c +++ b/hw/vfio/spapr.c @@ -9,7 +9,6 @@ */ #include "qemu/osdep.h" -#include "cpu.h" #include #include diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 079f53acf2..0ef1b5f4a6 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # pci.c vfio_intx_interrupt(const char *name, char line) " (%s) Pin %c" diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig index 0eda25c4e1..35ab45e209 100644 --- a/hw/virtio/Kconfig +++ b/hw/virtio/Kconfig @@ -58,3 +58,8 @@ config VIRTIO_MEM depends on LINUX depends on VIRTIO_MEM_SUPPORTED select MEM_DEVICE + +config VHOST_USER_I2C + bool + default y + depends on VIRTIO && VHOST_USER diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build index fbff9bc9d4..bc352a6009 100644 --- a/hw/virtio/meson.build +++ b/hw/virtio/meson.build @@ -25,6 +25,8 @@ virtio_ss.add(when: 'CONFIG_VHOST_USER_VSOCK', if_true: files('vhost-user-vsock. virtio_ss.add(when: 'CONFIG_VIRTIO_RNG', if_true: files('virtio-rng.c')) virtio_ss.add(when: 'CONFIG_VIRTIO_IOMMU', if_true: files('virtio-iommu.c')) virtio_ss.add(when: 'CONFIG_VIRTIO_MEM', if_true: files('virtio-mem.c')) +virtio_ss.add(when: 'CONFIG_VHOST_USER_I2C', if_true: files('vhost-user-i2c.c')) +virtio_ss.add(when: ['CONFIG_VIRTIO_PCI', 'CONFIG_VHOST_USER_I2C'], if_true: files('vhost-user-i2c-pci.c')) virtio_pci_ss = ss.source_set() virtio_pci_ss.add(when: 'CONFIG_VHOST_VSOCK', if_true: files('vhost-vsock-pci.c')) diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index c62727f879..8ed19e9d0c 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # vhost.c vhost_commit(bool started, bool changed) "Started: %d Changed: %d" diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c index 31b33bde37..594d770b75 100644 --- a/hw/virtio/vhost-backend.c +++ b/hw/virtio/vhost-backend.c @@ -24,13 +24,15 @@ static int vhost_kernel_call(struct vhost_dev *dev, unsigned long int request, void *arg) { int fd = (uintptr_t) dev->opaque; + int ret; assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_KERNEL); - return ioctl(fd, request, arg); + ret = ioctl(fd, request, arg); + return ret < 0 ? -errno : ret; } -static int vhost_kernel_init(struct vhost_dev *dev, void *opaque) +static int vhost_kernel_init(struct vhost_dev *dev, void *opaque, Error **errp) { assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_KERNEL); diff --git a/hw/virtio/vhost-user-fs.c b/hw/virtio/vhost-user-fs.c index 6f7f91533d..c595957983 100644 --- a/hw/virtio/vhost-user-fs.c +++ b/hw/virtio/vhost-user-fs.c @@ -235,9 +235,8 @@ static void vuf_device_realize(DeviceState *dev, Error **errp) fs->vhost_dev.nvqs = 1 + fs->conf.num_request_queues; fs->vhost_dev.vqs = g_new0(struct vhost_virtqueue, fs->vhost_dev.nvqs); ret = vhost_dev_init(&fs->vhost_dev, &fs->vhost_user, - VHOST_BACKEND_TYPE_USER, 0); + VHOST_BACKEND_TYPE_USER, 0, errp); if (ret < 0) { - error_setg_errno(errp, -ret, "vhost_dev_init failed"); goto err_virtio; } diff --git a/hw/virtio/vhost-user-i2c-pci.c b/hw/virtio/vhost-user-i2c-pci.c new file mode 100644 index 0000000000..70b7b65fd9 --- /dev/null +++ b/hw/virtio/vhost-user-i2c-pci.c @@ -0,0 +1,69 @@ +/* + * Vhost-user i2c virtio device PCI glue + * + * Copyright (c) 2021 Viresh Kumar + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/vhost-user-i2c.h" +#include "virtio-pci.h" + +struct VHostUserI2CPCI { + VirtIOPCIProxy parent_obj; + VHostUserI2C vdev; +}; + +typedef struct VHostUserI2CPCI VHostUserI2CPCI; + +#define TYPE_VHOST_USER_I2C_PCI "vhost-user-i2c-pci-base" + +DECLARE_INSTANCE_CHECKER(VHostUserI2CPCI, VHOST_USER_I2C_PCI, + TYPE_VHOST_USER_I2C_PCI) + +static void vhost_user_i2c_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VHostUserI2CPCI *dev = VHOST_USER_I2C_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + + vpci_dev->nvectors = 1; + qdev_realize(vdev, BUS(&vpci_dev->bus), errp); +} + +static void vhost_user_i2c_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + k->realize = vhost_user_i2c_pci_realize; + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = 0; /* Set by virtio-pci based on virtio id */ + pcidev_k->revision = 0x00; + pcidev_k->class_id = PCI_CLASS_COMMUNICATION_OTHER; +} + +static void vhost_user_i2c_pci_instance_init(Object *obj) +{ + VHostUserI2CPCI *dev = VHOST_USER_I2C_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VHOST_USER_I2C); +} + +static const VirtioPCIDeviceTypeInfo vhost_user_i2c_pci_info = { + .base_name = TYPE_VHOST_USER_I2C_PCI, + .non_transitional_name = "vhost-user-i2c-pci", + .instance_size = sizeof(VHostUserI2CPCI), + .instance_init = vhost_user_i2c_pci_instance_init, + .class_init = vhost_user_i2c_pci_class_init, +}; + +static void vhost_user_i2c_pci_register(void) +{ + virtio_pci_types_register(&vhost_user_i2c_pci_info); +} + +type_init(vhost_user_i2c_pci_register); diff --git a/hw/virtio/vhost-user-i2c.c b/hw/virtio/vhost-user-i2c.c new file mode 100644 index 0000000000..d172632bb0 --- /dev/null +++ b/hw/virtio/vhost-user-i2c.c @@ -0,0 +1,288 @@ +/* + * Vhost-user i2c virtio device + * + * Copyright (c) 2021 Viresh Kumar + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/virtio-bus.h" +#include "hw/virtio/vhost-user-i2c.h" +#include "qemu/error-report.h" +#include "standard-headers/linux/virtio_ids.h" + +/* Remove this once the header is updated in Linux kernel */ +#ifndef VIRTIO_ID_I2C_ADAPTER +#define VIRTIO_ID_I2C_ADAPTER 34 +#endif + +static void vu_i2c_start(VirtIODevice *vdev) +{ + BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + VHostUserI2C *i2c = VHOST_USER_I2C(vdev); + int ret, i; + + if (!k->set_guest_notifiers) { + error_report("binding does not support guest notifiers"); + return; + } + + ret = vhost_dev_enable_notifiers(&i2c->vhost_dev, vdev); + if (ret < 0) { + error_report("Error enabling host notifiers: %d", -ret); + return; + } + + ret = k->set_guest_notifiers(qbus->parent, i2c->vhost_dev.nvqs, true); + if (ret < 0) { + error_report("Error binding guest notifier: %d", -ret); + goto err_host_notifiers; + } + + i2c->vhost_dev.acked_features = vdev->guest_features; + + ret = vhost_dev_start(&i2c->vhost_dev, vdev); + if (ret < 0) { + error_report("Error starting vhost-user-i2c: %d", -ret); + goto err_guest_notifiers; + } + + /* + * guest_notifier_mask/pending not used yet, so just unmask + * everything here. virtio-pci will do the right thing by + * enabling/disabling irqfd. + */ + for (i = 0; i < i2c->vhost_dev.nvqs; i++) { + vhost_virtqueue_mask(&i2c->vhost_dev, vdev, i, false); + } + + return; + +err_guest_notifiers: + k->set_guest_notifiers(qbus->parent, i2c->vhost_dev.nvqs, false); +err_host_notifiers: + vhost_dev_disable_notifiers(&i2c->vhost_dev, vdev); +} + +static void vu_i2c_stop(VirtIODevice *vdev) +{ + VHostUserI2C *i2c = VHOST_USER_I2C(vdev); + BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); + VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + int ret; + + if (!k->set_guest_notifiers) { + return; + } + + vhost_dev_stop(&i2c->vhost_dev, vdev); + + ret = k->set_guest_notifiers(qbus->parent, i2c->vhost_dev.nvqs, false); + if (ret < 0) { + error_report("vhost guest notifier cleanup failed: %d", ret); + return; + } + + vhost_dev_disable_notifiers(&i2c->vhost_dev, vdev); +} + +static void vu_i2c_set_status(VirtIODevice *vdev, uint8_t status) +{ + VHostUserI2C *i2c = VHOST_USER_I2C(vdev); + bool should_start = status & VIRTIO_CONFIG_S_DRIVER_OK; + + if (!vdev->vm_running) { + should_start = false; + } + + if (i2c->vhost_dev.started == should_start) { + return; + } + + if (should_start) { + vu_i2c_start(vdev); + } else { + vu_i2c_stop(vdev); + } +} + +static uint64_t vu_i2c_get_features(VirtIODevice *vdev, + uint64_t requested_features, Error **errp) +{ + /* No feature bits used yet */ + return requested_features; +} + +static void vu_i2c_handle_output(VirtIODevice *vdev, VirtQueue *vq) +{ + /* + * Not normally called; it's the daemon that handles the queue; + * however virtio's cleanup path can call this. + */ +} + +static void vu_i2c_guest_notifier_mask(VirtIODevice *vdev, int idx, bool mask) +{ + VHostUserI2C *i2c = VHOST_USER_I2C(vdev); + + vhost_virtqueue_mask(&i2c->vhost_dev, vdev, idx, mask); +} + +static bool vu_i2c_guest_notifier_pending(VirtIODevice *vdev, int idx) +{ + VHostUserI2C *i2c = VHOST_USER_I2C(vdev); + + return vhost_virtqueue_pending(&i2c->vhost_dev, idx); +} + +static void do_vhost_user_cleanup(VirtIODevice *vdev, VHostUserI2C *i2c) +{ + vhost_user_cleanup(&i2c->vhost_user); + virtio_delete_queue(i2c->vq); + virtio_cleanup(vdev); + g_free(i2c->vhost_dev.vqs); + i2c->vhost_dev.vqs = NULL; +} + +static int vu_i2c_connect(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserI2C *i2c = VHOST_USER_I2C(vdev); + + if (i2c->connected) { + return 0; + } + i2c->connected = true; + + /* restore vhost state */ + if (virtio_device_started(vdev, vdev->status)) { + vu_i2c_start(vdev); + } + + return 0; +} + +static void vu_i2c_disconnect(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserI2C *i2c = VHOST_USER_I2C(vdev); + + if (!i2c->connected) { + return; + } + i2c->connected = false; + + if (i2c->vhost_dev.started) { + vu_i2c_stop(vdev); + } +} + +static void vu_i2c_event(void *opaque, QEMUChrEvent event) +{ + DeviceState *dev = opaque; + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserI2C *i2c = VHOST_USER_I2C(vdev); + + switch (event) { + case CHR_EVENT_OPENED: + if (vu_i2c_connect(dev) < 0) { + qemu_chr_fe_disconnect(&i2c->chardev); + return; + } + break; + case CHR_EVENT_CLOSED: + vu_i2c_disconnect(dev); + break; + case CHR_EVENT_BREAK: + case CHR_EVENT_MUX_IN: + case CHR_EVENT_MUX_OUT: + /* Ignore */ + break; + } +} + +static void vu_i2c_device_realize(DeviceState *dev, Error **errp) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserI2C *i2c = VHOST_USER_I2C(dev); + int ret; + + if (!i2c->chardev.chr) { + error_setg(errp, "vhost-user-i2c: missing chardev"); + return; + } + + if (!vhost_user_init(&i2c->vhost_user, &i2c->chardev, errp)) { + return; + } + + virtio_init(vdev, "vhost-user-i2c", VIRTIO_ID_I2C_ADAPTER, 0); + + i2c->vhost_dev.nvqs = 1; + i2c->vq = virtio_add_queue(vdev, 4, vu_i2c_handle_output); + i2c->vhost_dev.vqs = g_new0(struct vhost_virtqueue, i2c->vhost_dev.nvqs); + + ret = vhost_dev_init(&i2c->vhost_dev, &i2c->vhost_user, + VHOST_BACKEND_TYPE_USER, 0, errp); + if (ret < 0) { + do_vhost_user_cleanup(vdev, i2c); + } + + qemu_chr_fe_set_handlers(&i2c->chardev, NULL, NULL, vu_i2c_event, NULL, + dev, NULL, true); +} + +static void vu_i2c_device_unrealize(DeviceState *dev) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserI2C *i2c = VHOST_USER_I2C(dev); + + /* This will stop vhost backend if appropriate. */ + vu_i2c_set_status(vdev, 0); + vhost_dev_cleanup(&i2c->vhost_dev); + do_vhost_user_cleanup(vdev, i2c); +} + +static const VMStateDescription vu_i2c_vmstate = { + .name = "vhost-user-i2c", + .unmigratable = 1, +}; + +static Property vu_i2c_properties[] = { + DEFINE_PROP_CHR("chardev", VHostUserI2C, chardev), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vu_i2c_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + + device_class_set_props(dc, vu_i2c_properties); + dc->vmsd = &vu_i2c_vmstate; + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + vdc->realize = vu_i2c_device_realize; + vdc->unrealize = vu_i2c_device_unrealize; + vdc->get_features = vu_i2c_get_features; + vdc->set_status = vu_i2c_set_status; + vdc->guest_notifier_mask = vu_i2c_guest_notifier_mask; + vdc->guest_notifier_pending = vu_i2c_guest_notifier_pending; +} + +static const TypeInfo vu_i2c_info = { + .name = TYPE_VHOST_USER_I2C, + .parent = TYPE_VIRTIO_DEVICE, + .instance_size = sizeof(VHostUserI2C), + .class_init = vu_i2c_class_init, +}; + +static void vu_i2c_register_types(void) +{ + type_register_static(&vu_i2c_info); +} + +type_init(vu_i2c_register_types) diff --git a/hw/virtio/vhost-user-vsock.c b/hw/virtio/vhost-user-vsock.c index a6f08c26b9..6095ed7349 100644 --- a/hw/virtio/vhost-user-vsock.c +++ b/hw/virtio/vhost-user-vsock.c @@ -34,10 +34,12 @@ static void vuv_get_config(VirtIODevice *vdev, uint8_t *config) static int vuv_handle_config_change(struct vhost_dev *dev) { VHostUserVSock *vsock = VHOST_USER_VSOCK(dev->vdev); + Error *local_err = NULL; int ret = vhost_dev_get_config(dev, (uint8_t *)&vsock->vsockcfg, - sizeof(struct virtio_vsock_config)); + sizeof(struct virtio_vsock_config), + &local_err); if (ret < 0) { - error_report("get config space failed"); + error_report_err(local_err); return -1; } @@ -108,16 +110,14 @@ static void vuv_device_realize(DeviceState *dev, Error **errp) vhost_dev_set_config_notifier(&vvc->vhost_dev, &vsock_ops); ret = vhost_dev_init(&vvc->vhost_dev, &vsock->vhost_user, - VHOST_BACKEND_TYPE_USER, 0); + VHOST_BACKEND_TYPE_USER, 0, errp); if (ret < 0) { - error_setg_errno(errp, -ret, "vhost_dev_init failed"); goto err_virtio; } ret = vhost_dev_get_config(&vvc->vhost_dev, (uint8_t *)&vsock->vsockcfg, - sizeof(struct virtio_vsock_config)); + sizeof(struct virtio_vsock_config), errp); if (ret < 0) { - error_setg_errno(errp, -ret, "get config space failed"); goto err_vhost_dev; } diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index ded0c10453..aec6cc1990 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -303,7 +303,7 @@ struct vhost_user_read_cb_data { int ret; }; -static gboolean vhost_user_read_cb(GIOChannel *source, GIOCondition condition, +static gboolean vhost_user_read_cb(void *do_not_use, GIOCondition condition, gpointer opaque) { struct vhost_user_read_cb_data *data = opaque; @@ -1353,7 +1353,11 @@ static int vhost_user_get_u64(struct vhost_dev *dev, int request, uint64_t *u64) static int vhost_user_get_features(struct vhost_dev *dev, uint64_t *features) { - return vhost_user_get_u64(dev, VHOST_USER_GET_FEATURES, features); + if (vhost_user_get_u64(dev, VHOST_USER_GET_FEATURES, features) < 0) { + return -EPROTO; + } + + return 0; } static int vhost_user_set_owner(struct vhost_dev *dev) @@ -1364,7 +1368,7 @@ static int vhost_user_set_owner(struct vhost_dev *dev) }; if (vhost_user_write(dev, &msg, NULL, 0) < 0) { - return -1; + return -EPROTO; } return 0; @@ -1856,7 +1860,8 @@ static int vhost_user_postcopy_notifier(NotifierWithReturn *notifier, return 0; } -static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque) +static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque, + Error **errp) { uint64_t features, protocol_features, ram_slots; struct vhost_user *u; @@ -1880,7 +1885,7 @@ static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque) err = vhost_user_get_u64(dev, VHOST_USER_GET_PROTOCOL_FEATURES, &protocol_features); if (err < 0) { - return err; + return -EPROTO; } dev->protocol_features = @@ -1891,14 +1896,14 @@ static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque) dev->protocol_features &= ~(1ULL << VHOST_USER_PROTOCOL_F_CONFIG); } else if (!(protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_CONFIG))) { - error_report("Device expects VHOST_USER_PROTOCOL_F_CONFIG " - "but backend does not support it."); - return -1; + error_setg(errp, "Device expects VHOST_USER_PROTOCOL_F_CONFIG " + "but backend does not support it."); + return -EINVAL; } err = vhost_user_set_protocol_features(dev, dev->protocol_features); if (err < 0) { - return err; + return -EPROTO; } /* query the max queues we support if backend supports Multiple Queue */ @@ -1906,8 +1911,16 @@ static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque) err = vhost_user_get_u64(dev, VHOST_USER_GET_QUEUE_NUM, &dev->max_queues); if (err < 0) { - return err; + return -EPROTO; } + } else { + dev->max_queues = 1; + } + + if (dev->num_queues && dev->max_queues < dev->num_queues) { + error_setg(errp, "The maximum number of queues supported by the " + "backend is %" PRIu64, dev->max_queues); + return -EINVAL; } if (virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM) && @@ -1915,9 +1928,9 @@ static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque) VHOST_USER_PROTOCOL_F_SLAVE_REQ) && virtio_has_feature(dev->protocol_features, VHOST_USER_PROTOCOL_F_REPLY_ACK))) { - error_report("IOMMU support requires reply-ack and " - "slave-req protocol features."); - return -1; + error_setg(errp, "IOMMU support requires reply-ack and " + "slave-req protocol features."); + return -EINVAL; } /* get max memory regions if backend supports configurable RAM slots */ @@ -1927,15 +1940,15 @@ static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque) } else { err = vhost_user_get_max_memslots(dev, &ram_slots); if (err < 0) { - return err; + return -EPROTO; } if (ram_slots < u->user->memory_slots) { - error_report("The backend specified a max ram slots limit " - "of %" PRIu64", when the prior validated limit was %d. " - "This limit should never decrease.", ram_slots, - u->user->memory_slots); - return -1; + error_setg(errp, "The backend specified a max ram slots limit " + "of %" PRIu64", when the prior validated limit was " + "%d. This limit should never decrease.", ram_slots, + u->user->memory_slots); + return -EINVAL; } u->user->memory_slots = MIN(ram_slots, VHOST_USER_MAX_RAM_SLOTS); @@ -1953,7 +1966,7 @@ static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque) if (dev->vq_index == 0) { err = vhost_setup_slave_channel(dev); if (err < 0) { - return err; + return -EPROTO; } } @@ -2107,7 +2120,7 @@ static void vhost_user_set_iotlb_callback(struct vhost_dev *dev, int enabled) } static int vhost_user_get_config(struct vhost_dev *dev, uint8_t *config, - uint32_t config_len) + uint32_t config_len, Error **errp) { VhostUserMsg msg = { .hdr.request = VHOST_USER_GET_CONFIG, @@ -2117,32 +2130,32 @@ static int vhost_user_get_config(struct vhost_dev *dev, uint8_t *config, if (!virtio_has_feature(dev->protocol_features, VHOST_USER_PROTOCOL_F_CONFIG)) { - return -1; + error_setg(errp, "VHOST_USER_PROTOCOL_F_CONFIG not supported"); + return -EINVAL; } - if (config_len > VHOST_USER_MAX_CONFIG_SIZE) { - return -1; - } + assert(config_len <= VHOST_USER_MAX_CONFIG_SIZE); msg.payload.config.offset = 0; msg.payload.config.size = config_len; if (vhost_user_write(dev, &msg, NULL, 0) < 0) { - return -1; + return -EPROTO; } if (vhost_user_read(dev, &msg) < 0) { - return -1; + return -EPROTO; } if (msg.hdr.request != VHOST_USER_GET_CONFIG) { - error_report("Received unexpected msg type. Expected %d received %d", - VHOST_USER_GET_CONFIG, msg.hdr.request); - return -1; + error_setg(errp, + "Received unexpected msg type. Expected %d received %d", + VHOST_USER_GET_CONFIG, msg.hdr.request); + return -EINVAL; } if (msg.hdr.size != VHOST_USER_CONFIG_HDR_SIZE + config_len) { - error_report("Received bad msg size."); - return -1; + error_setg(errp, "Received bad msg size."); + return -EINVAL; } memcpy(config, msg.payload.config.region, config_len); diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c index 01d2101d09..4fa414feea 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c @@ -18,6 +18,7 @@ #include "hw/virtio/vhost-backend.h" #include "hw/virtio/virtio-net.h" #include "hw/virtio/vhost-vdpa.h" +#include "exec/address-spaces.h" #include "qemu/main-loop.h" #include "cpu.h" #include "trace.h" @@ -27,6 +28,8 @@ static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section) { return (!memory_region_is_ram(section->mr) && !memory_region_is_iommu(section->mr)) || + /* vhost-vDPA doesn't allow MMIO to be mapped */ + memory_region_is_ram_device(section->mr) || /* * Sizing an enabled 64-bit BAR can cause spurious mappings to * addresses in the upper part of the 64-bit address space. These @@ -171,22 +174,12 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener, vaddr, section->readonly); if (ret) { error_report("vhost vdpa map fail!"); - if (memory_region_is_ram_device(section->mr)) { - /* Allow unexpected mappings not to be fatal for RAM devices */ - error_report("map ram fail!"); - return ; - } goto fail; } return; fail: - if (memory_region_is_ram_device(section->mr)) { - error_report("failed to vdpa_dma_map. pci p2p may not work"); - return; - - } /* * On the initfn path, store the first error in the container so we * can gracefully fail. Runtime, there's not much we can do other @@ -252,10 +245,12 @@ static int vhost_vdpa_call(struct vhost_dev *dev, unsigned long int request, { struct vhost_vdpa *v = dev->opaque; int fd = v->device_fd; + int ret; assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); - return ioctl(fd, request, arg); + ret = ioctl(fd, request, arg); + return ret < 0 ? -errno : ret; } static void vhost_vdpa_add_status(struct vhost_dev *dev, uint8_t status) @@ -272,18 +267,15 @@ static void vhost_vdpa_add_status(struct vhost_dev *dev, uint8_t status) vhost_vdpa_call(dev, VHOST_VDPA_SET_STATUS, &s); } -static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque) +static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) { struct vhost_vdpa *v; - uint64_t features; assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); trace_vhost_vdpa_init(dev, opaque); v = opaque; v->dev = dev; dev->opaque = opaque ; - vhost_vdpa_call(dev, VHOST_GET_FEATURES, &features); - dev->backend_features = features; v->listener = vhost_vdpa_memory_listener; v->msg_type = VHOST_IOTLB_MSG_V2; @@ -293,12 +285,95 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque) return 0; } +static void vhost_vdpa_host_notifier_uninit(struct vhost_dev *dev, + int queue_index) +{ + size_t page_size = qemu_real_host_page_size; + struct vhost_vdpa *v = dev->opaque; + VirtIODevice *vdev = dev->vdev; + VhostVDPAHostNotifier *n; + + n = &v->notifier[queue_index]; + + if (n->addr) { + virtio_queue_set_host_notifier_mr(vdev, queue_index, &n->mr, false); + object_unparent(OBJECT(&n->mr)); + munmap(n->addr, page_size); + n->addr = NULL; + } +} + +static void vhost_vdpa_host_notifiers_uninit(struct vhost_dev *dev, int n) +{ + int i; + + for (i = 0; i < n; i++) { + vhost_vdpa_host_notifier_uninit(dev, i); + } +} + +static int vhost_vdpa_host_notifier_init(struct vhost_dev *dev, int queue_index) +{ + size_t page_size = qemu_real_host_page_size; + struct vhost_vdpa *v = dev->opaque; + VirtIODevice *vdev = dev->vdev; + VhostVDPAHostNotifier *n; + int fd = v->device_fd; + void *addr; + char *name; + + vhost_vdpa_host_notifier_uninit(dev, queue_index); + + n = &v->notifier[queue_index]; + + addr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, fd, + queue_index * page_size); + if (addr == MAP_FAILED) { + goto err; + } + + name = g_strdup_printf("vhost-vdpa/host-notifier@%p mmaps[%d]", + v, queue_index); + memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name, + page_size, addr); + g_free(name); + + if (virtio_queue_set_host_notifier_mr(vdev, queue_index, &n->mr, true)) { + munmap(addr, page_size); + goto err; + } + n->addr = addr; + + return 0; + +err: + return -1; +} + +static void vhost_vdpa_host_notifiers_init(struct vhost_dev *dev) +{ + int i; + + for (i = dev->vq_index; i < dev->vq_index + dev->nvqs; i++) { + if (vhost_vdpa_host_notifier_init(dev, i)) { + goto err; + } + } + + return; + +err: + vhost_vdpa_host_notifiers_uninit(dev, i); + return; +} + static int vhost_vdpa_cleanup(struct vhost_dev *dev) { struct vhost_vdpa *v; assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); v = dev->opaque; trace_vhost_vdpa_cleanup(dev, v); + vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs); memory_listener_unregister(&v->listener); dev->opaque = NULL; @@ -371,8 +446,8 @@ static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev) return 0; } -int vhost_vdpa_get_device_id(struct vhost_dev *dev, - uint32_t *device_id) +static int vhost_vdpa_get_device_id(struct vhost_dev *dev, + uint32_t *device_id) { int ret; ret = vhost_vdpa_call(dev, VHOST_VDPA_GET_DEVICE_ID, device_id); @@ -448,7 +523,7 @@ static int vhost_vdpa_set_config(struct vhost_dev *dev, const uint8_t *data, } static int vhost_vdpa_get_config(struct vhost_dev *dev, uint8_t *config, - uint32_t config_len) + uint32_t config_len, Error **errp) { struct vhost_vdpa_config *v_config; unsigned long config_size = offsetof(struct vhost_vdpa_config, buf); @@ -475,6 +550,7 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) if (started) { uint8_t status = 0; memory_listener_register(&v->listener, &address_space_memory); + vhost_vdpa_host_notifiers_init(dev); vhost_vdpa_set_vring_ready(dev); vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); vhost_vdpa_call(dev, VHOST_VDPA_GET_STATUS, &status); @@ -484,6 +560,7 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) vhost_vdpa_reset_device(dev); vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER); + vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs); memory_listener_unregister(&v->listener); return 0; diff --git a/hw/virtio/vhost-vsock.c b/hw/virtio/vhost-vsock.c index 8ddfb9abfe..1b1a5c70ed 100644 --- a/hw/virtio/vhost-vsock.c +++ b/hw/virtio/vhost-vsock.c @@ -21,6 +21,11 @@ #include "hw/virtio/vhost-vsock.h" #include "monitor/monitor.h" +const int feature_bits[] = { + VIRTIO_VSOCK_F_SEQPACKET, + VHOST_INVALID_FEATURE_BIT +}; + static void vhost_vsock_get_config(VirtIODevice *vdev, uint8_t *config) { VHostVSock *vsock = VHOST_VSOCK(vdev); @@ -108,8 +113,11 @@ static uint64_t vhost_vsock_get_features(VirtIODevice *vdev, uint64_t requested_features, Error **errp) { - /* No feature bits used yet */ - return requested_features; + VHostVSockCommon *vvc = VHOST_VSOCK_COMMON(vdev); + + virtio_add_feature(&requested_features, VIRTIO_VSOCK_F_SEQPACKET); + return vhost_get_features(&vvc->vhost_dev, feature_bits, + requested_features); } static const VMStateDescription vmstate_virtio_vhost_vsock = { @@ -170,9 +178,8 @@ static void vhost_vsock_device_realize(DeviceState *dev, Error **errp) vhost_vsock_common_realize(vdev, "vhost-vsock"); ret = vhost_dev_init(&vvc->vhost_dev, (void *)(uintptr_t)vhostfd, - VHOST_BACKEND_TYPE_KERNEL, 0); + VHOST_BACKEND_TYPE_KERNEL, 0, errp); if (ret < 0) { - error_setg_errno(errp, -ret, "vhost-vsock: vhost_dev_init failed"); goto err_virtio; } diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index e2163a0d63..e8f85a5d2d 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -21,7 +21,6 @@ #include "qemu/error-report.h" #include "qemu/memfd.h" #include "standard-headers/linux/vhost_types.h" -#include "exec/address-spaces.h" #include "hw/virtio/virtio-bus.h" #include "hw/virtio/virtio-access.h" #include "migration/blocker.h" @@ -1287,11 +1286,12 @@ static void vhost_virtqueue_cleanup(struct vhost_virtqueue *vq) } int vhost_dev_init(struct vhost_dev *hdev, void *opaque, - VhostBackendType backend_type, uint32_t busyloop_timeout) + VhostBackendType backend_type, uint32_t busyloop_timeout, + Error **errp) { + ERRP_GUARD(); uint64_t features; int i, r, n_initialized_vqs = 0; - Error *local_err = NULL; hdev->vdev = NULL; hdev->migration_blocker = NULL; @@ -1299,26 +1299,30 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, r = vhost_set_backend_type(hdev, backend_type); assert(r >= 0); - r = hdev->vhost_ops->vhost_backend_init(hdev, opaque); + r = hdev->vhost_ops->vhost_backend_init(hdev, opaque, errp); if (r < 0) { + if (!*errp) { + error_setg_errno(errp, -r, "vhost_backend_init failed"); + } goto fail; } r = hdev->vhost_ops->vhost_set_owner(hdev); if (r < 0) { - VHOST_OPS_DEBUG("vhost_set_owner failed"); + error_setg_errno(errp, -r, "vhost_set_owner failed"); goto fail; } r = hdev->vhost_ops->vhost_get_features(hdev, &features); if (r < 0) { - VHOST_OPS_DEBUG("vhost_get_features failed"); + error_setg_errno(errp, -r, "vhost_get_features failed"); goto fail; } for (i = 0; i < hdev->nvqs; ++i, ++n_initialized_vqs) { r = vhost_virtqueue_init(hdev, hdev->vqs + i, hdev->vq_index + i); if (r < 0) { + error_setg_errno(errp, -r, "Failed to initialize virtqueue %d", i); goto fail; } } @@ -1328,6 +1332,7 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, r = vhost_virtqueue_set_busyloop_timeout(hdev, hdev->vq_index + i, busyloop_timeout); if (r < 0) { + error_setg_errno(errp, -r, "Failed to set busyloop timeout"); goto fail_busyloop; } } @@ -1366,9 +1371,8 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, } if (hdev->migration_blocker != NULL) { - r = migrate_add_blocker(hdev->migration_blocker, &local_err); - if (local_err) { - error_report_err(local_err); + r = migrate_add_blocker(hdev->migration_blocker, errp); + if (*errp) { error_free(hdev->migration_blocker); goto fail_busyloop; } @@ -1385,9 +1389,9 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, QLIST_INSERT_HEAD(&vhost_devices, hdev, entry); if (used_memslots > hdev->vhost_ops->vhost_backend_memslots_limit(hdev)) { - error_report("vhost backend memory slots limit is less" - " than current number of present memory slots"); - r = -1; + error_setg(errp, "vhost backend memory slots limit is less" + " than current number of present memory slots"); + r = -EINVAL; goto fail_busyloop; } @@ -1558,15 +1562,23 @@ void vhost_ack_features(struct vhost_dev *hdev, const int *feature_bits, } int vhost_dev_get_config(struct vhost_dev *hdev, uint8_t *config, - uint32_t config_len) + uint32_t config_len, Error **errp) { + ERRP_GUARD(); + int ret; + assert(hdev->vhost_ops); if (hdev->vhost_ops->vhost_get_config) { - return hdev->vhost_ops->vhost_get_config(hdev, config, config_len); + ret = hdev->vhost_ops->vhost_get_config(hdev, config, config_len, errp); + if (ret < 0 && !*errp) { + error_setg_errno(errp, -ret, "vhost_get_config failed"); + } + return ret; } - return -1; + error_setg(errp, "vhost_get_config not implemented"); + return -ENOTSUP; } int vhost_dev_set_config(struct vhost_dev *hdev, const uint8_t *data, diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index d120bf8f43..4b5d9e5e50 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -663,9 +663,6 @@ virtio_balloon_free_page_hint_notify(NotifierWithReturn *n, void *data) } switch (pnd->reason) { - case PRECOPY_NOTIFY_SETUP: - precopy_enable_free_page_optimization(); - break; case PRECOPY_NOTIFY_BEFORE_BITMAP_SYNC: virtio_balloon_free_page_stop(dev); break; @@ -685,6 +682,7 @@ virtio_balloon_free_page_hint_notify(NotifierWithReturn *n, void *data) */ virtio_balloon_free_page_done(dev); break; + case PRECOPY_NOTIFY_SETUP: case PRECOPY_NOTIFY_COMPLETE: break; default: diff --git a/hw/virtio/virtio-bus.c b/hw/virtio/virtio-bus.c index d6332d45c3..859978d248 100644 --- a/hw/virtio/virtio-bus.c +++ b/hw/virtio/virtio-bus.c @@ -69,6 +69,11 @@ void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp) return; } + if (has_iommu && !virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM)) { + error_setg(errp, "iommu_platform=true is not supported by the device"); + return; + } + if (klass->device_plugged != NULL) { klass->device_plugged(qbus->parent, &local_err); } diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c index 655824ff81..df91e454b2 100644 --- a/hw/virtio/virtio-mem.c +++ b/hw/virtio/virtio-mem.c @@ -145,7 +145,173 @@ static bool virtio_mem_is_busy(void) return migration_in_incoming_postcopy() || !migration_is_idle(); } -static bool virtio_mem_test_bitmap(VirtIOMEM *vmem, uint64_t start_gpa, +typedef int (*virtio_mem_range_cb)(const VirtIOMEM *vmem, void *arg, + uint64_t offset, uint64_t size); + +static int virtio_mem_for_each_unplugged_range(const VirtIOMEM *vmem, void *arg, + virtio_mem_range_cb cb) +{ + unsigned long first_zero_bit, last_zero_bit; + uint64_t offset, size; + int ret = 0; + + first_zero_bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size); + while (first_zero_bit < vmem->bitmap_size) { + offset = first_zero_bit * vmem->block_size; + last_zero_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, + first_zero_bit + 1) - 1; + size = (last_zero_bit - first_zero_bit + 1) * vmem->block_size; + + ret = cb(vmem, arg, offset, size); + if (ret) { + break; + } + first_zero_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, + last_zero_bit + 2); + } + return ret; +} + +/* + * Adjust the memory section to cover the intersection with the given range. + * + * Returns false if the intersection is empty, otherwise returns true. + */ +static bool virito_mem_intersect_memory_section(MemoryRegionSection *s, + uint64_t offset, uint64_t size) +{ + uint64_t start = MAX(s->offset_within_region, offset); + uint64_t end = MIN(s->offset_within_region + int128_get64(s->size), + offset + size); + + if (end <= start) { + return false; + } + + s->offset_within_address_space += start - s->offset_within_region; + s->offset_within_region = start; + s->size = int128_make64(end - start); + return true; +} + +typedef int (*virtio_mem_section_cb)(MemoryRegionSection *s, void *arg); + +static int virtio_mem_for_each_plugged_section(const VirtIOMEM *vmem, + MemoryRegionSection *s, + void *arg, + virtio_mem_section_cb cb) +{ + unsigned long first_bit, last_bit; + uint64_t offset, size; + int ret = 0; + + first_bit = s->offset_within_region / vmem->bitmap_size; + first_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, first_bit); + while (first_bit < vmem->bitmap_size) { + MemoryRegionSection tmp = *s; + + offset = first_bit * vmem->block_size; + last_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, + first_bit + 1) - 1; + size = (last_bit - first_bit + 1) * vmem->block_size; + + if (!virito_mem_intersect_memory_section(&tmp, offset, size)) { + break; + } + ret = cb(&tmp, arg); + if (ret) { + break; + } + first_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, + last_bit + 2); + } + return ret; +} + +static int virtio_mem_notify_populate_cb(MemoryRegionSection *s, void *arg) +{ + RamDiscardListener *rdl = arg; + + return rdl->notify_populate(rdl, s); +} + +static int virtio_mem_notify_discard_cb(MemoryRegionSection *s, void *arg) +{ + RamDiscardListener *rdl = arg; + + rdl->notify_discard(rdl, s); + return 0; +} + +static void virtio_mem_notify_unplug(VirtIOMEM *vmem, uint64_t offset, + uint64_t size) +{ + RamDiscardListener *rdl; + + QLIST_FOREACH(rdl, &vmem->rdl_list, next) { + MemoryRegionSection tmp = *rdl->section; + + if (!virito_mem_intersect_memory_section(&tmp, offset, size)) { + continue; + } + rdl->notify_discard(rdl, &tmp); + } +} + +static int virtio_mem_notify_plug(VirtIOMEM *vmem, uint64_t offset, + uint64_t size) +{ + RamDiscardListener *rdl, *rdl2; + int ret = 0; + + QLIST_FOREACH(rdl, &vmem->rdl_list, next) { + MemoryRegionSection tmp = *rdl->section; + + if (!virito_mem_intersect_memory_section(&tmp, offset, size)) { + continue; + } + ret = rdl->notify_populate(rdl, &tmp); + if (ret) { + break; + } + } + + if (ret) { + /* Notify all already-notified listeners. */ + QLIST_FOREACH(rdl2, &vmem->rdl_list, next) { + MemoryRegionSection tmp = *rdl->section; + + if (rdl2 == rdl) { + break; + } + if (!virito_mem_intersect_memory_section(&tmp, offset, size)) { + continue; + } + rdl2->notify_discard(rdl2, &tmp); + } + } + return ret; +} + +static void virtio_mem_notify_unplug_all(VirtIOMEM *vmem) +{ + RamDiscardListener *rdl; + + if (!vmem->size) { + return; + } + + QLIST_FOREACH(rdl, &vmem->rdl_list, next) { + if (rdl->double_discard_supported) { + rdl->notify_discard(rdl, rdl->section); + } else { + virtio_mem_for_each_plugged_section(vmem, rdl->section, rdl, + virtio_mem_notify_discard_cb); + } + } +} + +static bool virtio_mem_test_bitmap(const VirtIOMEM *vmem, uint64_t start_gpa, uint64_t size, bool plugged) { const unsigned long first_bit = (start_gpa - vmem->addr) / vmem->block_size; @@ -198,7 +364,8 @@ static void virtio_mem_send_response_simple(VirtIOMEM *vmem, virtio_mem_send_response(vmem, elem, &resp); } -static bool virtio_mem_valid_range(VirtIOMEM *vmem, uint64_t gpa, uint64_t size) +static bool virtio_mem_valid_range(const VirtIOMEM *vmem, uint64_t gpa, + uint64_t size) { if (!QEMU_IS_ALIGNED(gpa, vmem->block_size)) { return false; @@ -219,19 +386,21 @@ static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, uint64_t size, bool plug) { const uint64_t offset = start_gpa - vmem->addr; - int ret; + RAMBlock *rb = vmem->memdev->mr.ram_block; if (virtio_mem_is_busy()) { return -EBUSY; } if (!plug) { - ret = ram_block_discard_range(vmem->memdev->mr.ram_block, offset, size); - if (ret) { - error_report("Unexpected error discarding RAM: %s", - strerror(-ret)); + if (ram_block_discard_range(rb, offset, size)) { return -EBUSY; } + virtio_mem_notify_unplug(vmem, offset, size); + } else if (virtio_mem_notify_plug(vmem, offset, size)) { + /* Could be a mapping attempt resulted in memory getting populated. */ + ram_block_discard_range(vmem->memdev->mr.ram_block, offset, size); + return -EBUSY; } virtio_mem_set_bitmap(vmem, start_gpa, size, plug); return 0; @@ -318,17 +487,16 @@ static void virtio_mem_resize_usable_region(VirtIOMEM *vmem, static int virtio_mem_unplug_all(VirtIOMEM *vmem) { RAMBlock *rb = vmem->memdev->mr.ram_block; - int ret; if (virtio_mem_is_busy()) { return -EBUSY; } - ret = ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb)); - if (ret) { - error_report("Unexpected error discarding RAM: %s", strerror(-ret)); + if (ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb))) { return -EBUSY; } + virtio_mem_notify_unplug_all(vmem); + bitmap_clear(vmem->bitmap, 0, vmem->bitmap_size); if (vmem->size) { vmem->size = 0; @@ -551,7 +719,7 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp) return; } - if (ram_block_discard_require(true)) { + if (ram_block_coordinated_discard_require(true)) { error_setg(errp, "Discarding RAM is disabled"); return; } @@ -559,7 +727,7 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp) ret = ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb)); if (ret) { error_setg_errno(errp, -ret, "Unexpected error discarding RAM"); - ram_block_discard_require(false); + ram_block_coordinated_discard_require(false); return; } @@ -577,6 +745,13 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp) vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem)); qemu_register_reset(virtio_mem_system_reset, vmem); precopy_add_notifier(&vmem->precopy_notifier); + + /* + * Set ourselves as RamDiscardManager before the plug handler maps the + * memory region and exposes it via an address space. + */ + memory_region_set_ram_discard_manager(&vmem->memdev->mr, + RAM_DISCARD_MANAGER(vmem)); } static void virtio_mem_device_unrealize(DeviceState *dev) @@ -584,6 +759,11 @@ static void virtio_mem_device_unrealize(DeviceState *dev) VirtIODevice *vdev = VIRTIO_DEVICE(dev); VirtIOMEM *vmem = VIRTIO_MEM(dev); + /* + * The unplug handler unmapped the memory region, it cannot be + * found via an address space anymore. Unset ourselves. + */ + memory_region_set_ram_discard_manager(&vmem->memdev->mr, NULL); precopy_remove_notifier(&vmem->precopy_notifier); qemu_unregister_reset(virtio_mem_system_reset, vmem); vmstate_unregister_ram(&vmem->memdev->mr, DEVICE(vmem)); @@ -591,43 +771,47 @@ static void virtio_mem_device_unrealize(DeviceState *dev) virtio_del_queue(vdev, 0); virtio_cleanup(vdev); g_free(vmem->bitmap); - ram_block_discard_require(false); + ram_block_coordinated_discard_require(false); +} + +static int virtio_mem_discard_range_cb(const VirtIOMEM *vmem, void *arg, + uint64_t offset, uint64_t size) +{ + RAMBlock *rb = vmem->memdev->mr.ram_block; + + return ram_block_discard_range(rb, offset, size) ? -EINVAL : 0; } static int virtio_mem_restore_unplugged(VirtIOMEM *vmem) { - RAMBlock *rb = vmem->memdev->mr.ram_block; - unsigned long first_zero_bit, last_zero_bit; - uint64_t offset, length; - int ret; - - /* Find consecutive unplugged blocks and discard the consecutive range. */ - first_zero_bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size); - while (first_zero_bit < vmem->bitmap_size) { - offset = first_zero_bit * vmem->block_size; - last_zero_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, - first_zero_bit + 1) - 1; - length = (last_zero_bit - first_zero_bit + 1) * vmem->block_size; - - ret = ram_block_discard_range(rb, offset, length); - if (ret) { - error_report("Unexpected error discarding RAM: %s", - strerror(-ret)); - return -EINVAL; - } - first_zero_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, - last_zero_bit + 2); - } - return 0; + /* Make sure all memory is really discarded after migration. */ + return virtio_mem_for_each_unplugged_range(vmem, NULL, + virtio_mem_discard_range_cb); } static int virtio_mem_post_load(void *opaque, int version_id) { + VirtIOMEM *vmem = VIRTIO_MEM(opaque); + RamDiscardListener *rdl; + int ret; + + /* + * We started out with all memory discarded and our memory region is mapped + * into an address space. Replay, now that we updated the bitmap. + */ + QLIST_FOREACH(rdl, &vmem->rdl_list, next) { + ret = virtio_mem_for_each_plugged_section(vmem, rdl->section, rdl, + virtio_mem_notify_populate_cb); + if (ret) { + return ret; + } + } + if (migration_in_incoming_postcopy()) { return 0; } - return virtio_mem_restore_unplugged(VIRTIO_MEM(opaque)); + return virtio_mem_restore_unplugged(vmem); } typedef struct VirtIOMEMMigSanityChecks { @@ -702,6 +886,7 @@ static const VMStateDescription vmstate_virtio_mem_device = { .name = "virtio-mem-device", .minimum_version_id = 1, .version_id = 1, + .priority = MIG_PRI_VIRTIO_MEM, .post_load = virtio_mem_post_load, .fields = (VMStateField[]) { VMSTATE_WITH_TMP(VirtIOMEM, VirtIOMEMMigSanityChecks, @@ -872,28 +1057,19 @@ static void virtio_mem_set_block_size(Object *obj, Visitor *v, const char *name, vmem->block_size = value; } -static void virtio_mem_precopy_exclude_unplugged(VirtIOMEM *vmem) +static int virtio_mem_precopy_exclude_range_cb(const VirtIOMEM *vmem, void *arg, + uint64_t offset, uint64_t size) { void * const host = qemu_ram_get_host_addr(vmem->memdev->mr.ram_block); - unsigned long first_zero_bit, last_zero_bit; - uint64_t offset, length; - /* - * Find consecutive unplugged blocks and exclude them from migration. - * - * Note: Blocks cannot get (un)plugged during precopy, no locking needed. - */ - first_zero_bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size); - while (first_zero_bit < vmem->bitmap_size) { - offset = first_zero_bit * vmem->block_size; - last_zero_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, - first_zero_bit + 1) - 1; - length = (last_zero_bit - first_zero_bit + 1) * vmem->block_size; + qemu_guest_free_page_hint(host + offset, size); + return 0; +} - qemu_guest_free_page_hint(host + offset, length); - first_zero_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, - last_zero_bit + 2); - } +static void virtio_mem_precopy_exclude_unplugged(VirtIOMEM *vmem) +{ + virtio_mem_for_each_unplugged_range(vmem, NULL, + virtio_mem_precopy_exclude_range_cb); } static int virtio_mem_precopy_notify(NotifierWithReturn *n, void *data) @@ -902,9 +1078,6 @@ static int virtio_mem_precopy_notify(NotifierWithReturn *n, void *data) PrecopyNotifyData *pnd = data; switch (pnd->reason) { - case PRECOPY_NOTIFY_SETUP: - precopy_enable_free_page_optimization(); - break; case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC: virtio_mem_precopy_exclude_unplugged(vmem); break; @@ -921,6 +1094,7 @@ static void virtio_mem_instance_init(Object *obj) notifier_list_init(&vmem->size_change_notifiers); vmem->precopy_notifier.notify = virtio_mem_precopy_notify; + QLIST_INIT(&vmem->rdl_list); object_property_add(obj, VIRTIO_MEM_SIZE_PROP, "size", virtio_mem_get_size, NULL, NULL, NULL); @@ -940,11 +1114,107 @@ static Property virtio_mem_properties[] = { DEFINE_PROP_END_OF_LIST(), }; +static uint64_t virtio_mem_rdm_get_min_granularity(const RamDiscardManager *rdm, + const MemoryRegion *mr) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(rdm); + + g_assert(mr == &vmem->memdev->mr); + return vmem->block_size; +} + +static bool virtio_mem_rdm_is_populated(const RamDiscardManager *rdm, + const MemoryRegionSection *s) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(rdm); + uint64_t start_gpa = vmem->addr + s->offset_within_region; + uint64_t end_gpa = start_gpa + int128_get64(s->size); + + g_assert(s->mr == &vmem->memdev->mr); + + start_gpa = QEMU_ALIGN_DOWN(start_gpa, vmem->block_size); + end_gpa = QEMU_ALIGN_UP(end_gpa, vmem->block_size); + + if (!virtio_mem_valid_range(vmem, start_gpa, end_gpa - start_gpa)) { + return false; + } + + return virtio_mem_test_bitmap(vmem, start_gpa, end_gpa - start_gpa, true); +} + +struct VirtIOMEMReplayData { + void *fn; + void *opaque; +}; + +static int virtio_mem_rdm_replay_populated_cb(MemoryRegionSection *s, void *arg) +{ + struct VirtIOMEMReplayData *data = arg; + + return ((ReplayRamPopulate)data->fn)(s, data->opaque); +} + +static int virtio_mem_rdm_replay_populated(const RamDiscardManager *rdm, + MemoryRegionSection *s, + ReplayRamPopulate replay_fn, + void *opaque) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(rdm); + struct VirtIOMEMReplayData data = { + .fn = replay_fn, + .opaque = opaque, + }; + + g_assert(s->mr == &vmem->memdev->mr); + return virtio_mem_for_each_plugged_section(vmem, s, &data, + virtio_mem_rdm_replay_populated_cb); +} + +static void virtio_mem_rdm_register_listener(RamDiscardManager *rdm, + RamDiscardListener *rdl, + MemoryRegionSection *s) +{ + VirtIOMEM *vmem = VIRTIO_MEM(rdm); + int ret; + + g_assert(s->mr == &vmem->memdev->mr); + rdl->section = memory_region_section_new_copy(s); + + QLIST_INSERT_HEAD(&vmem->rdl_list, rdl, next); + ret = virtio_mem_for_each_plugged_section(vmem, rdl->section, rdl, + virtio_mem_notify_populate_cb); + if (ret) { + error_report("%s: Replaying plugged ranges failed: %s", __func__, + strerror(-ret)); + } +} + +static void virtio_mem_rdm_unregister_listener(RamDiscardManager *rdm, + RamDiscardListener *rdl) +{ + VirtIOMEM *vmem = VIRTIO_MEM(rdm); + + g_assert(rdl->section->mr == &vmem->memdev->mr); + if (vmem->size) { + if (rdl->double_discard_supported) { + rdl->notify_discard(rdl, rdl->section); + } else { + virtio_mem_for_each_plugged_section(vmem, rdl->section, rdl, + virtio_mem_notify_discard_cb); + } + } + + memory_region_section_free_copy(rdl->section); + rdl->section = NULL; + QLIST_REMOVE(rdl, next); +} + static void virtio_mem_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); VirtIOMEMClass *vmc = VIRTIO_MEM_CLASS(klass); + RamDiscardManagerClass *rdmc = RAM_DISCARD_MANAGER_CLASS(klass); device_class_set_props(dc, virtio_mem_properties); dc->vmsd = &vmstate_virtio_mem; @@ -960,6 +1230,12 @@ static void virtio_mem_class_init(ObjectClass *klass, void *data) vmc->get_memory_region = virtio_mem_get_memory_region; vmc->add_size_change_notifier = virtio_mem_add_size_change_notifier; vmc->remove_size_change_notifier = virtio_mem_remove_size_change_notifier; + + rdmc->get_min_granularity = virtio_mem_rdm_get_min_granularity; + rdmc->is_populated = virtio_mem_rdm_is_populated; + rdmc->replay_populated = virtio_mem_rdm_replay_populated; + rdmc->register_listener = virtio_mem_rdm_register_listener; + rdmc->unregister_listener = virtio_mem_rdm_unregister_listener; } static const TypeInfo virtio_mem_info = { @@ -969,6 +1245,10 @@ static const TypeInfo virtio_mem_info = { .instance_init = virtio_mem_instance_init, .class_init = virtio_mem_class_init, .class_size = sizeof(VirtIOMEMClass), + .interfaces = (InterfaceInfo[]) { + { TYPE_RAM_DISCARD_MANAGER }, + { } + }, }; static void virtio_register_types(void) diff --git a/hw/virtio/virtio-mmio.c b/hw/virtio/virtio-mmio.c index 342c918ea7..1af48a1b04 100644 --- a/hw/virtio/virtio-mmio.c +++ b/hw/virtio/virtio-mmio.c @@ -29,6 +29,7 @@ #include "qemu/host-utils.h" #include "qemu/module.h" #include "sysemu/kvm.h" +#include "sysemu/replay.h" #include "hw/virtio/virtio-mmio.h" #include "qemu/error-report.h" #include "qemu/log.h" @@ -36,7 +37,9 @@ static bool virtio_mmio_ioeventfd_enabled(DeviceState *d) { - return kvm_eventfds_enabled(); + VirtIOMMIOProxy *proxy = VIRTIO_MMIO(d); + + return (proxy->flags & VIRTIO_IOMMIO_FLAG_USE_IOEVENTFD) != 0; } static int virtio_mmio_ioeventfd_assign(DeviceState *d, @@ -720,6 +723,8 @@ static Property virtio_mmio_properties[] = { DEFINE_PROP_BOOL("format_transport_address", VirtIOMMIOProxy, format_transport_address, true), DEFINE_PROP_BOOL("force-legacy", VirtIOMMIOProxy, legacy, true), + DEFINE_PROP_BIT("ioeventfd", VirtIOMMIOProxy, flags, + VIRTIO_IOMMIO_FLAG_USE_IOEVENTFD_BIT, true), DEFINE_PROP_END_OF_LIST(), }; @@ -731,6 +736,16 @@ static void virtio_mmio_realizefn(DeviceState *d, Error **errp) qbus_create_inplace(&proxy->bus, sizeof(proxy->bus), TYPE_VIRTIO_MMIO_BUS, d, NULL); sysbus_init_irq(sbd, &proxy->irq); + + if (!kvm_eventfds_enabled()) { + proxy->flags &= ~VIRTIO_IOMMIO_FLAG_USE_IOEVENTFD; + } + + /* fd-based ioevents can't be synchronized in record/replay */ + if (replay_mode != REPLAY_MODE_NONE) { + proxy->flags &= ~VIRTIO_IOMMIO_FLAG_USE_IOEVENTFD; + } + if (proxy->legacy) { memory_region_init_io(&proxy->iomem, OBJECT(d), &virtio_legacy_mem_ops, proxy, diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index b321604d9b..433060ac02 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -37,6 +37,7 @@ #include "qemu/range.h" #include "hw/virtio/virtio-bus.h" #include "qapi/visitor.h" +#include "sysemu/replay.h" #define VIRTIO_PCI_REGION_SIZE(dev) VIRTIO_PCI_CONFIG_OFF(msix_present(dev)) @@ -423,6 +424,11 @@ static uint64_t virtio_pci_config_read(void *opaque, hwaddr addr, VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus); uint32_t config = VIRTIO_PCI_CONFIG_SIZE(&proxy->pci_dev); uint64_t val = 0; + + if (vdev == NULL) { + return UINT64_MAX; + } + if (addr < config) { return virtio_ioport_read(proxy, addr); } @@ -454,6 +460,11 @@ static void virtio_pci_config_write(void *opaque, hwaddr addr, VirtIOPCIProxy *proxy = opaque; uint32_t config = VIRTIO_PCI_CONFIG_SIZE(&proxy->pci_dev); VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus); + + if (vdev == NULL) { + return; + } + if (addr < config) { virtio_ioport_write(proxy, addr, val); return; @@ -1146,6 +1157,10 @@ static uint64_t virtio_pci_common_read(void *opaque, hwaddr addr, uint32_t val = 0; int i; + if (vdev == NULL) { + return UINT64_MAX; + } + switch (addr) { case VIRTIO_PCI_COMMON_DFSELECT: val = proxy->dfselect; @@ -1229,6 +1244,10 @@ static void virtio_pci_common_write(void *opaque, hwaddr addr, VirtIOPCIProxy *proxy = opaque; VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus); + if (vdev == NULL) { + return; + } + switch (addr) { case VIRTIO_PCI_COMMON_DFSELECT: proxy->dfselect = val; @@ -1330,6 +1349,11 @@ static void virtio_pci_common_write(void *opaque, hwaddr addr, static uint64_t virtio_pci_notify_read(void *opaque, hwaddr addr, unsigned size) { + VirtIOPCIProxy *proxy = opaque; + if (virtio_bus_get_device(&proxy->bus) == NULL) { + return UINT64_MAX; + } + return 0; } @@ -1367,7 +1391,7 @@ static uint64_t virtio_pci_isr_read(void *opaque, hwaddr addr, uint64_t val; if (vdev == NULL) { - return 0; + return UINT64_MAX; } val = qatomic_xchg(&vdev->isr, 0); @@ -1388,7 +1412,7 @@ static uint64_t virtio_pci_device_read(void *opaque, hwaddr addr, uint64_t val; if (vdev == NULL) { - return 0; + return UINT64_MAX; } switch (size) { @@ -1760,6 +1784,11 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp) proxy->flags &= ~VIRTIO_PCI_FLAG_USE_IOEVENTFD; } + /* fd-based ioevents can't be synchronized in record/replay */ + if (replay_mode != REPLAY_MODE_NONE) { + proxy->flags &= ~VIRTIO_PCI_FLAG_USE_IOEVENTFD; + } + /* * virtio pci bar layout used by default. * subclasses can re-arrange things if needed. diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 07f4e60b30..874377f37a 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -15,7 +15,6 @@ #include "qapi/error.h" #include "cpu.h" #include "trace.h" -#include "exec/address-spaces.h" #include "qemu/error-report.h" #include "qemu/log.h" #include "qemu/main-loop.h" @@ -1973,9 +1972,7 @@ static enum virtio_device_endian virtio_default_endian(void) static enum virtio_device_endian virtio_current_cpu_endian(void) { - CPUClass *cc = CPU_GET_CLASS(current_cpu); - - if (cc->virtio_is_big_endian(current_cpu)) { + if (cpu_virtio_is_big_endian(current_cpu)) { return VIRTIO_DEVICE_ENDIAN_BIG; } else { return VIRTIO_DEVICE_ENDIAN_LITTLE; @@ -2450,6 +2447,7 @@ static void virtio_set_isr(VirtIODevice *vdev, int value) } } +/* Called within rcu_read_lock(). */ static bool virtio_split_should_notify(VirtIODevice *vdev, VirtQueue *vq) { uint16_t old, new; @@ -2486,6 +2484,7 @@ static bool vring_packed_need_event(VirtQueue *vq, bool wrap, return vring_need_event(off, new, old); } +/* Called within rcu_read_lock(). */ static bool virtio_packed_should_notify(VirtIODevice *vdev, VirtQueue *vq) { VRingPackedDescEvent e; @@ -2982,7 +2981,7 @@ int virtio_set_features(VirtIODevice *vdev, uint64_t val) return ret; } -size_t virtio_feature_get_config_size(VirtIOFeature *feature_sizes, +size_t virtio_feature_get_config_size(const VirtIOFeature *feature_sizes, uint64_t host_features) { size_t config_size = 0; @@ -3731,6 +3730,10 @@ static int virtio_device_start_ioeventfd_impl(VirtIODevice *vdev) VirtioBusState *qbus = VIRTIO_BUS(qdev_get_parent_bus(DEVICE(vdev))); int i, n, r, err; + /* + * Batch all the host notifiers in a single transaction to avoid + * quadratic time complexity in address_space_update_ioeventfds(). + */ memory_region_transaction_begin(); for (n = 0; n < VIRTIO_QUEUE_MAX; n++) { VirtQueue *vq = &vdev->vq[n]; @@ -3769,6 +3772,10 @@ assign_error: r = virtio_bus_set_host_notifier(qbus, n, false); assert(r >= 0); } + /* + * The transaction expects the ioeventfds to be open when it + * commits. Do it now, before the cleanup loop. + */ memory_region_transaction_commit(); while (--i >= 0) { @@ -3793,6 +3800,10 @@ static void virtio_device_stop_ioeventfd_impl(VirtIODevice *vdev) VirtioBusState *qbus = VIRTIO_BUS(qdev_get_parent_bus(DEVICE(vdev))); int n, r; + /* + * Batch all the host notifiers in a single transaction to avoid + * quadratic time complexity in address_space_update_ioeventfds(). + */ memory_region_transaction_begin(); for (n = 0; n < VIRTIO_QUEUE_MAX; n++) { VirtQueue *vq = &vdev->vq[n]; @@ -3804,6 +3815,10 @@ static void virtio_device_stop_ioeventfd_impl(VirtIODevice *vdev) r = virtio_bus_set_host_notifier(qbus, n, false); assert(r >= 0); } + /* + * The transaction expects the ioeventfds to be open when it + * commits. Do it now, before the cleanup loop. + */ memory_region_transaction_commit(); for (n = 0; n < VIRTIO_QUEUE_MAX; n++) { diff --git a/hw/watchdog/trace-events b/hw/watchdog/trace-events index 3124ca1f1b..c3bafbffa9 100644 --- a/hw/watchdog/trace-events +++ b/hw/watchdog/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # cmsdk-apb-watchdog.c cmsdk_apb_watchdog_read(uint64_t offset, uint64_t data, unsigned size) "CMSDK APB watchdog read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" diff --git a/hw/xen/trace-events b/hw/xen/trace-events index e6885bc751..3da3fd8348 100644 --- a/hw/xen/trace-events +++ b/hw/xen/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # ../../include/hw/xen/xen_common.h xen_default_ioreq_server(void) "" diff --git a/hw/xen/xen-bus-helper.c b/hw/xen/xen-bus-helper.c index b459bb9396..5a1e12b374 100644 --- a/hw/xen/xen-bus-helper.c +++ b/hw/xen/xen-bus-helper.c @@ -6,7 +6,6 @@ */ #include "qemu/osdep.h" -#include "hw/sysbus.h" #include "hw/xen/xen.h" #include "hw/xen/xen-bus.h" #include "hw/xen/xen-bus-helper.h" diff --git a/hw/xen/xen-legacy-backend.c b/hw/xen/xen-legacy-backend.c index b61a4855b7..dd8ae1452d 100644 --- a/hw/xen/xen-legacy-backend.c +++ b/hw/xen/xen-legacy-backend.c @@ -27,7 +27,6 @@ #include "hw/sysbus.h" #include "hw/boards.h" #include "hw/qdev-properties.h" -#include "qemu/log.h" #include "qemu/main-loop.h" #include "qapi/error.h" #include "hw/xen/xen-legacy-backend.h" diff --git a/hw/xen/xen_pt.c b/hw/xen/xen_pt.c index a513fdd62d..232482d65f 100644 --- a/hw/xen/xen_pt.c +++ b/hw/xen/xen_pt.c @@ -64,7 +64,6 @@ #include "hw/xen/xen-legacy-backend.h" #include "xen_pt.h" #include "qemu/range.h" -#include "exec/address-spaces.h" static bool has_igd_gfx_passthru; diff --git a/hw/xtensa/sim.c b/hw/xtensa/sim.c index cbac50db2d..2028fe793d 100644 --- a/hw/xtensa/sim.c +++ b/hw/xtensa/sim.c @@ -27,14 +27,12 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "sysemu/reset.h" #include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/loader.h" #include "elf.h" #include "exec/memory.h" -#include "exec/address-spaces.h" #include "qemu/error-report.h" #include "xtensa_memory.h" #include "xtensa_sim.h" diff --git a/hw/xtensa/virt.c b/hw/xtensa/virt.c index e47e1de676..a18e3fc910 100644 --- a/hw/xtensa/virt.c +++ b/hw/xtensa/virt.c @@ -27,16 +27,13 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "sysemu/reset.h" -#include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/loader.h" #include "hw/pci-host/gpex.h" #include "net/net.h" #include "elf.h" #include "exec/memory.h" -#include "exec/address-spaces.h" #include "qemu/error-report.h" #include "xtensa_memory.h" #include "xtensa_sim.h" diff --git a/hw/xtensa/xtensa_memory.c b/hw/xtensa/xtensa_memory.c index 1c5f62b014..2c1095f017 100644 --- a/hw/xtensa/xtensa_memory.c +++ b/hw/xtensa/xtensa_memory.c @@ -27,7 +27,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "cpu.h" #include "exec/memory.h" #include "qemu/error-report.h" #include "xtensa_memory.h" diff --git a/hw/xtensa/xtfpga.c b/hw/xtensa/xtfpga.c index 7be53f1895..17f087b395 100644 --- a/hw/xtensa/xtfpga.c +++ b/hw/xtensa/xtfpga.c @@ -35,7 +35,6 @@ #include "hw/qdev-properties.h" #include "elf.h" #include "exec/memory.h" -#include "exec/address-spaces.h" #include "hw/char/serial.h" #include "net/net.h" #include "hw/sysbus.h" diff --git a/include/block/aio.h b/include/block/aio.h index 5f342267d5..47fbe9d81f 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -232,6 +232,9 @@ struct AioContext { int64_t poll_grow; /* polling time growth factor */ int64_t poll_shrink; /* polling time shrink factor */ + /* AIO engine parameters */ + int64_t aio_max_batch; /* maximum number of requests in a batch */ + /* * List of handlers participating in userspace polling. Protected by * ctx->list_lock. Iterated and modified mostly by the event loop thread @@ -292,19 +295,44 @@ void aio_context_acquire(AioContext *ctx); void aio_context_release(AioContext *ctx); /** - * aio_bh_schedule_oneshot: Allocate a new bottom half structure that will run - * only once and as soon as possible. + * aio_bh_schedule_oneshot_full: Allocate a new bottom half structure that will + * run only once and as soon as possible. + * + * @name: A human-readable identifier for debugging purposes. */ -void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque); +void aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque, + const char *name); /** - * aio_bh_new: Allocate a new bottom half structure. + * aio_bh_schedule_oneshot: Allocate a new bottom half structure that will run + * only once and as soon as possible. + * + * A convenience wrapper for aio_bh_schedule_oneshot_full() that uses cb as the + * name string. + */ +#define aio_bh_schedule_oneshot(ctx, cb, opaque) \ + aio_bh_schedule_oneshot_full((ctx), (cb), (opaque), (stringify(cb))) + +/** + * aio_bh_new_full: Allocate a new bottom half structure. * * Bottom halves are lightweight callbacks whose invocation is guaranteed * to be wait-free, thread-safe and signal-safe. The #QEMUBH structure * is opaque and must be allocated prior to its use. + * + * @name: A human-readable identifier for debugging purposes. */ -QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque); +QEMUBH *aio_bh_new_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque, + const char *name); + +/** + * aio_bh_new: Allocate a new bottom half structure + * + * A convenience wrapper for aio_bh_new_full() that uses the cb as the name + * string. + */ +#define aio_bh_new(ctx, cb, opaque) \ + aio_bh_new_full((ctx), (cb), (opaque), (stringify(cb))) /** * aio_notify: Force processing of pending events. @@ -691,10 +719,13 @@ void aio_co_enter(AioContext *ctx, struct Coroutine *co); * Return the AioContext whose event loop runs in the current thread. * * If called from an IOThread this will be the IOThread's AioContext. If - * called from another thread it will be the main loop AioContext. + * called from the main thread or with the "big QEMU lock" taken it + * will be the main loop AioContext. */ AioContext *qemu_get_current_aio_context(void); +void qemu_set_current_aio_context(AioContext *ctx); + /** * aio_context_setup: * @ctx: the aio context @@ -727,4 +758,13 @@ void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns, int64_t grow, int64_t shrink, Error **errp); +/** + * aio_context_set_aio_params: + * @ctx: the aio context + * @max_batch: maximum number of requests in a batch, 0 means that the + * engine will use its default + */ +void aio_context_set_aio_params(AioContext *ctx, int64_t max_batch, + Error **errp); + #endif diff --git a/include/block/block-copy.h b/include/block/block-copy.h index 338f2ea7fd..5c8278895c 100644 --- a/include/block/block-copy.h +++ b/include/block/block-copy.h @@ -18,6 +18,8 @@ #include "block/block.h" #include "qemu/co-shared-resource.h" +/* All APIs are thread-safe */ + typedef void (*BlockCopyAsyncCallbackFunc)(void *opaque); typedef struct BlockCopyState BlockCopyState; typedef struct BlockCopyCallState BlockCopyCallState; diff --git a/include/block/block.h b/include/block/block.h index b3f6e509d4..3477290f9a 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -9,6 +9,7 @@ #include "block/dirty-bitmap.h" #include "block/blockjob.h" #include "qemu/hbitmap.h" +#include "qemu/transactions.h" /* * generated_co_wrapper @@ -101,6 +102,7 @@ typedef struct HDGeometry { uint32_t cylinders; } HDGeometry; +#define BDRV_O_NO_SHARE 0x0001 /* don't share permissions */ #define BDRV_O_RDWR 0x0002 #define BDRV_O_RESIZE 0x0004 /* request permission for resizing the node */ #define BDRV_O_SNAPSHOT 0x0008 /* open the file read only and save writes in a snapshot */ @@ -206,9 +208,8 @@ typedef struct BDRVReopenState { int flags; BlockdevDetectZeroesOptions detect_zeroes; bool backing_missing; - bool replace_backing_bs; /* new_backing_bs is ignored if this is false */ - BlockDriverState *new_backing_bs; /* If NULL then detach the current bs */ - uint64_t perm, shared_perm; + BlockDriverState *old_backing_bs; /* keep pointer for permissions update */ + BlockDriverState *old_file_bs; /* keep pointer for permissions update */ QDict *options; QDict *explicit_options; void *opaque; @@ -362,6 +363,7 @@ int bdrv_replace_node(BlockDriverState *from, BlockDriverState *to, Error **errp); BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *node_options, int flags, Error **errp); +int bdrv_drop_filter(BlockDriverState *bs, Error **errp); int bdrv_parse_aio(const char *mode, int *flags); int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough); @@ -384,13 +386,12 @@ BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name, BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, BlockDriverState *bs, QDict *options, bool keep_old_opts); +void bdrv_reopen_queue_free(BlockReopenQueue *bs_queue); int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp); +int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts, + Error **errp); int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only, Error **errp); -int bdrv_reopen_prepare(BDRVReopenState *reopen_state, - BlockReopenQueue *queue, Error **errp); -void bdrv_reopen_commit(BDRVReopenState *reopen_state); -void bdrv_reopen_abort(BDRVReopenState *reopen_state); int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, int64_t bytes, BdrvRequestFlags flags); int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags); @@ -424,7 +425,7 @@ int64_t bdrv_get_allocated_file_size(BlockDriverState *bs); BlockMeasureInfo *bdrv_measure(BlockDriver *drv, QemuOpts *opts, BlockDriverState *in_bs, Error **errp); void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr); -void bdrv_refresh_limits(BlockDriverState *bs, Error **errp); +void bdrv_refresh_limits(BlockDriverState *bs, Transaction *tran, Error **errp); int bdrv_commit(BlockDriverState *bs); int bdrv_make_empty(BdrvChild *c, Error **errp); int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file, @@ -702,6 +703,9 @@ bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx, GSList **ignore, Error **errp); bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx, GSList **ignore, Error **errp); +AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c); +AioContext *child_of_bds_get_parent_aio_context(BdrvChild *c); + int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz); int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo); diff --git a/include/block/block_int.h b/include/block/block_int.h index 88e4111939..f1a54db0f8 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -357,7 +357,7 @@ struct BlockDriver { * of in-flight requests, so don't waste the time if possible. * * One example usage is to avoid waiting for an nbd target node reconnect - * timeout during job-cancel. + * timeout during job-cancel with force=true. */ void (*bdrv_cancel_in_flight)(BlockDriverState *bs); @@ -695,6 +695,13 @@ typedef struct BlockLimits { * clamped down. */ uint32_t max_transfer; + /* Maximal hardware transfer length in bytes. Applies whenever + * transfers to the device bypass the kernel I/O scheduler, for + * example with SG_IO. If larger than max_transfer or if zero, + * blk_get_max_hw_transfer will fall back to max_transfer. + */ + uint64_t max_hw_transfer; + /* memory alignment, in bytes so that no bounce buffer is needed */ size_t min_mem_alignment; @@ -789,6 +796,8 @@ struct BdrvChildClass { bool (*can_set_aio_ctx)(BdrvChild *child, AioContext *ctx, GSList **ignore, Error **errp); void (*set_aio_ctx)(BdrvChild *child, AioContext *ctx, GSList **ignore); + + AioContext *(*get_parent_aio_context)(BdrvChild *child); }; extern const BdrvChildClass child_of_bds; @@ -811,11 +820,6 @@ struct BdrvChild { */ uint64_t shared_perm; - /* backup of permissions during permission update procedure */ - bool has_backup_perm; - uint64_t backup_perm; - uint64_t backup_shared_perm; - /* * This link is frozen: the child can neither be replaced nor * detached from the parent. @@ -846,7 +850,6 @@ struct BlockDriverState { * locking needed during I/O... */ int open_flags; /* flags used to open the file, re-used for re-open */ - bool read_only; /* if true, the media is read only */ bool encrypted; /* if true, the media is encrypted */ bool sg; /* if true, the device is a /dev/sg* */ bool probed; /* if true, format was probed rather than specified */ @@ -957,12 +960,8 @@ struct BlockDriverState { */ int64_t total_sectors; - /* Callback before write request is processed */ - NotifierWithReturnList before_write_notifiers; - /* threshold limit for writes, in bytes. "High water mark". */ uint64_t write_threshold_offset; - NotifierWithReturn write_threshold_notifier; /* Writing to the list requires the BQL _and_ the dirty_bitmap_mutex. * Reading from the list can be done with either the BQL or the @@ -1015,7 +1014,6 @@ struct BlockDriverState { struct BlockBackendRootState { int open_flags; - bool read_only; BlockdevDetectZeroesOptions detect_zeroes; }; @@ -1087,15 +1085,6 @@ void bdrv_parse_filename_strip_prefix(const char *filename, const char *prefix, bool bdrv_backing_overridden(BlockDriverState *bs); -/** - * bdrv_add_before_write_notifier: - * - * Register a callback that is invoked before write requests are processed but - * after any throttling or waiting for overlapping requests. - */ -void bdrv_add_before_write_notifier(BlockDriverState *bs, - NotifierWithReturn *notifier); - /** * bdrv_add_aio_context_notifier: * @@ -1306,7 +1295,6 @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, const char *child_name, const BdrvChildClass *child_class, BdrvChildRole child_role, - AioContext *ctx, uint64_t perm, uint64_t shared_perm, void *opaque, Error **errp); void bdrv_root_unref_child(BdrvChild *child); diff --git a/include/block/nbd.h b/include/block/nbd.h index 5f34d23bb0..78d101b774 100644 --- a/include/block/nbd.h +++ b/include/block/nbd.h @@ -406,4 +406,22 @@ const char *nbd_info_lookup(uint16_t info); const char *nbd_cmd_lookup(uint16_t info); const char *nbd_err_lookup(int err); +/* nbd/client-connection.c */ +typedef struct NBDClientConnection NBDClientConnection; + +void nbd_client_connection_enable_retry(NBDClientConnection *conn); + +NBDClientConnection *nbd_client_connection_new(const SocketAddress *saddr, + bool do_negotiation, + const char *export_name, + const char *x_dirty_bitmap, + QCryptoTLSCreds *tlscreds); +void nbd_client_connection_release(NBDClientConnection *conn); + +QIOChannel *coroutine_fn +nbd_co_establish_connection(NBDClientConnection *conn, NBDExportInfo *info, + bool blocking, Error **errp); + +void coroutine_fn nbd_co_establish_connection_cancel(NBDClientConnection *conn); + #endif diff --git a/include/block/nvme.h b/include/block/nvme.h index 4ac926fbc6..77aae01174 100644 --- a/include/block/nvme.h +++ b/include/block/nvme.h @@ -7,9 +7,9 @@ typedef struct QEMU_PACKED NvmeBar { uint32_t intms; uint32_t intmc; uint32_t cc; - uint32_t rsvd1; + uint8_t rsvd24[4]; uint32_t csts; - uint32_t nssrc; + uint32_t nssr; uint32_t aqa; uint64_t asq; uint64_t acq; @@ -26,10 +26,38 @@ typedef struct QEMU_PACKED NvmeBar { uint32_t pmrsts; uint32_t pmrebs; uint32_t pmrswtp; - uint64_t pmrmsc; + uint32_t pmrmscl; + uint32_t pmrmscu; uint8_t css[484]; } NvmeBar; +enum NvmeBarRegs { + NVME_REG_CAP = offsetof(NvmeBar, cap), + NVME_REG_VS = offsetof(NvmeBar, vs), + NVME_REG_INTMS = offsetof(NvmeBar, intms), + NVME_REG_INTMC = offsetof(NvmeBar, intmc), + NVME_REG_CC = offsetof(NvmeBar, cc), + NVME_REG_CSTS = offsetof(NvmeBar, csts), + NVME_REG_NSSR = offsetof(NvmeBar, nssr), + NVME_REG_AQA = offsetof(NvmeBar, aqa), + NVME_REG_ASQ = offsetof(NvmeBar, asq), + NVME_REG_ACQ = offsetof(NvmeBar, acq), + NVME_REG_CMBLOC = offsetof(NvmeBar, cmbloc), + NVME_REG_CMBSZ = offsetof(NvmeBar, cmbsz), + NVME_REG_BPINFO = offsetof(NvmeBar, bpinfo), + NVME_REG_BPRSEL = offsetof(NvmeBar, bprsel), + NVME_REG_BPMBL = offsetof(NvmeBar, bpmbl), + NVME_REG_CMBMSC = offsetof(NvmeBar, cmbmsc), + NVME_REG_CMBSTS = offsetof(NvmeBar, cmbsts), + NVME_REG_PMRCAP = offsetof(NvmeBar, pmrcap), + NVME_REG_PMRCTL = offsetof(NvmeBar, pmrctl), + NVME_REG_PMRSTS = offsetof(NvmeBar, pmrsts), + NVME_REG_PMREBS = offsetof(NvmeBar, pmrebs), + NVME_REG_PMRSWTP = offsetof(NvmeBar, pmrswtp), + NVME_REG_PMRMSCL = offsetof(NvmeBar, pmrmscl), + NVME_REG_PMRMSCU = offsetof(NvmeBar, pmrmscu), +}; + enum NvmeCapShift { CAP_MQES_SHIFT = 0, CAP_CQR_SHIFT = 16, @@ -475,25 +503,25 @@ enum NvmePmrswtpMask { #define NVME_PMRSWTP_SET_PMRSWTV(pmrswtp, val) \ (pmrswtp |= (uint64_t)(val & PMRSWTP_PMRSWTV_MASK) << PMRSWTP_PMRSWTV_SHIFT) -enum NvmePmrmscShift { - PMRMSC_CMSE_SHIFT = 1, - PMRMSC_CBA_SHIFT = 12, +enum NvmePmrmsclShift { + PMRMSCL_CMSE_SHIFT = 1, + PMRMSCL_CBA_SHIFT = 12, }; -enum NvmePmrmscMask { - PMRMSC_CMSE_MASK = 0x1, - PMRMSC_CBA_MASK = 0xfffffffffffff, +enum NvmePmrmsclMask { + PMRMSCL_CMSE_MASK = 0x1, + PMRMSCL_CBA_MASK = 0xfffff, }; -#define NVME_PMRMSC_CMSE(pmrmsc) \ - ((pmrmsc >> PMRMSC_CMSE_SHIFT) & PMRMSC_CMSE_MASK) -#define NVME_PMRMSC_CBA(pmrmsc) \ - ((pmrmsc >> PMRMSC_CBA_SHIFT) & PMRMSC_CBA_MASK) +#define NVME_PMRMSCL_CMSE(pmrmscl) \ + ((pmrmscl >> PMRMSCL_CMSE_SHIFT) & PMRMSCL_CMSE_MASK) +#define NVME_PMRMSCL_CBA(pmrmscl) \ + ((pmrmscl >> PMRMSCL_CBA_SHIFT) & PMRMSCL_CBA_MASK) -#define NVME_PMRMSC_SET_CMSE(pmrmsc, val) \ - (pmrmsc |= (uint64_t)(val & PMRMSC_CMSE_MASK) << PMRMSC_CMSE_SHIFT) -#define NVME_PMRMSC_SET_CBA(pmrmsc, val) \ - (pmrmsc |= (uint64_t)(val & PMRMSC_CBA_MASK) << PMRMSC_CBA_SHIFT) +#define NVME_PMRMSCL_SET_CMSE(pmrmscl, val) \ + (pmrmscl |= (uint32_t)(val & PMRMSCL_CMSE_MASK) << PMRMSCL_CMSE_SHIFT) +#define NVME_PMRMSCL_SET_CBA(pmrmscl, val) \ + (pmrmscl |= (uint32_t)(val & PMRMSCL_CBA_MASK) << PMRMSCL_CBA_SHIFT) enum NvmeSglDescriptorType { NVME_SGL_DESCR_TYPE_DATA_BLOCK = 0x0, @@ -708,6 +736,14 @@ enum { #define NVME_RW_PRINFO(control) ((control >> 10) & 0xf) +enum { + NVME_PRINFO_PRACT = 1 << 3, + NVME_PRINFO_PRCHK_GUARD = 1 << 2, + NVME_PRINFO_PRCHK_APP = 1 << 1, + NVME_PRINFO_PRCHK_REF = 1 << 0, + NVME_PRINFO_PRCHK_MASK = 7 << 0, +}; + typedef struct QEMU_PACKED NvmeDsmCmd { uint8_t opcode; uint8_t flags; @@ -848,8 +884,8 @@ enum NvmeStatusCodes { NVME_FW_REQ_SUSYSTEM_RESET = 0x0110, NVME_NS_ALREADY_ATTACHED = 0x0118, NVME_NS_PRIVATE = 0x0119, - NVME_NS_NOT_ATTACHED = 0x011A, - NVME_NS_CTRL_LIST_INVALID = 0x011C, + NVME_NS_NOT_ATTACHED = 0x011a, + NVME_NS_CTRL_LIST_INVALID = 0x011c, NVME_CONFLICTING_ATTRS = 0x0180, NVME_INVALID_PROT_INFO = 0x0181, NVME_WRITE_TO_RO = 0x0182, @@ -980,6 +1016,7 @@ enum NvmeIdCns { NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_NS_ATTACHED_CTRL_LIST = 0x12, + NVME_ID_CNS_CTRL_LIST = 0x13, NVME_ID_CNS_CS_NS_PRESENT_LIST = 0x1a, NVME_ID_CNS_CS_NS_PRESENT = 0x1b, NVME_ID_CNS_IO_COMMAND_SET = 0x1c, @@ -1341,6 +1378,15 @@ enum NvmeIdNsDps { NVME_ID_NS_DPS_FIRST_EIGHT = 8, }; +enum NvmeIdNsFlbas { + NVME_ID_NS_FLBAS_EXTENDED = 1 << 4, +}; + +enum NvmeIdNsMc { + NVME_ID_NS_MC_EXTENDED = 1 << 0, + NVME_ID_NS_MC_SEPARATE = 1 << 1, +}; + #define NVME_ID_NS_DPS_TYPE(dps) (dps & NVME_ID_NS_DPS_TYPE_MASK) typedef struct NvmeDifTuple { @@ -1409,9 +1455,9 @@ typedef enum NvmeZoneState { NVME_ZONE_STATE_IMPLICITLY_OPEN = 0x02, NVME_ZONE_STATE_EXPLICITLY_OPEN = 0x03, NVME_ZONE_STATE_CLOSED = 0x04, - NVME_ZONE_STATE_READ_ONLY = 0x0D, - NVME_ZONE_STATE_FULL = 0x0E, - NVME_ZONE_STATE_OFFLINE = 0x0F, + NVME_ZONE_STATE_READ_ONLY = 0x0d, + NVME_ZONE_STATE_FULL = 0x0e, + NVME_ZONE_STATE_OFFLINE = 0x0f, } NvmeZoneState; static inline void _nvme_check_size(void) diff --git a/include/block/qdict.h b/include/block/qdict.h index d8cb502d7d..ced2acfb92 100644 --- a/include/block/qdict.h +++ b/include/block/qdict.h @@ -20,8 +20,6 @@ void qdict_join(QDict *dest, QDict *src, bool overwrite); void qdict_extract_subqdict(QDict *src, QDict **dst, const char *start); void qdict_array_split(QDict *src, QList **dst); int qdict_array_entries(QDict *src, const char *subqdict); -QObject *qdict_crumple(const QDict *src, Error **errp); -void qdict_flatten(QDict *qdict); typedef struct QDictRenames { const char *from; diff --git a/replication.h b/include/block/replication.h similarity index 98% rename from replication.h rename to include/block/replication.h index d49fc22cb9..21931b4f0c 100644 --- a/replication.h +++ b/include/block/replication.h @@ -23,7 +23,7 @@ typedef struct ReplicationOps ReplicationOps; typedef struct ReplicationState ReplicationState; /** - * SECTION:replication.h + * SECTION:block/replication.h * @title:Base Replication System * @short_description: interfaces for handling replication * @@ -32,7 +32,7 @@ typedef struct ReplicationState ReplicationState; * * How to use replication interfaces * - * #include "replication.h" + * #include "block/replication.h" * * typedef struct BDRVReplicationState { * ReplicationState *rs; diff --git a/include/block/write-threshold.h b/include/block/write-threshold.h index c646f267a4..f50f923e7e 100644 --- a/include/block/write-threshold.h +++ b/include/block/write-threshold.h @@ -13,7 +13,7 @@ #ifndef BLOCK_WRITE_THRESHOLD_H #define BLOCK_WRITE_THRESHOLD_H -#include "block/block_int.h" +#include "qemu/typedefs.h" /* * bdrv_write_threshold_set: @@ -36,27 +36,12 @@ void bdrv_write_threshold_set(BlockDriverState *bs, uint64_t threshold_bytes); uint64_t bdrv_write_threshold_get(const BlockDriverState *bs); /* - * bdrv_write_threshold_is_set + * bdrv_write_threshold_check_write * - * Tell if a write threshold is set for a given BDS. + * Check whether the specified request exceeds the write threshold. + * If so, send a corresponding event and disable write threshold checking. */ -bool bdrv_write_threshold_is_set(const BlockDriverState *bs); - -/* - * bdrv_write_threshold_exceeded - * - * Return the extent of a write request that exceeded the threshold, - * or zero if the request is below the threshold. - * Return zero also if the threshold was not set. - * - * NOTE: here we assume the following holds for each request this code - * deals with: - * - * assert((req->offset + req->bytes) <= UINT64_MAX) - * - * Please not there is *not* an actual C assert(). - */ -uint64_t bdrv_write_threshold_exceeded(const BlockDriverState *bs, - const BdrvTrackedRequest *req); +void bdrv_write_threshold_check_write(BlockDriverState *bs, int64_t offset, + int64_t bytes); #endif diff --git a/include/chardev/char-fe.h b/include/chardev/char-fe.h index a553843364..867ef1b3b2 100644 --- a/include/chardev/char-fe.h +++ b/include/chardev/char-fe.h @@ -174,6 +174,9 @@ void qemu_chr_fe_set_open(CharBackend *be, int fe_open); void qemu_chr_fe_printf(CharBackend *be, const char *fmt, ...) GCC_FMT_ATTR(2, 3); + +typedef gboolean (*FEWatchFunc)(void *do_not_use, GIOCondition condition, void *data); + /** * qemu_chr_fe_add_watch: * @cond: the condition to poll for @@ -188,10 +191,13 @@ void qemu_chr_fe_printf(CharBackend *be, const char *fmt, ...) * Note that you are responsible to update the front-end sources if * you are switching the main context with qemu_chr_fe_set_handlers(). * + * Warning: DO NOT use the first callback argument (it may be either + * a GIOChannel or a QIOChannel, depending on the underlying chardev) + * * Returns: the source tag */ guint qemu_chr_fe_add_watch(CharBackend *be, GIOCondition cond, - GIOFunc func, void *user_data); + FEWatchFunc func, void *user_data); /** * qemu_chr_fe_write: diff --git a/include/crypto/tls-cipher-suites.h b/include/crypto/tls-cipher-suites.h index bb9ee53e03..7eb1b76122 100644 --- a/include/crypto/tls-cipher-suites.h +++ b/include/crypto/tls-cipher-suites.h @@ -19,12 +19,6 @@ typedef struct QCryptoTLSCipherSuites QCryptoTLSCipherSuites; DECLARE_INSTANCE_CHECKER(QCryptoTLSCipherSuites, QCRYPTO_TLS_CIPHER_SUITES, TYPE_QCRYPTO_TLS_CIPHER_SUITES) -struct QCryptoTLSCipherSuites { - /* */ - QCryptoTLSCreds parent_obj; - /* */ -}; - /** * qcrypto_tls_cipher_suites_get_data: * @obj: pointer to a TLS cipher suites object diff --git a/include/crypto/tlscreds.h b/include/crypto/tlscreds.h index d0808e391e..2a8a857010 100644 --- a/include/crypto/tlscreds.h +++ b/include/crypto/tlscreds.h @@ -24,10 +24,6 @@ #include "qapi/qapi-types-crypto.h" #include "qom/object.h" -#ifdef CONFIG_GNUTLS -#include -#endif - #define TYPE_QCRYPTO_TLS_CREDS "tls-creds" typedef struct QCryptoTLSCreds QCryptoTLSCreds; typedef struct QCryptoTLSCredsClass QCryptoTLSCredsClass; @@ -48,22 +44,24 @@ typedef bool (*CryptoTLSCredsReload)(QCryptoTLSCreds *, Error **); * certificate credentials. */ -struct QCryptoTLSCreds { - Object parent_obj; - char *dir; - QCryptoTLSCredsEndpoint endpoint; -#ifdef CONFIG_GNUTLS - gnutls_dh_params_t dh_params; -#endif - bool verifyPeer; - char *priority; -}; - - struct QCryptoTLSCredsClass { ObjectClass parent_class; CryptoTLSCredsReload reload; }; +/** + * qcrypto_tls_creds_check_endpoint: + * @creds: pointer to a TLS credentials object + * @endpoint: type of network endpoint that will be using the credentials + * @errp: pointer to a NULL-initialized error object + * + * Check whether the credentials is setup according to + * the type of @endpoint argument. + * + * Returns true if the credentials is setup for the endpoint, false otherwise + */ +bool qcrypto_tls_creds_check_endpoint(QCryptoTLSCreds *creds, + QCryptoTLSCredsEndpoint endpoint, + Error **errp); #endif /* QCRYPTO_TLSCREDS_H */ diff --git a/include/crypto/tlscredsanon.h b/include/crypto/tlscredsanon.h index 3f464a3809..bd3023f9ea 100644 --- a/include/crypto/tlscredsanon.h +++ b/include/crypto/tlscredsanon.h @@ -92,18 +92,6 @@ typedef struct QCryptoTLSCredsAnonClass QCryptoTLSCredsAnonClass; * */ - -struct QCryptoTLSCredsAnon { - QCryptoTLSCreds parent_obj; -#ifdef CONFIG_GNUTLS - union { - gnutls_anon_server_credentials_t server; - gnutls_anon_client_credentials_t client; - } data; -#endif -}; - - struct QCryptoTLSCredsAnonClass { QCryptoTLSCredsClass parent_class; }; diff --git a/include/crypto/tlscredspsk.h b/include/crypto/tlscredspsk.h index d7e6bdb5ed..bcd07dc4f6 100644 --- a/include/crypto/tlscredspsk.h +++ b/include/crypto/tlscredspsk.h @@ -87,18 +87,6 @@ typedef struct QCryptoTLSCredsPSKClass QCryptoTLSCredsPSKClass; * The PSK file can be created and managed using psktool. */ -struct QCryptoTLSCredsPSK { - QCryptoTLSCreds parent_obj; - char *username; -#ifdef CONFIG_GNUTLS - union { - gnutls_psk_server_credentials_t server; - gnutls_psk_client_credentials_t client; - } data; -#endif -}; - - struct QCryptoTLSCredsPSKClass { QCryptoTLSCredsClass parent_class; }; diff --git a/include/crypto/tlscredsx509.h b/include/crypto/tlscredsx509.h index c6d89b7881..c4daba21a6 100644 --- a/include/crypto/tlscredsx509.h +++ b/include/crypto/tlscredsx509.h @@ -96,16 +96,6 @@ typedef struct QCryptoTLSCredsX509Class QCryptoTLSCredsX509Class; * */ -struct QCryptoTLSCredsX509 { - QCryptoTLSCreds parent_obj; -#ifdef CONFIG_GNUTLS - gnutls_certificate_credentials_t data; -#endif - bool sanityCheck; - char *passwordid; -}; - - struct QCryptoTLSCredsX509Class { QCryptoTLSCredsClass parent_class; }; diff --git a/include/disas/dis-asm.h b/include/disas/dis-asm.h index 13fa1edd41..524f29196d 100644 --- a/include/disas/dis-asm.h +++ b/include/disas/dis-asm.h @@ -9,6 +9,12 @@ #ifndef DISAS_DIS_ASM_H #define DISAS_DIS_ASM_H +#include "qemu/bswap.h" + +#ifdef __cplusplus +extern "C" { +#endif + typedef void *PTR; typedef uint64_t bfd_vma; typedef int64_t bfd_signed_vma; @@ -243,8 +249,6 @@ enum bfd_architecture #define bfd_mach_nios2 0 #define bfd_mach_nios2r1 1 #define bfd_mach_nios2r2 2 - bfd_arch_lm32, /* Lattice Mico32 */ -#define bfd_mach_lm32 1 bfd_arch_rx, /* Renesas RX */ #define bfd_mach_rx 0x75 #define bfd_mach_rx_v2 0x76 @@ -437,7 +441,6 @@ int print_insn_m32r (bfd_vma, disassemble_info*); int print_insn_m88k (bfd_vma, disassemble_info*); int print_insn_mn10200 (bfd_vma, disassemble_info*); int print_insn_mn10300 (bfd_vma, disassemble_info*); -int print_insn_moxie (bfd_vma, disassemble_info*); int print_insn_ns32k (bfd_vma, disassemble_info*); int print_insn_big_powerpc (bfd_vma, disassemble_info*); int print_insn_little_powerpc (bfd_vma, disassemble_info*); @@ -452,7 +455,6 @@ int print_insn_crisv32 (bfd_vma, disassemble_info*); int print_insn_crisv10 (bfd_vma, disassemble_info*); int print_insn_microblaze (bfd_vma, disassemble_info*); int print_insn_ia64 (bfd_vma, disassemble_info*); -int print_insn_lm32 (bfd_vma, disassemble_info*); int print_insn_big_nios2 (bfd_vma, disassemble_info*); int print_insn_little_nios2 (bfd_vma, disassemble_info*); int print_insn_xtensa (bfd_vma, disassemble_info*); @@ -479,8 +481,6 @@ bool cap_disas_plugin(disassemble_info *info, uint64_t pc, size_t size); /* from libbfd */ -#include "qemu/bswap.h" - static inline bfd_vma bfd_getl64(const bfd_byte *addr) { return ldq_le_p(addr); @@ -508,4 +508,8 @@ static inline bfd_vma bfd_getb16(const bfd_byte *addr) typedef bool bfd_boolean; +#ifdef __cplusplus +} +#endif + #endif /* DISAS_DIS_ASM_H */ diff --git a/include/elf.h b/include/elf.h index 78237c9a87..811bf4a1cb 100644 --- a/include/elf.h +++ b/include/elf.h @@ -174,9 +174,8 @@ typedef struct mips_elf_abiflags_v0 { #define EM_OPENRISC 92 /* OpenCores OpenRISC */ -#define EM_UNICORE32 110 /* UniCore32 */ - #define EM_HEXAGON 164 /* Qualcomm Hexagon */ + #define EM_RX 173 /* Renesas RX family */ #define EM_RISCV 243 /* RISC-V */ @@ -206,9 +205,6 @@ typedef struct mips_elf_abiflags_v0 { #define EM_AARCH64 183 -#define EM_MOXIE 223 /* Moxie processor family */ -#define EM_MOXIE_OLD 0xFEED - #define EF_AVR_MACH 0x7F /* Mask for AVR e_flags to get core type */ /* This is the info that is needed to parse the dynamic section of the file */ @@ -609,6 +605,13 @@ typedef struct { #define HWCAP_S390_HIGH_GPRS 512 #define HWCAP_S390_TE 1024 #define HWCAP_S390_VXRS 2048 +#define HWCAP_S390_VXRS_BCD 4096 +#define HWCAP_S390_VXRS_EXT 8192 +#define HWCAP_S390_GS 16384 +#define HWCAP_S390_VXRS_EXT2 32768 +#define HWCAP_S390_VXRS_PDE 65536 +#define HWCAP_S390_SORT 131072 +#define HWCAP_S390_DFLT 262144 /* M68K specific definitions. */ /* We use the top 24 bits to encode information about the diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index 5a0a2d93e0..039d422bf4 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -57,7 +57,9 @@ const char *qemu_ram_get_idstr(RAMBlock *rb); void *qemu_ram_get_host_addr(RAMBlock *rb); ram_addr_t qemu_ram_get_offset(RAMBlock *rb); ram_addr_t qemu_ram_get_used_length(RAMBlock *rb); +ram_addr_t qemu_ram_get_max_length(RAMBlock *rb); bool qemu_ram_is_shared(RAMBlock *rb); +bool qemu_ram_is_noreserve(RAMBlock *rb); bool qemu_ram_is_uf_zeroable(RAMBlock *rb); void qemu_ram_set_uf_zeroable(RAMBlock *rb); bool qemu_ram_is_migratable(RAMBlock *rb); diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index 6b036cae8f..5d1b6d80fb 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -21,7 +21,6 @@ #define EXEC_ALL_H #include "cpu.h" -#include "exec/tb-context.h" #ifdef CONFIG_TCG #include "exec/cpu_ldst.h" #endif @@ -262,6 +261,31 @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr, void tlb_flush_page_bits_by_mmuidx_all_cpus_synced (CPUState *cpu, target_ulong addr, uint16_t idxmap, unsigned bits); +/** + * tlb_flush_range_by_mmuidx + * @cpu: CPU whose TLB should be flushed + * @addr: virtual address of the start of the range to be flushed + * @len: length of range to be flushed + * @idxmap: bitmap of mmu indexes to flush + * @bits: number of significant bits in address + * + * For each mmuidx in @idxmap, flush all pages within [@addr,@addr+@len), + * comparing only the low @bits worth of each virtual page. + */ +void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits); + +/* Similarly, with broadcast and syncing. */ +void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits); +void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, + target_ulong addr, + target_ulong len, + uint16_t idxmap, + unsigned bits); + /** * tlb_set_page_with_attrs: * @cpu: CPU to add this TLB entry for @@ -365,6 +389,25 @@ tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *cpu, target_ulong addr, uint16_t idxmap, unsigned bits) { } +static inline void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits) +{ +} +static inline void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, + target_ulong addr, + target_ulong len, + uint16_t idxmap, + unsigned bits) +{ +} +static inline void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, + target_ulong addr, + target_long len, + uint16_t idxmap, + unsigned bits) +{ +} #endif /** * probe_access: @@ -449,13 +492,18 @@ struct TranslationBlock { target_ulong cs_base; /* CS base for this block */ uint32_t flags; /* flags defining in which context the code was generated */ uint32_t cflags; /* compile flags */ -#define CF_COUNT_MASK 0x00007fff -#define CF_LAST_IO 0x00008000 /* Last insn may be an IO access. */ -#define CF_MEMI_ONLY 0x00010000 /* Only instrument memory ops */ -#define CF_USE_ICOUNT 0x00020000 -#define CF_INVALID 0x00040000 /* TB is stale. Set with @jmp_lock held */ -#define CF_PARALLEL 0x00080000 /* Generate code for a parallel context */ -#define CF_CLUSTER_MASK 0xff000000 /* Top 8 bits are cluster ID */ + +/* Note that TCG_MAX_INSNS is 512; we validate this match elsewhere. */ +#define CF_COUNT_MASK 0x000001ff +#define CF_NO_GOTO_TB 0x00000200 /* Do not chain with goto_tb */ +#define CF_NO_GOTO_PTR 0x00000400 /* Do not chain with goto_ptr */ +#define CF_SINGLE_STEP 0x00000800 /* gdbstub single-step in effect */ +#define CF_LAST_IO 0x00008000 /* Last insn may be an IO access. */ +#define CF_MEMI_ONLY 0x00010000 /* Only instrument memory ops */ +#define CF_USE_ICOUNT 0x00020000 +#define CF_INVALID 0x00040000 /* TB is stale. Set with @jmp_lock held */ +#define CF_PARALLEL 0x00080000 /* Generate code for a parallel context */ +#define CF_CLUSTER_MASK 0xff000000 /* Top 8 bits are cluster ID */ #define CF_CLUSTER_SHIFT 24 /* Per-vCPU dynamic tracing state used to generate this TB */ @@ -520,10 +568,7 @@ static inline uint32_t tb_cflags(const TranslationBlock *tb) } /* current cflags for hashing/comparison */ -static inline uint32_t curr_cflags(CPUState *cpu) -{ - return cpu->tcg_cflags; -} +uint32_t curr_cflags(CPUState *cpu); /* TranslationBlock invalidate API */ #if defined(CONFIG_USER_ONLY) diff --git a/include/exec/gen-icount.h b/include/exec/gen-icount.h index 298e01eef4..467529d84c 100644 --- a/include/exec/gen-icount.h +++ b/include/exec/gen-icount.h @@ -1,6 +1,7 @@ #ifndef GEN_ICOUNT_H #define GEN_ICOUNT_H +#include "exec/exec-all.h" #include "qemu/timer.h" /* Helpers for instruction counting code generation. */ diff --git a/include/exec/helper-gen.h b/include/exec/helper-gen.h index 29c02f85dc..1c2e7a8ed3 100644 --- a/include/exec/helper-gen.h +++ b/include/exec/helper-gen.h @@ -81,8 +81,8 @@ static inline void glue(gen_helper_, name)(dh_retvar_decl(ret) \ #include "helper.h" #include "trace/generated-helpers.h" #include "trace/generated-helpers-wrappers.h" -#include "tcg-runtime.h" -#include "plugin-helpers.h" +#include "accel/tcg/tcg-runtime.h" +#include "accel/tcg/plugin-helpers.h" #undef DEF_HELPER_FLAGS_0 #undef DEF_HELPER_FLAGS_1 diff --git a/include/exec/helper-head.h b/include/exec/helper-head.h index 3094c7946d..b974eb394a 100644 --- a/include/exec/helper-head.h +++ b/include/exec/helper-head.h @@ -85,32 +85,14 @@ #define dh_retvar_ptr tcgv_ptr_temp(retval) #define dh_retvar(t) glue(dh_retvar_, dh_alias(t)) -#define dh_is_64bit_void 0 -#define dh_is_64bit_noreturn 0 -#define dh_is_64bit_i32 0 -#define dh_is_64bit_i64 1 -#define dh_is_64bit_ptr (sizeof(void *) == 8) -#define dh_is_64bit_cptr dh_is_64bit_ptr -#define dh_is_64bit(t) glue(dh_is_64bit_, dh_alias(t)) - -#define dh_is_signed_void 0 -#define dh_is_signed_noreturn 0 -#define dh_is_signed_i32 0 -#define dh_is_signed_s32 1 -#define dh_is_signed_i64 0 -#define dh_is_signed_s64 1 -#define dh_is_signed_f16 0 -#define dh_is_signed_f32 0 -#define dh_is_signed_f64 0 -#define dh_is_signed_tl 0 -#define dh_is_signed_int 1 -/* ??? This is highly specific to the host cpu. There are even special - extension instructions that may be required, e.g. ia64's addp4. But - for now we don't support any 64-bit targets with 32-bit pointers. */ -#define dh_is_signed_ptr 0 -#define dh_is_signed_cptr dh_is_signed_ptr -#define dh_is_signed_env dh_is_signed_ptr -#define dh_is_signed(t) dh_is_signed_##t +#define dh_typecode_void 0 +#define dh_typecode_noreturn 0 +#define dh_typecode_i32 2 +#define dh_typecode_s32 3 +#define dh_typecode_i64 4 +#define dh_typecode_s64 5 +#define dh_typecode_ptr 6 +#define dh_typecode(t) glue(dh_typecode_, dh_alias(t)) #define dh_callflag_i32 0 #define dh_callflag_s32 0 @@ -126,8 +108,7 @@ #define dh_callflag_noreturn TCG_CALL_NO_RETURN #define dh_callflag(t) glue(dh_callflag_, dh_alias(t)) -#define dh_sizemask(t, n) \ - ((dh_is_64bit(t) << (n*2)) | (dh_is_signed(t) << (n*2+1))) +#define dh_typemask(t, n) (dh_typecode(t) << (n * 3)) #define dh_arg(t, n) \ glue(glue(tcgv_, dh_alias(t)), _temp)(glue(arg, n)) diff --git a/include/exec/helper-proto.h b/include/exec/helper-proto.h index 659f9298e8..ba100793a7 100644 --- a/include/exec/helper-proto.h +++ b/include/exec/helper-proto.h @@ -39,8 +39,8 @@ dh_ctype(ret) HELPER(name) (dh_ctype(t1), dh_ctype(t2), dh_ctype(t3), \ #include "helper.h" #include "trace/generated-helpers.h" -#include "tcg-runtime.h" -#include "plugin-helpers.h" +#include "accel/tcg/tcg-runtime.h" +#include "accel/tcg/plugin-helpers.h" #undef IN_HELPER_PROTO diff --git a/include/exec/helper-tcg.h b/include/exec/helper-tcg.h index 27870509a2..16cd318b83 100644 --- a/include/exec/helper-tcg.h +++ b/include/exec/helper-tcg.h @@ -13,55 +13,55 @@ #define DEF_HELPER_FLAGS_0(NAME, FLAGS, ret) \ { .func = HELPER(NAME), .name = str(NAME), \ .flags = FLAGS | dh_callflag(ret), \ - .sizemask = dh_sizemask(ret, 0) }, + .typemask = dh_typemask(ret, 0) }, #define DEF_HELPER_FLAGS_1(NAME, FLAGS, ret, t1) \ { .func = HELPER(NAME), .name = str(NAME), \ .flags = FLAGS | dh_callflag(ret), \ - .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) }, + .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) }, #define DEF_HELPER_FLAGS_2(NAME, FLAGS, ret, t1, t2) \ { .func = HELPER(NAME), .name = str(NAME), \ .flags = FLAGS | dh_callflag(ret), \ - .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) \ - | dh_sizemask(t2, 2) }, + .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ + | dh_typemask(t2, 2) }, #define DEF_HELPER_FLAGS_3(NAME, FLAGS, ret, t1, t2, t3) \ { .func = HELPER(NAME), .name = str(NAME), \ .flags = FLAGS | dh_callflag(ret), \ - .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) \ - | dh_sizemask(t2, 2) | dh_sizemask(t3, 3) }, + .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ + | dh_typemask(t2, 2) | dh_typemask(t3, 3) }, #define DEF_HELPER_FLAGS_4(NAME, FLAGS, ret, t1, t2, t3, t4) \ { .func = HELPER(NAME), .name = str(NAME), \ .flags = FLAGS | dh_callflag(ret), \ - .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) \ - | dh_sizemask(t2, 2) | dh_sizemask(t3, 3) | dh_sizemask(t4, 4) }, + .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ + | dh_typemask(t2, 2) | dh_typemask(t3, 3) | dh_typemask(t4, 4) }, #define DEF_HELPER_FLAGS_5(NAME, FLAGS, ret, t1, t2, t3, t4, t5) \ { .func = HELPER(NAME), .name = str(NAME), \ .flags = FLAGS | dh_callflag(ret), \ - .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) \ - | dh_sizemask(t2, 2) | dh_sizemask(t3, 3) | dh_sizemask(t4, 4) \ - | dh_sizemask(t5, 5) }, + .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ + | dh_typemask(t2, 2) | dh_typemask(t3, 3) | dh_typemask(t4, 4) \ + | dh_typemask(t5, 5) }, #define DEF_HELPER_FLAGS_6(NAME, FLAGS, ret, t1, t2, t3, t4, t5, t6) \ { .func = HELPER(NAME), .name = str(NAME), \ .flags = FLAGS | dh_callflag(ret), \ - .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) \ - | dh_sizemask(t2, 2) | dh_sizemask(t3, 3) | dh_sizemask(t4, 4) \ - | dh_sizemask(t5, 5) | dh_sizemask(t6, 6) }, + .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ + | dh_typemask(t2, 2) | dh_typemask(t3, 3) | dh_typemask(t4, 4) \ + | dh_typemask(t5, 5) | dh_typemask(t6, 6) }, #define DEF_HELPER_FLAGS_7(NAME, FLAGS, ret, t1, t2, t3, t4, t5, t6, t7) \ { .func = HELPER(NAME), .name = str(NAME), .flags = FLAGS, \ - .sizemask = dh_sizemask(ret, 0) | dh_sizemask(t1, 1) \ - | dh_sizemask(t2, 2) | dh_sizemask(t3, 3) | dh_sizemask(t4, 4) \ - | dh_sizemask(t5, 5) | dh_sizemask(t6, 6) | dh_sizemask(t7, 7) }, + .typemask = dh_typemask(ret, 0) | dh_typemask(t1, 1) \ + | dh_typemask(t2, 2) | dh_typemask(t3, 3) | dh_typemask(t4, 4) \ + | dh_typemask(t5, 5) | dh_typemask(t6, 6) | dh_typemask(t7, 7) }, #include "helper.h" #include "trace/generated-helpers.h" -#include "tcg-runtime.h" -#include "plugin-helpers.h" +#include "accel/tcg/tcg-runtime.h" +#include "accel/tcg/plugin-helpers.h" #undef str #undef DEF_HELPER_FLAGS_0 diff --git a/include/exec/memory.h b/include/exec/memory.h index 71257b942f..ad2509087d 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -42,6 +42,12 @@ typedef struct IOMMUMemoryRegionClass IOMMUMemoryRegionClass; DECLARE_OBJ_CHECKERS(IOMMUMemoryRegion, IOMMUMemoryRegionClass, IOMMU_MEMORY_REGION, TYPE_IOMMU_MEMORY_REGION) +#define TYPE_RAM_DISCARD_MANAGER "qemu:ram-discard-manager" +typedef struct RamDiscardManagerClass RamDiscardManagerClass; +typedef struct RamDiscardManager RamDiscardManager; +DECLARE_OBJ_CHECKERS(RamDiscardManager, RamDiscardManagerClass, + RAM_DISCARD_MANAGER, TYPE_RAM_DISCARD_MANAGER); + #ifdef CONFIG_FUZZ void fuzz_dma_read_cb(size_t addr, size_t len, @@ -65,6 +71,28 @@ struct ReservedRegion { unsigned type; }; +/** + * struct MemoryRegionSection: describes a fragment of a #MemoryRegion + * + * @mr: the region, or %NULL if empty + * @fv: the flat view of the address space the region is mapped in + * @offset_within_region: the beginning of the section, relative to @mr's start + * @size: the size of the section; will not exceed @mr's boundaries + * @offset_within_address_space: the address of the first byte of the section + * relative to the region's address space + * @readonly: writes to this section are ignored + * @nonvolatile: this section is non-volatile + */ +struct MemoryRegionSection { + Int128 size; + MemoryRegion *mr; + FlatView *fv; + hwaddr offset_within_region; + hwaddr offset_within_address_space; + bool readonly; + bool nonvolatile; +}; + typedef struct IOMMUTLBEntry IOMMUTLBEntry; /* See address_space_translate: bit 0 is read, bit 1 is write. */ @@ -131,7 +159,7 @@ typedef struct IOMMUTLBEvent { #define RAM_SHARED (1 << 1) /* Only a portion of RAM (used_length) is actually used, and migrated. - * This used_length size can change across reboots. + * Resizing RAM while migrating can result in the migration being canceled. */ #define RAM_RESIZEABLE (1 << 2) @@ -155,6 +183,13 @@ typedef struct IOMMUTLBEvent { */ #define RAM_UF_WRITEPROTECT (1 << 6) +/* + * RAM is mmap-ed with MAP_NORESERVE. When set, reserving swap space (or huge + * pages if applicable) is skipped: will bail out if not supported. When not + * set, the OS will do the reservation, if supported for the memory type. + */ +#define RAM_NORESERVE (1 << 7) + static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn, IOMMUNotifierFlag flags, hwaddr start, hwaddr end, @@ -441,6 +476,206 @@ struct IOMMUMemoryRegionClass { Error **errp); }; +typedef struct RamDiscardListener RamDiscardListener; +typedef int (*NotifyRamPopulate)(RamDiscardListener *rdl, + MemoryRegionSection *section); +typedef void (*NotifyRamDiscard)(RamDiscardListener *rdl, + MemoryRegionSection *section); + +struct RamDiscardListener { + /* + * @notify_populate: + * + * Notification that previously discarded memory is about to get populated. + * Listeners are able to object. If any listener objects, already + * successfully notified listeners are notified about a discard again. + * + * @rdl: the #RamDiscardListener getting notified + * @section: the #MemoryRegionSection to get populated. The section + * is aligned within the memory region to the minimum granularity + * unless it would exceed the registered section. + * + * Returns 0 on success. If the notification is rejected by the listener, + * an error is returned. + */ + NotifyRamPopulate notify_populate; + + /* + * @notify_discard: + * + * Notification that previously populated memory was discarded successfully + * and listeners should drop all references to such memory and prevent + * new population (e.g., unmap). + * + * @rdl: the #RamDiscardListener getting notified + * @section: the #MemoryRegionSection to get populated. The section + * is aligned within the memory region to the minimum granularity + * unless it would exceed the registered section. + */ + NotifyRamDiscard notify_discard; + + /* + * @double_discard_supported: + * + * The listener suppors getting @notify_discard notifications that span + * already discarded parts. + */ + bool double_discard_supported; + + MemoryRegionSection *section; + QLIST_ENTRY(RamDiscardListener) next; +}; + +static inline void ram_discard_listener_init(RamDiscardListener *rdl, + NotifyRamPopulate populate_fn, + NotifyRamDiscard discard_fn, + bool double_discard_supported) +{ + rdl->notify_populate = populate_fn; + rdl->notify_discard = discard_fn; + rdl->double_discard_supported = double_discard_supported; +} + +typedef int (*ReplayRamPopulate)(MemoryRegionSection *section, void *opaque); + +/* + * RamDiscardManagerClass: + * + * A #RamDiscardManager coordinates which parts of specific RAM #MemoryRegion + * regions are currently populated to be used/accessed by the VM, notifying + * after parts were discarded (freeing up memory) and before parts will be + * populated (consuming memory), to be used/acessed by the VM. + * + * A #RamDiscardManager can only be set for a RAM #MemoryRegion while the + * #MemoryRegion isn't mapped yet; it cannot change while the #MemoryRegion is + * mapped. + * + * The #RamDiscardManager is intended to be used by technologies that are + * incompatible with discarding of RAM (e.g., VFIO, which may pin all + * memory inside a #MemoryRegion), and require proper coordination to only + * map the currently populated parts, to hinder parts that are expected to + * remain discarded from silently getting populated and consuming memory. + * Technologies that support discarding of RAM don't have to bother and can + * simply map the whole #MemoryRegion. + * + * An example #RamDiscardManager is virtio-mem, which logically (un)plugs + * memory within an assigned RAM #MemoryRegion, coordinated with the VM. + * Logically unplugging memory consists of discarding RAM. The VM agreed to not + * access unplugged (discarded) memory - especially via DMA. virtio-mem will + * properly coordinate with listeners before memory is plugged (populated), + * and after memory is unplugged (discarded). + * + * Listeners are called in multiples of the minimum granularity (unless it + * would exceed the registered range) and changes are aligned to the minimum + * granularity within the #MemoryRegion. Listeners have to prepare for memory + * becomming discarded in a different granularity than it was populated and the + * other way around. + */ +struct RamDiscardManagerClass { + /* private */ + InterfaceClass parent_class; + + /* public */ + + /** + * @get_min_granularity: + * + * Get the minimum granularity in which listeners will get notified + * about changes within the #MemoryRegion via the #RamDiscardManager. + * + * @rdm: the #RamDiscardManager + * @mr: the #MemoryRegion + * + * Returns the minimum granularity. + */ + uint64_t (*get_min_granularity)(const RamDiscardManager *rdm, + const MemoryRegion *mr); + + /** + * @is_populated: + * + * Check whether the given #MemoryRegionSection is completely populated + * (i.e., no parts are currently discarded) via the #RamDiscardManager. + * There are no alignment requirements. + * + * @rdm: the #RamDiscardManager + * @section: the #MemoryRegionSection + * + * Returns whether the given range is completely populated. + */ + bool (*is_populated)(const RamDiscardManager *rdm, + const MemoryRegionSection *section); + + /** + * @replay_populated: + * + * Call the #ReplayRamPopulate callback for all populated parts within the + * #MemoryRegionSection via the #RamDiscardManager. + * + * In case any call fails, no further calls are made. + * + * @rdm: the #RamDiscardManager + * @section: the #MemoryRegionSection + * @replay_fn: the #ReplayRamPopulate callback + * @opaque: pointer to forward to the callback + * + * Returns 0 on success, or a negative error if any notification failed. + */ + int (*replay_populated)(const RamDiscardManager *rdm, + MemoryRegionSection *section, + ReplayRamPopulate replay_fn, void *opaque); + + /** + * @register_listener: + * + * Register a #RamDiscardListener for the given #MemoryRegionSection and + * immediately notify the #RamDiscardListener about all populated parts + * within the #MemoryRegionSection via the #RamDiscardManager. + * + * In case any notification fails, no further notifications are triggered + * and an error is logged. + * + * @rdm: the #RamDiscardManager + * @rdl: the #RamDiscardListener + * @section: the #MemoryRegionSection + */ + void (*register_listener)(RamDiscardManager *rdm, + RamDiscardListener *rdl, + MemoryRegionSection *section); + + /** + * @unregister_listener: + * + * Unregister a previously registered #RamDiscardListener via the + * #RamDiscardManager after notifying the #RamDiscardListener about all + * populated parts becoming unpopulated within the registered + * #MemoryRegionSection. + * + * @rdm: the #RamDiscardManager + * @rdl: the #RamDiscardListener + */ + void (*unregister_listener)(RamDiscardManager *rdm, + RamDiscardListener *rdl); +}; + +uint64_t ram_discard_manager_get_min_granularity(const RamDiscardManager *rdm, + const MemoryRegion *mr); + +bool ram_discard_manager_is_populated(const RamDiscardManager *rdm, + const MemoryRegionSection *section); + +int ram_discard_manager_replay_populated(const RamDiscardManager *rdm, + MemoryRegionSection *section, + ReplayRamPopulate replay_fn, + void *opaque); + +void ram_discard_manager_register_listener(RamDiscardManager *rdm, + RamDiscardListener *rdl, + MemoryRegionSection *section); + +void ram_discard_manager_unregister_listener(RamDiscardManager *rdm, + RamDiscardListener *rdl); + typedef struct CoalescedMemoryRange CoalescedMemoryRange; typedef struct MemoryRegionIoeventfd MemoryRegionIoeventfd; @@ -487,6 +722,7 @@ struct MemoryRegion { const char *name; unsigned ioeventfd_nb; MemoryRegionIoeventfd *ioeventfds; + RamDiscardManager *rdm; /* Only for RAM */ }; struct IOMMUMemoryRegion { @@ -571,7 +807,7 @@ struct MemoryListener { * @log_start: * * Called during an address space update transaction, after - * one of #MemoryListener.region_add(),#MemoryListener.region_del() or + * one of #MemoryListener.region_add(), #MemoryListener.region_del() or * #MemoryListener.region_nop(), if dirty memory logging clients have * become active since the last transaction. * @@ -616,6 +852,18 @@ struct MemoryListener { */ void (*log_sync)(MemoryListener *listener, MemoryRegionSection *section); + /** + * @log_sync_global: + * + * This is the global version of @log_sync when the listener does + * not have a way to synchronize the log with finer granularity. + * When the listener registers with @log_sync_global defined, then + * its @log_sync must be NULL. Vice versa. + * + * @listener: The #MemoryListener. + */ + void (*log_sync_global)(MemoryListener *listener); + /** * @log_clear: * @@ -806,28 +1054,6 @@ typedef bool (*flatview_cb)(Int128 start, */ void flatview_for_each_range(FlatView *fv, flatview_cb cb, void *opaque); -/** - * struct MemoryRegionSection: describes a fragment of a #MemoryRegion - * - * @mr: the region, or %NULL if empty - * @fv: the flat view of the address space the region is mapped in - * @offset_within_region: the beginning of the section, relative to @mr's start - * @size: the size of the section; will not exceed @mr's boundaries - * @offset_within_address_space: the address of the first byte of the section - * relative to the region's address space - * @readonly: writes to this section are ignored - * @nonvolatile: this section is non-volatile - */ -struct MemoryRegionSection { - Int128 size; - MemoryRegion *mr; - FlatView *fv; - hwaddr offset_within_region; - hwaddr offset_within_address_space; - bool readonly; - bool nonvolatile; -}; - static inline bool MemoryRegionSection_eq(MemoryRegionSection *a, MemoryRegionSection *b) { @@ -840,6 +1066,26 @@ static inline bool MemoryRegionSection_eq(MemoryRegionSection *a, a->nonvolatile == b->nonvolatile; } +/** + * memory_region_section_new_copy: Copy a memory region section + * + * Allocate memory for a new copy, copy the memory region section, and + * properly take a reference on all relevant members. + * + * @s: the #MemoryRegionSection to copy + */ +MemoryRegionSection *memory_region_section_new_copy(MemoryRegionSection *s); + +/** + * memory_region_section_new_copy: Free a copied memory region section + * + * Free a copy of a memory section created via memory_region_section_new_copy(). + * properly dropping references on all relevant members. + * + * @s: the #MemoryRegionSection to copy + */ +void memory_region_section_free_copy(MemoryRegionSection *s); + /** * memory_region_init: Initialize a memory region * @@ -934,34 +1180,36 @@ void memory_region_init_ram_nomigrate(MemoryRegion *mr, Error **errp); /** - * memory_region_init_ram_shared_nomigrate: Initialize RAM memory region. - * Accesses into the region will - * modify memory directly. + * memory_region_init_ram_flags_nomigrate: Initialize RAM memory region. + * Accesses into the region will + * modify memory directly. * * @mr: the #MemoryRegion to be initialized. * @owner: the object that tracks the region's reference count * @name: Region name, becomes part of RAMBlock name used in migration stream * must be unique within any device * @size: size of the region. - * @share: allow remapping RAM to different addresses + * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_NORESERVE. * @errp: pointer to Error*, to store an error if it happens. * - * Note that this function is similar to memory_region_init_ram_nomigrate. - * The only difference is part of the RAM region can be remapped. + * Note that this function does not do anything to cause the data in the + * RAM memory region to be migrated; that is the responsibility of the caller. */ -void memory_region_init_ram_shared_nomigrate(MemoryRegion *mr, - Object *owner, - const char *name, - uint64_t size, - bool share, - Error **errp); +void memory_region_init_ram_flags_nomigrate(MemoryRegion *mr, + Object *owner, + const char *name, + uint64_t size, + uint32_t ram_flags, + Error **errp); /** * memory_region_init_resizeable_ram: Initialize memory region with resizeable * RAM. Accesses into the region will * modify memory directly. Only an initial * portion of this RAM is actually used. - * The used size can change across reboots. + * Changing the size while migrating + * can result in the migration being + * canceled. * * @mr: the #MemoryRegion to be initialized. * @owner: the object that tracks the region's reference count @@ -997,10 +1245,8 @@ void memory_region_init_resizeable_ram(MemoryRegion *mr, * @size: size of the region. * @align: alignment of the region base address; if 0, the default alignment * (getpagesize()) will be used. - * @ram_flags: Memory region features: - * - RAM_SHARED: memory must be mmaped with the MAP_SHARED flag - * - RAM_PMEM: the memory is persistent memory - * Other bits are ignored now. + * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_PMEM, + * RAM_NORESERVE, * @path: the path in which to allocate the RAM. * @readonly: true to open @path for reading, false for read/write. * @errp: pointer to Error*, to store an error if it happens. @@ -1026,7 +1272,8 @@ void memory_region_init_ram_from_file(MemoryRegion *mr, * @owner: the object that tracks the region's reference count * @name: the name of the region. * @size: size of the region. - * @share: %true if memory must be mmaped with the MAP_SHARED flag + * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_PMEM, + * RAM_NORESERVE. * @fd: the fd to mmap. * @offset: offset within the file referenced by fd * @errp: pointer to Error*, to store an error if it happens. @@ -1038,7 +1285,7 @@ void memory_region_init_ram_from_fd(MemoryRegion *mr, Object *owner, const char *name, uint64_t size, - bool share, + uint32_t ram_flags, int fd, ram_addr_t offset, Error **errp); @@ -1592,8 +1839,8 @@ void *memory_region_get_ram_ptr(MemoryRegion *mr); /* memory_region_ram_resize: Resize a RAM region. * - * Only legal before guest might have detected the memory size: e.g. on - * incoming migration, or right after reset. + * Resizing RAM while migrating can result in the migration being canceled. + * Care has to be taken if the guest might have already detected the memory. * * @mr: a memory region created with @memory_region_init_resizeable_ram. * @newsize: the new size the region @@ -2028,6 +2275,41 @@ bool memory_region_present(MemoryRegion *container, hwaddr addr); */ bool memory_region_is_mapped(MemoryRegion *mr); +/** + * memory_region_get_ram_discard_manager: get the #RamDiscardManager for a + * #MemoryRegion + * + * The #RamDiscardManager cannot change while a memory region is mapped. + * + * @mr: the #MemoryRegion + */ +RamDiscardManager *memory_region_get_ram_discard_manager(MemoryRegion *mr); + +/** + * memory_region_has_ram_discard_manager: check whether a #MemoryRegion has a + * #RamDiscardManager assigned + * + * @mr: the #MemoryRegion + */ +static inline bool memory_region_has_ram_discard_manager(MemoryRegion *mr) +{ + return !!memory_region_get_ram_discard_manager(mr); +} + +/** + * memory_region_set_ram_discard_manager: set the #RamDiscardManager for a + * #MemoryRegion + * + * This function must not be called for a mapped #MemoryRegion, a #MemoryRegion + * that does not cover RAM, or a #MemoryRegion that already has a + * #RamDiscardManager assigned. + * + * @mr: the #MemoryRegion + * @rdm: #RamDiscardManager to set + */ +void memory_region_set_ram_discard_manager(MemoryRegion *mr, + RamDiscardManager *rdm); + /** * memory_region_find: translate an address/size relative to a * MemoryRegion into a #MemoryRegionSection. @@ -2328,7 +2610,7 @@ static inline uint8_t address_space_ldub_cached(MemoryRegionCache *cache, } static inline void address_space_stb_cached(MemoryRegionCache *cache, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result) + hwaddr addr, uint8_t val, MemTxAttrs attrs, MemTxResult *result) { assert(addr < cache->len); if (likely(cache->ptr)) { @@ -2636,6 +2918,12 @@ static inline MemOp devend_memop(enum device_endian end) */ int ram_block_discard_disable(bool state); +/* + * See ram_block_discard_disable(): only disable uncoordinated discards, + * keeping coordinated discards (via the RamDiscardManager) enabled. + */ +int ram_block_uncoordinated_discard_disable(bool state); + /* * Inhibit technologies that disable discarding of pages in RAM blocks. * @@ -2645,12 +2933,20 @@ int ram_block_discard_disable(bool state); int ram_block_discard_require(bool state); /* - * Test if discarding of memory in ram blocks is disabled. + * See ram_block_discard_require(): only inhibit technologies that disable + * uncoordinated discarding of pages in RAM blocks, allowing co-existance with + * technologies that only inhibit uncoordinated discards (via the + * RamDiscardManager). + */ +int ram_block_coordinated_discard_require(bool state); + +/* + * Test if any discarding of memory in ram blocks is disabled. */ bool ram_block_discard_is_disabled(void); /* - * Test if discarding of memory in ram blocks is required to work reliably. + * Test if any discarding of memory in ram blocks is required to work reliably. */ bool ram_block_discard_is_required(void); diff --git a/include/exec/memory_ldst.h.inc b/include/exec/memory_ldst.h.inc index 46e6c220d3..7c3a641f7e 100644 --- a/include/exec/memory_ldst.h.inc +++ b/include/exec/memory_ldst.h.inc @@ -20,7 +20,7 @@ */ #ifdef TARGET_ENDIANNESS -extern uint32_t glue(address_space_lduw, SUFFIX)(ARG1_DECL, +extern uint16_t glue(address_space_lduw, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); extern uint32_t glue(address_space_ldl, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); @@ -29,17 +29,17 @@ extern uint64_t glue(address_space_ldq, SUFFIX)(ARG1_DECL, extern void glue(address_space_stl_notdirty, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stw, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stl, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stq, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t val, MemTxAttrs attrs, MemTxResult *result); #else -extern uint32_t glue(address_space_ldub, SUFFIX)(ARG1_DECL, +extern uint8_t glue(address_space_ldub, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); -extern uint32_t glue(address_space_lduw_le, SUFFIX)(ARG1_DECL, +extern uint16_t glue(address_space_lduw_le, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); -extern uint32_t glue(address_space_lduw_be, SUFFIX)(ARG1_DECL, +extern uint16_t glue(address_space_lduw_be, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); extern uint32_t glue(address_space_ldl_le, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); @@ -50,11 +50,11 @@ extern uint64_t glue(address_space_ldq_le, SUFFIX)(ARG1_DECL, extern uint64_t glue(address_space_ldq_be, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stb, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); + hwaddr addr, uint8_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stw_le, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stw_be, SUFFIX)(ARG1_DECL, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stl_le, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); extern void glue(address_space_stl_be, SUFFIX)(ARG1_DECL, diff --git a/include/exec/memory_ldst_cached.h.inc b/include/exec/memory_ldst_cached.h.inc index 7bc8790d34..d7834f852c 100644 --- a/include/exec/memory_ldst_cached.h.inc +++ b/include/exec/memory_ldst_cached.h.inc @@ -24,6 +24,18 @@ #define LD_P(size) \ glue(glue(ld, size), glue(ENDIANNESS, _p)) +static inline uint16_t ADDRESS_SPACE_LD_CACHED(uw)(MemoryRegionCache *cache, + hwaddr addr, MemTxAttrs attrs, MemTxResult *result) +{ + assert(addr < cache->len && 2 <= cache->len - addr); + fuzz_dma_read_cb(cache->xlat + addr, 2, cache->mrs.mr); + if (likely(cache->ptr)) { + return LD_P(uw)(cache->ptr + addr); + } else { + return ADDRESS_SPACE_LD_CACHED_SLOW(uw)(cache, addr, attrs, result); + } +} + static inline uint32_t ADDRESS_SPACE_LD_CACHED(l)(MemoryRegionCache *cache, hwaddr addr, MemTxAttrs attrs, MemTxResult *result) { @@ -48,18 +60,6 @@ static inline uint64_t ADDRESS_SPACE_LD_CACHED(q)(MemoryRegionCache *cache, } } -static inline uint32_t ADDRESS_SPACE_LD_CACHED(uw)(MemoryRegionCache *cache, - hwaddr addr, MemTxAttrs attrs, MemTxResult *result) -{ - assert(addr < cache->len && 2 <= cache->len - addr); - fuzz_dma_read_cb(cache->xlat + addr, 2, cache->mrs.mr); - if (likely(cache->ptr)) { - return LD_P(uw)(cache->ptr + addr); - } else { - return ADDRESS_SPACE_LD_CACHED_SLOW(uw)(cache, addr, attrs, result); - } -} - #undef ADDRESS_SPACE_LD_CACHED #undef ADDRESS_SPACE_LD_CACHED_SLOW #undef LD_P @@ -71,6 +71,17 @@ static inline uint32_t ADDRESS_SPACE_LD_CACHED(uw)(MemoryRegionCache *cache, #define ST_P(size) \ glue(glue(st, size), glue(ENDIANNESS, _p)) +static inline void ADDRESS_SPACE_ST_CACHED(w)(MemoryRegionCache *cache, + hwaddr addr, uint16_t val, MemTxAttrs attrs, MemTxResult *result) +{ + assert(addr < cache->len && 2 <= cache->len - addr); + if (likely(cache->ptr)) { + ST_P(w)(cache->ptr + addr, val); + } else { + ADDRESS_SPACE_ST_CACHED_SLOW(w)(cache, addr, val, attrs, result); + } +} + static inline void ADDRESS_SPACE_ST_CACHED(l)(MemoryRegionCache *cache, hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result) { @@ -82,17 +93,6 @@ static inline void ADDRESS_SPACE_ST_CACHED(l)(MemoryRegionCache *cache, } } -static inline void ADDRESS_SPACE_ST_CACHED(w)(MemoryRegionCache *cache, - hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result) -{ - assert(addr < cache->len && 2 <= cache->len - addr); - if (likely(cache->ptr)) { - ST_P(w)(cache->ptr + addr, val); - } else { - ADDRESS_SPACE_ST_CACHED_SLOW(w)(cache, addr, val, attrs, result); - } -} - static inline void ADDRESS_SPACE_ST_CACHED(q)(MemoryRegionCache *cache, hwaddr addr, uint64_t val, MemTxAttrs attrs, MemTxResult *result) { diff --git a/include/exec/memory_ldst_phys.h.inc b/include/exec/memory_ldst_phys.h.inc index b9dd53c389..ecd678610d 100644 --- a/include/exec/memory_ldst_phys.h.inc +++ b/include/exec/memory_ldst_phys.h.inc @@ -20,6 +20,12 @@ */ #ifdef TARGET_ENDIANNESS +static inline uint16_t glue(lduw_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +{ + return glue(address_space_lduw, SUFFIX)(ARG1, addr, + MEMTXATTRS_UNSPECIFIED, NULL); +} + static inline uint32_t glue(ldl_phys, SUFFIX)(ARG1_DECL, hwaddr addr) { return glue(address_space_ldl, SUFFIX)(ARG1, addr, @@ -32,10 +38,10 @@ static inline uint64_t glue(ldq_phys, SUFFIX)(ARG1_DECL, hwaddr addr) MEMTXATTRS_UNSPECIFIED, NULL); } -static inline uint32_t glue(lduw_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +static inline void glue(stw_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint16_t val) { - return glue(address_space_lduw, SUFFIX)(ARG1, addr, - MEMTXATTRS_UNSPECIFIED, NULL); + glue(address_space_stw, SUFFIX)(ARG1, addr, val, + MEMTXATTRS_UNSPECIFIED, NULL); } static inline void glue(stl_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) @@ -44,18 +50,30 @@ static inline void glue(stl_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) MEMTXATTRS_UNSPECIFIED, NULL); } -static inline void glue(stw_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) -{ - glue(address_space_stw, SUFFIX)(ARG1, addr, val, - MEMTXATTRS_UNSPECIFIED, NULL); -} - static inline void glue(stq_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t val) { glue(address_space_stq, SUFFIX)(ARG1, addr, val, MEMTXATTRS_UNSPECIFIED, NULL); } #else +static inline uint8_t glue(ldub_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +{ + return glue(address_space_ldub, SUFFIX)(ARG1, addr, + MEMTXATTRS_UNSPECIFIED, NULL); +} + +static inline uint16_t glue(lduw_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +{ + return glue(address_space_lduw_le, SUFFIX)(ARG1, addr, + MEMTXATTRS_UNSPECIFIED, NULL); +} + +static inline uint16_t glue(lduw_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +{ + return glue(address_space_lduw_be, SUFFIX)(ARG1, addr, + MEMTXATTRS_UNSPECIFIED, NULL); +} + static inline uint32_t glue(ldl_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr) { return glue(address_space_ldl_le, SUFFIX)(ARG1, addr, @@ -80,22 +98,22 @@ static inline uint64_t glue(ldq_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr) MEMTXATTRS_UNSPECIFIED, NULL); } -static inline uint32_t glue(ldub_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +static inline void glue(stb_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint8_t val) { - return glue(address_space_ldub, SUFFIX)(ARG1, addr, - MEMTXATTRS_UNSPECIFIED, NULL); + glue(address_space_stb, SUFFIX)(ARG1, addr, val, + MEMTXATTRS_UNSPECIFIED, NULL); } -static inline uint32_t glue(lduw_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +static inline void glue(stw_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint16_t val) { - return glue(address_space_lduw_le, SUFFIX)(ARG1, addr, - MEMTXATTRS_UNSPECIFIED, NULL); + glue(address_space_stw_le, SUFFIX)(ARG1, addr, val, + MEMTXATTRS_UNSPECIFIED, NULL); } -static inline uint32_t glue(lduw_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr) +static inline void glue(stw_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint16_t val) { - return glue(address_space_lduw_be, SUFFIX)(ARG1, addr, - MEMTXATTRS_UNSPECIFIED, NULL); + glue(address_space_stw_be, SUFFIX)(ARG1, addr, val, + MEMTXATTRS_UNSPECIFIED, NULL); } static inline void glue(stl_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) @@ -110,24 +128,6 @@ static inline void glue(stl_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t va MEMTXATTRS_UNSPECIFIED, NULL); } -static inline void glue(stb_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) -{ - glue(address_space_stb, SUFFIX)(ARG1, addr, val, - MEMTXATTRS_UNSPECIFIED, NULL); -} - -static inline void glue(stw_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) -{ - glue(address_space_stw_le, SUFFIX)(ARG1, addr, val, - MEMTXATTRS_UNSPECIFIED, NULL); -} - -static inline void glue(stw_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val) -{ - glue(address_space_stw_be, SUFFIX)(ARG1, addr, val, - MEMTXATTRS_UNSPECIFIED, NULL); -} - static inline void glue(stq_le_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t val) { glue(address_space_stq_le, SUFFIX)(ARG1, addr, val, diff --git a/include/exec/poison.h b/include/exec/poison.h index 4cd3f8abb4..7ad4ad18e8 100644 --- a/include/exec/poison.h +++ b/include/exec/poison.h @@ -4,6 +4,8 @@ #ifndef HW_POISON_H #define HW_POISON_H +#include "config-poison.h" + #pragma GCC poison TARGET_I386 #pragma GCC poison TARGET_X86_64 #pragma GCC poison TARGET_AARCH64 @@ -12,7 +14,6 @@ #pragma GCC poison TARGET_CRIS #pragma GCC poison TARGET_HEXAGON #pragma GCC poison TARGET_HPPA -#pragma GCC poison TARGET_LM32 #pragma GCC poison TARGET_M68K #pragma GCC poison TARGET_MICROBLAZE #pragma GCC poison TARGET_MIPS @@ -20,7 +21,6 @@ #pragma GCC poison TARGET_ABI_MIPSO32 #pragma GCC poison TARGET_MIPS64 #pragma GCC poison TARGET_ABI_MIPSN64 -#pragma GCC poison TARGET_MOXIE #pragma GCC poison TARGET_NIOS2 #pragma GCC poison TARGET_OPENRISC #pragma GCC poison TARGET_PPC @@ -32,7 +32,6 @@ #pragma GCC poison TARGET_SPARC #pragma GCC poison TARGET_SPARC64 #pragma GCC poison TARGET_TRICORE -#pragma GCC poison TARGET_UNICORE32 #pragma GCC poison TARGET_XTENSA #pragma GCC poison TARGET_ALIGNED_ONLY @@ -74,12 +73,10 @@ #pragma GCC poison CONFIG_HPPA_DIS #pragma GCC poison CONFIG_I386_DIS #pragma GCC poison CONFIG_HEXAGON_DIS -#pragma GCC poison CONFIG_LM32_DIS #pragma GCC poison CONFIG_M68K_DIS #pragma GCC poison CONFIG_MICROBLAZE_DIS #pragma GCC poison CONFIG_MIPS_DIS #pragma GCC poison CONFIG_NANOMIPS_DIS -#pragma GCC poison CONFIG_MOXIE_DIS #pragma GCC poison CONFIG_NIOS2_DIS #pragma GCC poison CONFIG_PPC_DIS #pragma GCC poison CONFIG_RISCV_DIS @@ -88,8 +85,12 @@ #pragma GCC poison CONFIG_SPARC_DIS #pragma GCC poison CONFIG_XTENSA_DIS +#pragma GCC poison CONFIG_HAX +#pragma GCC poison CONFIG_HVF #pragma GCC poison CONFIG_LINUX_USER #pragma GCC poison CONFIG_KVM #pragma GCC poison CONFIG_SOFTMMU +#pragma GCC poison CONFIG_WHPX +#pragma GCC poison CONFIG_XEN #endif diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index e0c641badc..5cb9789d56 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -104,11 +104,8 @@ long qemu_maxrampagesize(void); * Parameters: * @size: the size in bytes of the ram block * @mr: the memory region where the ram block is - * @ram_flags: specify the properties of the ram block, which can be one - * or bit-or of following values - * - RAM_SHARED: mmap the backing file or device with MAP_SHARED - * - RAM_PMEM: the backend @mem_path or @fd is persistent memory - * Other bits are ignored. + * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_PMEM, + * RAM_NORESERVE. * @mem_path or @fd: specify the backing file or device * @readonly: true to open @path for reading, false for read/write. * @errp: pointer to Error*, to store an error if it happens @@ -126,7 +123,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host, MemoryRegion *mr, Error **errp); -RAMBlock *qemu_ram_alloc(ram_addr_t size, bool share, MemoryRegion *mr, +RAMBlock *qemu_ram_alloc(ram_addr_t size, uint32_t ram_flags, MemoryRegion *mr, Error **errp); RAMBlock *qemu_ram_alloc_resizeable(ram_addr_t size, ram_addr_t max_size, void (*resized)(const char*, diff --git a/include/exec/ramblock.h b/include/exec/ramblock.h index 07d50864d8..664701b759 100644 --- a/include/exec/ramblock.h +++ b/include/exec/ramblock.h @@ -59,6 +59,16 @@ struct RAMBlock { */ unsigned long *clear_bmap; uint8_t clear_bmap_shift; + + /* + * RAM block length that corresponds to the used_length on the migration + * source (after RAM block sizes were synchronized). Especially, after + * starting to run the guest, used_length and postcopy_length can differ. + * Used to register/unregister uffd handlers and as the size of the received + * bitmap. Receiving any page beyond this length will bail out, as it + * could not have been valid on the source. + */ + ram_addr_t postcopy_length; }; #endif #endif diff --git a/include/exec/ramlist.h b/include/exec/ramlist.h index 44fade626d..e135e80fa2 100644 --- a/include/exec/ramlist.h +++ b/include/exec/ramlist.h @@ -67,15 +67,20 @@ void qemu_mutex_lock_ramlist(void); void qemu_mutex_unlock_ramlist(void); struct RAMBlockNotifier { - void (*ram_block_added)(RAMBlockNotifier *n, void *host, size_t size); - void (*ram_block_removed)(RAMBlockNotifier *n, void *host, size_t size); + void (*ram_block_added)(RAMBlockNotifier *n, void *host, size_t size, + size_t max_size); + void (*ram_block_removed)(RAMBlockNotifier *n, void *host, size_t size, + size_t max_size); + void (*ram_block_resized)(RAMBlockNotifier *n, void *host, size_t old_size, + size_t new_size); QLIST_ENTRY(RAMBlockNotifier) next; }; void ram_block_notifier_add(RAMBlockNotifier *n); void ram_block_notifier_remove(RAMBlockNotifier *n); -void ram_block_notify_add(void *host, size_t size); -void ram_block_notify_remove(void *host, size_t size); +void ram_block_notify_add(void *host, size_t size, size_t max_size); +void ram_block_notify_remove(void *host, size_t size, size_t max_size); +void ram_block_notify_resize(void *host, size_t old_size, size_t new_size); void ram_block_dump(Monitor *mon); diff --git a/include/exec/tb-lookup.h b/include/exec/tb-lookup.h deleted file mode 100644 index 29d61ceb34..0000000000 --- a/include/exec/tb-lookup.h +++ /dev/null @@ -1,49 +0,0 @@ -/* - * Copyright (C) 2017, Emilio G. Cota - * - * License: GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - */ -#ifndef EXEC_TB_LOOKUP_H -#define EXEC_TB_LOOKUP_H - -#ifdef NEED_CPU_H -#include "cpu.h" -#else -#include "exec/poison.h" -#endif - -#include "exec/exec-all.h" -#include "exec/tb-hash.h" - -/* Might cause an exception, so have a longjmp destination ready */ -static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc, - target_ulong cs_base, - uint32_t flags, uint32_t cflags) -{ - TranslationBlock *tb; - uint32_t hash; - - /* we should never be trying to look up an INVALID tb */ - tcg_debug_assert(!(cflags & CF_INVALID)); - - hash = tb_jmp_cache_hash_func(pc); - tb = qatomic_rcu_read(&cpu->tb_jmp_cache[hash]); - - if (likely(tb && - tb->pc == pc && - tb->cs_base == cs_base && - tb->flags == flags && - tb->trace_vcpu_dstate == *cpu->trace_dstate && - tb_cflags(tb) == cflags)) { - return tb; - } - tb = tb_htable_lookup(cpu, pc, cs_base, flags, cflags); - if (tb == NULL) { - return NULL; - } - qatomic_set(&cpu->tb_jmp_cache[hash], tb); - return tb; -} - -#endif /* EXEC_TB_LOOKUP_H */ diff --git a/include/exec/translator.h b/include/exec/translator.h index 24232ead41..d318803267 100644 --- a/include/exec/translator.h +++ b/include/exec/translator.h @@ -89,15 +89,6 @@ typedef struct DisasContextBase { * @insn_start: * Emit the tcg_gen_insn_start opcode. * - * @breakpoint_check: - * When called, the breakpoint has already been checked to match the PC, - * but the target may decide the breakpoint missed the address - * (e.g., due to conditions encoded in their flags). Return true to - * indicate that the breakpoint did hit, in which case no more breakpoints - * are checked. If the breakpoint did hit, emit any code required to - * signal the exception, and set db->is_jmp as necessary to terminate - * the main loop. - * * @translate_insn: * Disassemble one instruction and set db->pc_next for the start * of the following instruction. Set db->is_jmp as necessary to @@ -113,8 +104,6 @@ typedef struct TranslatorOps { void (*init_disas_context)(DisasContextBase *db, CPUState *cpu); void (*tb_start)(DisasContextBase *db, CPUState *cpu); void (*insn_start)(DisasContextBase *db, CPUState *cpu); - bool (*breakpoint_check)(DisasContextBase *db, CPUState *cpu, - const CPUBreakpoint *bp); void (*translate_insn)(DisasContextBase *db, CPUState *cpu); void (*tb_stop)(DisasContextBase *db, CPUState *cpu); void (*disas_log)(const DisasContextBase *db, CPUState *cpu); @@ -145,6 +134,16 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db, void translator_loop_temp_check(DisasContextBase *db); +/** + * translator_use_goto_tb + * @db: Disassembly context + * @dest: target pc of the goto + * + * Return true if goto_tb is allowed between the current TB + * and the destination PC. + */ +bool translator_use_goto_tb(DisasContextBase *db, target_ulong dest); + /* * Translator Load Functions * diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h index 2f0674fbdd..a98d759cd3 100644 --- a/include/fpu/softfloat-helpers.h +++ b/include/fpu/softfloat-helpers.h @@ -48,8 +48,8 @@ this code that are retained. =============================================================================== */ -#ifndef _SOFTFLOAT_HELPERS_H_ -#define _SOFTFLOAT_HELPERS_H_ +#ifndef SOFTFLOAT_HELPERS_H +#define SOFTFLOAT_HELPERS_H #include "fpu/softfloat-types.h" @@ -69,7 +69,7 @@ static inline void set_float_exception_flags(int val, float_status *status) status->float_exception_flags = val; } -static inline void set_floatx80_rounding_precision(int val, +static inline void set_floatx80_rounding_precision(FloatX80RoundPrec val, float_status *status) { status->floatx80_rounding_precision = val; @@ -120,7 +120,8 @@ static inline int get_float_exception_flags(float_status *status) return status->float_exception_flags; } -static inline int get_floatx80_rounding_precision(float_status *status) +static inline FloatX80RoundPrec +get_floatx80_rounding_precision(float_status *status) { return status->floatx80_rounding_precision; } diff --git a/include/fpu/softfloat-macros.h b/include/fpu/softfloat-macros.h index a35ec2893a..81c3fe8256 100644 --- a/include/fpu/softfloat-macros.h +++ b/include/fpu/softfloat-macros.h @@ -83,6 +83,43 @@ this code that are retained. #define FPU_SOFTFLOAT_MACROS_H #include "fpu/softfloat-types.h" +#include "qemu/host-utils.h" + +/** + * shl_double: double-word merging left shift + * @l: left or most-significant word + * @r: right or least-significant word + * @c: shift count + * + * Shift @l left by @c bits, shifting in bits from @r. + */ +static inline uint64_t shl_double(uint64_t l, uint64_t r, int c) +{ +#if defined(__x86_64__) + asm("shld %b2, %1, %0" : "+r"(l) : "r"(r), "ci"(c)); + return l; +#else + return c ? (l << c) | (r >> (64 - c)) : l; +#endif +} + +/** + * shr_double: double-word merging right shift + * @l: left or most-significant word + * @r: right or least-significant word + * @c: shift count + * + * Shift @r right by @c bits, shifting in bits from @l. + */ +static inline uint64_t shr_double(uint64_t l, uint64_t r, int c) +{ +#if defined(__x86_64__) + asm("shrd %b2, %1, %0" : "+r"(r) : "r"(l), "ci"(c)); + return r; +#else + return c ? (r >> c) | (l << (64 - c)) : r; +#endif +} /*---------------------------------------------------------------------------- | Shifts `a' right by the number of bits given in `count'. If any nonzero @@ -403,16 +440,12 @@ static inline void | are stored at the locations pointed to by `z0Ptr' and `z1Ptr'. *----------------------------------------------------------------------------*/ -static inline void - add128( - uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1, uint64_t *z0Ptr, uint64_t *z1Ptr ) +static inline void add128(uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1, + uint64_t *z0Ptr, uint64_t *z1Ptr) { - uint64_t z1; - - z1 = a1 + b1; - *z1Ptr = z1; - *z0Ptr = a0 + b0 + ( z1 < a1 ); - + bool c = 0; + *z1Ptr = uadd64_carry(a1, b1, &c); + *z0Ptr = uadd64_carry(a0, b0, &c); } /*---------------------------------------------------------------------------- @@ -423,34 +456,14 @@ static inline void | `z1Ptr', and `z2Ptr'. *----------------------------------------------------------------------------*/ -static inline void - add192( - uint64_t a0, - uint64_t a1, - uint64_t a2, - uint64_t b0, - uint64_t b1, - uint64_t b2, - uint64_t *z0Ptr, - uint64_t *z1Ptr, - uint64_t *z2Ptr - ) +static inline void add192(uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t b0, uint64_t b1, uint64_t b2, + uint64_t *z0Ptr, uint64_t *z1Ptr, uint64_t *z2Ptr) { - uint64_t z0, z1, z2; - int8_t carry0, carry1; - - z2 = a2 + b2; - carry1 = ( z2 < a2 ); - z1 = a1 + b1; - carry0 = ( z1 < a1 ); - z0 = a0 + b0; - z1 += carry1; - z0 += ( z1 < carry1 ); - z0 += carry0; - *z2Ptr = z2; - *z1Ptr = z1; - *z0Ptr = z0; - + bool c = 0; + *z2Ptr = uadd64_carry(a2, b2, &c); + *z1Ptr = uadd64_carry(a1, b1, &c); + *z0Ptr = uadd64_carry(a0, b0, &c); } /*---------------------------------------------------------------------------- @@ -461,14 +474,12 @@ static inline void | `z1Ptr'. *----------------------------------------------------------------------------*/ -static inline void - sub128( - uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1, uint64_t *z0Ptr, uint64_t *z1Ptr ) +static inline void sub128(uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1, + uint64_t *z0Ptr, uint64_t *z1Ptr) { - - *z1Ptr = a1 - b1; - *z0Ptr = a0 - b0 - ( a1 < b1 ); - + bool c = 0; + *z1Ptr = usub64_borrow(a1, b1, &c); + *z0Ptr = usub64_borrow(a0, b0, &c); } /*---------------------------------------------------------------------------- @@ -479,34 +490,14 @@ static inline void | pointed to by `z0Ptr', `z1Ptr', and `z2Ptr'. *----------------------------------------------------------------------------*/ -static inline void - sub192( - uint64_t a0, - uint64_t a1, - uint64_t a2, - uint64_t b0, - uint64_t b1, - uint64_t b2, - uint64_t *z0Ptr, - uint64_t *z1Ptr, - uint64_t *z2Ptr - ) +static inline void sub192(uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t b0, uint64_t b1, uint64_t b2, + uint64_t *z0Ptr, uint64_t *z1Ptr, uint64_t *z2Ptr) { - uint64_t z0, z1, z2; - int8_t borrow0, borrow1; - - z2 = a2 - b2; - borrow1 = ( a2 < b2 ); - z1 = a1 - b1; - borrow0 = ( a1 < b1 ); - z0 = a0 - b0; - z0 -= ( z1 < borrow1 ); - z1 -= borrow1; - z0 -= borrow0; - *z2Ptr = z2; - *z1Ptr = z1; - *z0Ptr = z0; - + bool c = 0; + *z2Ptr = usub64_borrow(a2, b2, &c); + *z1Ptr = usub64_borrow(a1, b1, &c); + *z0Ptr = usub64_borrow(a0, b0, &c); } /*---------------------------------------------------------------------------- @@ -515,27 +506,10 @@ static inline void | `z0Ptr' and `z1Ptr'. *----------------------------------------------------------------------------*/ -static inline void mul64To128( uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t *z1Ptr ) +static inline void +mul64To128(uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t *z1Ptr) { - uint32_t aHigh, aLow, bHigh, bLow; - uint64_t z0, zMiddleA, zMiddleB, z1; - - aLow = a; - aHigh = a>>32; - bLow = b; - bHigh = b>>32; - z1 = ( (uint64_t) aLow ) * bLow; - zMiddleA = ( (uint64_t) aLow ) * bHigh; - zMiddleB = ( (uint64_t) aHigh ) * bLow; - z0 = ( (uint64_t) aHigh ) * bHigh; - zMiddleA += zMiddleB; - z0 += ( ( (uint64_t) ( zMiddleA < zMiddleB ) )<<32 ) + ( zMiddleA>>32 ); - zMiddleA <<= 32; - z1 += zMiddleA; - z0 += ( z1 < zMiddleA ); - *z1Ptr = z1; - *z0Ptr = z0; - + mulu64(z1Ptr, z0Ptr, a, b); } /*---------------------------------------------------------------------------- @@ -546,24 +520,14 @@ static inline void mul64To128( uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t *----------------------------------------------------------------------------*/ static inline void - mul128By64To192( - uint64_t a0, - uint64_t a1, - uint64_t b, - uint64_t *z0Ptr, - uint64_t *z1Ptr, - uint64_t *z2Ptr - ) +mul128By64To192(uint64_t a0, uint64_t a1, uint64_t b, + uint64_t *z0Ptr, uint64_t *z1Ptr, uint64_t *z2Ptr) { - uint64_t z0, z1, z2, more1; - - mul64To128( a1, b, &z1, &z2 ); - mul64To128( a0, b, &z0, &more1 ); - add128( z0, more1, 0, z1, &z0, &z1 ); - *z2Ptr = z2; - *z1Ptr = z1; - *z0Ptr = z0; + uint64_t z0, z1, m1; + mul64To128(a1, b, &m1, z2Ptr); + mul64To128(a0, b, &z0, &z1); + add128(z0, z1, 0, m1, z0Ptr, z1Ptr); } /*---------------------------------------------------------------------------- @@ -573,34 +537,21 @@ static inline void | the locations pointed to by `z0Ptr', `z1Ptr', `z2Ptr', and `z3Ptr'. *----------------------------------------------------------------------------*/ -static inline void - mul128To256( - uint64_t a0, - uint64_t a1, - uint64_t b0, - uint64_t b1, - uint64_t *z0Ptr, - uint64_t *z1Ptr, - uint64_t *z2Ptr, - uint64_t *z3Ptr - ) +static inline void mul128To256(uint64_t a0, uint64_t a1, + uint64_t b0, uint64_t b1, + uint64_t *z0Ptr, uint64_t *z1Ptr, + uint64_t *z2Ptr, uint64_t *z3Ptr) { - uint64_t z0, z1, z2, z3; - uint64_t more1, more2; + uint64_t z0, z1, z2; + uint64_t m0, m1, m2, n1, n2; - mul64To128( a1, b1, &z2, &z3 ); - mul64To128( a1, b0, &z1, &more2 ); - add128( z1, more2, 0, z2, &z1, &z2 ); - mul64To128( a0, b0, &z0, &more1 ); - add128( z0, more1, 0, z1, &z0, &z1 ); - mul64To128( a0, b1, &more1, &more2 ); - add128( more1, more2, 0, z2, &more1, &z2 ); - add128( z0, z1, 0, more1, &z0, &z1 ); - *z3Ptr = z3; - *z2Ptr = z2; - *z1Ptr = z1; - *z0Ptr = z0; + mul64To128(a1, b0, &m1, &m2); + mul64To128(a0, b1, &n1, &n2); + mul64To128(a1, b1, &z2, z3Ptr); + mul64To128(a0, b0, &z0, &z1); + add192( 0, m1, m2, 0, n1, n2, &m0, &m1, &m2); + add192(m0, m1, m2, z0, z1, z2, z0Ptr, z1Ptr, z2Ptr); } /*---------------------------------------------------------------------------- @@ -794,4 +745,38 @@ static inline bool ne128(uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1) return a0 != b0 || a1 != b1; } +/* + * Similarly, comparisons of 192-bit values. + */ + +static inline bool eq192(uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t b0, uint64_t b1, uint64_t b2) +{ + return ((a0 ^ b0) | (a1 ^ b1) | (a2 ^ b2)) == 0; +} + +static inline bool le192(uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t b0, uint64_t b1, uint64_t b2) +{ + if (a0 != b0) { + return a0 < b0; + } + if (a1 != b1) { + return a1 < b1; + } + return a2 <= b2; +} + +static inline bool lt192(uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t b0, uint64_t b1, uint64_t b2) +{ + if (a0 != b0) { + return a0 < b0; + } + if (a1 != b1) { + return a1 < b1; + } + return a2 < b2; +} + #endif diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index 60f098ab40..3c051b0a58 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -147,8 +147,10 @@ typedef enum __attribute__((__packed__)) { float_round_up = 2, float_round_to_zero = 3, float_round_ties_away = 4, - /* Not an IEEE rounding mode: round to the closest odd mantissa value */ + /* Not an IEEE rounding mode: round to closest odd, overflow to max */ float_round_to_odd = 5, + /* Not an IEEE rounding mode: round to closest odd, overflow to inf */ + float_round_to_odd_inf = 6, } FloatRoundMode; /* @@ -165,6 +167,14 @@ enum { float_flag_output_denormal = 128 }; +/* + * Rounding precision for floatx80. + */ +typedef enum __attribute__((__packed__)) { + floatx80_precision_x, + floatx80_precision_d, + floatx80_precision_s, +} FloatX80RoundPrec; /* * Floating Point Status. Individual architectures may maintain @@ -176,7 +186,7 @@ enum { typedef struct float_status { FloatRoundMode float_rounding_mode; uint8_t float_exception_flags; - signed char floatx80_rounding_precision; + FloatX80RoundPrec floatx80_rounding_precision; bool tininess_before_rounding; /* should denormalised results go to zero and set the inexact flag? */ bool flush_to_zero; diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index 78ad5ca738..ec7dca0960 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -100,7 +100,10 @@ typedef enum { | Routine to raise any or all of the software IEC/IEEE floating-point | exception flags. *----------------------------------------------------------------------------*/ -void float_raise(uint8_t flags, float_status *status); +static inline void float_raise(uint8_t flags, float_status *status) +{ + status->float_exception_flags |= flags; +} /*---------------------------------------------------------------------------- | If `a' is denormal and we are in flush-to-zero mode then set the @@ -1149,7 +1152,7 @@ floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status); | Floating-Point Arithmetic. *----------------------------------------------------------------------------*/ -floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, +floatx80 roundAndPackFloatx80(FloatX80RoundPrec roundingPrecision, bool zSign, int32_t zExp, uint64_t zSig0, uint64_t zSig1, float_status *status); @@ -1162,7 +1165,7 @@ floatx80 roundAndPackFloatx80(int8_t roundingPrecision, bool zSign, | normalized. *----------------------------------------------------------------------------*/ -floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision, +floatx80 normalizeRoundAndPackFloatx80(FloatX80RoundPrec roundingPrecision, bool zSign, int32_t zExp, uint64_t zSig0, uint64_t zSig1, float_status *status); @@ -1194,11 +1197,19 @@ float128 float128_round_to_int(float128, float_status *status); float128 float128_add(float128, float128, float_status *status); float128 float128_sub(float128, float128, float_status *status); float128 float128_mul(float128, float128, float_status *status); +float128 float128_muladd(float128, float128, float128, int, + float_status *status); float128 float128_div(float128, float128, float_status *status); float128 float128_rem(float128, float128, float_status *status); float128 float128_sqrt(float128, float_status *status); FloatRelation float128_compare(float128, float128, float_status *status); FloatRelation float128_compare_quiet(float128, float128, float_status *status); +float128 float128_min(float128, float128, float_status *status); +float128 float128_max(float128, float128, float_status *status); +float128 float128_minnum(float128, float128, float_status *status); +float128 float128_maxnum(float128, float128, float_status *status); +float128 float128_minnummag(float128, float128, float_status *status); +float128 float128_maxnummag(float128, float128, float_status *status); bool float128_is_quiet_nan(float128, float_status *status); bool float128_is_signaling_nan(float128, float_status *status); float128 float128_silence_nan(float128, float_status *status); diff --git a/include/glib-compat.h b/include/glib-compat.h index 695a96f7ea..9e95c888f5 100644 --- a/include/glib-compat.h +++ b/include/glib-compat.h @@ -19,12 +19,12 @@ /* Ask for warnings for anything that was marked deprecated in * the defined version, or before. It is a candidate for rewrite. */ -#define GLIB_VERSION_MIN_REQUIRED GLIB_VERSION_2_48 +#define GLIB_VERSION_MIN_REQUIRED GLIB_VERSION_2_56 /* Ask for warnings if code tries to use function that did not * exist in the defined version. These risk breaking builds */ -#define GLIB_VERSION_MAX_ALLOWED GLIB_VERSION_2_48 +#define GLIB_VERSION_MAX_ALLOWED GLIB_VERSION_2_56 #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wdeprecated-declarations" @@ -68,15 +68,6 @@ * without generating warnings. */ -#if defined(_WIN32) && !GLIB_CHECK_VERSION(2, 50, 0) -/* - * g_poll has a problem on Windows when using - * timeouts < 10ms, so use wrapper. - */ -#define g_poll(fds, nfds, timeout) g_poll_fixed(fds, nfds, timeout) -gint g_poll_fixed(GPollFD *fds, guint nfds, gint timeout); -#endif - #if defined(G_OS_UNIX) /* * Note: The fallback implementation is not MT-safe, and it returns a copy of @@ -100,6 +91,23 @@ g_unix_get_passwd_entry_qemu(const gchar *user_name, GError **error) } #endif /* G_OS_UNIX */ +static inline bool +qemu_g_test_slow(void) +{ + static int cached = -1; + if (cached == -1) { + cached = g_test_slow() || getenv("G_TEST_SLOW") != NULL; + } + return cached; +} + +#undef g_test_slow +#undef g_test_thorough +#undef g_test_quick +#define g_test_slow() qemu_g_test_slow() +#define g_test_thorough() qemu_g_test_slow() +#define g_test_quick() (!qemu_g_test_slow()) + #pragma GCC diagnostic pop #endif diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h index 2ae8bc1ded..674f6958e9 100644 --- a/include/hw/acpi/ghes.h +++ b/include/hw/acpi/ghes.h @@ -64,6 +64,7 @@ enum { typedef struct AcpiGhesState { uint64_t ghes_addr_le; + bool present; /* True if GHES is present at all on this board */ } AcpiGhesState; void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker); @@ -72,4 +73,12 @@ void acpi_build_hest(GArray *table_data, BIOSLinker *linker, void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s, GArray *hardware_errors); int acpi_ghes_record_errors(uint8_t notify, uint64_t error_physical_addr); + +/** + * acpi_ghes_present: Report whether ACPI GHES table is present + * + * Returns: true if the system has an ACPI GHES table and it is + * safe to call acpi_ghes_record_errors() to record a memory error. + */ +bool acpi_ghes_present(void); #endif diff --git a/include/hw/acpi/ich9.h b/include/hw/acpi/ich9.h index df519e40b5..a329ce43ab 100644 --- a/include/hw/acpi/ich9.h +++ b/include/hw/acpi/ich9.h @@ -24,10 +24,13 @@ #include "hw/acpi/acpi.h" #include "hw/acpi/cpu_hotplug.h" #include "hw/acpi/cpu.h" +#include "hw/acpi/pcihp.h" #include "hw/acpi/memory_hotplug.h" #include "hw/acpi/acpi_dev_interface.h" #include "hw/acpi/tco.h" +#define ACPI_PCIHP_ADDR_ICH9 0x0cc4 + typedef struct ICH9LPCPMRegs { /* * In ich9 spec says that pm1_cnt register is 32bit width and @@ -53,6 +56,8 @@ typedef struct ICH9LPCPMRegs { AcpiCpuHotplug gpe_cpu; CPUHotplugState cpuhp_state; + bool use_acpi_hotplug_bridge; + AcpiPciHpState acpi_pci_hotplug; MemHotplugState acpi_memory_hotplug; uint8_t disable_s3; diff --git a/include/hw/acpi/pcihp.h b/include/hw/acpi/pcihp.h index 2dd90aea30..af1a169fc3 100644 --- a/include/hw/acpi/pcihp.h +++ b/include/hw/acpi/pcihp.h @@ -55,7 +55,8 @@ typedef struct AcpiPciHpState { } AcpiPciHpState; void acpi_pcihp_init(Object *owner, AcpiPciHpState *, PCIBus *root, - MemoryRegion *address_space_io, bool bridges_enabled); + MemoryRegion *address_space_io, bool bridges_enabled, + uint16_t io_base); void acpi_pcihp_device_pre_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp); diff --git a/include/hw/acpi/tpm.h b/include/hw/acpi/tpm.h index 1a2a57a21f..559ba6906c 100644 --- a/include/hw/acpi/tpm.h +++ b/include/hw/acpi/tpm.h @@ -21,6 +21,8 @@ #include "hw/acpi/aml-build.h" #include "sysemu/tpm.h" +#ifdef CONFIG_TPM + #define TPM_TIS_ADDR_BASE 0xFED40000 #define TPM_TIS_ADDR_SIZE 0x5000 @@ -209,4 +211,6 @@ REG32(CRB_DATA_BUFFER, 0x80) void tpm_build_ppi_acpi(TPMIf *tpm, Aml *dev); +#endif /* CONFIG_TPM */ + #endif /* HW_ACPI_TPM_H */ diff --git a/include/hw/misc/max111x.h b/include/hw/adc/max111x.h similarity index 100% rename from include/hw/misc/max111x.h rename to include/hw/adc/max111x.h diff --git a/include/hw/misc/zynq-xadc.h b/include/hw/adc/zynq-xadc.h similarity index 100% rename from include/hw/misc/zynq-xadc.h rename to include/hw/adc/zynq-xadc.h diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index cc308a5d2c..63025fb27c 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -18,7 +18,7 @@ */ /* - * The Allwinner H3 is a System on Chip containing four ARM Cortex A7 + * The Allwinner H3 is a System on Chip containing four ARM Cortex-A7 * processor cores. Features and specifications include DDR2/DDR3 memory, * SD/MMC storage cards, 10/100/1000Mbit Ethernet, USB 2.0, HDMI and * various I/O modules. diff --git a/include/hw/arm/armsse.h b/include/hw/arm/armsse.h index 36592be62c..9648e7a419 100644 --- a/include/hw/arm/armsse.h +++ b/include/hw/arm/armsse.h @@ -198,6 +198,8 @@ struct ARMSSE { MemoryRegion alias2; MemoryRegion alias3[SSE_MAX_CPUS]; MemoryRegion sram[MAX_SRAM_BANKS]; + MemoryRegion itcm; + MemoryRegion dtcm; qemu_irq *exp_irqs[SSE_MAX_CPUS]; qemu_irq ppc0_irq; diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h index 189b23a8ce..bc6733c518 100644 --- a/include/hw/arm/armv7m.h +++ b/include/hw/arm/armv7m.h @@ -46,6 +46,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(ARMv7MState, ARMV7M) * devices will be automatically layered on top of this view.) * + Property "idau": IDAU interface (forwarded to CPU object) * + Property "init-svtor": secure VTOR reset value (forwarded to CPU object) + * + Property "init-nsvtor": non-secure VTOR reset value (forwarded to CPU object) * + Property "vfp": enable VFP (forwarded to CPU object) * + Property "dsp": enable DSP (forwarded to CPU object) * + Property "enable-bitband": expose bitbanded IO @@ -69,6 +70,7 @@ struct ARMv7MState { MemoryRegion *board_memory; Object *idau; uint32_t init_svtor; + uint32_t init_nsvtor; bool enable_bitband; bool start_powered_off; bool vfp; diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h index 9359d6da33..d9161d26d6 100644 --- a/include/hw/arm/aspeed_soc.h +++ b/include/hw/arm/aspeed_soc.h @@ -21,6 +21,7 @@ #include "hw/rtc/aspeed_rtc.h" #include "hw/i2c/aspeed_i2c.h" #include "hw/ssi/aspeed_smc.h" +#include "hw/misc/aspeed_hace.h" #include "hw/watchdog/wdt_aspeed.h" #include "hw/net/ftgmac100.h" #include "target/arm/cpu.h" @@ -50,6 +51,7 @@ struct AspeedSoCState { AspeedTimerCtrlState timerctrl; AspeedI2CState i2c; AspeedSCUState scu; + AspeedHACEState hace; AspeedXDMAState xdma; AspeedSMCState fmc; AspeedSMCState spi[ASPEED_SPIS_NUM]; @@ -133,6 +135,7 @@ enum { ASPEED_DEV_XDMA, ASPEED_DEV_EMMC, ASPEED_DEV_KCS, + ASPEED_DEV_HACE, }; #endif /* ASPEED_SOC_H */ diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index 479e2346e8..d864879421 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -24,6 +24,7 @@ #include "hw/misc/bcm2835_mphi.h" #include "hw/misc/bcm2835_thermal.h" #include "hw/misc/bcm2835_cprman.h" +#include "hw/misc/bcm2835_powermgt.h" #include "hw/sd/sdhci.h" #include "hw/sd/bcm2835_sdhost.h" #include "hw/gpio/bcm2835_gpio.h" @@ -48,7 +49,7 @@ struct BCM2835PeripheralState { BCM2835MphiState mphi; UnimplementedDeviceState txp; UnimplementedDeviceState armtmr; - UnimplementedDeviceState powermgt; + BCM2835PowerMgtState powermgt; BCM2835CprmanState cprman; PL011State uart0; BCM2835AuxState aux; diff --git a/include/hw/arm/stm32f100_soc.h b/include/hw/arm/stm32f100_soc.h new file mode 100644 index 0000000000..71bffcf4fd --- /dev/null +++ b/include/hw/arm/stm32f100_soc.h @@ -0,0 +1,57 @@ +/* + * STM32F100 SoC + * + * Copyright (c) 2021 Alexandre Iooss + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef HW_ARM_STM32F100_SOC_H +#define HW_ARM_STM32F100_SOC_H + +#include "hw/char/stm32f2xx_usart.h" +#include "hw/ssi/stm32f2xx_spi.h" +#include "hw/arm/armv7m.h" +#include "qom/object.h" + +#define TYPE_STM32F100_SOC "stm32f100-soc" +OBJECT_DECLARE_SIMPLE_TYPE(STM32F100State, STM32F100_SOC) + +#define STM_NUM_USARTS 3 +#define STM_NUM_SPIS 2 + +#define FLASH_BASE_ADDRESS 0x08000000 +#define FLASH_SIZE (128 * 1024) +#define SRAM_BASE_ADDRESS 0x20000000 +#define SRAM_SIZE (8 * 1024) + +struct STM32F100State { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + char *cpu_type; + + ARMv7MState armv7m; + + STM32F2XXUsartState usart[STM_NUM_USARTS]; + STM32F2XXSPIState spi[STM_NUM_SPIS]; +}; + +#endif diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index 921416f918..9661c46699 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -147,6 +147,7 @@ struct VirtMachineState { OnOffAuto acpi; VirtGICType gic_version; VirtIOMMUType iommu; + bool default_bus_bypass_iommu; VirtMSIControllerType msi_controller; uint16_t virtio_iommu_bdf; struct arm_boot_info bootinfo; diff --git a/include/hw/block/block.h b/include/hw/block/block.h index 007cd8ecd9..20e5019781 100644 --- a/include/hw/block/block.h +++ b/include/hw/block/block.h @@ -19,6 +19,7 @@ typedef struct BlockConf { BlockBackend *blk; + OnOffAuto backend_defaults; uint32_t physical_block_size; uint32_t logical_block_size; uint32_t min_io_size; @@ -48,6 +49,8 @@ static inline unsigned int get_physical_block_exp(BlockConf *conf) } #define DEFINE_BLOCK_PROPERTIES_BASE(_state, _conf) \ + DEFINE_PROP_ON_OFF_AUTO("backend_defaults", _state, \ + _conf.backend_defaults, ON_OFF_AUTO_AUTO), \ DEFINE_PROP_BLOCKSIZE("logical_block_size", _state, \ _conf.logical_block_size), \ DEFINE_PROP_BLOCKSIZE("physical_block_size", _state, \ diff --git a/include/hw/block/flash.h b/include/hw/block/flash.h index 7dde0adcee..86d8363bb0 100644 --- a/include/hw/block/flash.h +++ b/include/hw/block/flash.h @@ -74,6 +74,6 @@ typedef struct { uint8_t ecc_digest(ECCState *s, uint8_t sample); void ecc_reset(ECCState *s); -extern VMStateDescription vmstate_ecc_state; +extern const VMStateDescription vmstate_ecc_state; #endif diff --git a/include/hw/boards.h b/include/hw/boards.h index ad6c8fd537..accd6eff35 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -26,7 +26,6 @@ OBJECT_DECLARE_TYPE(MachineState, MachineClass, MACHINE) extern MachineState *current_machine; void machine_run_board_init(MachineState *machine); -bool machine_smp_parse(MachineState *ms, QemuOpts *opts, Error **errp); bool machine_usb(MachineState *machine); int machine_phandle_start(MachineState *machine); bool machine_dump_guest_core(MachineState *machine); @@ -210,7 +209,7 @@ struct MachineClass { void (*reset)(MachineState *state); void (*wakeup)(MachineState *state); int (*kvm_type)(MachineState *machine, const char *arg); - void (*smp_parse)(MachineState *ms, QemuOpts *opts); + void (*smp_parse)(MachineState *ms, SMPConfiguration *config, Error **errp); BlockInterfaceType block_default_type; int units_per_default_bus; @@ -282,6 +281,7 @@ typedef struct DeviceMemoryState { */ typedef struct CpuTopology { unsigned int cpus; + unsigned int dies; unsigned int cores; unsigned int threads; unsigned int sockets; @@ -353,6 +353,9 @@ struct MachineState { } \ type_init(machine_initfn##_register_types) +extern GlobalProperty hw_compat_6_0[]; +extern const size_t hw_compat_6_0_len; + extern GlobalProperty hw_compat_5_2[]; extern const size_t hw_compat_5_2_len; diff --git a/include/hw/char/avr_usart.h b/include/hw/char/avr_usart.h index bb57532403..62eaa1528e 100644 --- a/include/hw/char/avr_usart.h +++ b/include/hw/char/avr_usart.h @@ -24,7 +24,6 @@ #include "hw/sysbus.h" #include "chardev/char-fe.h" -#include "hw/hw.h" #include "qom/object.h" /* Offsets of registers. */ diff --git a/include/hw/char/ibex_uart.h b/include/hw/char/ibex_uart.h index 546f958eb8..a39985516a 100644 --- a/include/hw/char/ibex_uart.h +++ b/include/hw/char/ibex_uart.h @@ -31,43 +31,6 @@ #include "qemu/timer.h" #include "qom/object.h" -REG32(INTR_STATE, 0x00) - FIELD(INTR_STATE, TX_WATERMARK, 0, 1) - FIELD(INTR_STATE, RX_WATERMARK, 1, 1) - FIELD(INTR_STATE, TX_EMPTY, 2, 1) - FIELD(INTR_STATE, RX_OVERFLOW, 3, 1) -REG32(INTR_ENABLE, 0x04) -REG32(INTR_TEST, 0x08) -REG32(CTRL, 0x0C) - FIELD(CTRL, TX_ENABLE, 0, 1) - FIELD(CTRL, RX_ENABLE, 1, 1) - FIELD(CTRL, NF, 2, 1) - FIELD(CTRL, SLPBK, 4, 1) - FIELD(CTRL, LLPBK, 5, 1) - FIELD(CTRL, PARITY_EN, 6, 1) - FIELD(CTRL, PARITY_ODD, 7, 1) - FIELD(CTRL, RXBLVL, 8, 2) - FIELD(CTRL, NCO, 16, 16) -REG32(STATUS, 0x10) - FIELD(STATUS, TXFULL, 0, 1) - FIELD(STATUS, RXFULL, 1, 1) - FIELD(STATUS, TXEMPTY, 2, 1) - FIELD(STATUS, RXIDLE, 4, 1) - FIELD(STATUS, RXEMPTY, 5, 1) -REG32(RDATA, 0x14) -REG32(WDATA, 0x18) -REG32(FIFO_CTRL, 0x1c) - FIELD(FIFO_CTRL, RXRST, 0, 1) - FIELD(FIFO_CTRL, TXRST, 1, 1) - FIELD(FIFO_CTRL, RXILVL, 2, 3) - FIELD(FIFO_CTRL, TXILVL, 5, 2) -REG32(FIFO_STATUS, 0x20) - FIELD(FIFO_STATUS, TXLVL, 0, 5) - FIELD(FIFO_STATUS, RXLVL, 16, 5) -REG32(OVRD, 0x24) -REG32(VAL, 0x28) -REG32(TIMEOUT_CTRL, 0x2c) - #define IBEX_UART_TX_FIFO_SIZE 16 #define IBEX_UART_CLOCK 50000000 /* 50MHz clock */ diff --git a/include/hw/char/lm32_juart.h b/include/hw/char/lm32_juart.h deleted file mode 100644 index 6fce278326..0000000000 --- a/include/hw/char/lm32_juart.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef QEMU_HW_CHAR_LM32_JUART_H -#define QEMU_HW_CHAR_LM32_JUART_H - -#include "hw/qdev-core.h" - -#define TYPE_LM32_JUART "lm32-juart" - -uint32_t lm32_juart_get_jtx(DeviceState *d); -uint32_t lm32_juart_get_jrx(DeviceState *d); -void lm32_juart_set_jtx(DeviceState *d, uint32_t jtx); -void lm32_juart_set_jrx(DeviceState *d, uint32_t jrx); - -#endif /* QEMU_HW_CHAR_LM32_JUART_H */ diff --git a/include/hw/char/shakti_uart.h b/include/hw/char/shakti_uart.h new file mode 100644 index 0000000000..526c408233 --- /dev/null +++ b/include/hw/char/shakti_uart.h @@ -0,0 +1,74 @@ +/* + * SHAKTI UART + * + * Copyright (c) 2021 Vijai Kumar K + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef HW_SHAKTI_UART_H +#define HW_SHAKTI_UART_H + +#include "hw/sysbus.h" +#include "chardev/char-fe.h" + +#define SHAKTI_UART_BAUD 0x00 +#define SHAKTI_UART_TX 0x04 +#define SHAKTI_UART_RX 0x08 +#define SHAKTI_UART_STATUS 0x0C +#define SHAKTI_UART_DELAY 0x10 +#define SHAKTI_UART_CONTROL 0x14 +#define SHAKTI_UART_INT_EN 0x18 +#define SHAKTI_UART_IQ_CYCLES 0x1C +#define SHAKTI_UART_RX_THRES 0x20 + +#define SHAKTI_UART_STATUS_TX_EMPTY (1 << 0) +#define SHAKTI_UART_STATUS_TX_FULL (1 << 1) +#define SHAKTI_UART_STATUS_RX_NOT_EMPTY (1 << 2) +#define SHAKTI_UART_STATUS_RX_FULL (1 << 3) +/* 9600 8N1 is the default setting */ +/* Reg value = (50000000 Hz)/(16 * 9600)*/ +#define SHAKTI_UART_BAUD_DEFAULT 0x0145 +#define SHAKTI_UART_CONTROL_DEFAULT 0x0100 + +#define TYPE_SHAKTI_UART "shakti-uart" +#define SHAKTI_UART(obj) \ + OBJECT_CHECK(ShaktiUartState, (obj), TYPE_SHAKTI_UART) + +typedef struct { + /* */ + SysBusDevice parent_obj; + + /* */ + MemoryRegion mmio; + + uint32_t uart_baud; + uint32_t uart_tx; + uint32_t uart_rx; + uint32_t uart_status; + uint32_t uart_delay; + uint32_t uart_control; + uint32_t uart_interrupt; + uint32_t uart_iq_cycles; + uint32_t uart_rx_threshold; + + CharBackend chr; +} ShaktiUartState; + +#endif /* HW_SHAKTI_UART_H */ diff --git a/include/hw/char/sifive_uart.h b/include/hw/char/sifive_uart.h index 3e962be659..7f6c79f8bd 100644 --- a/include/hw/char/sifive_uart.h +++ b/include/hw/char/sifive_uart.h @@ -21,6 +21,7 @@ #define HW_SIFIVE_UART_H #include "chardev/char-fe.h" +#include "hw/qdev-properties.h" #include "hw/sysbus.h" #include "qom/object.h" @@ -49,12 +50,10 @@ enum { #define SIFIVE_UART_GET_TXCNT(txctrl) ((txctrl >> 16) & 0x7) #define SIFIVE_UART_GET_RXCNT(rxctrl) ((rxctrl >> 16) & 0x7) +#define SIFIVE_UART_RX_FIFO_SIZE 8 #define TYPE_SIFIVE_UART "riscv.sifive.uart" - -typedef struct SiFiveUARTState SiFiveUARTState; -DECLARE_INSTANCE_CHECKER(SiFiveUARTState, SIFIVE_UART, - TYPE_SIFIVE_UART) +OBJECT_DECLARE_SIMPLE_TYPE(SiFiveUARTState, SIFIVE_UART) struct SiFiveUARTState { /*< private >*/ @@ -64,8 +63,8 @@ struct SiFiveUARTState { qemu_irq irq; MemoryRegion mmio; CharBackend chr; - uint8_t rx_fifo[8]; - unsigned int rx_fifo_len; + uint8_t rx_fifo[SIFIVE_UART_RX_FIFO_SIZE]; + uint8_t rx_fifo_len; uint32_t ie; uint32_t ip; uint32_t txctrl; diff --git a/include/hw/core/accel-cpu.h b/include/hw/core/accel-cpu.h index 24a6697412..5dbfd79955 100644 --- a/include/hw/core/accel-cpu.h +++ b/include/hw/core/accel-cpu.h @@ -32,7 +32,7 @@ typedef struct AccelCPUClass { void (*cpu_class_init)(CPUClass *cc); void (*cpu_instance_init)(CPUState *cpu); - void (*cpu_realizefn)(CPUState *cpu, Error **errp); + bool (*cpu_realizefn)(CPUState *cpu, Error **errp); } AccelCPUClass; #endif /* ACCEL_CPU_H */ diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index 6af097bda5..b6664cc1c9 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -80,6 +80,9 @@ struct TCGCPUOps; /* see accel-cpu.h */ struct AccelCPUClass; +/* see sysemu-cpu-ops.h */ +struct SysemuCPUOps; + /** * CPUClass: * @class_by_name: Callback to map -cpu command line model name to an @@ -87,16 +90,9 @@ struct AccelCPUClass; * @parse_features: Callback to parse command line arguments. * @reset_dump_flags: #CPUDumpFlags to use for reset logging. * @has_work: Callback for checking if there is work to do. - * @virtio_is_big_endian: Callback to return %true if a CPU which supports - * runtime configurable endianness is currently big-endian. Non-configurable - * CPUs can use the default implementation of this method. This method should - * not be used by any callers other than the pre-1.0 virtio devices. * @memory_rw_debug: Callback for GDB memory access. * @dump_state: Callback for dumping state. - * @dump_statistics: Callback for dumping statistics. * @get_arch_id: Callback for getting architecture-dependent CPU ID. - * @get_paging_enabled: Callback for inquiring whether paging is enabled. - * @get_memory_mapping: Callback for obtaining the memory mappings. * @set_pc: Callback for setting the Program Counter register. This * should have the semantics used by the target architecture when * setting the PC from a source such as an ELF file entry point; @@ -105,24 +101,11 @@ struct AccelCPUClass; * If the target behaviour here is anything other than "set * the PC register to the value passed in" then the target must * also implement the synchronize_from_tb hook. - * @get_phys_page_debug: Callback for obtaining a physical address. - * @get_phys_page_attrs_debug: Callback for obtaining a physical address and the - * associated memory transaction attributes to use for the access. - * CPUs which use memory transaction attributes should implement this - * instead of get_phys_page_debug. - * @asidx_from_attrs: Callback to return the CPU AddressSpace to use for - * a memory access with the specified memory transaction attributes. * @gdb_read_register: Callback for letting GDB read a register. * @gdb_write_register: Callback for letting GDB write a register. - * @write_elf64_note: Callback for writing a CPU-specific ELF note to a - * 64-bit VM coredump. - * @write_elf32_qemunote: Callback for writing a CPU- and QEMU-specific ELF - * note to a 32-bit VM coredump. - * @write_elf32_note: Callback for writing a CPU-specific ELF note to a - * 32-bit VM coredump. - * @write_elf32_qemunote: Callback for writing a CPU- and QEMU-specific ELF - * note to a 32-bit VM coredump. - * @vmsd: State description for migration. + * @gdb_adjust_breakpoint: Callback for adjusting the address of a + * breakpoint. Used by AVR to handle a gdb mis-feature with + * its Harvard architecture split code and data. * @gdb_num_core_regs: Number of core registers accessible to GDB. * @gdb_core_xml_file: File name for core registers GDB XML description. * @gdb_stop_before_watchpoint: Indicates whether GDB expects the CPU to stop @@ -150,34 +133,15 @@ struct CPUClass { int reset_dump_flags; bool (*has_work)(CPUState *cpu); - bool (*virtio_is_big_endian)(CPUState *cpu); int (*memory_rw_debug)(CPUState *cpu, vaddr addr, uint8_t *buf, int len, bool is_write); void (*dump_state)(CPUState *cpu, FILE *, int flags); - GuestPanicInformation* (*get_crash_info)(CPUState *cpu); - void (*dump_statistics)(CPUState *cpu, int flags); int64_t (*get_arch_id)(CPUState *cpu); - bool (*get_paging_enabled)(const CPUState *cpu); - void (*get_memory_mapping)(CPUState *cpu, MemoryMappingList *list, - Error **errp); void (*set_pc)(CPUState *cpu, vaddr value); - hwaddr (*get_phys_page_debug)(CPUState *cpu, vaddr addr); - hwaddr (*get_phys_page_attrs_debug)(CPUState *cpu, vaddr addr, - MemTxAttrs *attrs); - int (*asidx_from_attrs)(CPUState *cpu, MemTxAttrs attrs); int (*gdb_read_register)(CPUState *cpu, GByteArray *buf, int reg); int (*gdb_write_register)(CPUState *cpu, uint8_t *buf, int reg); + vaddr (*gdb_adjust_breakpoint)(CPUState *cpu, vaddr addr); - int (*write_elf64_note)(WriteCoreDumpFunction f, CPUState *cpu, - int cpuid, void *opaque); - int (*write_elf64_qemunote)(WriteCoreDumpFunction f, CPUState *cpu, - void *opaque); - int (*write_elf32_note)(WriteCoreDumpFunction f, CPUState *cpu, - int cpuid, void *opaque); - int (*write_elf32_qemunote)(WriteCoreDumpFunction f, CPUState *cpu, - void *opaque); - - const VMStateDescription *vmsd; const char *gdb_core_xml_file; gchar * (*gdb_arch_name)(CPUState *cpu); const char * (*gdb_get_dynamic_xml)(CPUState *cpu, const char *xmlname); @@ -190,8 +154,17 @@ struct CPUClass { bool gdb_stop_before_watchpoint; struct AccelCPUClass *accel_cpu; + /* when system emulation is not available, this pointer is NULL */ + const struct SysemuCPUOps *sysemu_ops; + /* when TCG is not available, this pointer is NULL */ - struct TCGCPUOps *tcg_ops; + const struct TCGCPUOps *tcg_ops; + + /* + * if not NULL, this is called in order for the CPUClass to initialize + * class data that depends on the accelerator, see accel/accel-common.c. + */ + void (*init_accel_cpu)(struct AccelCPUClass *accel_cpu, CPUClass *cc); }; /* @@ -258,6 +231,7 @@ struct KVMState; struct kvm_run; struct hax_vcpu_state; +struct hvf_vcpu_state; #define TB_JMP_CACHE_BITS 12 #define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS) @@ -336,6 +310,10 @@ struct qemu_work_item; * @ignore_memory_transaction_failures: Cached copy of the MachineState * flag of the same name: allows the board to suppress calling of the * CPU do_transaction_failed hook function. + * @kvm_dirty_gfns: Points to the KVM dirty ring for this CPU when KVM dirty + * ring is enabled. + * @kvm_fetch_index: Keeps the index that we last fetched from the per-vCPU + * dirty ring structure. * * State of one CPU core or thread. */ @@ -409,9 +387,12 @@ struct CPUState { */ uintptr_t mem_io_pc; + /* Only used in KVM */ int kvm_fd; struct KVMState *kvm_state; struct kvm_run *kvm_run; + struct kvm_dirty_gfn *kvm_dirty_gfns; + uint32_t kvm_fetch_index; /* Used for events with 'vcpu' and *without* the 'disabled' properties */ DECLARE_BITMAP(trace_dstate_delayed, CPU_TRACE_DSTATE_MAX_EVENTS); @@ -445,7 +426,7 @@ struct CPUState { struct hax_vcpu_state *hax_vcpu; - int hvf_fd; + struct hvf_vcpu_state *hvf; /* track IOMMUs whose translations we've cached in the TCG TLB */ GArray *iommu_notifiers; @@ -571,16 +552,6 @@ enum CPUDumpFlags { */ void cpu_dump_state(CPUState *cpu, FILE *f, int flags); -/** - * cpu_dump_statistics: - * @cpu: The CPU whose state is to be dumped. - * @flags: Flags what to dump. - * - * Dump CPU statistics to the current monitor if we have one, else to - * stdout. - */ -void cpu_dump_statistics(CPUState *cpu, int flags); - #ifndef CONFIG_USER_ONLY /** * cpu_get_phys_page_attrs_debug: @@ -595,18 +566,8 @@ void cpu_dump_statistics(CPUState *cpu, int flags); * * Returns: Corresponding physical page address or -1 if no page found. */ -static inline hwaddr cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, - MemTxAttrs *attrs) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - - if (cc->get_phys_page_attrs_debug) { - return cc->get_phys_page_attrs_debug(cpu, addr, attrs); - } - /* Fallback for CPUs which don't implement the _attrs_ hook */ - *attrs = MEMTXATTRS_UNSPECIFIED; - return cc->get_phys_page_debug(cpu, addr); -} +hwaddr cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, + MemTxAttrs *attrs); /** * cpu_get_phys_page_debug: @@ -618,12 +579,7 @@ static inline hwaddr cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, * * Returns: Corresponding physical page address or -1 if no page found. */ -static inline hwaddr cpu_get_phys_page_debug(CPUState *cpu, vaddr addr) -{ - MemTxAttrs attrs = {}; - - return cpu_get_phys_page_attrs_debug(cpu, addr, &attrs); -} +hwaddr cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); /** cpu_asidx_from_attrs: * @cpu: CPU @@ -632,17 +588,16 @@ static inline hwaddr cpu_get_phys_page_debug(CPUState *cpu, vaddr addr) * Returns the address space index specifying the CPU AddressSpace * to use for a memory access with the given transaction attributes. */ -static inline int cpu_asidx_from_attrs(CPUState *cpu, MemTxAttrs attrs) -{ - CPUClass *cc = CPU_GET_CLASS(cpu); - int ret = 0; +int cpu_asidx_from_attrs(CPUState *cpu, MemTxAttrs attrs); - if (cc->asidx_from_attrs) { - ret = cc->asidx_from_attrs(cpu, attrs); - assert(ret < cpu->num_ases && ret >= 0); - } - return ret; -} +/** + * cpu_virtio_is_big_endian: + * @cpu: CPU + + * Returns %true if a CPU which supports runtime configurable endianness + * is currently big-endian. + */ +bool cpu_virtio_is_big_endian(CPUState *cpu); #endif /* CONFIG_USER_ONLY */ @@ -1105,10 +1060,8 @@ bool target_words_bigendian(void); #ifdef NEED_CPU_H #ifdef CONFIG_SOFTMMU + extern const VMStateDescription vmstate_cpu_common; -#else -#define vmstate_cpu_common vmstate_dummy -#endif #define VMSTATE_CPU() { \ .name = "parent_obj", \ @@ -1117,6 +1070,7 @@ extern const VMStateDescription vmstate_cpu_common; .flags = VMS_STRUCT, \ .offset = 0, \ } +#endif /* CONFIG_SOFTMMU */ #endif /* NEED_CPU_H */ diff --git a/include/hw/core/sysemu-cpu-ops.h b/include/hw/core/sysemu-cpu-ops.h new file mode 100644 index 0000000000..a9ba39e5f2 --- /dev/null +++ b/include/hw/core/sysemu-cpu-ops.h @@ -0,0 +1,92 @@ +/* + * CPU operations specific to system emulation + * + * Copyright (c) 2012 SUSE LINUX Products GmbH + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef SYSEMU_CPU_OPS_H +#define SYSEMU_CPU_OPS_H + +#include "hw/core/cpu.h" + +/* + * struct SysemuCPUOps: System operations specific to a CPU class + */ +typedef struct SysemuCPUOps { + /** + * @get_memory_mapping: Callback for obtaining the memory mappings. + */ + void (*get_memory_mapping)(CPUState *cpu, MemoryMappingList *list, + Error **errp); + /** + * @get_paging_enabled: Callback for inquiring whether paging is enabled. + */ + bool (*get_paging_enabled)(const CPUState *cpu); + /** + * @get_phys_page_debug: Callback for obtaining a physical address. + */ + hwaddr (*get_phys_page_debug)(CPUState *cpu, vaddr addr); + /** + * @get_phys_page_attrs_debug: Callback for obtaining a physical address + * and the associated memory transaction attributes to use for the + * access. + * CPUs which use memory transaction attributes should implement this + * instead of get_phys_page_debug. + */ + hwaddr (*get_phys_page_attrs_debug)(CPUState *cpu, vaddr addr, + MemTxAttrs *attrs); + /** + * @asidx_from_attrs: Callback to return the CPU AddressSpace to use for + * a memory access with the specified memory transaction attributes. + */ + int (*asidx_from_attrs)(CPUState *cpu, MemTxAttrs attrs); + /** + * @get_crash_info: Callback for reporting guest crash information in + * GUEST_PANICKED events. + */ + GuestPanicInformation* (*get_crash_info)(CPUState *cpu); + /** + * @write_elf32_note: Callback for writing a CPU-specific ELF note to a + * 32-bit VM coredump. + */ + int (*write_elf32_note)(WriteCoreDumpFunction f, CPUState *cpu, + int cpuid, void *opaque); + /** + * @write_elf64_note: Callback for writing a CPU-specific ELF note to a + * 64-bit VM coredump. + */ + int (*write_elf64_note)(WriteCoreDumpFunction f, CPUState *cpu, + int cpuid, void *opaque); + /** + * @write_elf32_qemunote: Callback for writing a CPU- and QEMU-specific ELF + * note to a 32-bit VM coredump. + */ + int (*write_elf32_qemunote)(WriteCoreDumpFunction f, CPUState *cpu, + void *opaque); + /** + * @write_elf64_qemunote: Callback for writing a CPU- and QEMU-specific ELF + * note to a 64-bit VM coredump. + */ + int (*write_elf64_qemunote)(WriteCoreDumpFunction f, CPUState *cpu, + void *opaque); + /** + * @virtio_is_big_endian: Callback to return %true if a CPU which supports + * runtime configurable endianness is currently big-endian. + * Non-configurable CPUs can use the default implementation of this method. + * This method should not be used by any callers other than the pre-1.0 + * virtio devices. + */ + bool (*virtio_is_big_endian)(CPUState *cpu); + + /** + * @legacy_vmsd: Legacy state for migration. + * Do not use in new targets, use #DeviceClass::vmsd instead. + */ + const VMStateDescription *legacy_vmsd; + +} SysemuCPUOps; + +#endif /* SYSEMU_CPU_OPS_H */ diff --git a/include/hw/core/tcg-cpu-ops.h b/include/hw/core/tcg-cpu-ops.h index 72d791438c..eab27d0c03 100644 --- a/include/hw/core/tcg-cpu-ops.h +++ b/include/hw/core/tcg-cpu-ops.h @@ -88,6 +88,12 @@ struct TCGCPUOps { */ bool (*debug_check_watchpoint)(CPUState *cpu, CPUWatchpoint *wp); + /** + * @debug_check_breakpoint: return true if the architectural + * breakpoint whose PC has matched should really fire. + */ + bool (*debug_check_breakpoint)(CPUState *cpu); + /** * @io_recompile_replay_branch: Callback for cpu_io_recompile. * diff --git a/include/hw/display/edid.h b/include/hw/display/edid.h index 1f8fc9b375..520f8ec202 100644 --- a/include/hw/display/edid.h +++ b/include/hw/display/edid.h @@ -11,6 +11,7 @@ typedef struct qemu_edid_info { uint32_t prefy; uint32_t maxx; uint32_t maxy; + uint32_t refresh_rate; } qemu_edid_info; void qemu_edid_generate(uint8_t *edid, size_t size, @@ -21,10 +22,11 @@ void qemu_edid_region_io(MemoryRegion *region, Object *owner, uint32_t qemu_edid_dpi_to_mm(uint32_t dpi, uint32_t res); -#define DEFINE_EDID_PROPERTIES(_state, _edid_info) \ - DEFINE_PROP_UINT32("xres", _state, _edid_info.prefx, 0), \ - DEFINE_PROP_UINT32("yres", _state, _edid_info.prefy, 0), \ - DEFINE_PROP_UINT32("xmax", _state, _edid_info.maxx, 0), \ - DEFINE_PROP_UINT32("ymax", _state, _edid_info.maxy, 0) +#define DEFINE_EDID_PROPERTIES(_state, _edid_info) \ + DEFINE_PROP_UINT32("xres", _state, _edid_info.prefx, 0), \ + DEFINE_PROP_UINT32("yres", _state, _edid_info.prefy, 0), \ + DEFINE_PROP_UINT32("xmax", _state, _edid_info.maxx, 0), \ + DEFINE_PROP_UINT32("ymax", _state, _edid_info.maxy, 0), \ + DEFINE_PROP_UINT32("refresh_rate", _state, _edid_info.refresh_rate, 0) #endif /* EDID_H */ diff --git a/include/hw/display/milkymist_tmu2.h b/include/hw/display/milkymist_tmu2.h deleted file mode 100644 index fdce9535a1..0000000000 --- a/include/hw/display/milkymist_tmu2.h +++ /dev/null @@ -1,42 +0,0 @@ -/* - * QEMU model of the Milkymist texture mapping unit. - * - * Copyright (c) 2010 Michael Walle - * Copyright (c) 2010 Sebastien Bourdeauducq - * - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see . - * - * - * Specification available at: - * http://milkymist.walle.cc/socdoc/tmu2.pdf - * - */ - -#ifndef HW_DISPLAY_MILKYMIST_TMU2_H -#define HW_DISPLAY_MILKYMIST_TMU2_H - -#include "exec/hwaddr.h" -#include "hw/qdev-core.h" - -#if defined(CONFIG_X11) && defined(CONFIG_OPENGL) -DeviceState *milkymist_tmu2_create(hwaddr base, qemu_irq irq); -#else -static inline DeviceState *milkymist_tmu2_create(hwaddr base, qemu_irq irq) -{ - return NULL; -} -#endif - -#endif /* HW_DISPLAY_MILKYMIST_TMU2_H */ diff --git a/include/hw/display/vga.h b/include/hw/display/vga.h index ca0003dbfd..5f7825e0e3 100644 --- a/include/hw/display/vga.h +++ b/include/hw/display/vga.h @@ -11,6 +11,12 @@ #include "exec/hwaddr.h" +/* + * modules can reference this symbol to avoid being loaded + * into system emulators without vga support + */ +extern bool have_vga; + enum vga_retrace_method { VGA_RETRACE_DUMB, VGA_RETRACE_PRECISE diff --git a/include/hw/elf_ops.h b/include/hw/elf_ops.h index 6ee458e7bc..1c37cec4ae 100644 --- a/include/hw/elf_ops.h +++ b/include/hw/elf_ops.h @@ -368,14 +368,6 @@ static int glue(load_elf, SZ)(const char *name, int fd, } } break; - case EM_MOXIE: - if (ehdr.e_machine != EM_MOXIE) { - if (ehdr.e_machine != EM_MOXIE_OLD) { - ret = ELF_LOAD_WRONG_ARCH; - goto fail; - } - } - break; case EM_MIPS: case EM_NANOMIPS: if ((ehdr.e_machine != EM_MIPS) && diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h index 02a0ced0a0..5a0dd0c8cf 100644 --- a/include/hw/firmware/smbios.h +++ b/include/hw/firmware/smbios.h @@ -258,6 +258,17 @@ struct smbios_type_32 { uint8_t boot_status; } QEMU_PACKED; +/* SMBIOS type 41 - Onboard Devices Extended Information */ +struct smbios_type_41 { + struct smbios_structure_header header; + uint8_t reference_designation_str; + uint8_t device_type; + uint8_t device_type_instance; + uint16_t segment_group_number; + uint8_t bus_number; + uint8_t device_number; +} QEMU_PACKED; + /* SMBIOS type 127 -- End-of-table */ struct smbios_type_127 { struct smbios_structure_header header; @@ -273,5 +284,6 @@ void smbios_get_tables(MachineState *ms, const struct smbios_phys_mem_area *mem_array, const unsigned int mem_array_size, uint8_t **tables, size_t *tables_len, - uint8_t **anchor, size_t *anchor_len); + uint8_t **anchor, size_t *anchor_len, + Error **errp); #endif /* QEMU_SMBIOS_H */ diff --git a/include/hw/i2c/i2c.h b/include/hw/i2c/i2c.h index 277dd9f2d6..5ca3b708c0 100644 --- a/include/hw/i2c/i2c.h +++ b/include/hw/i2c/i2c.h @@ -16,6 +16,7 @@ enum i2c_event { I2C_NACK /* Masker NACKed a receive byte. */ }; +typedef struct I2CNodeList I2CNodeList; #define TYPE_I2C_SLAVE "i2c-slave" OBJECT_DECLARE_TYPE(I2CSlave, I2CSlaveClass, @@ -39,6 +40,16 @@ struct I2CSlaveClass { * return code is not used and should be zero. */ int (*event)(I2CSlave *s, enum i2c_event event); + + /* + * Check if this device matches the address provided. Returns bool of + * true if it matches (or broadcast), and updates the device list, false + * otherwise. + * + * If broadcast is true, match should add the device and return true. + */ + bool (*match_and_add)(I2CSlave *candidate, uint8_t address, bool broadcast, + I2CNodeList *current_devs); }; struct I2CSlave { @@ -58,22 +69,58 @@ struct I2CNode { QLIST_ENTRY(I2CNode) next; }; +typedef QLIST_HEAD(I2CNodeList, I2CNode) I2CNodeList; + struct I2CBus { BusState qbus; - QLIST_HEAD(, I2CNode) current_devs; + I2CNodeList current_devs; uint8_t saved_address; bool broadcast; }; I2CBus *i2c_init_bus(DeviceState *parent, const char *name); -void i2c_set_slave_address(I2CSlave *dev, uint8_t address); int i2c_bus_busy(I2CBus *bus); -int i2c_start_transfer(I2CBus *bus, uint8_t address, int recv); + +/** + * i2c_start_transfer: start a transfer on an I2C bus. + * + * @bus: #I2CBus to be used + * @address: address of the slave + * @is_recv: indicates the transfer direction + * + * When @is_recv is a known boolean constant, use the + * i2c_start_recv() or i2c_start_send() helper instead. + * + * Returns: 0 on success, -1 on error + */ +int i2c_start_transfer(I2CBus *bus, uint8_t address, bool is_recv); + +/** + * i2c_start_recv: start a 'receive' transfer on an I2C bus. + * + * @bus: #I2CBus to be used + * @address: address of the slave + * + * Returns: 0 on success, -1 on error + */ +int i2c_start_recv(I2CBus *bus, uint8_t address); + +/** + * i2c_start_send: start a 'send' transfer on an I2C bus. + * + * @bus: #I2CBus to be used + * @address: address of the slave + * + * Returns: 0 on success, -1 on error + */ +int i2c_start_send(I2CBus *bus, uint8_t address); + void i2c_end_transfer(I2CBus *bus); void i2c_nack(I2CBus *bus); -int i2c_send_recv(I2CBus *bus, uint8_t *data, bool send); int i2c_send(I2CBus *bus, uint8_t data); uint8_t i2c_recv(I2CBus *bus); +bool i2c_scan_bus(I2CBus *bus, uint8_t address, bool broadcast, + I2CNodeList *current_devs); /** * Create an I2C slave device on the heap. @@ -127,8 +174,12 @@ I2CSlave *i2c_slave_create_simple(I2CBus *bus, const char *name, uint8_t addr); */ bool i2c_slave_realize_and_unref(I2CSlave *dev, I2CBus *bus, Error **errp); -/* lm832x.c */ -void lm832x_key_event(DeviceState *dev, int key, int state); +/** + * Set the I2C bus address of a slave device + * @dev: I2C slave device + * @address: I2C address of the slave when put on a bus + */ +void i2c_slave_set_address(I2CSlave *dev, uint8_t address); extern const VMStateDescription vmstate_i2c_slave; diff --git a/include/hw/i2c/i2c_mux_pca954x.h b/include/hw/i2c/i2c_mux_pca954x.h new file mode 100644 index 0000000000..8aaf9bbc39 --- /dev/null +++ b/include/hw/i2c/i2c_mux_pca954x.h @@ -0,0 +1,19 @@ +#ifndef QEMU_I2C_MUX_PCA954X +#define QEMU_I2C_MUX_PCA954X + +#include "hw/i2c/i2c.h" + +#define TYPE_PCA9546 "pca9546" +#define TYPE_PCA9548 "pca9548" + +/** + * Retrieves the i2c bus associated with the specified channel on this i2c + * mux. + * @mux: an i2c mux device. + * @channel: the i2c channel requested + * + * Returns: a pointer to the associated i2c bus. + */ +I2CBus *pca954x_i2c_get_bus(I2CSlave *mux, uint8_t channel); + +#endif diff --git a/include/hw/i2c/pmbus_device.h b/include/hw/i2c/pmbus_device.h new file mode 100644 index 0000000000..62bd38c83f --- /dev/null +++ b/include/hw/i2c/pmbus_device.h @@ -0,0 +1,517 @@ +/* + * QEMU PMBus device emulation + * + * Copyright 2021 Google LLC + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_PMBUS_DEVICE_H +#define HW_PMBUS_DEVICE_H + +#include "qemu/bitops.h" +#include "hw/i2c/smbus_slave.h" + +enum pmbus_registers { + PMBUS_PAGE = 0x00, /* R/W byte */ + PMBUS_OPERATION = 0x01, /* R/W byte */ + PMBUS_ON_OFF_CONFIG = 0x02, /* R/W byte */ + PMBUS_CLEAR_FAULTS = 0x03, /* Send Byte */ + PMBUS_PHASE = 0x04, /* R/W byte */ + PMBUS_PAGE_PLUS_WRITE = 0x05, /* Block Write-only */ + PMBUS_PAGE_PLUS_READ = 0x06, /* Block Read-only */ + PMBUS_WRITE_PROTECT = 0x10, /* R/W byte */ + PMBUS_STORE_DEFAULT_ALL = 0x11, /* Send Byte */ + PMBUS_RESTORE_DEFAULT_ALL = 0x12, /* Send Byte */ + PMBUS_STORE_DEFAULT_CODE = 0x13, /* Write-only Byte */ + PMBUS_RESTORE_DEFAULT_CODE = 0x14, /* Write-only Byte */ + PMBUS_STORE_USER_ALL = 0x15, /* Send Byte */ + PMBUS_RESTORE_USER_ALL = 0x16, /* Send Byte */ + PMBUS_STORE_USER_CODE = 0x17, /* Write-only Byte */ + PMBUS_RESTORE_USER_CODE = 0x18, /* Write-only Byte */ + PMBUS_CAPABILITY = 0x19, /* Read-Only byte */ + PMBUS_QUERY = 0x1A, /* Write-Only */ + PMBUS_SMBALERT_MASK = 0x1B, /* Block read, Word write */ + PMBUS_VOUT_MODE = 0x20, /* R/W byte */ + PMBUS_VOUT_COMMAND = 0x21, /* R/W word */ + PMBUS_VOUT_TRIM = 0x22, /* R/W word */ + PMBUS_VOUT_CAL_OFFSET = 0x23, /* R/W word */ + PMBUS_VOUT_MAX = 0x24, /* R/W word */ + PMBUS_VOUT_MARGIN_HIGH = 0x25, /* R/W word */ + PMBUS_VOUT_MARGIN_LOW = 0x26, /* R/W word */ + PMBUS_VOUT_TRANSITION_RATE = 0x27, /* R/W word */ + PMBUS_VOUT_DROOP = 0x28, /* R/W word */ + PMBUS_VOUT_SCALE_LOOP = 0x29, /* R/W word */ + PMBUS_VOUT_SCALE_MONITOR = 0x2A, /* R/W word */ + PMBUS_COEFFICIENTS = 0x30, /* Read-only block 5 bytes */ + PMBUS_POUT_MAX = 0x31, /* R/W word */ + PMBUS_MAX_DUTY = 0x32, /* R/W word */ + PMBUS_FREQUENCY_SWITCH = 0x33, /* R/W word */ + PMBUS_VIN_ON = 0x35, /* R/W word */ + PMBUS_VIN_OFF = 0x36, /* R/W word */ + PMBUS_INTERLEAVE = 0x37, /* R/W word */ + PMBUS_IOUT_CAL_GAIN = 0x38, /* R/W word */ + PMBUS_IOUT_CAL_OFFSET = 0x39, /* R/W word */ + PMBUS_FAN_CONFIG_1_2 = 0x3A, /* R/W byte */ + PMBUS_FAN_COMMAND_1 = 0x3B, /* R/W word */ + PMBUS_FAN_COMMAND_2 = 0x3C, /* R/W word */ + PMBUS_FAN_CONFIG_3_4 = 0x3D, /* R/W byte */ + PMBUS_FAN_COMMAND_3 = 0x3E, /* R/W word */ + PMBUS_FAN_COMMAND_4 = 0x3F, /* R/W word */ + PMBUS_VOUT_OV_FAULT_LIMIT = 0x40, /* R/W word */ + PMBUS_VOUT_OV_FAULT_RESPONSE = 0x41, /* R/W byte */ + PMBUS_VOUT_OV_WARN_LIMIT = 0x42, /* R/W word */ + PMBUS_VOUT_UV_WARN_LIMIT = 0x43, /* R/W word */ + PMBUS_VOUT_UV_FAULT_LIMIT = 0x44, /* R/W word */ + PMBUS_VOUT_UV_FAULT_RESPONSE = 0x45, /* R/W byte */ + PMBUS_IOUT_OC_FAULT_LIMIT = 0x46, /* R/W word */ + PMBUS_IOUT_OC_FAULT_RESPONSE = 0x47, /* R/W byte */ + PMBUS_IOUT_OC_LV_FAULT_LIMIT = 0x48, /* R/W word */ + PMBUS_IOUT_OC_LV_FAULT_RESPONSE = 0x49, /* R/W byte */ + PMBUS_IOUT_OC_WARN_LIMIT = 0x4A, /* R/W word */ + PMBUS_IOUT_UC_FAULT_LIMIT = 0x4B, /* R/W word */ + PMBUS_IOUT_UC_FAULT_RESPONSE = 0x4C, /* R/W byte */ + PMBUS_OT_FAULT_LIMIT = 0x4F, /* R/W word */ + PMBUS_OT_FAULT_RESPONSE = 0x50, /* R/W byte */ + PMBUS_OT_WARN_LIMIT = 0x51, /* R/W word */ + PMBUS_UT_WARN_LIMIT = 0x52, /* R/W word */ + PMBUS_UT_FAULT_LIMIT = 0x53, /* R/W word */ + PMBUS_UT_FAULT_RESPONSE = 0x54, /* R/W byte */ + PMBUS_VIN_OV_FAULT_LIMIT = 0x55, /* R/W word */ + PMBUS_VIN_OV_FAULT_RESPONSE = 0x56, /* R/W byte */ + PMBUS_VIN_OV_WARN_LIMIT = 0x57, /* R/W word */ + PMBUS_VIN_UV_WARN_LIMIT = 0x58, /* R/W word */ + PMBUS_VIN_UV_FAULT_LIMIT = 0x59, /* R/W word */ + PMBUS_VIN_UV_FAULT_RESPONSE = 0x5A, /* R/W byte */ + PMBUS_IIN_OC_FAULT_LIMIT = 0x5B, /* R/W word */ + PMBUS_IIN_OC_FAULT_RESPONSE = 0x5C, /* R/W byte */ + PMBUS_IIN_OC_WARN_LIMIT = 0x5D, /* R/W word */ + PMBUS_POWER_GOOD_ON = 0x5E, /* R/W word */ + PMBUS_POWER_GOOD_OFF = 0x5F, /* R/W word */ + PMBUS_TON_DELAY = 0x60, /* R/W word */ + PMBUS_TON_RISE = 0x61, /* R/W word */ + PMBUS_TON_MAX_FAULT_LIMIT = 0x62, /* R/W word */ + PMBUS_TON_MAX_FAULT_RESPONSE = 0x63, /* R/W byte */ + PMBUS_TOFF_DELAY = 0x64, /* R/W word */ + PMBUS_TOFF_FALL = 0x65, /* R/W word */ + PMBUS_TOFF_MAX_WARN_LIMIT = 0x66, /* R/W word */ + PMBUS_POUT_OP_FAULT_LIMIT = 0x68, /* R/W word */ + PMBUS_POUT_OP_FAULT_RESPONSE = 0x69, /* R/W byte */ + PMBUS_POUT_OP_WARN_LIMIT = 0x6A, /* R/W word */ + PMBUS_PIN_OP_WARN_LIMIT = 0x6B, /* R/W word */ + PMBUS_STATUS_BYTE = 0x78, /* R/W byte */ + PMBUS_STATUS_WORD = 0x79, /* R/W word */ + PMBUS_STATUS_VOUT = 0x7A, /* R/W byte */ + PMBUS_STATUS_IOUT = 0x7B, /* R/W byte */ + PMBUS_STATUS_INPUT = 0x7C, /* R/W byte */ + PMBUS_STATUS_TEMPERATURE = 0x7D, /* R/W byte */ + PMBUS_STATUS_CML = 0x7E, /* R/W byte */ + PMBUS_STATUS_OTHER = 0x7F, /* R/W byte */ + PMBUS_STATUS_MFR_SPECIFIC = 0x80, /* R/W byte */ + PMBUS_STATUS_FANS_1_2 = 0x81, /* R/W byte */ + PMBUS_STATUS_FANS_3_4 = 0x82, /* R/W byte */ + PMBUS_READ_EIN = 0x86, /* Read-Only block 5 bytes */ + PMBUS_READ_EOUT = 0x87, /* Read-Only block 5 bytes */ + PMBUS_READ_VIN = 0x88, /* Read-Only word */ + PMBUS_READ_IIN = 0x89, /* Read-Only word */ + PMBUS_READ_VCAP = 0x8A, /* Read-Only word */ + PMBUS_READ_VOUT = 0x8B, /* Read-Only word */ + PMBUS_READ_IOUT = 0x8C, /* Read-Only word */ + PMBUS_READ_TEMPERATURE_1 = 0x8D, /* Read-Only word */ + PMBUS_READ_TEMPERATURE_2 = 0x8E, /* Read-Only word */ + PMBUS_READ_TEMPERATURE_3 = 0x8F, /* Read-Only word */ + PMBUS_READ_FAN_SPEED_1 = 0x90, /* Read-Only word */ + PMBUS_READ_FAN_SPEED_2 = 0x91, /* Read-Only word */ + PMBUS_READ_FAN_SPEED_3 = 0x92, /* Read-Only word */ + PMBUS_READ_FAN_SPEED_4 = 0x93, /* Read-Only word */ + PMBUS_READ_DUTY_CYCLE = 0x94, /* Read-Only word */ + PMBUS_READ_FREQUENCY = 0x95, /* Read-Only word */ + PMBUS_READ_POUT = 0x96, /* Read-Only word */ + PMBUS_READ_PIN = 0x97, /* Read-Only word */ + PMBUS_REVISION = 0x98, /* Read-Only byte */ + PMBUS_MFR_ID = 0x99, /* R/W block */ + PMBUS_MFR_MODEL = 0x9A, /* R/W block */ + PMBUS_MFR_REVISION = 0x9B, /* R/W block */ + PMBUS_MFR_LOCATION = 0x9C, /* R/W block */ + PMBUS_MFR_DATE = 0x9D, /* R/W block */ + PMBUS_MFR_SERIAL = 0x9E, /* R/W block */ + PMBUS_APP_PROFILE_SUPPORT = 0x9F, /* Read-Only block-read */ + PMBUS_MFR_VIN_MIN = 0xA0, /* Read-Only word */ + PMBUS_MFR_VIN_MAX = 0xA1, /* Read-Only word */ + PMBUS_MFR_IIN_MAX = 0xA2, /* Read-Only word */ + PMBUS_MFR_PIN_MAX = 0xA3, /* Read-Only word */ + PMBUS_MFR_VOUT_MIN = 0xA4, /* Read-Only word */ + PMBUS_MFR_VOUT_MAX = 0xA5, /* Read-Only word */ + PMBUS_MFR_IOUT_MAX = 0xA6, /* Read-Only word */ + PMBUS_MFR_POUT_MAX = 0xA7, /* Read-Only word */ + PMBUS_MFR_TAMBIENT_MAX = 0xA8, /* Read-Only word */ + PMBUS_MFR_TAMBIENT_MIN = 0xA9, /* Read-Only word */ + PMBUS_MFR_EFFICIENCY_LL = 0xAA, /* Read-Only block 14 bytes */ + PMBUS_MFR_EFFICIENCY_HL = 0xAB, /* Read-Only block 14 bytes */ + PMBUS_MFR_PIN_ACCURACY = 0xAC, /* Read-Only byte */ + PMBUS_IC_DEVICE_ID = 0xAD, /* Read-Only block-read */ + PMBUS_IC_DEVICE_REV = 0xAE, /* Read-Only block-read */ + PMBUS_MFR_MAX_TEMP_1 = 0xC0, /* R/W word */ + PMBUS_MFR_MAX_TEMP_2 = 0xC1, /* R/W word */ + PMBUS_MFR_MAX_TEMP_3 = 0xC2, /* R/W word */ +}; + +/* STATUS_WORD */ +#define PB_STATUS_VOUT BIT(15) +#define PB_STATUS_IOUT_POUT BIT(14) +#define PB_STATUS_INPUT BIT(13) +#define PB_STATUS_WORD_MFR BIT(12) +#define PB_STATUS_POWER_GOOD_N BIT(11) +#define PB_STATUS_FAN BIT(10) +#define PB_STATUS_OTHER BIT(9) +#define PB_STATUS_UNKNOWN BIT(8) +/* STATUS_BYTE */ +#define PB_STATUS_BUSY BIT(7) +#define PB_STATUS_OFF BIT(6) +#define PB_STATUS_VOUT_OV BIT(5) +#define PB_STATUS_IOUT_OC BIT(4) +#define PB_STATUS_VIN_UV BIT(3) +#define PB_STATUS_TEMPERATURE BIT(2) +#define PB_STATUS_CML BIT(1) +#define PB_STATUS_NONE_ABOVE BIT(0) + +/* STATUS_VOUT */ +#define PB_STATUS_VOUT_OV_FAULT BIT(7) /* Output Overvoltage Fault */ +#define PB_STATUS_VOUT_OV_WARN BIT(6) /* Output Overvoltage Warning */ +#define PB_STATUS_VOUT_UV_WARN BIT(5) /* Output Undervoltage Warning */ +#define PB_STATUS_VOUT_UV_FAULT BIT(4) /* Output Undervoltage Fault */ +#define PB_STATUS_VOUT_MAX BIT(3) +#define PB_STATUS_VOUT_TON_MAX_FAULT BIT(2) +#define PB_STATUS_VOUT_TOFF_MAX_WARN BIT(1) + +/* STATUS_IOUT */ +#define PB_STATUS_IOUT_OC_FAULT BIT(7) /* Output Overcurrent Fault */ +#define PB_STATUS_IOUT_OC_LV_FAULT BIT(6) /* Output OC And Low Voltage Fault */ +#define PB_STATUS_IOUT_OC_WARN BIT(5) /* Output Overcurrent Warning */ +#define PB_STATUS_IOUT_UC_FAULT BIT(4) /* Output Undercurrent Fault */ +#define PB_STATUS_CURR_SHARE BIT(3) /* Current Share Fault */ +#define PB_STATUS_PWR_LIM_MODE BIT(2) /* In Power Limiting Mode */ +#define PB_STATUS_POUT_OP_FAULT BIT(1) /* Output Overpower Fault */ +#define PB_STATUS_POUT_OP_WARN BIT(0) /* Output Overpower Warning */ + +/* STATUS_INPUT */ +#define PB_STATUS_INPUT_VIN_OV_FAULT BIT(7) /* Input Overvoltage Fault */ +#define PB_STATUS_INPUT_VIN_OV_WARN BIT(6) /* Input Overvoltage Warning */ +#define PB_STATUS_INPUT_VIN_UV_WARN BIT(5) /* Input Undervoltage Warning */ +#define PB_STATUS_INPUT_VIN_UV_FAULT BIT(4) /* Input Undervoltage Fault */ +#define PB_STATUS_INPUT_IIN_OC_FAULT BIT(2) /* Input Overcurrent Fault */ +#define PB_STATUS_INPUT_IIN_OC_WARN BIT(1) /* Input Overcurrent Warning */ +#define PB_STATUS_INPUT_PIN_OP_WARN BIT(0) /* Input Overpower Warning */ + +/* STATUS_TEMPERATURE */ +#define PB_STATUS_OT_FAULT BIT(7) /* Overtemperature Fault */ +#define PB_STATUS_OT_WARN BIT(6) /* Overtemperature Warning */ +#define PB_STATUS_UT_WARN BIT(5) /* Undertemperature Warning */ +#define PB_STATUS_UT_FAULT BIT(4) /* Undertemperature Fault */ + +/* STATUS_CML */ +#define PB_CML_FAULT_INVALID_CMD BIT(7) /* Invalid/Unsupported Command */ +#define PB_CML_FAULT_INVALID_DATA BIT(6) /* Invalid/Unsupported Data */ +#define PB_CML_FAULT_PEC BIT(5) /* Packet Error Check Failed */ +#define PB_CML_FAULT_MEMORY BIT(4) /* Memory Fault Detected */ +#define PB_CML_FAULT_PROCESSOR BIT(3) /* Processor Fault Detected */ +#define PB_CML_FAULT_OTHER_COMM BIT(1) /* Other communication fault */ +#define PB_CML_FAULT_OTHER_MEM_LOGIC BIT(0) /* Other Memory Or Logic Fault */ + +/* OPERATION*/ +#define PB_OP_ON BIT(7) /* PSU is switched on */ +#define PB_OP_MARGIN_HIGH BIT(5) /* PSU vout is set to margin high */ +#define PB_OP_MARGIN_LOW BIT(4) /* PSU vout is set to margin low */ + +/* PAGES */ +#define PB_MAX_PAGES 0x1F +#define PB_ALL_PAGES 0xFF + +#define TYPE_PMBUS_DEVICE "pmbus-device" +OBJECT_DECLARE_TYPE(PMBusDevice, PMBusDeviceClass, + PMBUS_DEVICE) + +/* flags */ +#define PB_HAS_COEFFICIENTS BIT_ULL(9) +#define PB_HAS_VIN BIT_ULL(10) +#define PB_HAS_VOUT BIT_ULL(11) +#define PB_HAS_VOUT_MARGIN BIT_ULL(12) +#define PB_HAS_VIN_RATING BIT_ULL(13) +#define PB_HAS_VOUT_RATING BIT_ULL(14) +#define PB_HAS_VOUT_MODE BIT_ULL(15) +#define PB_HAS_IOUT BIT_ULL(21) +#define PB_HAS_IIN BIT_ULL(22) +#define PB_HAS_IOUT_RATING BIT_ULL(23) +#define PB_HAS_IIN_RATING BIT_ULL(24) +#define PB_HAS_IOUT_GAIN BIT_ULL(25) +#define PB_HAS_POUT BIT_ULL(30) +#define PB_HAS_PIN BIT_ULL(31) +#define PB_HAS_EIN BIT_ULL(32) +#define PB_HAS_EOUT BIT_ULL(33) +#define PB_HAS_POUT_RATING BIT_ULL(34) +#define PB_HAS_PIN_RATING BIT_ULL(35) +#define PB_HAS_TEMPERATURE BIT_ULL(40) +#define PB_HAS_TEMP2 BIT_ULL(41) +#define PB_HAS_TEMP3 BIT_ULL(42) +#define PB_HAS_TEMP_RATING BIT_ULL(43) +#define PB_HAS_MFR_INFO BIT_ULL(50) + +struct PMBusDeviceClass { + SMBusDeviceClass parent_class; + uint8_t device_num_pages; + + /** + * Implement quick_cmd, receive byte, and write_data to support non-standard + * PMBus functionality + */ + void (*quick_cmd)(PMBusDevice *dev, uint8_t read); + int (*write_data)(PMBusDevice *dev, const uint8_t *buf, uint8_t len); + uint8_t (*receive_byte)(PMBusDevice *dev); +}; + +/* + * According to the spec, each page may offer the full range of PMBus commands + * available for each output or non-PMBus device. + * Therefore, we can't assume that any registers will always be the same across + * all pages. + * The page 0xFF is intended for writes to all pages + */ +typedef struct PMBusPage { + uint64_t page_flags; + + uint8_t page; /* R/W byte */ + uint8_t operation; /* R/W byte */ + uint8_t on_off_config; /* R/W byte */ + uint8_t write_protect; /* R/W byte */ + uint8_t phase; /* R/W byte */ + uint8_t vout_mode; /* R/W byte */ + uint16_t vout_command; /* R/W word */ + uint16_t vout_trim; /* R/W word */ + uint16_t vout_cal_offset; /* R/W word */ + uint16_t vout_max; /* R/W word */ + uint16_t vout_margin_high; /* R/W word */ + uint16_t vout_margin_low; /* R/W word */ + uint16_t vout_transition_rate; /* R/W word */ + uint16_t vout_droop; /* R/W word */ + uint16_t vout_scale_loop; /* R/W word */ + uint16_t vout_scale_monitor; /* R/W word */ + uint8_t coefficients[5]; /* Read-only block 5 bytes */ + uint16_t pout_max; /* R/W word */ + uint16_t max_duty; /* R/W word */ + uint16_t frequency_switch; /* R/W word */ + uint16_t vin_on; /* R/W word */ + uint16_t vin_off; /* R/W word */ + uint16_t iout_cal_gain; /* R/W word */ + uint16_t iout_cal_offset; /* R/W word */ + uint8_t fan_config_1_2; /* R/W byte */ + uint16_t fan_command_1; /* R/W word */ + uint16_t fan_command_2; /* R/W word */ + uint8_t fan_config_3_4; /* R/W byte */ + uint16_t fan_command_3; /* R/W word */ + uint16_t fan_command_4; /* R/W word */ + uint16_t vout_ov_fault_limit; /* R/W word */ + uint8_t vout_ov_fault_response; /* R/W byte */ + uint16_t vout_ov_warn_limit; /* R/W word */ + uint16_t vout_uv_warn_limit; /* R/W word */ + uint16_t vout_uv_fault_limit; /* R/W word */ + uint8_t vout_uv_fault_response; /* R/W byte */ + uint16_t iout_oc_fault_limit; /* R/W word */ + uint8_t iout_oc_fault_response; /* R/W byte */ + uint16_t iout_oc_lv_fault_limit; /* R/W word */ + uint8_t iout_oc_lv_fault_response; /* R/W byte */ + uint16_t iout_oc_warn_limit; /* R/W word */ + uint16_t iout_uc_fault_limit; /* R/W word */ + uint8_t iout_uc_fault_response; /* R/W byte */ + uint16_t ot_fault_limit; /* R/W word */ + uint8_t ot_fault_response; /* R/W byte */ + uint16_t ot_warn_limit; /* R/W word */ + uint16_t ut_warn_limit; /* R/W word */ + uint16_t ut_fault_limit; /* R/W word */ + uint8_t ut_fault_response; /* R/W byte */ + uint16_t vin_ov_fault_limit; /* R/W word */ + uint8_t vin_ov_fault_response; /* R/W byte */ + uint16_t vin_ov_warn_limit; /* R/W word */ + uint16_t vin_uv_warn_limit; /* R/W word */ + uint16_t vin_uv_fault_limit; /* R/W word */ + uint8_t vin_uv_fault_response; /* R/W byte */ + uint16_t iin_oc_fault_limit; /* R/W word */ + uint8_t iin_oc_fault_response; /* R/W byte */ + uint16_t iin_oc_warn_limit; /* R/W word */ + uint16_t power_good_on; /* R/W word */ + uint16_t power_good_off; /* R/W word */ + uint16_t ton_delay; /* R/W word */ + uint16_t ton_rise; /* R/W word */ + uint16_t ton_max_fault_limit; /* R/W word */ + uint8_t ton_max_fault_response; /* R/W byte */ + uint16_t toff_delay; /* R/W word */ + uint16_t toff_fall; /* R/W word */ + uint16_t toff_max_warn_limit; /* R/W word */ + uint16_t pout_op_fault_limit; /* R/W word */ + uint8_t pout_op_fault_response; /* R/W byte */ + uint16_t pout_op_warn_limit; /* R/W word */ + uint16_t pin_op_warn_limit; /* R/W word */ + uint16_t status_word; /* R/W word */ + uint8_t status_vout; /* R/W byte */ + uint8_t status_iout; /* R/W byte */ + uint8_t status_input; /* R/W byte */ + uint8_t status_temperature; /* R/W byte */ + uint8_t status_cml; /* R/W byte */ + uint8_t status_other; /* R/W byte */ + uint8_t status_mfr_specific; /* R/W byte */ + uint8_t status_fans_1_2; /* R/W byte */ + uint8_t status_fans_3_4; /* R/W byte */ + uint8_t read_ein[5]; /* Read-Only block 5 bytes */ + uint8_t read_eout[5]; /* Read-Only block 5 bytes */ + uint16_t read_vin; /* Read-Only word */ + uint16_t read_iin; /* Read-Only word */ + uint16_t read_vcap; /* Read-Only word */ + uint16_t read_vout; /* Read-Only word */ + uint16_t read_iout; /* Read-Only word */ + uint16_t read_temperature_1; /* Read-Only word */ + uint16_t read_temperature_2; /* Read-Only word */ + uint16_t read_temperature_3; /* Read-Only word */ + uint16_t read_fan_speed_1; /* Read-Only word */ + uint16_t read_fan_speed_2; /* Read-Only word */ + uint16_t read_fan_speed_3; /* Read-Only word */ + uint16_t read_fan_speed_4; /* Read-Only word */ + uint16_t read_duty_cycle; /* Read-Only word */ + uint16_t read_frequency; /* Read-Only word */ + uint16_t read_pout; /* Read-Only word */ + uint16_t read_pin; /* Read-Only word */ + uint8_t revision; /* Read-Only byte */ + const char *mfr_id; /* R/W block */ + const char *mfr_model; /* R/W block */ + const char *mfr_revision; /* R/W block */ + const char *mfr_location; /* R/W block */ + const char *mfr_date; /* R/W block */ + const char *mfr_serial; /* R/W block */ + const char *app_profile_support; /* Read-Only block-read */ + uint16_t mfr_vin_min; /* Read-Only word */ + uint16_t mfr_vin_max; /* Read-Only word */ + uint16_t mfr_iin_max; /* Read-Only word */ + uint16_t mfr_pin_max; /* Read-Only word */ + uint16_t mfr_vout_min; /* Read-Only word */ + uint16_t mfr_vout_max; /* Read-Only word */ + uint16_t mfr_iout_max; /* Read-Only word */ + uint16_t mfr_pout_max; /* Read-Only word */ + uint16_t mfr_tambient_max; /* Read-Only word */ + uint16_t mfr_tambient_min; /* Read-Only word */ + uint8_t mfr_efficiency_ll[14]; /* Read-Only block 14 bytes */ + uint8_t mfr_efficiency_hl[14]; /* Read-Only block 14 bytes */ + uint8_t mfr_pin_accuracy; /* Read-Only byte */ + uint16_t mfr_max_temp_1; /* R/W word */ + uint16_t mfr_max_temp_2; /* R/W word */ + uint16_t mfr_max_temp_3; /* R/W word */ +} PMBusPage; + +/* State */ +struct PMBusDevice { + SMBusDevice smb; + + uint8_t num_pages; + uint8_t code; + uint8_t page; + + /* + * PMBus registers are stored in a PMBusPage structure allocated by + * calling pmbus_pages_alloc() + */ + PMBusPage *pages; + uint8_t capability; + + + int32_t in_buf_len; + uint8_t *in_buf; + int32_t out_buf_len; + uint8_t out_buf[SMBUS_DATA_MAX_LEN]; +}; + +/** + * Direct mode coefficients + * @var m - mantissa + * @var b - offset + * @var R - exponent + */ +typedef struct PMBusCoefficients { + int32_t m; /* mantissa */ + int64_t b; /* offset */ + int32_t R; /* exponent */ +} PMBusCoefficients; + +/** + * Convert sensor values to direct mode format + * + * Y = (m * x - b) * 10^R + * + * @return uint32_t + */ +uint16_t pmbus_data2direct_mode(PMBusCoefficients c, uint32_t value); + +/** + * Convert direct mode formatted data into sensor reading + * + * X = (Y * 10^-R - b) / m + * + * @return uint32_t + */ +uint32_t pmbus_direct_mode2data(PMBusCoefficients c, uint16_t value); + +/** + * @brief Send a block of data over PMBus + * Assumes that the bytes in the block are already ordered correctly, + * also assumes the length has been prepended to the block if necessary + * | low_byte | ... | high_byte | + * @param state - maintains state of the PMBus device + * @param data - byte array to be sent by device + * @param len - number + */ +void pmbus_send(PMBusDevice *state, const uint8_t *data, uint16_t len); +void pmbus_send8(PMBusDevice *state, uint8_t data); +void pmbus_send16(PMBusDevice *state, uint16_t data); +void pmbus_send32(PMBusDevice *state, uint32_t data); +void pmbus_send64(PMBusDevice *state, uint64_t data); + +/** + * @brief Send a string over PMBus with length prepended. + * Length is calculated using str_len() + */ +void pmbus_send_string(PMBusDevice *state, const char *data); + +/** + * @brief Receive data over PMBus + * These methods help track how much data is being received over PMBus + * Log to GUEST_ERROR if too much or too little is sent. + */ +uint8_t pmbus_receive8(PMBusDevice *pmdev); +uint16_t pmbus_receive16(PMBusDevice *pmdev); +uint32_t pmbus_receive32(PMBusDevice *pmdev); +uint64_t pmbus_receive64(PMBusDevice *pmdev); + +/** + * PMBus page config must be called before any page is first used. + * It will allocate memory for all the pages if needed. + * Passed in flags overwrite existing flags if any. + * @param page_index the page to which the flags are applied, setting page_index + * to 0xFF applies the passed in flags to all pages. + * @param flags + */ +int pmbus_page_config(PMBusDevice *pmdev, uint8_t page_index, uint64_t flags); + +/** + * Update the status registers when sensor values change. + * Useful if modifying sensors through qmp, this way status registers get + * updated + */ +void pmbus_check_limits(PMBusDevice *pmdev); + +extern const VMStateDescription vmstate_pmbus_device; + +#define VMSTATE_PMBUS_DEVICE(_field, _state) { \ + .name = (stringify(_field)), \ + .size = sizeof(PMBusDevice), \ + .vmsd = &vmstate_pmbus_device, \ + .flags = VMS_STRUCT, \ + .offset = vmstate_offset_value(_state, _field, PMBusDevice), \ +} + +#endif diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index dcf060b791..88dffe7517 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -19,7 +19,6 @@ * PCMachineState: * @acpi_dev: link to ACPI PM device that performs ACPI hotplug handling * @boot_cpus: number of present VCPUs - * @smp_dies: number of dies per one package */ typedef struct PCMachineState { /*< private >*/ @@ -45,6 +44,7 @@ typedef struct PCMachineState { bool sata_enabled; bool pit_enabled; bool hpet_enabled; + bool default_bus_bypass_iommu; uint64_t max_fw_size; /* NUMA information: */ @@ -139,8 +139,6 @@ extern int fd_bootchk; void pc_acpi_smi_interrupt(void *opaque, int irq, int level); -void pc_smp_parse(MachineState *ms, QemuOpts *opts); - void pc_guest_info_init(PCMachineState *pcms); #define PCI_HOST_PROP_PCI_HOLE_START "pci-hole-start" @@ -191,12 +189,16 @@ void pc_system_flash_cleanup_unused(PCMachineState *pcms); void pc_system_firmware_init(PCMachineState *pcms, MemoryRegion *rom_memory); bool pc_system_ovmf_table_find(const char *entry, uint8_t **data, int *data_len); +void pc_system_parse_ovmf_flash(uint8_t *flash_ptr, size_t flash_size); /* acpi-build.c */ void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid, const CPUArchIdList *apic_ids, GArray *entry); +extern GlobalProperty pc_compat_6_0[]; +extern const size_t pc_compat_6_0_len; + extern GlobalProperty pc_compat_5_2[]; extern const size_t pc_compat_5_2_len; diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h index c09b648dff..6e9244a82c 100644 --- a/include/hw/i386/x86.h +++ b/include/hw/i386/x86.h @@ -62,7 +62,6 @@ struct X86MachineState { unsigned pci_irq_mask; unsigned apic_id_limit; uint16_t boot_cpus; - unsigned smp_dies; OnOffAuto smm; OnOffAuto acpi; @@ -74,12 +73,20 @@ struct X86MachineState { * will be translated to MSI messages in the address space. */ AddressSpace *ioapic_as; + + /* + * Ratelimit enforced on detected bus locks in guest. + * The default value of the bus_lock_ratelimit is 0 per second, + * which means no limitation on the guest's bus locks. + */ + uint64_t bus_lock_ratelimit; }; #define X86_MACHINE_SMM "smm" #define X86_MACHINE_ACPI "acpi" #define X86_MACHINE_OEM_ID "x-oem-id" #define X86_MACHINE_OEM_TABLE_ID "x-oem-table-id" +#define X86_MACHINE_BUS_LOCK_RATELIMIT "bus-lock-ratelimit" #define TYPE_X86_MACHINE MACHINE_TYPE_NAME("x86") OBJECT_DECLARE_TYPE(X86MachineState, X86MachineClass, X86_MACHINE) diff --git a/include/hw/ide/internal.h b/include/hw/ide/internal.h index 665c717c6d..d00b02c920 100644 --- a/include/hw/ide/internal.h +++ b/include/hw/ide/internal.h @@ -625,7 +625,7 @@ int ide_init_drive(IDEState *s, BlockBackend *blk, IDEDriveKind kind, int chs_trans, Error **errp); void ide_init2(IDEBus *bus, qemu_irq irq); void ide_exit(IDEState *s); -void ide_init_ioport(IDEBus *bus, ISADevice *isa, int iobase, int iobase2); +int ide_init_ioport(IDEBus *bus, ISADevice *isa, int iobase, int iobase2); void ide_register_restart_cb(IDEBus *bus); void ide_exec_cmd(IDEBus *bus, uint32_t val); diff --git a/include/hw/input/lm832x.h b/include/hw/input/lm832x.h new file mode 100644 index 0000000000..2a58ccf891 --- /dev/null +++ b/include/hw/input/lm832x.h @@ -0,0 +1,28 @@ +/* + * National Semiconductor LM8322/8323 GPIO keyboard & PWM chips. + * + * Copyright (C) 2008 Nokia Corporation + * Written by Andrzej Zaborowski + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 or + * (at your option) version 3 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see . + */ + +#ifndef HW_INPUT_LM832X +#define HW_INPUT_LM832X + +#define TYPE_LM8323 "lm8323" + +void lm832x_key_event(DeviceState *dev, int key, int state); + +#endif diff --git a/include/hw/isa/isa.h b/include/hw/isa/isa.h index 734787c8a2..6fd8bef29a 100644 --- a/include/hw/isa/isa.h +++ b/include/hw/isa/isa.h @@ -138,12 +138,15 @@ void isa_unregister_ioport(ISADevice *dev, MemoryRegion *io); * @portio: the ports, sorted by offset. * @opaque: passed into the portio callbacks. * @name: passed into memory_region_init_io. + * + * Returns: 0 on success, negative error code otherwise (e.g. if the + * ISA bus is not available) */ -void isa_register_portio_list(ISADevice *dev, - PortioList *piolist, - uint16_t start, - const MemoryRegionPortio *portio, - void *opaque, const char *name); +int isa_register_portio_list(ISADevice *dev, + PortioList *piolist, + uint16_t start, + const MemoryRegionPortio *portio, + void *opaque, const char *name); static inline ISABus *isa_bus_from_device(ISADevice *d) { diff --git a/include/hw/isa/vt82c686.h b/include/hw/isa/vt82c686.h index 9b6d610e83..0f01aaa471 100644 --- a/include/hw/isa/vt82c686.h +++ b/include/hw/isa/vt82c686.h @@ -2,8 +2,8 @@ #define HW_VT82C686_H #define TYPE_VT82C686B_ISA "vt82c686b-isa" -#define TYPE_VT82C686B_SUPERIO "vt82c686b-superio" #define TYPE_VT82C686B_PM "vt82c686b-pm" +#define TYPE_VT8231_ISA "vt8231-isa" #define TYPE_VT8231_PM "vt8231-pm" #define TYPE_VIA_AC97 "via-ac97" #define TYPE_VIA_MC97 "via-mc97" diff --git a/include/hw/lm32/lm32_pic.h b/include/hw/lm32/lm32_pic.h deleted file mode 100644 index 9e5e038437..0000000000 --- a/include/hw/lm32/lm32_pic.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef QEMU_HW_LM32_PIC_H -#define QEMU_HW_LM32_PIC_H - - -uint32_t lm32_pic_get_ip(DeviceState *d); -uint32_t lm32_pic_get_im(DeviceState *d); -void lm32_pic_set_ip(DeviceState *d, uint32_t ip); -void lm32_pic_set_im(DeviceState *d, uint32_t im); - -#endif /* QEMU_HW_LM32_PIC_H */ diff --git a/include/hw/mem/pc-dimm.h b/include/hw/mem/pc-dimm.h index 3d3db82641..1473e6db62 100644 --- a/include/hw/mem/pc-dimm.h +++ b/include/hw/mem/pc-dimm.h @@ -56,9 +56,6 @@ struct PCDIMMDevice { * PCDIMMDeviceClass: * @realize: called after common dimm is realized so that the dimm based * devices get the chance to do specified operations. - * @get_vmstate_memory_region: returns #MemoryRegion which indicates the - * memory of @dimm should be kept during live migration. Will not fail - * after the device was realized. */ struct PCDIMMDeviceClass { /* private */ @@ -66,8 +63,6 @@ struct PCDIMMDeviceClass { /* public */ void (*realize)(PCDIMMDevice *dimm, Error **errp); - MemoryRegion *(*get_vmstate_memory_region)(PCDIMMDevice *dimm, - Error **errp); }; void pc_dimm_pre_plug(PCDIMMDevice *dimm, MachineState *machine, diff --git a/include/hw/misc/aspeed_hace.h b/include/hw/misc/aspeed_hace.h new file mode 100644 index 0000000000..94d5ada95f --- /dev/null +++ b/include/hw/misc/aspeed_hace.h @@ -0,0 +1,43 @@ +/* + * ASPEED Hash and Crypto Engine + * + * Copyright (C) 2021 IBM Corp. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef ASPEED_HACE_H +#define ASPEED_HACE_H + +#include "hw/sysbus.h" + +#define TYPE_ASPEED_HACE "aspeed.hace" +#define TYPE_ASPEED_AST2400_HACE TYPE_ASPEED_HACE "-ast2400" +#define TYPE_ASPEED_AST2500_HACE TYPE_ASPEED_HACE "-ast2500" +#define TYPE_ASPEED_AST2600_HACE TYPE_ASPEED_HACE "-ast2600" +OBJECT_DECLARE_TYPE(AspeedHACEState, AspeedHACEClass, ASPEED_HACE) + +#define ASPEED_HACE_NR_REGS (0x64 >> 2) + +struct AspeedHACEState { + SysBusDevice parent; + + MemoryRegion iomem; + qemu_irq irq; + + uint32_t regs[ASPEED_HACE_NR_REGS]; + + MemoryRegion *dram_mr; + AddressSpace dram_as; +}; + + +struct AspeedHACEClass { + SysBusDeviceClass parent_class; + + uint32_t src_mask; + uint32_t dest_mask; + uint32_t hash_mask; +}; + +#endif /* _ASPEED_HACE_H_ */ diff --git a/include/hw/misc/aspeed_xdma.h b/include/hw/misc/aspeed_xdma.h index a2dea96984..b1478fd1c6 100644 --- a/include/hw/misc/aspeed_xdma.h +++ b/include/hw/misc/aspeed_xdma.h @@ -13,7 +13,10 @@ #include "qom/object.h" #define TYPE_ASPEED_XDMA "aspeed.xdma" -OBJECT_DECLARE_SIMPLE_TYPE(AspeedXDMAState, ASPEED_XDMA) +#define TYPE_ASPEED_2400_XDMA TYPE_ASPEED_XDMA "-ast2400" +#define TYPE_ASPEED_2500_XDMA TYPE_ASPEED_XDMA "-ast2500" +#define TYPE_ASPEED_2600_XDMA TYPE_ASPEED_XDMA "-ast2600" +OBJECT_DECLARE_TYPE(AspeedXDMAState, AspeedXDMAClass, ASPEED_XDMA) #define ASPEED_XDMA_NUM_REGS (ASPEED_XDMA_REG_SIZE / sizeof(uint32_t)) #define ASPEED_XDMA_REG_SIZE 0x7C @@ -28,4 +31,16 @@ struct AspeedXDMAState { uint32_t regs[ASPEED_XDMA_NUM_REGS]; }; +struct AspeedXDMAClass { + SysBusDeviceClass parent_class; + + uint8_t cmdq_endp; + uint8_t cmdq_wrp; + uint8_t cmdq_rdp; + uint8_t intr_ctrl; + uint32_t intr_ctrl_mask; + uint8_t intr_status; + uint32_t intr_complete; +}; + #endif /* ASPEED_XDMA_H */ diff --git a/include/hw/misc/avr_power.h b/include/hw/misc/avr_power.h index 707df030b1..388e421aa7 100644 --- a/include/hw/misc/avr_power.h +++ b/include/hw/misc/avr_power.h @@ -26,7 +26,6 @@ #define HW_MISC_AVR_POWER_H #include "hw/sysbus.h" -#include "hw/hw.h" #include "qom/object.h" diff --git a/include/hw/misc/bcm2835_powermgt.h b/include/hw/misc/bcm2835_powermgt.h new file mode 100644 index 0000000000..303b9a6f68 --- /dev/null +++ b/include/hw/misc/bcm2835_powermgt.h @@ -0,0 +1,29 @@ +/* + * BCM2835 Power Management emulation + * + * Copyright (C) 2017 Marcin Chojnacki + * Copyright (C) 2021 Nolan Leake + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef BCM2835_POWERMGT_H +#define BCM2835_POWERMGT_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_BCM2835_POWERMGT "bcm2835-powermgt" +OBJECT_DECLARE_SIMPLE_TYPE(BCM2835PowerMgtState, BCM2835_POWERMGT) + +struct BCM2835PowerMgtState { + SysBusDevice busdev; + MemoryRegion iomem; + + uint32_t rstc; + uint32_t rsts; + uint32_t wdog; +}; + +#endif diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h index 49d070616a..3b2d13ac9c 100644 --- a/include/hw/misc/mps2-scc.h +++ b/include/hw/misc/mps2-scc.h @@ -9,6 +9,24 @@ * (at your option) any later version. */ +/* + * This is a model of the Serial Communication Controller (SCC) + * block found in most MPS FPGA images. + * + * QEMU interface: + * + sysbus MMIO region 0: the register bank + * + QOM property "scc-cfg4": value of the read-only CFG4 register + * + QOM property "scc-aid": value of the read-only SCC_AID register + * + QOM property "scc-id": value of the read-only SCC_ID register + * + QOM property "scc-cfg0": reset value of the CFG0 register + * + QOM property array "oscclk": reset values of the OSCCLK registers + * (which are accessed via the SYS_CFG channel provided by this device) + * + named GPIO output "remap": this tracks the value of CFG0 register + * bit 0. Boards where this bit controls memory remapping should + * connect this GPIO line to a function performing that mapping. + * Boards where bit 0 has no special function should leave the GPIO + * output disconnected. + */ #ifndef MPS2_SCC_H #define MPS2_SCC_H @@ -43,6 +61,9 @@ struct MPS2SCC { uint32_t num_oscclk; uint32_t *oscclk; uint32_t *oscclk_reset; + uint32_t cfg0_reset; + + qemu_irq remap; }; #endif diff --git a/include/hw/misc/stm32f4xx_exti.h b/include/hw/misc/stm32f4xx_exti.h index 24b6fa7724..ea6b0097b0 100644 --- a/include/hw/misc/stm32f4xx_exti.h +++ b/include/hw/misc/stm32f4xx_exti.h @@ -26,7 +26,6 @@ #define HW_STM_EXTI_H #include "hw/sysbus.h" -#include "hw/hw.h" #include "qom/object.h" #define EXTI_IMR 0x00 diff --git a/include/hw/misc/stm32f4xx_syscfg.h b/include/hw/misc/stm32f4xx_syscfg.h index 8c31feccd3..6f8ca49228 100644 --- a/include/hw/misc/stm32f4xx_syscfg.h +++ b/include/hw/misc/stm32f4xx_syscfg.h @@ -26,7 +26,6 @@ #define HW_STM_SYSCFG_H #include "hw/sysbus.h" -#include "hw/hw.h" #include "qom/object.h" #define SYSCFG_MEMRMP 0x00 diff --git a/include/hw/pci-host/gpex.h b/include/hw/pci-host/gpex.h index d48a020a95..fcf8b63820 100644 --- a/include/hw/pci-host/gpex.h +++ b/include/hw/pci-host/gpex.h @@ -49,8 +49,12 @@ struct GPEXHost { MemoryRegion io_ioport; MemoryRegion io_mmio; + MemoryRegion io_ioport_window; + MemoryRegion io_mmio_window; qemu_irq irq[GPEX_NUM_IRQS]; int irq_num[GPEX_NUM_IRQS]; + + bool allow_unmapped_accesses; }; struct GPEXConfig { diff --git a/include/hw/pci-host/i440fx.h b/include/hw/pci-host/i440fx.h index 24fd53942c..7fcfd9485c 100644 --- a/include/hw/pci-host/i440fx.h +++ b/include/hw/pci-host/i440fx.h @@ -11,7 +11,6 @@ #ifndef HW_PCI_I440FX_H #define HW_PCI_I440FX_H -#include "hw/hw.h" #include "hw/pci/pci_bus.h" #include "hw/pci-host/pam.h" #include "qom/object.h" diff --git a/include/hw/pci-host/mv64361.h b/include/hw/pci-host/mv64361.h new file mode 100644 index 0000000000..9cdb35cb3c --- /dev/null +++ b/include/hw/pci-host/mv64361.h @@ -0,0 +1,8 @@ +#ifndef MV64361_H +#define MV64361_H + +#define TYPE_MV64361 "mv64361" + +PCIBus *mv64361_get_pci_bus(DeviceState *dev, int n); + +#endif diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h index 6be4e0c460..d0f4266e37 100644 --- a/include/hw/pci/pci.h +++ b/include/hw/pci/pci.h @@ -450,6 +450,7 @@ static inline PCIBus *pci_get_bus(const PCIDevice *dev) return PCI_BUS(qdev_get_parent_bus(DEVICE(dev))); } int pci_bus_num(PCIBus *s); +void pci_bus_range(PCIBus *bus, int *min_bus, int *max_bus); static inline int pci_dev_bus_num(const PCIDevice *dev) { return pci_bus_num(pci_get_bus(dev)); @@ -480,6 +481,7 @@ void pci_for_each_bus(PCIBus *bus, PCIBus *pci_device_root_bus(const PCIDevice *d); const char *pci_root_bus_path(PCIDevice *dev); +bool pci_bus_bypass_iommu(PCIBus *bus); PCIDevice *pci_find_device(PCIBus *bus, int bus_num, uint8_t devfn); int pci_qdev_find_device(const char *id, PCIDevice **pdev); void pci_bus_get_w64_range(PCIBus *bus, Range *range); diff --git a/include/hw/pci/pci_host.h b/include/hw/pci/pci_host.h index 52e038c019..c6f4eb4585 100644 --- a/include/hw/pci/pci_host.h +++ b/include/hw/pci/pci_host.h @@ -43,6 +43,7 @@ struct PCIHostState { uint32_t config_reg; bool mig_enabled; PCIBus *bus; + bool bypass_iommu; QLIST_ENTRY(PCIHostState) next; }; diff --git a/include/hw/pci/pci_ids.h b/include/hw/pci/pci_ids.h index d17949157b..38b41189c6 100644 --- a/include/hw/pci/pci_ids.h +++ b/include/hw/pci/pci_ids.h @@ -204,15 +204,17 @@ #define PCI_VENDOR_ID_XILINX 0x10ee #define PCI_VENDOR_ID_VIA 0x1106 -#define PCI_DEVICE_ID_VIA_ISA_BRIDGE 0x0686 +#define PCI_DEVICE_ID_VIA_82C686B_ISA 0x0686 #define PCI_DEVICE_ID_VIA_IDE 0x0571 #define PCI_DEVICE_ID_VIA_UHCI 0x3038 #define PCI_DEVICE_ID_VIA_82C686B_PM 0x3057 #define PCI_DEVICE_ID_VIA_AC97 0x3058 #define PCI_DEVICE_ID_VIA_MC97 0x3068 +#define PCI_DEVICE_ID_VIA_8231_ISA 0x8231 #define PCI_DEVICE_ID_VIA_8231_PM 0x8235 #define PCI_VENDOR_ID_MARVELL 0x11ab +#define PCI_DEVICE_ID_MARVELL_MV6436X 0x6460 #define PCI_VENDOR_ID_SILICON_MOTION 0x126f #define PCI_DEVICE_ID_SM501 0x0501 @@ -225,6 +227,9 @@ #define PCI_VENDOR_ID_FREESCALE 0x1957 #define PCI_DEVICE_ID_MPC8533E 0x0030 +#define PCI_VENDOR_ID_BAIDU 0x1d22 +#define PCI_DEVICE_ID_KUNLUN_VF 0x3685 + #define PCI_VENDOR_ID_INTEL 0x8086 #define PCI_DEVICE_ID_INTEL_82378 0x0484 #define PCI_DEVICE_ID_INTEL_82441 0x1237 diff --git a/include/hw/pci/pcie_port.h b/include/hw/pci/pcie_port.h index bea8ecad0f..e25b289ce8 100644 --- a/include/hw/pci/pcie_port.h +++ b/include/hw/pci/pcie_port.h @@ -57,8 +57,11 @@ struct PCIESlot { /* Disable ACS (really for a pcie_root_port) */ bool disable_acs; - /* Indicates whether hot-plug is enabled on the slot */ + /* Indicates whether any type of hot-plug is allowed on the slot */ bool hotplug; + + bool native_hotplug; + QLIST_ENTRY(PCIESlot) next; }; diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h index bf7cab7a2c..637652ad16 100644 --- a/include/hw/ppc/spapr.h +++ b/include/hw/ppc/spapr.h @@ -12,6 +12,7 @@ #include "hw/ppc/spapr_xive.h" /* For SpaprXive */ #include "hw/ppc/xics.h" /* For ICSState */ #include "hw/ppc/spapr_tpm_proxy.h" +#include "hw/ppc/vof.h" struct SpaprVioBus; struct SpaprPhbState; @@ -74,8 +75,10 @@ typedef enum { #define SPAPR_CAP_CCF_ASSIST 0x09 /* Implements PAPR FWNMI option */ #define SPAPR_CAP_FWNMI 0x0A +/* Support H_RPT_INVALIDATE */ +#define SPAPR_CAP_RPT_INVALIDATE 0x0B /* Num Caps */ -#define SPAPR_CAP_NUM (SPAPR_CAP_FWNMI + 1) +#define SPAPR_CAP_NUM (SPAPR_CAP_RPT_INVALIDATE + 1) /* * Capability Values @@ -95,7 +98,7 @@ typedef enum { #define SPAPR_CAP_FIXED_CCD 0x03 #define SPAPR_CAP_FIXED_NA 0x10 /* Lets leave a bit of a gap... */ -#define FDT_MAX_SIZE 0x100000 +#define FDT_MAX_SIZE 0x200000 /* * NUMA related macros. MAX_DISTANCE_REF_POINTS was taken @@ -180,6 +183,7 @@ struct SpaprMachineState { uint64_t kernel_addr; uint32_t initrd_base; long initrd_size; + Vof *vof; uint64_t rtc_offset; /* Now used only during incoming migration */ struct PPCTimebase tb; bool has_graphics; @@ -223,6 +227,9 @@ struct SpaprMachineState { int fwnmi_machine_check_interlock; QemuCond fwnmi_machine_check_interlock_cond; + /* Set by -boot */ + char *boot_device; + /*< public >*/ char *kvm_type; char *host_model; @@ -363,7 +370,7 @@ struct SpaprMachineState { /* Values for 2nd argument to H_SET_MODE */ #define H_SET_MODE_RESOURCE_SET_CIABR 1 -#define H_SET_MODE_RESOURCE_SET_DAWR 2 +#define H_SET_MODE_RESOURCE_SET_DAWR0 2 #define H_SET_MODE_RESOURCE_ADDR_TRANS_MODE 3 #define H_SET_MODE_RESOURCE_LE 4 @@ -395,10 +402,13 @@ struct SpaprMachineState { #define H_CPU_CHAR_THR_RECONF_TRIG PPC_BIT(6) #define H_CPU_CHAR_CACHE_COUNT_DIS PPC_BIT(7) #define H_CPU_CHAR_BCCTR_FLUSH_ASSIST PPC_BIT(9) + #define H_CPU_BEHAV_FAVOUR_SECURITY PPC_BIT(0) #define H_CPU_BEHAV_L1D_FLUSH_PR PPC_BIT(1) #define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR PPC_BIT(2) #define H_CPU_BEHAV_FLUSH_COUNT_CACHE PPC_BIT(5) +#define H_CPU_BEHAV_NO_L1D_FLUSH_ENTRY PPC_BIT(7) +#define H_CPU_BEHAV_NO_L1D_FLUSH_UACCESS PPC_BIT(8) /* Each control block has to be on a 4K boundary */ #define H_CB_ALIGNMENT 4096 @@ -538,8 +548,10 @@ struct SpaprMachineState { #define H_SCM_BIND_MEM 0x3EC #define H_SCM_UNBIND_MEM 0x3F0 #define H_SCM_UNBIND_ALL 0x3FC +#define H_SCM_HEALTH 0x400 +#define H_RPT_INVALIDATE 0x448 -#define MAX_HCALL_OPCODE H_SCM_UNBIND_ALL +#define MAX_HCALL_OPCODE H_RPT_INVALIDATE /* The hcalls above are standardized in PAPR and implemented by pHyp * as well. @@ -554,7 +566,9 @@ struct SpaprMachineState { /* Client Architecture support */ #define KVMPPC_H_CAS (KVMPPC_HCALL_BASE + 0x2) #define KVMPPC_H_UPDATE_DT (KVMPPC_HCALL_BASE + 0x3) -#define KVMPPC_HCALL_MAX KVMPPC_H_UPDATE_DT +/* 0x4 was used for KVMPPC_H_UPDATE_PHANDLE in SLOF */ +#define KVMPPC_H_VOF_CLIENT (KVMPPC_HCALL_BASE + 0x5) +#define KVMPPC_HCALL_MAX KVMPPC_H_VOF_CLIENT /* * The hcall range 0xEF00 to 0xEF80 is reserved for use in facilitating @@ -581,6 +595,12 @@ typedef target_ulong (*spapr_hcall_fn)(PowerPCCPU *cpu, SpaprMachineState *sm, void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn); target_ulong spapr_hypercall(PowerPCCPU *cpu, target_ulong opcode, target_ulong *args); +target_ulong softmmu_resize_hpt_prepare(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong shift); +target_ulong softmmu_resize_hpt_commit(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong flags, target_ulong shift); +bool is_ram_address(SpaprMachineState *spapr, hwaddr addr); +void push_sregs_to_kvm_pr(SpaprMachineState *spapr); /* Virtual Processor Area structure constants */ #define VPA_MIN_SIZE 640 @@ -760,7 +780,7 @@ void spapr_load_rtas(SpaprMachineState *spapr, void *fdt, hwaddr addr); #define SPAPR_IS_PCI_LIOBN(liobn) (!!((liobn) & 0x80000000)) #define SPAPR_PCI_DMA_WINDOW_NUM(liobn) ((liobn) & 0xff) -#define RTAS_SIZE 2048 +#define RTAS_MIN_SIZE 20 /* hv_rtas_size in SLOF */ #define RTAS_ERROR_LOG_MAX 2048 /* Offset from rtas-base where error log is placed */ @@ -820,6 +840,7 @@ void spapr_dt_events(SpaprMachineState *sm, void *fdt); void close_htab_fd(SpaprMachineState *spapr); void spapr_setup_hpt(SpaprMachineState *spapr); void spapr_free_hpt(SpaprMachineState *spapr); +void spapr_check_mmu_mode(bool guest_radix); SpaprTceTable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn); void spapr_tce_table_enable(SpaprTceTable *tcet, uint32_t page_shift, uint64_t bus_offset, @@ -921,6 +942,7 @@ extern const VMStateDescription vmstate_spapr_cap_nested_kvm_hv; extern const VMStateDescription vmstate_spapr_cap_large_decr; extern const VMStateDescription vmstate_spapr_cap_ccf_assist; extern const VMStateDescription vmstate_spapr_cap_fwnmi; +extern const VMStateDescription vmstate_spapr_cap_rpt_invalidate; static inline uint8_t spapr_get_cap(SpaprMachineState *spapr, int cap) { @@ -945,4 +967,16 @@ bool spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize, void spapr_set_all_lpcrs(target_ulong value, target_ulong mask); hwaddr spapr_get_rtas_addr(void); bool spapr_memory_hot_unplug_supported(SpaprMachineState *spapr); + +void spapr_vof_reset(SpaprMachineState *spapr, void *fdt, Error **errp); +void spapr_vof_quiesce(MachineState *ms); +bool spapr_vof_setprop(MachineState *ms, const char *path, const char *propname, + void *val, int vallen); +target_ulong spapr_h_vof_client(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args); +target_ulong spapr_vof_client_architecture_support(MachineState *ms, + CPUState *cs, + target_ulong ovec_addr); +void spapr_vof_client_dt_finalize(SpaprMachineState *spapr, void *fdt); + #endif /* HW_SPAPR_H */ diff --git a/include/hw/ppc/spapr_nvdimm.h b/include/hw/ppc/spapr_nvdimm.h index 73be250e2a..764f999f54 100644 --- a/include/hw/ppc/spapr_nvdimm.h +++ b/include/hw/ppc/spapr_nvdimm.h @@ -11,19 +11,9 @@ #define HW_SPAPR_NVDIMM_H #include "hw/mem/nvdimm.h" -#include "hw/ppc/spapr.h" -/* - * The nvdimm size should be aligned to SCM block size. - * The SCM block size should be aligned to SPAPR_MEMORY_BLOCK_SIZE - * inorder to have SCM regions not to overlap with dimm memory regions. - * The SCM devices can have variable block sizes. For now, fixing the - * block size to the minimum value. - */ -#define SPAPR_MINIMUM_SCM_BLOCK_SIZE SPAPR_MEMORY_BLOCK_SIZE - -/* Have an explicit check for alignment */ -QEMU_BUILD_BUG_ON(SPAPR_MINIMUM_SCM_BLOCK_SIZE % SPAPR_MEMORY_BLOCK_SIZE); +typedef struct SpaprDrc SpaprDrc; +typedef struct SpaprMachineState SpaprMachineState; int spapr_pmem_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr, void *fdt, int *fdt_start_offset, Error **errp); diff --git a/include/hw/ppc/vof.h b/include/hw/ppc/vof.h new file mode 100644 index 0000000000..97fdef758b --- /dev/null +++ b/include/hw/ppc/vof.h @@ -0,0 +1,60 @@ +/* + * Virtual Open Firmware + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef HW_VOF_H +#define HW_VOF_H + +typedef struct Vof { + uint64_t top_addr; /* copied from rma_size */ + GArray *claimed; /* array of SpaprOfClaimed */ + uint64_t claimed_base; + GHashTable *of_instances; /* ihandle -> SpaprOfInstance */ + uint32_t of_instance_last; + char *bootargs; + long fw_size; +} Vof; + +int vof_client_call(MachineState *ms, Vof *vof, void *fdt, + target_ulong args_real); +uint64_t vof_claim(Vof *vof, uint64_t virt, uint64_t size, uint64_t align); +void vof_init(Vof *vof, uint64_t top_addr, Error **errp); +void vof_cleanup(Vof *vof); +void vof_build_dt(void *fdt, Vof *vof); +uint32_t vof_client_open_store(void *fdt, Vof *vof, const char *nodename, + const char *prop, const char *path); + +#define TYPE_VOF_MACHINE_IF "vof-machine-if" + +typedef struct VofMachineIfClass VofMachineIfClass; +DECLARE_CLASS_CHECKERS(VofMachineIfClass, VOF_MACHINE, TYPE_VOF_MACHINE_IF) + +struct VofMachineIfClass { + InterfaceClass parent; + target_ulong (*client_architecture_support)(MachineState *ms, CPUState *cs, + target_ulong vec); + void (*quiesce)(MachineState *ms); + bool (*setprop)(MachineState *ms, const char *path, const char *propname, + void *val, int vallen); +}; + +/* + * Initial stack size is from + * https://www.devicetree.org/open-firmware/bindings/ppc/release/ppc-2_1.html#REF27292 + * + * "Client programs shall be invoked with a valid stack pointer (r1) with + * at least 32K bytes of memory available for stack growth". + */ +#define VOF_STACK_SIZE 0x8000 + +#define VOF_MEM_READ(pa, buf, size) \ + address_space_read(&address_space_memory, \ + (pa), MEMTXATTRS_UNSPECIFIED, (buf), (size)) +#define VOF_MEM_WRITE(pa, buf, size) \ + address_space_write(&address_space_memory, \ + (pa), MEMTXATTRS_UNSPECIFIED, (buf), (size)) + +#define PROM_ERROR (~0U) + +#endif /* HW_VOF_H */ diff --git a/include/hw/riscv/boot.h b/include/hw/riscv/boot.h index 11a21dd584..0e89400b09 100644 --- a/include/hw/riscv/boot.h +++ b/include/hw/riscv/boot.h @@ -24,6 +24,11 @@ #include "hw/loader.h" #include "hw/riscv/riscv_hart.h" +#define RISCV32_BIOS_BIN "opensbi-riscv32-generic-fw_dynamic.bin" +#define RISCV32_BIOS_ELF "opensbi-riscv32-generic-fw_dynamic.elf" +#define RISCV64_BIOS_BIN "opensbi-riscv64-generic-fw_dynamic.bin" +#define RISCV64_BIOS_ELF "opensbi-riscv64-generic-fw_dynamic.elf" + bool riscv_is_32bit(RISCVHartArrayState *harts); target_ulong riscv_calc_kernel_start_addr(RISCVHartArrayState *harts, diff --git a/include/hw/riscv/opentitan.h b/include/hw/riscv/opentitan.h index a5ea3a5e4e..9f93bebdac 100644 --- a/include/hw/riscv/opentitan.h +++ b/include/hw/riscv/opentitan.h @@ -22,6 +22,7 @@ #include "hw/riscv/riscv_hart.h" #include "hw/intc/ibex_plic.h" #include "hw/char/ibex_uart.h" +#include "hw/timer/ibex_timer.h" #include "qom/object.h" #define TYPE_RISCV_IBEX_SOC "riscv.lowrisc.ibex.soc" @@ -35,9 +36,11 @@ struct LowRISCIbexSoCState { RISCVHartArrayState cpus; IbexPlicState plic; IbexUartState uart; + IbexTimerState timer; MemoryRegion flash_mem; MemoryRegion rom; + MemoryRegion flash_alias; }; typedef struct OpenTitanState { @@ -52,12 +55,13 @@ enum { IBEX_DEV_ROM, IBEX_DEV_RAM, IBEX_DEV_FLASH, + IBEX_DEV_FLASH_VIRTUAL, IBEX_DEV_UART, IBEX_DEV_GPIO, IBEX_DEV_SPI, IBEX_DEV_I2C, IBEX_DEV_PATTGEN, - IBEX_DEV_RV_TIMER, + IBEX_DEV_TIMER, IBEX_DEV_SENSOR_CTRL, IBEX_DEV_OTP_CTRL, IBEX_DEV_PWRMGR, @@ -79,17 +83,19 @@ enum { IBEX_DEV_ALERT_HANDLER, IBEX_DEV_NMI_GEN, IBEX_DEV_OTBN, + IBEX_DEV_PERI, }; enum { - IBEX_UART_RX_PARITY_ERR_IRQ = 0x28, - IBEX_UART_RX_TIMEOUT_IRQ = 0x27, - IBEX_UART_RX_BREAK_ERR_IRQ = 0x26, - IBEX_UART_RX_FRAME_ERR_IRQ = 0x25, - IBEX_UART_RX_OVERFLOW_IRQ = 0x24, - IBEX_UART_TX_EMPTY_IRQ = 0x23, - IBEX_UART_RX_WATERMARK_IRQ = 0x22, - IBEX_UART_TX_WATERMARK_IRQ = 0x21, + IBEX_TIMER_TIMEREXPIRED0_0 = 125, + IBEX_UART0_RX_PARITY_ERR_IRQ = 8, + IBEX_UART0_RX_TIMEOUT_IRQ = 7, + IBEX_UART0_RX_BREAK_ERR_IRQ = 6, + IBEX_UART0_RX_FRAME_ERR_IRQ = 5, + IBEX_UART0_RX_OVERFLOW_IRQ = 4, + IBEX_UART0_TX_EMPTY_IRQ = 3, + IBEX_UART0_RX_WATERMARK_IRQ = 2, + IBEX_UART0_TX_WATERMARK_IRQ = 1, }; #endif diff --git a/include/hw/riscv/shakti_c.h b/include/hw/riscv/shakti_c.h new file mode 100644 index 0000000000..50a2b79086 --- /dev/null +++ b/include/hw/riscv/shakti_c.h @@ -0,0 +1,75 @@ +/* + * Shakti C-class SoC emulation + * + * Copyright (c) 2021 Vijai Kumar K + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see . + */ + +#ifndef HW_SHAKTI_H +#define HW_SHAKTI_H + +#include "hw/riscv/riscv_hart.h" +#include "hw/boards.h" +#include "hw/char/shakti_uart.h" + +#define TYPE_RISCV_SHAKTI_SOC "riscv.shakti.cclass.soc" +#define RISCV_SHAKTI_SOC(obj) \ + OBJECT_CHECK(ShaktiCSoCState, (obj), TYPE_RISCV_SHAKTI_SOC) + +typedef struct ShaktiCSoCState { + /*< private >*/ + DeviceState parent_obj; + + /*< public >*/ + RISCVHartArrayState cpus; + DeviceState *plic; + ShaktiUartState uart; + MemoryRegion rom; + +} ShaktiCSoCState; + +#define TYPE_RISCV_SHAKTI_MACHINE MACHINE_TYPE_NAME("shakti_c") +#define RISCV_SHAKTI_MACHINE(obj) \ + OBJECT_CHECK(ShaktiCMachineState, (obj), TYPE_RISCV_SHAKTI_MACHINE) +typedef struct ShaktiCMachineState { + /*< private >*/ + MachineState parent_obj; + + /*< public >*/ + ShaktiCSoCState soc; +} ShaktiCMachineState; + +enum { + SHAKTI_C_ROM, + SHAKTI_C_RAM, + SHAKTI_C_UART, + SHAKTI_C_GPIO, + SHAKTI_C_PLIC, + SHAKTI_C_CLINT, + SHAKTI_C_I2C, +}; + +#define SHAKTI_C_PLIC_HART_CONFIG "MS" +/* Including Interrupt ID 0 (no interrupt)*/ +#define SHAKTI_C_PLIC_NUM_SOURCES 28 +/* Excluding Priority 0 */ +#define SHAKTI_C_PLIC_NUM_PRIORITIES 2 +#define SHAKTI_C_PLIC_PRIORITY_BASE 0x04 +#define SHAKTI_C_PLIC_PENDING_BASE 0x1000 +#define SHAKTI_C_PLIC_ENABLE_BASE 0x2000 +#define SHAKTI_C_PLIC_ENABLE_STRIDE 0x80 +#define SHAKTI_C_PLIC_CONTEXT_BASE 0x200000 +#define SHAKTI_C_PLIC_CONTEXT_STRIDE 0x1000 + +#endif diff --git a/include/hw/s390x/css.h b/include/hw/s390x/css.h index bba7593d2e..10ed1df1bb 100644 --- a/include/hw/s390x/css.h +++ b/include/hw/s390x/css.h @@ -138,8 +138,10 @@ struct SubchDev { int (*ccw_cb) (SubchDev *, CCW1); void (*disable_cb)(SubchDev *); IOInstEnding (*do_subchannel_work) (SubchDev *); + void (*irb_cb)(SubchDev *, IRB *); SenseId id; void *driver_data; + ESW esw; }; static inline void sch_gen_unit_exception(SubchDev *sch) @@ -201,6 +203,7 @@ int css_sch_build_schib(SubchDev *sch, CssDevId *dev_id); unsigned int css_find_free_chpid(uint8_t cssid); uint16_t css_build_subchannel_id(SubchDev *sch); void copy_scsw_to_guest(SCSW *dest, const SCSW *src); +void copy_esw_to_guest(ESW *dest, const ESW *src); void css_inject_io_interrupt(SubchDev *sch); void css_reset(void); void css_reset_sch(SubchDev *sch); @@ -215,6 +218,8 @@ void css_clear_sei_pending(void); IOInstEnding s390_ccw_cmd_request(SubchDev *sch); IOInstEnding do_subchannel_work_virtual(SubchDev *sub); IOInstEnding do_subchannel_work_passthrough(SubchDev *sub); +void build_irb_passthrough(SubchDev *sch, IRB *irb); +void build_irb_virtual(SubchDev *sch, IRB *irb); int s390_ccw_halt(SubchDev *sch); int s390_ccw_clear(SubchDev *sch); diff --git a/include/hw/s390x/ioinst.h b/include/hw/s390x/ioinst.h index c6737a30d4..3771fff9d4 100644 --- a/include/hw/s390x/ioinst.h +++ b/include/hw/s390x/ioinst.h @@ -123,10 +123,20 @@ typedef struct SCHIB { uint8_t mda[4]; } QEMU_PACKED SCHIB; +/* format-0 extended-status word */ +typedef struct ESW { + uint32_t word0; /* subchannel logout for format 0 */ + uint32_t erw; + uint64_t word2; /* failing-storage address for format 0 */ + uint32_t word4; /* secondary-CCW address for format 0 */ +} QEMU_PACKED ESW; + +#define ESW_ERW_SENSE 0x01000000 + /* interruption response block */ typedef struct IRB { SCSW scsw; - uint32_t esw[5]; + ESW esw; uint32_t ecw[8]; uint32_t emw[8]; } IRB; diff --git a/include/hw/s390x/tod.h b/include/hw/s390x/tod.h index ff3195a4bf..0935e85089 100644 --- a/include/hw/s390x/tod.h +++ b/include/hw/s390x/tod.h @@ -12,7 +12,7 @@ #define HW_S390_TOD_H #include "hw/qdev-core.h" -#include "target/s390x/s390-tod.h" +#include "tcg/s390-tod.h" #include "qom/object.h" typedef struct S390TOD { diff --git a/include/hw/scsi/esp.h b/include/hw/scsi/esp.h index aada3680b7..b1ec27612f 100644 --- a/include/hw/scsi/esp.h +++ b/include/hw/scsi/esp.h @@ -37,6 +37,7 @@ struct ESPState { SCSIRequest *current_req; Fifo8 cmdfifo; uint8_t cmdfifo_cdb_offset; + uint8_t lun; uint32_t do_cmd; bool data_in_ready; diff --git a/include/hw/misc/emc141x_regs.h b/include/hw/sensor/emc141x_regs.h similarity index 100% rename from include/hw/misc/emc141x_regs.h rename to include/hw/sensor/emc141x_regs.h diff --git a/hw/misc/tmp105.h b/include/hw/sensor/tmp105.h similarity index 97% rename from hw/misc/tmp105.h rename to include/hw/sensor/tmp105.h index 7c97071ad7..244e2989fe 100644 --- a/hw/misc/tmp105.h +++ b/include/hw/sensor/tmp105.h @@ -15,7 +15,7 @@ #define QEMU_TMP105_H #include "hw/i2c/i2c.h" -#include "hw/misc/tmp105_regs.h" +#include "hw/sensor/tmp105_regs.h" #include "qom/object.h" #define TYPE_TMP105 "tmp105" diff --git a/include/hw/misc/tmp105_regs.h b/include/hw/sensor/tmp105_regs.h similarity index 100% rename from include/hw/misc/tmp105_regs.h rename to include/hw/sensor/tmp105_regs.h diff --git a/include/hw/ssi/aspeed_smc.h b/include/hw/ssi/aspeed_smc.h index 16c03fe64f..cdaf165300 100644 --- a/include/hw/ssi/aspeed_smc.h +++ b/include/hw/ssi/aspeed_smc.h @@ -47,7 +47,7 @@ typedef struct AspeedSMCController { const AspeedSegments *segments; hwaddr flash_window_base; uint32_t flash_window_size; - bool has_dma; + uint32_t features; hwaddr dma_flash_mask; hwaddr dma_dram_mask; uint32_t nregs; @@ -55,6 +55,7 @@ typedef struct AspeedSMCController { const AspeedSegments *seg); void (*reg_to_segment)(const struct AspeedSMCState *s, uint32_t reg, AspeedSegments *seg); + void (*dma_ctrl)(struct AspeedSMCState *s, uint32_t value); } AspeedSMCController; typedef struct AspeedSMCFlash { @@ -84,6 +85,7 @@ struct AspeedSMCState { MemoryRegion mmio; MemoryRegion mmio_flash; + MemoryRegion mmio_flash_alias; qemu_irq irq; int irqline; @@ -103,9 +105,6 @@ struct AspeedSMCState { uint8_t r_timings; uint8_t conf_enable_w0; - /* for DMA support */ - uint64_t sdram_base; - AddressSpace flash_as; MemoryRegion *dram_mr; AddressSpace dram_as; diff --git a/include/hw/timer/avr_timer16.h b/include/hw/timer/avr_timer16.h index 0536254337..a1a032a24d 100644 --- a/include/hw/timer/avr_timer16.h +++ b/include/hw/timer/avr_timer16.h @@ -30,7 +30,6 @@ #include "hw/sysbus.h" #include "qemu/timer.h" -#include "hw/hw.h" #include "qom/object.h" enum NextInterrupt { diff --git a/hw/usb/host-stub.c b/include/hw/timer/ibex_timer.h similarity index 60% rename from hw/usb/host-stub.c rename to include/hw/timer/ibex_timer.h index 538ed29684..6a43537003 100644 --- a/hw/usb/host-stub.c +++ b/include/hw/timer/ibex_timer.h @@ -1,15 +1,7 @@ /* - * Stub host USB redirector + * QEMU lowRISC Ibex Timer device * - * Copyright (c) 2005 Fabrice Bellard - * - * Copyright (c) 2008 Max Krasnyansky - * Support for host device auto connect & disconnect - * Major rewrite to support fully async operation - * - * Copyright 2008 TJ - * Added flexible support for /dev/bus/usb /sys/bus/usb/devices in addition - * to the legacy /proc/bus/usb USB device discovery and handling + * Copyright (c) 2021 Western Digital * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -30,17 +22,31 @@ * THE SOFTWARE. */ -#include "qemu/osdep.h" -#include "ui/console.h" -#include "hw/usb.h" -#include "monitor/monitor.h" +#ifndef HW_IBEX_TIMER_H +#define HW_IBEX_TIMER_H -void hmp_info_usbhost(Monitor *mon, const QDict *qdict) -{ - monitor_printf(mon, "USB host devices not supported\n"); -} +#include "hw/sysbus.h" -bool usb_host_dev_is_scsi_storage(USBDevice *ud) -{ - return false; -} +#define TYPE_IBEX_TIMER "ibex-timer" +OBJECT_DECLARE_SIMPLE_TYPE(IbexTimerState, IBEX_TIMER) + +struct IbexTimerState { + /* */ + SysBusDevice parent_obj; + + /* */ + MemoryRegion mmio; + + uint32_t timer_ctrl; + uint32_t timer_cfg0; + uint32_t timer_compare_lower0; + uint32_t timer_compare_upper0; + uint32_t timer_intr_enable; + uint32_t timer_intr_state; + uint32_t timer_intr_test; + + uint32_t timebase_freq; + + qemu_irq irq; +}; +#endif /* HW_IBEX_TIMER_H */ diff --git a/include/hw/tricore/tricore_testdevice.h b/include/hw/tricore/tricore_testdevice.h new file mode 100644 index 0000000000..2c56c51bcb --- /dev/null +++ b/include/hw/tricore/tricore_testdevice.h @@ -0,0 +1,38 @@ +/* + * Copyright (c) 2018-2021 Bastian Koppelmann Paderborn University + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see . + */ + + +#ifndef HW_TRICORE_TESTDEV_H +#define HW_TRICORE_TESTDEV_H + +#include "hw/sysbus.h" +#include "hw/hw.h" + +#define TYPE_TRICORE_TESTDEVICE "tricore_testdevice" +#define TRICORE_TESTDEVICE(obj) \ + OBJECT_CHECK(TriCoreTestDeviceState, (obj), TYPE_TRICORE_TESTDEVICE) + +typedef struct { + /* */ + SysBusDevice parent_obj; + + /* */ + MemoryRegion iomem; + +} TriCoreTestDeviceState; + +#endif diff --git a/include/hw/unicore32/puv3.h b/include/hw/unicore32/puv3.h deleted file mode 100644 index f587a1f622..0000000000 --- a/include/hw/unicore32/puv3.h +++ /dev/null @@ -1,40 +0,0 @@ -/* - * Misc PKUnity SoC declarations - * - * Copyright (C) 2010-2012 Guan Xuetao - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation, or any later version. - * See the COPYING file in the top-level directory. - */ - -#ifndef QEMU_HW_PUV3_H -#define QEMU_HW_PUV3_H - -#define PUV3_REGS_OFFSET (0x1000) /* 4K is reasonable */ - -/* Hardware interrupts */ -#define PUV3_IRQS_NR (32) - -#define PUV3_IRQS_GPIOLOW0 (0) -#define PUV3_IRQS_GPIOLOW1 (1) -#define PUV3_IRQS_GPIOLOW2 (2) -#define PUV3_IRQS_GPIOLOW3 (3) -#define PUV3_IRQS_GPIOLOW4 (4) -#define PUV3_IRQS_GPIOLOW5 (5) -#define PUV3_IRQS_GPIOLOW6 (6) -#define PUV3_IRQS_GPIOLOW7 (7) -#define PUV3_IRQS_GPIOHIGH (8) -#define PUV3_IRQS_PS2_KBD (22) -#define PUV3_IRQS_PS2_AUX (23) -#define PUV3_IRQS_OST0 (26) - -/* All puv3_*.c use DPRINTF for debug. */ -#ifdef DEBUG_PUV3 -#define DPRINTF(fmt, ...) printf("%s: " fmt , __func__, ## __VA_ARGS__) -#else -#define DPRINTF(fmt, ...) do {} while (0) -#endif - -#endif /* QEMU_HW_PUV3_H */ diff --git a/include/hw/usb.h b/include/hw/usb.h index 436e07b304..33668dd0a9 100644 --- a/include/hw/usb.h +++ b/include/hw/usb.h @@ -219,6 +219,7 @@ enum USBDeviceFlags { USB_DEV_FLAG_IS_HOST, USB_DEV_FLAG_MSOS_DESC_ENABLE, USB_DEV_FLAG_MSOS_DESC_IN_USE, + USB_DEV_FLAG_IS_SCSI_STORAGE, }; /* definition of a USB device */ @@ -465,7 +466,6 @@ void usb_generic_async_ctrl_complete(USBDevice *s, USBPacket *p); /* usb-linux.c */ void hmp_info_usbhost(Monitor *mon, const QDict *qdict); -bool usb_host_dev_is_scsi_storage(USBDevice *usbdev); /* usb ports of the VM */ @@ -561,6 +561,11 @@ const char *usb_device_get_product_desc(USBDevice *dev); const USBDesc *usb_device_get_usb_desc(USBDevice *dev); +static inline bool usb_device_is_scsi_storage(USBDevice *dev) +{ + return dev->flags & (1 << USB_DEV_FLAG_IS_SCSI_STORAGE); +} + /* quirks.c */ /* In bulk endpoints are streaming data sources (iow behave like isoc eps) */ diff --git a/include/hw/usb/dwc2-regs.h b/include/hw/usb/dwc2-regs.h index 40af23a0ba..a7eb531485 100644 --- a/include/hw/usb/dwc2-regs.h +++ b/include/hw/usb/dwc2-regs.h @@ -39,8 +39,8 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -#ifndef __DWC2_HW_H__ -#define __DWC2_HW_H__ +#ifndef DWC2_HW_H +#define DWC2_HW_H #define HSOTG_REG(x) (x) diff --git a/include/hw/usb/xlnx-usb-subsystem.h b/include/hw/usb/xlnx-usb-subsystem.h index 739bef7f45..999e423951 100644 --- a/include/hw/usb/xlnx-usb-subsystem.h +++ b/include/hw/usb/xlnx-usb-subsystem.h @@ -22,8 +22,8 @@ * THE SOFTWARE. */ -#ifndef _XLNX_VERSAL_USB_SUBSYSTEM_H_ -#define _XLNX_VERSAL_USB_SUBSYSTEM_H_ +#ifndef XLNX_VERSAL_USB_SUBSYSTEM_H +#define XLNX_VERSAL_USB_SUBSYSTEM_H #include "hw/usb/xlnx-versal-usb2-ctrl-regs.h" #include "hw/usb/hcd-dwc3.h" diff --git a/include/hw/usb/xlnx-versal-usb2-ctrl-regs.h b/include/hw/usb/xlnx-versal-usb2-ctrl-regs.h index 975a717627..b76dce0419 100644 --- a/include/hw/usb/xlnx-versal-usb2-ctrl-regs.h +++ b/include/hw/usb/xlnx-versal-usb2-ctrl-regs.h @@ -23,8 +23,8 @@ * THE SOFTWARE. */ -#ifndef _XLNX_USB2_REGS_H_ -#define _XLNX_USB2_REGS_H_ +#ifndef XLNX_USB2_REGS_H +#define XLNX_USB2_REGS_H #define TYPE_XILINX_VERSAL_USB2_CTRL_REGS "xlnx.versal-usb2-ctrl-regs" diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 6141162d7a..8af11b0a76 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -88,9 +88,11 @@ typedef struct VFIOContainer { uint64_t dirty_pgsizes; uint64_t max_dirty_bitmap_size; unsigned long pgsizes; + unsigned int dma_max_mappings; QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list; QLIST_HEAD(, VFIOGroup) group_list; + QLIST_HEAD(, VFIORamDiscardListener) vrdl_list; QLIST_ENTRY(VFIOContainer) next; } VFIOContainer; @@ -102,6 +104,16 @@ typedef struct VFIOGuestIOMMU { QLIST_ENTRY(VFIOGuestIOMMU) giommu_next; } VFIOGuestIOMMU; +typedef struct VFIORamDiscardListener { + VFIOContainer *container; + MemoryRegion *mr; + hwaddr offset_within_address_space; + hwaddr size; + uint64_t granularity; + RamDiscardListener listener; + QLIST_ENTRY(VFIORamDiscardListener) next; +} VFIORamDiscardListener; + typedef struct VFIOHostDMAWindow { hwaddr min_iova; hwaddr max_iova; diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h index 8a6f8e2a7a..8475c5a29d 100644 --- a/include/hw/virtio/vhost-backend.h +++ b/include/hw/virtio/vhost-backend.h @@ -37,7 +37,8 @@ struct vhost_scsi_target; struct vhost_iotlb_msg; struct vhost_virtqueue; -typedef int (*vhost_backend_init)(struct vhost_dev *dev, void *opaque); +typedef int (*vhost_backend_init)(struct vhost_dev *dev, void *opaque, + Error **errp); typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev); typedef int (*vhost_backend_memslots_limit)(struct vhost_dev *dev); @@ -97,7 +98,7 @@ typedef int (*vhost_set_config_op)(struct vhost_dev *dev, const uint8_t *data, uint32_t offset, uint32_t size, uint32_t flags); typedef int (*vhost_get_config_op)(struct vhost_dev *dev, uint8_t *config, - uint32_t config_len); + uint32_t config_len, Error **errp); typedef int (*vhost_crypto_create_session_op)(struct vhost_dev *dev, void *session_info, diff --git a/include/hw/virtio/vhost-user-i2c.h b/include/hw/virtio/vhost-user-i2c.h new file mode 100644 index 0000000000..deae47a76d --- /dev/null +++ b/include/hw/virtio/vhost-user-i2c.h @@ -0,0 +1,28 @@ +/* + * Vhost-user i2c virtio device + * + * Copyright (c) 2021 Viresh Kumar + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef _QEMU_VHOST_USER_I2C_H +#define _QEMU_VHOST_USER_I2C_H + +#include "hw/virtio/vhost.h" +#include "hw/virtio/vhost-user.h" + +#define TYPE_VHOST_USER_I2C "vhost-user-i2c-device" +OBJECT_DECLARE_SIMPLE_TYPE(VHostUserI2C, VHOST_USER_I2C) + +struct VHostUserI2C { + VirtIODevice parent; + CharBackend chardev; + struct vhost_virtqueue *vhost_vq; + struct vhost_dev vhost_dev; + VhostUserState vhost_user; + VirtQueue *vq; + bool connected; +}; + +#endif /* _QEMU_VHOST_USER_I2C_H */ diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h index 9b81a409da..9188226d8b 100644 --- a/include/hw/virtio/vhost-vdpa.h +++ b/include/hw/virtio/vhost-vdpa.h @@ -14,14 +14,17 @@ #include "hw/virtio/virtio.h" +typedef struct VhostVDPAHostNotifier { + MemoryRegion mr; + void *addr; +} VhostVDPAHostNotifier; + typedef struct vhost_vdpa { int device_fd; uint32_t msg_type; MemoryListener listener; struct vhost_dev *dev; + VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX]; } VhostVDPA; -extern AddressSpace address_space_memory; -extern int vhost_vdpa_get_device_id(struct vhost_dev *dev, - uint32_t *device_id); #endif diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h index 4a8bc75415..045d0fd9f2 100644 --- a/include/hw/virtio/vhost.h +++ b/include/hw/virtio/vhost.h @@ -74,6 +74,8 @@ struct vhost_dev { int nvqs; /* the first virtqueue which would be used by this vhost dev */ int vq_index; + /* if non-zero, minimum required value for max_queues */ + int num_queues; uint64_t features; uint64_t acked_features; uint64_t backend_features; @@ -102,7 +104,7 @@ struct vhost_net { int vhost_dev_init(struct vhost_dev *hdev, void *opaque, VhostBackendType backend_type, - uint32_t busyloop_timeout); + uint32_t busyloop_timeout, Error **errp); void vhost_dev_cleanup(struct vhost_dev *hdev); int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev); void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev); @@ -128,8 +130,8 @@ int vhost_net_set_backend(struct vhost_dev *hdev, struct vhost_vring_file *file); int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write); -int vhost_dev_get_config(struct vhost_dev *dev, uint8_t *config, - uint32_t config_len); +int vhost_dev_get_config(struct vhost_dev *hdev, uint8_t *config, + uint32_t config_len, Error **errp); int vhost_dev_set_config(struct vhost_dev *dev, const uint8_t *data, uint32_t offset, uint32_t size, uint32_t flags); /* notifier callback in case vhost device config space changed diff --git a/include/hw/virtio/virtio-gpu-bswap.h b/include/hw/virtio/virtio-gpu-bswap.h index 203f9e1718..e2bee8f595 100644 --- a/include/hw/virtio/virtio-gpu-bswap.h +++ b/include/hw/virtio/virtio-gpu-bswap.h @@ -59,4 +59,20 @@ virtio_gpu_t2d_bswap(struct virtio_gpu_transfer_to_host_2d *t2d) le32_to_cpus(&t2d->padding); } +static inline void +virtio_gpu_create_blob_bswap(struct virtio_gpu_resource_create_blob *cblob) +{ + virtio_gpu_ctrl_hdr_bswap(&cblob->hdr); + le32_to_cpus(&cblob->resource_id); + le32_to_cpus(&cblob->blob_flags); + le64_to_cpus(&cblob->size); +} + +static inline void +virtio_gpu_scanout_blob_bswap(struct virtio_gpu_set_scanout_blob *ssb) +{ + virtio_gpu_bswap_32(ssb, sizeof(*ssb) - sizeof(ssb->offsets[3])); + le32_to_cpus(&ssb->offsets[3]); +} + #endif diff --git a/include/hw/virtio/virtio-gpu.h b/include/hw/virtio/virtio-gpu.h index fae149235c..24c6628944 100644 --- a/include/hw/virtio/virtio-gpu.h +++ b/include/hw/virtio/virtio-gpu.h @@ -29,7 +29,10 @@ OBJECT_DECLARE_TYPE(VirtIOGPUBase, VirtIOGPUBaseClass, VIRTIO_GPU_BASE) #define TYPE_VIRTIO_GPU "virtio-gpu-device" -OBJECT_DECLARE_SIMPLE_TYPE(VirtIOGPU, VIRTIO_GPU) +OBJECT_DECLARE_TYPE(VirtIOGPU, VirtIOGPUClass, VIRTIO_GPU) + +#define TYPE_VIRTIO_GPU_GL "virtio-gpu-gl-device" +OBJECT_DECLARE_SIMPLE_TYPE(VirtIOGPUGL, VIRTIO_GPU_GL) #define TYPE_VHOST_USER_GPU "vhost-user-gpu" OBJECT_DECLARE_SIMPLE_TYPE(VhostUserGPU, VHOST_USER_GPU) @@ -47,9 +50,23 @@ struct virtio_gpu_simple_resource { uint32_t scanout_bitmask; pixman_image_t *image; uint64_t hostmem; + + uint64_t blob_size; + void *blob; + int dmabuf_fd; + uint8_t *remapped; + QTAILQ_ENTRY(virtio_gpu_simple_resource) next; }; +struct virtio_gpu_framebuffer { + pixman_format_code_t format; + uint32_t bytes_pp; + uint32_t width, height; + uint32_t stride; + uint32_t offset; +}; + struct virtio_gpu_scanout { QemuConsole *con; DisplaySurface *ds; @@ -72,6 +89,7 @@ enum virtio_gpu_base_conf_flags { VIRTIO_GPU_FLAG_STATS_ENABLED, VIRTIO_GPU_FLAG_EDID_ENABLED, VIRTIO_GPU_FLAG_DMABUF_ENABLED, + VIRTIO_GPU_FLAG_BLOB_ENABLED, }; #define virtio_gpu_virgl_enabled(_cfg) \ @@ -82,6 +100,8 @@ enum virtio_gpu_base_conf_flags { (_cfg.flags & (1 << VIRTIO_GPU_FLAG_EDID_ENABLED)) #define virtio_gpu_dmabuf_enabled(_cfg) \ (_cfg.flags & (1 << VIRTIO_GPU_FLAG_DMABUF_ENABLED)) +#define virtio_gpu_blob_enabled(_cfg) \ + (_cfg.flags & (1 << VIRTIO_GPU_FLAG_BLOB_ENABLED)) struct virtio_gpu_base_conf { uint32_t max_outputs; @@ -108,7 +128,6 @@ struct VirtIOGPUBase { struct virtio_gpu_config virtio_config; const GraphicHwOps *hw_ops; - bool use_virgl_renderer; int renderer_blocked; int enable; @@ -131,6 +150,12 @@ struct VirtIOGPUBaseClass { DEFINE_PROP_UINT32("xres", _state, _conf.xres, 1024), \ DEFINE_PROP_UINT32("yres", _state, _conf.yres, 768) +typedef struct VGPUDMABuf { + QemuDmaBuf buf; + uint32_t scanout_id; + QTAILQ_ENTRY(VGPUDMABuf) next; +} VGPUDMABuf; + struct VirtIOGPU { VirtIOGPUBase parent_obj; @@ -149,8 +174,6 @@ struct VirtIOGPU { uint64_t hostmem; bool processing_cmdq; - bool renderer_inited; - bool renderer_reset; QEMUTimer *fence_poll; QEMUTimer *print_stats; @@ -161,6 +184,28 @@ struct VirtIOGPU { uint32_t req_3d; uint32_t bytes_3d; } stats; + + struct { + QTAILQ_HEAD(, VGPUDMABuf) bufs; + VGPUDMABuf *primary; + } dmabuf; +}; + +struct VirtIOGPUClass { + VirtIOGPUBaseClass parent; + + void (*handle_ctrl)(VirtIODevice *vdev, VirtQueue *vq); + void (*process_cmd)(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd); + void (*update_cursor_data)(VirtIOGPU *g, + struct virtio_gpu_scanout *s, + uint32_t resource_id); +}; + +struct VirtIOGPUGL { + struct VirtIOGPU parent_obj; + + bool renderer_inited; + bool renderer_reset; }; struct VhostUserGPU { @@ -207,17 +252,34 @@ void virtio_gpu_get_display_info(VirtIOGPU *g, void virtio_gpu_get_edid(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd); int virtio_gpu_create_mapping_iov(VirtIOGPU *g, - struct virtio_gpu_resource_attach_backing *ab, + uint32_t nr_entries, uint32_t offset, struct virtio_gpu_ctrl_command *cmd, - uint64_t **addr, struct iovec **iov); + uint64_t **addr, struct iovec **iov, + uint32_t *niov); void virtio_gpu_cleanup_mapping_iov(VirtIOGPU *g, struct iovec *iov, uint32_t count); void virtio_gpu_process_cmdq(VirtIOGPU *g); +void virtio_gpu_device_realize(DeviceState *qdev, Error **errp); +void virtio_gpu_reset(VirtIODevice *vdev); +void virtio_gpu_simple_process_cmd(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd); +void virtio_gpu_update_cursor_data(VirtIOGPU *g, + struct virtio_gpu_scanout *s, + uint32_t resource_id); + +/* virtio-gpu-udmabuf.c */ +bool virtio_gpu_have_udmabuf(void); +void virtio_gpu_init_udmabuf(struct virtio_gpu_simple_resource *res); +void virtio_gpu_fini_udmabuf(struct virtio_gpu_simple_resource *res); +int virtio_gpu_update_dmabuf(VirtIOGPU *g, + uint32_t scanout_id, + struct virtio_gpu_simple_resource *res, + struct virtio_gpu_framebuffer *fb); /* virtio-gpu-3d.c */ void virtio_gpu_virgl_process_cmd(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd); void virtio_gpu_virgl_fence_poll(VirtIOGPU *g); +void virtio_gpu_virgl_reset_scanout(VirtIOGPU *g); void virtio_gpu_virgl_reset(VirtIOGPU *g); int virtio_gpu_virgl_init(VirtIOGPU *g); int virtio_gpu_virgl_get_num_capsets(VirtIOGPU *g); diff --git a/include/hw/virtio/virtio-mem.h b/include/hw/virtio/virtio-mem.h index 4eeb82d5dd..9a6e348fa2 100644 --- a/include/hw/virtio/virtio-mem.h +++ b/include/hw/virtio/virtio-mem.h @@ -67,6 +67,9 @@ struct VirtIOMEM { /* don't migrate unplugged memory */ NotifierWithReturn precopy_notifier; + + /* listeners to notify on plug/unplug activity. */ + QLIST_HEAD(, RamDiscardListener) rdl_list; }; struct VirtIOMEMClass { diff --git a/include/hw/virtio/virtio-mmio.h b/include/hw/virtio/virtio-mmio.h index d4c4c386ab..090f7730e7 100644 --- a/include/hw/virtio/virtio-mmio.h +++ b/include/hw/virtio/virtio-mmio.h @@ -49,12 +49,17 @@ typedef struct VirtIOMMIOQueue { uint32_t used[2]; } VirtIOMMIOQueue; +#define VIRTIO_IOMMIO_FLAG_USE_IOEVENTFD_BIT 1 +#define VIRTIO_IOMMIO_FLAG_USE_IOEVENTFD \ + (1 << VIRTIO_IOMMIO_FLAG_USE_IOEVENTFD_BIT) + struct VirtIOMMIOProxy { /* Generic */ SysBusDevice parent_obj; MemoryRegion iomem; qemu_irq irq; bool legacy; + uint32_t flags; /* Guest accessible state needing migration and reset */ uint32_t host_features_sel; uint32_t guest_features_sel; diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h index 7e96d193aa..824a69c23f 100644 --- a/include/hw/virtio/virtio-net.h +++ b/include/hw/virtio/virtio-net.h @@ -21,6 +21,8 @@ #include "qemu/option_int.h" #include "qom/object.h" +#include "ebpf/ebpf_rss.h" + #define TYPE_VIRTIO_NET "virtio-net-device" OBJECT_DECLARE_SIMPLE_TYPE(VirtIONet, VIRTIO_NET) @@ -130,6 +132,7 @@ typedef struct VirtioNetRscChain { typedef struct VirtioNetRssData { bool enabled; + bool enabled_software_rss; bool redirect; bool populate_hash; uint32_t hash_types; @@ -209,6 +212,7 @@ struct VirtIONet { Notifier migration_state; VirtioNetRssData rss_data; struct NetRxPkt *rx_pkt; + struct EBPFRSSContext ebpf_rss; }; void virtio_net_set_netclient_name(VirtIONet *n, const char *name, diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h index b7ece7a6a8..8bab9cfb75 100644 --- a/include/hw/virtio/virtio.h +++ b/include/hw/virtio/virtio.h @@ -43,7 +43,7 @@ typedef struct VirtIOFeature { size_t end; } VirtIOFeature; -size_t virtio_feature_get_config_size(VirtIOFeature *features, +size_t virtio_feature_get_config_size(const VirtIOFeature *features, uint64_t host_features); typedef struct VirtQueue VirtQueue; diff --git a/include/hw/xen/xen_common.h b/include/hw/xen/xen_common.h index 82e56339dd..a8118b41ac 100644 --- a/include/hw/xen/xen_common.h +++ b/include/hw/xen/xen_common.h @@ -134,6 +134,12 @@ static inline xenforeignmemory_resource_handle *xenforeignmemory_map_resource( return NULL; } +static inline int xenforeignmemory_unmap_resource( + xenforeignmemory_handle *fmem, xenforeignmemory_resource_handle *fres) +{ + return 0; +} + #endif /* CONFIG_XEN_CTRL_INTERFACE_VERSION < 41100 */ #if CONFIG_XEN_CTRL_INTERFACE_VERSION < 41000 diff --git a/include/migration/misc.h b/include/migration/misc.h index 738675ef52..465906710d 100644 --- a/include/migration/misc.h +++ b/include/migration/misc.h @@ -37,7 +37,6 @@ void precopy_infrastructure_init(void); void precopy_add_notifier(NotifierWithReturn *n); void precopy_remove_notifier(NotifierWithReturn *n); int precopy_notify(PrecopyNotifyReason reason, Error **errp); -void precopy_enable_free_page_optimization(void); void ram_mig_init(void); void qemu_guest_free_page_hint(void *addr, size_t len); diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index 075ee80096..017c03675c 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -153,6 +153,7 @@ typedef enum { MIG_PRI_DEFAULT = 0, MIG_PRI_IOMMU, /* Must happen before PCI devices */ MIG_PRI_PCI_BUS, /* Must happen before IOMMU */ + MIG_PRI_VIRTIO_MEM, /* Must happen before IOMMU */ MIG_PRI_GICV3_ITS, /* Must happen before PCI devices */ MIG_PRI_GICV3, /* Must happen before the ITS */ MIG_PRI_MAX, @@ -194,8 +195,6 @@ struct VMStateDescription { const VMStateDescription **subsections; }; -extern const VMStateDescription vmstate_dummy; - extern const VMStateInfo vmstate_info_bool; extern const VMStateInfo vmstate_info_int8; diff --git a/include/monitor/hmp.h b/include/monitor/hmp.h index 605d57287a..3baa1058e2 100644 --- a/include/monitor/hmp.h +++ b/include/monitor/hmp.h @@ -129,5 +129,7 @@ void hmp_info_replay(Monitor *mon, const QDict *qdict); void hmp_replay_break(Monitor *mon, const QDict *qdict); void hmp_replay_delete_break(Monitor *mon, const QDict *qdict); void hmp_replay_seek(Monitor *mon, const QDict *qdict); +void hmp_info_dirty_rate(Monitor *mon, const QDict *qdict); +void hmp_calc_dirty_rate(Monitor *mon, const QDict *qdict); #endif diff --git a/include/monitor/monitor.h b/include/monitor/monitor.h index af3887bb71..1a8a369b50 100644 --- a/include/monitor/monitor.h +++ b/include/monitor/monitor.h @@ -4,7 +4,7 @@ #include "block/block.h" #include "qapi/qapi-types-misc.h" #include "qemu/readline.h" -#include "include/exec/hwaddr.h" +#include "exec/hwaddr.h" typedef struct MonitorHMP MonitorHMP; typedef struct MonitorOptions MonitorOptions; @@ -51,4 +51,7 @@ int monitor_fdset_dup_fd_add(int64_t fdset_id, int flags); void monitor_fdset_dup_fd_remove(int dup_fd); int64_t monitor_fdset_dup_fd_find(int dup_fd); +void monitor_register_hmp(const char *name, bool info, + void (*cmd)(Monitor *mon, const QDict *qdict)); + #endif /* MONITOR_H */ diff --git a/include/net/net.h b/include/net/net.h index 1ef536d771..5d1508081f 100644 --- a/include/net/net.h +++ b/include/net/net.h @@ -61,6 +61,7 @@ typedef int (SetVnetBE)(NetClientState *, bool); typedef struct SocketReadState SocketReadState; typedef void (SocketReadStateFinalize)(SocketReadState *rs); typedef void (NetAnnounce)(NetClientState *); +typedef bool (SetSteeringEBPF)(NetClientState *, int); typedef struct NetClientInfo { NetClientDriver type; @@ -82,6 +83,7 @@ typedef struct NetClientInfo { SetVnetLE *set_vnet_le; SetVnetBE *set_vnet_be; NetAnnounce *announce; + SetSteeringEBPF *set_steering_ebpf; } NetClientInfo; struct NetClientState { diff --git a/include/net/vhost-vdpa.h b/include/net/vhost-vdpa.h index 45e34b7cfc..b81f9a6f2a 100644 --- a/include/net/vhost-vdpa.h +++ b/include/net/vhost-vdpa.h @@ -15,7 +15,6 @@ #define TYPE_VHOST_VDPA "vhost-vdpa" struct vhost_net *vhost_vdpa_get_vhost_net(NetClientState *nc); -uint64_t vhost_vdpa_get_acked_features(NetClientState *nc); extern const int vdpa_feature_bits[]; diff --git a/include/qapi/forward-visitor.h b/include/qapi/forward-visitor.h new file mode 100644 index 0000000000..50fb3e9d50 --- /dev/null +++ b/include/qapi/forward-visitor.h @@ -0,0 +1,27 @@ +/* + * Forwarding visitor + * + * Copyright Red Hat, Inc. 2021 + * + * Author: Paolo Bonzini + * + * This work is licensed under the terms of the GNU LGPL, version 2.1 or later. + * See the COPYING.LIB file in the top-level directory. + * + */ + +#ifndef FORWARD_VISITOR_H +#define FORWARD_VISITOR_H + +#include "qapi/visitor.h" + +typedef struct ForwardFieldVisitor ForwardFieldVisitor; + +/* + * The forwarding visitor only expects a single name, @from, to be passed for + * toplevel fields. It is converted to @to and forwarded to the @target visitor. + * Calls within a struct are forwarded without changing the name. + */ +Visitor *visitor_forward_field(Visitor *target, const char *from, const char *to); + +#endif diff --git a/include/qapi/qmp/qdict.h b/include/qapi/qmp/qdict.h index 9934539c1b..d5b5430e21 100644 --- a/include/qapi/qmp/qdict.h +++ b/include/qapi/qmp/qdict.h @@ -64,4 +64,7 @@ const char *qdict_get_try_str(const QDict *qdict, const char *key); QDict *qdict_clone_shallow(const QDict *src); +QObject *qdict_crumple(const QDict *src, Error **errp); +void qdict_flatten(QDict *qdict); + #endif /* QDICT_H */ diff --git a/include/qemu/accel.h b/include/qemu/accel.h index b9d6d69eb8..4f4c283f6f 100644 --- a/include/qemu/accel.h +++ b/include/qemu/accel.h @@ -78,4 +78,17 @@ int accel_init_machine(AccelState *accel, MachineState *ms); void accel_setup_post(MachineState *ms); #endif /* !CONFIG_USER_ONLY */ +/** + * accel_cpu_instance_init: + * @cpu: The CPU that needs to do accel-specific object initializations. + */ +void accel_cpu_instance_init(CPUState *cpu); + +/** + * accel_cpu_realizefn: + * @cpu: The CPU that needs to call accel-specific cpu realization. + * @errp: currently unused. + */ +bool accel_cpu_realizefn(CPUState *cpu, Error **errp); + #endif /* QEMU_ACCEL_H */ diff --git a/include/qemu/atomic.h b/include/qemu/atomic.h index 8f4b3a80fb..112a29910b 100644 --- a/include/qemu/atomic.h +++ b/include/qemu/atomic.h @@ -8,7 +8,7 @@ * This work is licensed under the terms of the GNU GPL, version 2 or later. * See the COPYING file in the top-level directory. * - * See docs/devel/atomics.txt for discussion about the guarantees each + * See docs/devel/atomics.rst for discussion about the guarantees each * atomic primitive is meant to provide. */ @@ -60,8 +60,9 @@ (unsigned short)1, \ (expr)+0)))))) -#ifdef __ATOMIC_RELAXED -/* For C11 atomic ops */ +#ifndef __ATOMIC_RELAXED +#error "Expecting C11 atomic ops" +#endif /* Manual memory barriers * @@ -239,212 +240,27 @@ #define qatomic_xor(ptr, n) \ ((void) __atomic_fetch_xor(ptr, n, __ATOMIC_SEQ_CST)) -#else /* __ATOMIC_RELAXED */ - -#ifdef __alpha__ -#define smp_read_barrier_depends() asm volatile("mb":::"memory") -#endif - -#if defined(__i386__) || defined(__x86_64__) || defined(__s390x__) - -/* - * Because of the strongly ordered storage model, wmb() and rmb() are nops - * here (a compiler barrier only). QEMU doesn't do accesses to write-combining - * qemu memory or non-temporal load/stores from C code. - */ -#define smp_mb_release() barrier() -#define smp_mb_acquire() barrier() - -/* - * __sync_lock_test_and_set() is documented to be an acquire barrier only, - * but it is a full barrier at the hardware level. Add a compiler barrier - * to make it a full barrier also at the compiler level. - */ -#define qatomic_xchg(ptr, i) (barrier(), __sync_lock_test_and_set(ptr, i)) - -#elif defined(_ARCH_PPC) - -/* - * We use an eieio() for wmb() on powerpc. This assumes we don't - * need to order cacheable and non-cacheable stores with respect to - * each other. - * - * smp_mb has the same problem as on x86 for not-very-new GCC - * (http://patchwork.ozlabs.org/patch/126184/, Nov 2011). - */ -#define smp_wmb() ({ asm volatile("eieio" ::: "memory"); (void)0; }) -#if defined(__powerpc64__) -#define smp_mb_release() ({ asm volatile("lwsync" ::: "memory"); (void)0; }) -#define smp_mb_acquire() ({ asm volatile("lwsync" ::: "memory"); (void)0; }) -#else -#define smp_mb_release() ({ asm volatile("sync" ::: "memory"); (void)0; }) -#define smp_mb_acquire() ({ asm volatile("sync" ::: "memory"); (void)0; }) -#endif -#define smp_mb() ({ asm volatile("sync" ::: "memory"); (void)0; }) - -#endif /* _ARCH_PPC */ - -/* - * For (host) platforms we don't have explicit barrier definitions - * for, we use the gcc __sync_synchronize() primitive to generate a - * full barrier. This should be safe on all platforms, though it may - * be overkill for smp_mb_acquire() and smp_mb_release(). - */ -#ifndef smp_mb -#define smp_mb() __sync_synchronize() -#endif - -#ifndef smp_mb_acquire -#define smp_mb_acquire() __sync_synchronize() -#endif - -#ifndef smp_mb_release -#define smp_mb_release() __sync_synchronize() -#endif - -#ifndef smp_read_barrier_depends -#define smp_read_barrier_depends() barrier() -#endif - -#ifndef signal_barrier -#define signal_barrier() barrier() -#endif - -/* These will only be atomic if the processor does the fetch or store - * in a single issue memory operation - */ -#define qatomic_read__nocheck(p) (*(__typeof__(*(p)) volatile*) (p)) -#define qatomic_set__nocheck(p, i) ((*(__typeof__(*(p)) volatile*) (p)) = (i)) - -#define qatomic_read(ptr) qatomic_read__nocheck(ptr) -#define qatomic_set(ptr, i) qatomic_set__nocheck(ptr,i) - -/** - * qatomic_rcu_read - reads a RCU-protected pointer to a local variable - * into a RCU read-side critical section. The pointer can later be safely - * dereferenced within the critical section. - * - * This ensures that the pointer copy is invariant thorough the whole critical - * section. - * - * Inserts memory barriers on architectures that require them (currently only - * Alpha) and documents which pointers are protected by RCU. - * - * qatomic_rcu_read also includes a compiler barrier to ensure that - * value-speculative optimizations (e.g. VSS: Value Speculation - * Scheduling) does not perform the data read before the pointer read - * by speculating the value of the pointer. - * - * Should match qatomic_rcu_set(), qatomic_xchg(), qatomic_cmpxchg(). - */ -#define qatomic_rcu_read(ptr) ({ \ - typeof(*ptr) _val = qatomic_read(ptr); \ - smp_read_barrier_depends(); \ - _val; \ -}) - -/** - * qatomic_rcu_set - assigns (publicizes) a pointer to a new data structure - * meant to be read by RCU read-side critical sections. - * - * Documents which pointers will be dereferenced by RCU read-side critical - * sections and adds the required memory barriers on architectures requiring - * them. It also makes sure the compiler does not reorder code initializing the - * data structure before its publication. - * - * Should match qatomic_rcu_read(). - */ -#define qatomic_rcu_set(ptr, i) do { \ - smp_wmb(); \ - qatomic_set(ptr, i); \ -} while (0) - -#define qatomic_load_acquire(ptr) ({ \ - typeof(*ptr) _val = qatomic_read(ptr); \ - smp_mb_acquire(); \ - _val; \ -}) - -#define qatomic_store_release(ptr, i) do { \ - smp_mb_release(); \ - qatomic_set(ptr, i); \ -} while (0) - -#ifndef qatomic_xchg -#if defined(__clang__) -#define qatomic_xchg(ptr, i) __sync_swap(ptr, i) -#else -/* __sync_lock_test_and_set() is documented to be an acquire barrier only. */ -#define qatomic_xchg(ptr, i) (smp_mb(), __sync_lock_test_and_set(ptr, i)) -#endif -#endif -#define qatomic_xchg__nocheck qatomic_xchg - -/* Provide shorter names for GCC atomic builtins. */ -#define qatomic_fetch_inc(ptr) __sync_fetch_and_add(ptr, 1) -#define qatomic_fetch_dec(ptr) __sync_fetch_and_add(ptr, -1) - -#define qatomic_fetch_add(ptr, n) __sync_fetch_and_add(ptr, n) -#define qatomic_fetch_sub(ptr, n) __sync_fetch_and_sub(ptr, n) -#define qatomic_fetch_and(ptr, n) __sync_fetch_and_and(ptr, n) -#define qatomic_fetch_or(ptr, n) __sync_fetch_and_or(ptr, n) -#define qatomic_fetch_xor(ptr, n) __sync_fetch_and_xor(ptr, n) - -#define qatomic_inc_fetch(ptr) __sync_add_and_fetch(ptr, 1) -#define qatomic_dec_fetch(ptr) __sync_add_and_fetch(ptr, -1) -#define qatomic_add_fetch(ptr, n) __sync_add_and_fetch(ptr, n) -#define qatomic_sub_fetch(ptr, n) __sync_sub_and_fetch(ptr, n) -#define qatomic_and_fetch(ptr, n) __sync_and_and_fetch(ptr, n) -#define qatomic_or_fetch(ptr, n) __sync_or_and_fetch(ptr, n) -#define qatomic_xor_fetch(ptr, n) __sync_xor_and_fetch(ptr, n) - -#define qatomic_cmpxchg(ptr, old, new) \ - __sync_val_compare_and_swap(ptr, old, new) -#define qatomic_cmpxchg__nocheck(ptr, old, new) qatomic_cmpxchg(ptr, old, new) - -/* And even shorter names that return void. */ -#define qatomic_inc(ptr) ((void) __sync_fetch_and_add(ptr, 1)) -#define qatomic_dec(ptr) ((void) __sync_fetch_and_add(ptr, -1)) -#define qatomic_add(ptr, n) ((void) __sync_fetch_and_add(ptr, n)) -#define qatomic_sub(ptr, n) ((void) __sync_fetch_and_sub(ptr, n)) -#define qatomic_and(ptr, n) ((void) __sync_fetch_and_and(ptr, n)) -#define qatomic_or(ptr, n) ((void) __sync_fetch_and_or(ptr, n)) -#define qatomic_xor(ptr, n) ((void) __sync_fetch_and_xor(ptr, n)) - -#endif /* __ATOMIC_RELAXED */ - -#ifndef smp_wmb #define smp_wmb() smp_mb_release() -#endif -#ifndef smp_rmb #define smp_rmb() smp_mb_acquire() -#endif - -/* This is more efficient than a store plus a fence. */ -#if !defined(__SANITIZE_THREAD__) -#if defined(__i386__) || defined(__x86_64__) || defined(__s390x__) -#define qatomic_mb_set(ptr, i) ((void)qatomic_xchg(ptr, i)) -#endif -#endif /* qatomic_mb_read/set semantics map Java volatile variables. They are * less expensive on some platforms (notably POWER) than fully * sequentially consistent operations. * * As long as they are used as paired operations they are safe to - * use. See docs/devel/atomics.txt for more discussion. + * use. See docs/devel/atomics.rst for more discussion. */ -#ifndef qatomic_mb_read #define qatomic_mb_read(ptr) \ qatomic_load_acquire(ptr) -#endif -#ifndef qatomic_mb_set -#define qatomic_mb_set(ptr, i) do { \ - qatomic_store_release(ptr, i); \ - smp_mb(); \ -} while(0) +#if !defined(__SANITIZE_THREAD__) && \ + (defined(__i386__) || defined(__x86_64__) || defined(__s390x__)) +/* This is more efficient than a store plus a fence. */ +# define qatomic_mb_set(ptr, i) ((void)qatomic_xchg(ptr, i)) +#else +# define qatomic_mb_set(ptr, i) \ + ({ qatomic_store_release(ptr, i); smp_mb(); }) #endif #define qatomic_fetch_inc_nonzero(ptr) ({ \ @@ -455,28 +271,29 @@ _oldn; \ }) -/* Abstractions to access atomically (i.e. "once") i64/u64 variables */ +/* + * Abstractions to access atomically (i.e. "once") i64/u64 variables. + * + * The i386 abi is odd in that by default members are only aligned to + * 4 bytes, which means that 8-byte types can wind up mis-aligned. + * Clang will then warn about this, and emit a call into libatomic. + * + * Use of these types in structures when they will be used with atomic + * operations can avoid this. + */ +typedef int64_t aligned_int64_t __attribute__((aligned(8))); +typedef uint64_t aligned_uint64_t __attribute__((aligned(8))); + #ifdef CONFIG_ATOMIC64 -static inline int64_t qatomic_read_i64(const int64_t *ptr) -{ - /* use __nocheck because sizeof(void *) might be < sizeof(u64) */ - return qatomic_read__nocheck(ptr); -} - -static inline uint64_t qatomic_read_u64(const uint64_t *ptr) -{ - return qatomic_read__nocheck(ptr); -} - -static inline void qatomic_set_i64(int64_t *ptr, int64_t val) -{ - qatomic_set__nocheck(ptr, val); -} - -static inline void qatomic_set_u64(uint64_t *ptr, uint64_t val) -{ - qatomic_set__nocheck(ptr, val); -} +/* Use __nocheck because sizeof(void *) might be < sizeof(u64) */ +#define qatomic_read_i64(P) \ + _Generic(*(P), int64_t: qatomic_read__nocheck(P)) +#define qatomic_read_u64(P) \ + _Generic(*(P), uint64_t: qatomic_read__nocheck(P)) +#define qatomic_set_i64(P, V) \ + _Generic(*(P), int64_t: qatomic_set__nocheck(P, V)) +#define qatomic_set_u64(P, V) \ + _Generic(*(P), uint64_t: qatomic_set__nocheck(P, V)) static inline void qatomic64_init(void) { diff --git a/include/qemu/atomic128.h b/include/qemu/atomic128.h index ad2bcf45b4..adb9a1a260 100644 --- a/include/qemu/atomic128.h +++ b/include/qemu/atomic128.h @@ -6,7 +6,7 @@ * This work is licensed under the terms of the GNU GPL, version 2 or later. * See the COPYING file in the top-level directory. * - * See docs/devel/atomics.txt for discussion about the guarantees each + * See docs/devel/atomics.rst for discussion about the guarantees each * atomic primitive is meant to provide. */ diff --git a/include/qemu/bitops.h b/include/qemu/bitops.h index 3acbf3384c..03213ce952 100644 --- a/include/qemu/bitops.h +++ b/include/qemu/bitops.h @@ -140,7 +140,8 @@ static inline int test_bit(long nr, const unsigned long *addr) * @addr: The address to start the search at * @size: The maximum size to search * - * Returns the bit number of the first set bit, or size. + * Returns the bit number of the last set bit, + * or @size if there is no set bit in the bitmap. */ unsigned long find_last_bit(const unsigned long *addr, unsigned long size); @@ -150,6 +151,9 @@ unsigned long find_last_bit(const unsigned long *addr, * @addr: The address to base the search on * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * + * Returns the bit number of the next set bit, + * or @size if there are no further set bits in the bitmap. */ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, @@ -160,6 +164,9 @@ unsigned long find_next_bit(const unsigned long *addr, * @addr: The address to base the search on * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * + * Returns the bit number of the next cleared bit, + * or @size if there are no further clear bits in the bitmap. */ unsigned long find_next_zero_bit(const unsigned long *addr, @@ -171,7 +178,8 @@ unsigned long find_next_zero_bit(const unsigned long *addr, * @addr: The address to start the search at * @size: The maximum size to search * - * Returns the bit number of the first set bit. + * Returns the bit number of the first set bit, + * or @size if there is no set bit in the bitmap. */ static inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) @@ -194,7 +202,8 @@ static inline unsigned long find_first_bit(const unsigned long *addr, * @addr: The address to start the search at * @size: The maximum size to search * - * Returns the bit number of the first cleared bit. + * Returns the bit number of the first cleared bit, + * or @size if there is no clear bit in the bitmap. */ static inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) @@ -282,6 +291,35 @@ static inline uint64_t ror64(uint64_t word, unsigned int shift) return (word >> shift) | (word << ((64 - shift) & 63)); } +/** + * hswap32 - swap 16-bit halfwords within a 32-bit value + * @h: value to swap + */ +static inline uint32_t hswap32(uint32_t h) +{ + return rol32(h, 16); +} + +/** + * hswap64 - swap 16-bit halfwords within a 64-bit value + * @h: value to swap + */ +static inline uint64_t hswap64(uint64_t h) +{ + uint64_t m = 0x0000ffff0000ffffull; + h = rol64(h, 32); + return ((h & m) << 16) | ((h >> 16) & m); +} + +/** + * wswap64 - swap 32-bit words within a 64-bit value + * @h: value to swap + */ +static inline uint64_t wswap64(uint64_t h) +{ + return rol64(h, 32); +} + /** * extract32: * @value: the value to extract the bit field from diff --git a/include/qemu/bswap.h b/include/qemu/bswap.h index 4aaf992b5d..2d3bb8bbed 100644 --- a/include/qemu/bswap.h +++ b/include/qemu/bswap.h @@ -1,8 +1,6 @@ #ifndef BSWAP_H #define BSWAP_H -#include "fpu/softfloat-types.h" - #ifdef CONFIG_MACHINE_BSWAP_H # include # include @@ -12,7 +10,18 @@ # include #elif defined(CONFIG_BYTESWAP_H) # include +#define BSWAP_FROM_BYTESWAP +# else +#define BSWAP_FROM_FALLBACKS +#endif /* ! CONFIG_MACHINE_BSWAP_H */ +#ifdef __cplusplus +extern "C" { +#endif + +#include "fpu/softfloat-types.h" + +#ifdef BSWAP_FROM_BYTESWAP static inline uint16_t bswap16(uint16_t x) { return bswap_16(x); @@ -27,7 +36,9 @@ static inline uint64_t bswap64(uint64_t x) { return bswap_64(x); } -# else +#endif + +#ifdef BSWAP_FROM_FALLBACKS static inline uint16_t bswap16(uint16_t x) { return (((x & 0x00ff) << 8) | @@ -53,7 +64,10 @@ static inline uint64_t bswap64(uint64_t x) ((x & 0x00ff000000000000ULL) >> 40) | ((x & 0xff00000000000000ULL) >> 56)); } -#endif /* ! CONFIG_MACHINE_BSWAP_H */ +#endif + +#undef BSWAP_FROM_BYTESWAP +#undef BSWAP_FROM_FALLBACKS static inline void bswap16s(uint16_t *s) { @@ -494,4 +508,8 @@ DO_STN_LDN_P(be) #undef le_bswaps #undef be_bswaps +#ifdef __cplusplus +} +#endif + #endif /* BSWAP_H */ diff --git a/include/qemu/co-shared-resource.h b/include/qemu/co-shared-resource.h index 4e4503004c..78ca5850f8 100644 --- a/include/qemu/co-shared-resource.h +++ b/include/qemu/co-shared-resource.h @@ -26,15 +26,13 @@ #ifndef QEMU_CO_SHARED_RESOURCE_H #define QEMU_CO_SHARED_RESOURCE_H - +/* Accesses to co-shared-resource API are thread-safe */ typedef struct SharedResource SharedResource; /* * Create SharedResource structure * * @total: total amount of some resource to be shared between clients - * - * Note: this API is not thread-safe. */ SharedResource *shres_create(uint64_t total); diff --git a/include/qemu/compiler.h b/include/qemu/compiler.h index 81ac52bdf4..d45021770e 100644 --- a/include/qemu/compiler.h +++ b/include/qemu/compiler.h @@ -72,22 +72,11 @@ int:(x) ? -1 : 1; \ } -/* QEMU_BUILD_BUG_MSG() emits the message given if _Static_assert is - * supported; otherwise, it will be omitted from the compiler error - * message (but as it remains present in the source code, it can still - * be useful when debugging). */ -#if defined(CONFIG_STATIC_ASSERT) #ifdef __cplusplus #define QEMU_BUILD_BUG_MSG(x, msg) static_assert(!(x), msg) #else #define QEMU_BUILD_BUG_MSG(x, msg) _Static_assert(!(x), msg) #endif -#elif defined(__COUNTER__) -#define QEMU_BUILD_BUG_MSG(x, msg) typedef QEMU_BUILD_BUG_ON_STRUCT(x) \ - glue(qemu_build_bug_on__, __COUNTER__) __attribute__((unused)) -#else -#define QEMU_BUILD_BUG_MSG(x, msg) -#endif #define QEMU_BUILD_BUG_ON(x) QEMU_BUILD_BUG_MSG(x, "not expecting: " #x) @@ -177,46 +166,6 @@ #define QEMU_ALWAYS_INLINE #endif -/* Implement C11 _Generic via GCC builtins. Example: - * - * QEMU_GENERIC(x, (float, sinf), (long double, sinl), sin) (x) - * - * The first argument is the discriminator. The last is the default value. - * The middle ones are tuples in "(type, expansion)" format. - */ - -/* First, find out the number of generic cases. */ -#define QEMU_GENERIC(x, ...) \ - QEMU_GENERIC_(typeof(x), __VA_ARGS__, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) - -/* There will be extra arguments, but they are not used. */ -#define QEMU_GENERIC_(x, a0, a1, a2, a3, a4, a5, a6, a7, a8, a9, count, ...) \ - QEMU_GENERIC##count(x, a0, a1, a2, a3, a4, a5, a6, a7, a8, a9) - -/* Two more helper macros, this time to extract items from a parenthesized - * list. - */ -#define QEMU_FIRST_(a, b) a -#define QEMU_SECOND_(a, b) b - -/* ... and a final one for the common part of the "recursion". */ -#define QEMU_GENERIC_IF(x, type_then, else_) \ - __builtin_choose_expr(__builtin_types_compatible_p(x, \ - QEMU_FIRST_ type_then), \ - QEMU_SECOND_ type_then, else_) - -/* CPP poor man's "recursion". */ -#define QEMU_GENERIC1(x, a0, ...) (a0) -#define QEMU_GENERIC2(x, a0, ...) QEMU_GENERIC_IF(x, a0, QEMU_GENERIC1(x, __VA_ARGS__)) -#define QEMU_GENERIC3(x, a0, ...) QEMU_GENERIC_IF(x, a0, QEMU_GENERIC2(x, __VA_ARGS__)) -#define QEMU_GENERIC4(x, a0, ...) QEMU_GENERIC_IF(x, a0, QEMU_GENERIC3(x, __VA_ARGS__)) -#define QEMU_GENERIC5(x, a0, ...) QEMU_GENERIC_IF(x, a0, QEMU_GENERIC4(x, __VA_ARGS__)) -#define QEMU_GENERIC6(x, a0, ...) QEMU_GENERIC_IF(x, a0, QEMU_GENERIC5(x, __VA_ARGS__)) -#define QEMU_GENERIC7(x, a0, ...) QEMU_GENERIC_IF(x, a0, QEMU_GENERIC6(x, __VA_ARGS__)) -#define QEMU_GENERIC8(x, a0, ...) QEMU_GENERIC_IF(x, a0, QEMU_GENERIC7(x, __VA_ARGS__)) -#define QEMU_GENERIC9(x, a0, ...) QEMU_GENERIC_IF(x, a0, QEMU_GENERIC8(x, __VA_ARGS__)) -#define QEMU_GENERIC10(x, a0, ...) QEMU_GENERIC_IF(x, a0, QEMU_GENERIC9(x, __VA_ARGS__)) - /** * qemu_build_not_reached() * diff --git a/include/qemu/config-file.h b/include/qemu/config-file.h index 8d3e53ae4d..f605423321 100644 --- a/include/qemu/config-file.h +++ b/include/qemu/config-file.h @@ -1,7 +1,9 @@ #ifndef QEMU_CONFIG_FILE_H #define QEMU_CONFIG_FILE_H +typedef void QEMUConfigCB(const char *group, QDict *qdict, void *opaque, Error **errp); +void qemu_load_module_for_opts(const char *group); QemuOptsList *qemu_find_opts(const char *group); QemuOptsList *qemu_find_opts_err(const char *group, Error **errp); QemuOpts *qemu_find_opts_singleton(const char *group); @@ -14,7 +16,10 @@ void qemu_config_write(FILE *fp); int qemu_config_parse(FILE *fp, QemuOptsList **lists, const char *fname, Error **errp); -int qemu_read_config_file(const char *filename, Error **errp); +/* A default callback for qemu_read_config_file(). */ +void qemu_config_do_parse(const char *group, QDict *qdict, void *opaque, Error **errp); + +int qemu_read_config_file(const char *filename, QEMUConfigCB *f, Error **errp); /* Parse QDict options as a replacement for a config file (allowing multiple enumerated (0..(n-1)) configuration "sections") */ diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index ce5b9c6851..4829ff373d 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -210,13 +210,15 @@ void coroutine_fn qemu_co_queue_wait_impl(CoQueue *queue, QemuLockable *lock); /** * Removes the next coroutine from the CoQueue, and wake it up. * Returns true if a coroutine was removed, false if the queue is empty. + * OK to run from coroutine and non-coroutine context. */ -bool coroutine_fn qemu_co_queue_next(CoQueue *queue); +bool qemu_co_queue_next(CoQueue *queue); /** * Empties the CoQueue; all coroutines are woken up. + * OK to run from coroutine and non-coroutine context. */ -void coroutine_fn qemu_co_queue_restart_all(CoQueue *queue); +void qemu_co_queue_restart_all(CoQueue *queue); /** * Removes the next coroutine from the CoQueue, and wake it up. Unlike @@ -291,20 +293,27 @@ void qemu_co_rwlock_wrlock(CoRwlock *lock); */ void qemu_co_rwlock_unlock(CoRwlock *lock); -typedef struct QemuCoSleepState QemuCoSleepState; +typedef struct QemuCoSleep { + Coroutine *to_wake; +} QemuCoSleep; /** - * Yield the coroutine for a given duration. During this yield, @sleep_state - * (if not NULL) is set to an opaque pointer, which may be used for - * qemu_co_sleep_wake(). Be careful, the pointer is set back to zero when the - * timer fires. Don't save the obtained value to other variables and don't call - * qemu_co_sleep_wake from another aio context. + * Yield the coroutine for a given duration. Initializes @w so that, + * during this yield, it can be passed to qemu_co_sleep_wake() to + * terminate the sleep. */ -void coroutine_fn qemu_co_sleep_ns_wakeable(QEMUClockType type, int64_t ns, - QemuCoSleepState **sleep_state); +void coroutine_fn qemu_co_sleep_ns_wakeable(QemuCoSleep *w, + QEMUClockType type, int64_t ns); + +/** + * Yield the coroutine until the next call to qemu_co_sleep_wake. + */ +void coroutine_fn qemu_co_sleep(QemuCoSleep *w); + static inline void coroutine_fn qemu_co_sleep_ns(QEMUClockType type, int64_t ns) { - qemu_co_sleep_ns_wakeable(type, ns, NULL); + QemuCoSleep w = { 0 }; + qemu_co_sleep_ns_wakeable(&w, type, ns); } /** @@ -313,7 +322,7 @@ static inline void coroutine_fn qemu_co_sleep_ns(QEMUClockType type, int64_t ns) * qemu_co_sleep_ns() and should be checked to be non-NULL before calling * qemu_co_sleep_wake(). */ -void qemu_co_sleep_wake(QemuCoSleepState *sleep_state); +void qemu_co_sleep_wake(QemuCoSleep *w); /** * Yield until a file descriptor becomes readable diff --git a/include/qemu/host-utils.h b/include/qemu/host-utils.h index cdca2991d8..711b221704 100644 --- a/include/qemu/host-utils.h +++ b/include/qemu/host-utils.h @@ -26,6 +26,7 @@ #ifndef HOST_UTILS_H #define HOST_UTILS_H +#include "qemu/compiler.h" #include "qemu/bswap.h" #ifdef CONFIG_INT128 @@ -272,6 +273,9 @@ static inline int ctpop64(uint64_t val) */ static inline uint8_t revbit8(uint8_t x) { +#if __has_builtin(__builtin_bitreverse8) + return __builtin_bitreverse8(x); +#else /* Assign the correct nibble position. */ x = ((x & 0xf0) >> 4) | ((x & 0x0f) << 4); @@ -281,6 +285,7 @@ static inline uint8_t revbit8(uint8_t x) | ((x & 0x22) << 1) | ((x & 0x11) << 3); return x; +#endif } /** @@ -289,6 +294,9 @@ static inline uint8_t revbit8(uint8_t x) */ static inline uint16_t revbit16(uint16_t x) { +#if __has_builtin(__builtin_bitreverse16) + return __builtin_bitreverse16(x); +#else /* Assign the correct byte position. */ x = bswap16(x); /* Assign the correct nibble position. */ @@ -300,6 +308,7 @@ static inline uint16_t revbit16(uint16_t x) | ((x & 0x2222) << 1) | ((x & 0x1111) << 3); return x; +#endif } /** @@ -308,6 +317,9 @@ static inline uint16_t revbit16(uint16_t x) */ static inline uint32_t revbit32(uint32_t x) { +#if __has_builtin(__builtin_bitreverse32) + return __builtin_bitreverse32(x); +#else /* Assign the correct byte position. */ x = bswap32(x); /* Assign the correct nibble position. */ @@ -319,6 +331,7 @@ static inline uint32_t revbit32(uint32_t x) | ((x & 0x22222222u) << 1) | ((x & 0x11111111u) << 3); return x; +#endif } /** @@ -327,6 +340,9 @@ static inline uint32_t revbit32(uint32_t x) */ static inline uint64_t revbit64(uint64_t x) { +#if __has_builtin(__builtin_bitreverse64) + return __builtin_bitreverse64(x); +#else /* Assign the correct byte position. */ x = bswap64(x); /* Assign the correct nibble position. */ @@ -338,6 +354,281 @@ static inline uint64_t revbit64(uint64_t x) | ((x & 0x2222222222222222ull) << 1) | ((x & 0x1111111111111111ull) << 3); return x; +#endif +} + +/** + * sadd32_overflow - addition with overflow indication + * @x, @y: addends + * @ret: Output for sum + * + * Computes *@ret = @x + @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool sadd32_overflow(int32_t x, int32_t y, int32_t *ret) +{ +#if __has_builtin(__builtin_add_overflow) || __GNUC__ >= 5 + return __builtin_add_overflow(x, y, ret); +#else + *ret = x + y; + return ((*ret ^ x) & ~(x ^ y)) < 0; +#endif +} + +/** + * sadd64_overflow - addition with overflow indication + * @x, @y: addends + * @ret: Output for sum + * + * Computes *@ret = @x + @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool sadd64_overflow(int64_t x, int64_t y, int64_t *ret) +{ +#if __has_builtin(__builtin_add_overflow) || __GNUC__ >= 5 + return __builtin_add_overflow(x, y, ret); +#else + *ret = x + y; + return ((*ret ^ x) & ~(x ^ y)) < 0; +#endif +} + +/** + * uadd32_overflow - addition with overflow indication + * @x, @y: addends + * @ret: Output for sum + * + * Computes *@ret = @x + @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool uadd32_overflow(uint32_t x, uint32_t y, uint32_t *ret) +{ +#if __has_builtin(__builtin_add_overflow) || __GNUC__ >= 5 + return __builtin_add_overflow(x, y, ret); +#else + *ret = x + y; + return *ret < x; +#endif +} + +/** + * uadd64_overflow - addition with overflow indication + * @x, @y: addends + * @ret: Output for sum + * + * Computes *@ret = @x + @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool uadd64_overflow(uint64_t x, uint64_t y, uint64_t *ret) +{ +#if __has_builtin(__builtin_add_overflow) || __GNUC__ >= 5 + return __builtin_add_overflow(x, y, ret); +#else + *ret = x + y; + return *ret < x; +#endif +} + +/** + * ssub32_overflow - subtraction with overflow indication + * @x: Minuend + * @y: Subtrahend + * @ret: Output for difference + * + * Computes *@ret = @x - @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool ssub32_overflow(int32_t x, int32_t y, int32_t *ret) +{ +#if __has_builtin(__builtin_sub_overflow) || __GNUC__ >= 5 + return __builtin_sub_overflow(x, y, ret); +#else + *ret = x - y; + return ((*ret ^ x) & (x ^ y)) < 0; +#endif +} + +/** + * ssub64_overflow - subtraction with overflow indication + * @x: Minuend + * @y: Subtrahend + * @ret: Output for sum + * + * Computes *@ret = @x - @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool ssub64_overflow(int64_t x, int64_t y, int64_t *ret) +{ +#if __has_builtin(__builtin_sub_overflow) || __GNUC__ >= 5 + return __builtin_sub_overflow(x, y, ret); +#else + *ret = x - y; + return ((*ret ^ x) & (x ^ y)) < 0; +#endif +} + +/** + * usub32_overflow - subtraction with overflow indication + * @x: Minuend + * @y: Subtrahend + * @ret: Output for sum + * + * Computes *@ret = @x - @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool usub32_overflow(uint32_t x, uint32_t y, uint32_t *ret) +{ +#if __has_builtin(__builtin_sub_overflow) || __GNUC__ >= 5 + return __builtin_sub_overflow(x, y, ret); +#else + *ret = x - y; + return x < y; +#endif +} + +/** + * usub64_overflow - subtraction with overflow indication + * @x: Minuend + * @y: Subtrahend + * @ret: Output for sum + * + * Computes *@ret = @x - @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool usub64_overflow(uint64_t x, uint64_t y, uint64_t *ret) +{ +#if __has_builtin(__builtin_sub_overflow) || __GNUC__ >= 5 + return __builtin_sub_overflow(x, y, ret); +#else + *ret = x - y; + return x < y; +#endif +} + +/** + * smul32_overflow - multiplication with overflow indication + * @x, @y: Input multipliers + * @ret: Output for product + * + * Computes *@ret = @x * @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool smul32_overflow(int32_t x, int32_t y, int32_t *ret) +{ +#if __has_builtin(__builtin_mul_overflow) || __GNUC__ >= 5 + return __builtin_mul_overflow(x, y, ret); +#else + int64_t z = (int64_t)x * y; + *ret = z; + return *ret != z; +#endif +} + +/** + * smul64_overflow - multiplication with overflow indication + * @x, @y: Input multipliers + * @ret: Output for product + * + * Computes *@ret = @x * @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool smul64_overflow(int64_t x, int64_t y, int64_t *ret) +{ +#if __has_builtin(__builtin_mul_overflow) || __GNUC__ >= 5 + return __builtin_mul_overflow(x, y, ret); +#else + uint64_t hi, lo; + muls64(&lo, &hi, x, y); + *ret = lo; + return hi != ((int64_t)lo >> 63); +#endif +} + +/** + * umul32_overflow - multiplication with overflow indication + * @x, @y: Input multipliers + * @ret: Output for product + * + * Computes *@ret = @x * @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool umul32_overflow(uint32_t x, uint32_t y, uint32_t *ret) +{ +#if __has_builtin(__builtin_mul_overflow) || __GNUC__ >= 5 + return __builtin_mul_overflow(x, y, ret); +#else + uint64_t z = (uint64_t)x * y; + *ret = z; + return z > UINT32_MAX; +#endif +} + +/** + * umul64_overflow - multiplication with overflow indication + * @x, @y: Input multipliers + * @ret: Output for product + * + * Computes *@ret = @x * @y, and returns true if and only if that + * value has been truncated. + */ +static inline bool umul64_overflow(uint64_t x, uint64_t y, uint64_t *ret) +{ +#if __has_builtin(__builtin_mul_overflow) || __GNUC__ >= 5 + return __builtin_mul_overflow(x, y, ret); +#else + uint64_t hi; + mulu64(ret, &hi, x, y); + return hi != 0; +#endif +} + +/** + * uadd64_carry - addition with carry-in and carry-out + * @x, @y: addends + * @pcarry: in-out carry value + * + * Computes @x + @y + *@pcarry, placing the carry-out back + * into *@pcarry and returning the 64-bit sum. + */ +static inline uint64_t uadd64_carry(uint64_t x, uint64_t y, bool *pcarry) +{ +#if __has_builtin(__builtin_addcll) + unsigned long long c = *pcarry; + x = __builtin_addcll(x, y, c, &c); + *pcarry = c & 1; + return x; +#else + bool c = *pcarry; + /* This is clang's internal expansion of __builtin_addc. */ + c = uadd64_overflow(x, c, &x); + c |= uadd64_overflow(x, y, &x); + *pcarry = c; + return x; +#endif +} + +/** + * usub64_borrow - subtraction with borrow-in and borrow-out + * @x, @y: addends + * @pborrow: in-out borrow value + * + * Computes @x - @y - *@pborrow, placing the borrow-out back + * into *@pborrow and returning the 64-bit sum. + */ +static inline uint64_t usub64_borrow(uint64_t x, uint64_t y, bool *pborrow) +{ +#if __has_builtin(__builtin_subcll) + unsigned long long b = *pborrow; + x = __builtin_subcll(x, y, b, &b); + *pborrow = b & 1; + return x; +#else + bool b = *pborrow; + b = usub64_overflow(x, b, &x); + b |= usub64_overflow(x, y, &x); + *pborrow = b; + return x; +#endif } /* Host type specific sizes of these routines. */ diff --git a/include/qemu/int128.h b/include/qemu/int128.h index 52fc238421..64500385e3 100644 --- a/include/qemu/int128.h +++ b/include/qemu/int128.h @@ -11,6 +11,11 @@ static inline Int128 int128_make64(uint64_t a) return a; } +static inline Int128 int128_makes64(int64_t a) +{ + return a; +} + static inline Int128 int128_make128(uint64_t lo, uint64_t hi) { return (__uint128_t)hi << 64 | lo; @@ -167,6 +172,11 @@ static inline Int128 int128_make64(uint64_t a) return (Int128) { a, 0 }; } +static inline Int128 int128_makes64(int64_t a) +{ + return (Int128) { a, a >> 63 }; +} + static inline Int128 int128_make128(uint64_t lo, uint64_t hi) { return (Int128) { lo, hi }; diff --git a/include/qemu/job.h b/include/qemu/job.h index efc6fa7544..41162ed494 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -254,7 +254,7 @@ struct JobDriver { /** * If the callback is not NULL, it will be invoked in job_cancel_async */ - void (*cancel)(Job *job); + void (*cancel)(Job *job, bool force); /** Called when the job is freed */ diff --git a/include/qemu/lockable.h b/include/qemu/lockable.h index b620023141..86db7cb04c 100644 --- a/include/qemu/lockable.h +++ b/include/qemu/lockable.h @@ -24,79 +24,71 @@ struct QemuLockable { QemuLockUnlockFunc *unlock; }; -/* This function gives an error if an invalid, non-NULL pointer type is passed - * to QEMU_MAKE_LOCKABLE. For optimized builds, we can rely on dead-code elimination - * from the compiler, and give the errors already at link time. - */ -#if defined(__OPTIMIZE__) && !defined(__SANITIZE_ADDRESS__) -void unknown_lock_type(void *); -#else -static inline void unknown_lock_type(void *unused) -{ - abort(); -} -#endif - static inline __attribute__((__always_inline__)) QemuLockable * qemu_make_lockable(void *x, QemuLockable *lockable) { - /* We cannot test this in a macro, otherwise we get compiler + /* + * We cannot test this in a macro, otherwise we get compiler * warnings like "the address of 'm' will always evaluate as 'true'". */ return x ? lockable : NULL; } -/* Auxiliary macros to simplify QEMU_MAKE_LOCABLE. */ -#define QEMU_LOCK_FUNC(x) ((QemuLockUnlockFunc *) \ - QEMU_GENERIC(x, \ - (QemuMutex *, qemu_mutex_lock), \ - (QemuRecMutex *, qemu_rec_mutex_lock), \ - (CoMutex *, qemu_co_mutex_lock), \ - (QemuSpin *, qemu_spin_lock), \ - unknown_lock_type)) +static inline __attribute__((__always_inline__)) QemuLockable * +qemu_null_lockable(void *x) +{ + if (x != NULL) { + qemu_build_not_reached(); + } + return NULL; +} -#define QEMU_UNLOCK_FUNC(x) ((QemuLockUnlockFunc *) \ - QEMU_GENERIC(x, \ - (QemuMutex *, qemu_mutex_unlock), \ - (QemuRecMutex *, qemu_rec_mutex_unlock), \ - (CoMutex *, qemu_co_mutex_unlock), \ - (QemuSpin *, qemu_spin_unlock), \ - unknown_lock_type)) - -/* In C, compound literals have the lifetime of an automatic variable. +/* + * In C, compound literals have the lifetime of an automatic variable. * In C++ it would be different, but then C++ wouldn't need QemuLockable * either... */ -#define QEMU_MAKE_LOCKABLE_(x) (&(QemuLockable) { \ - .object = (x), \ - .lock = QEMU_LOCK_FUNC(x), \ - .unlock = QEMU_UNLOCK_FUNC(x), \ +#define QML_OBJ_(x, name) (&(QemuLockable) { \ + .object = (x), \ + .lock = (QemuLockUnlockFunc *) qemu_ ## name ## _lock, \ + .unlock = (QemuLockUnlockFunc *) qemu_ ## name ## _unlock \ }) -/* QEMU_MAKE_LOCKABLE - Make a polymorphic QemuLockable +/** + * QEMU_MAKE_LOCKABLE - Make a polymorphic QemuLockable * - * @x: a lock object (currently one of QemuMutex, QemuRecMutex, CoMutex, QemuSpin). + * @x: a lock object (currently one of QemuMutex, QemuRecMutex, + * CoMutex, QemuSpin). * * Returns a QemuLockable object that can be passed around * to a function that can operate with locks of any kind, or * NULL if @x is %NULL. - */ -#define QEMU_MAKE_LOCKABLE(x) \ - QEMU_GENERIC(x, \ - (QemuLockable *, (x)), \ - qemu_make_lockable((x), QEMU_MAKE_LOCKABLE_(x))) - -/* QEMU_MAKE_LOCKABLE_NONNULL - Make a polymorphic QemuLockable * - * @x: a lock object (currently one of QemuMutex, QemuRecMutex, CoMutex, QemuSpin). + * Note the special case for void *, so that we may pass "NULL". + */ +#define QEMU_MAKE_LOCKABLE(x) \ + _Generic((x), QemuLockable *: (x), \ + void *: qemu_null_lockable(x), \ + QemuMutex *: qemu_make_lockable(x, QML_OBJ_(x, mutex)), \ + QemuRecMutex *: qemu_make_lockable(x, QML_OBJ_(x, rec_mutex)), \ + CoMutex *: qemu_make_lockable(x, QML_OBJ_(x, co_mutex)), \ + QemuSpin *: qemu_make_lockable(x, QML_OBJ_(x, spin))) + +/** + * QEMU_MAKE_LOCKABLE_NONNULL - Make a polymorphic QemuLockable + * + * @x: a lock object (currently one of QemuMutex, QemuRecMutex, + * CoMutex, QemuSpin). * * Returns a QemuLockable object that can be passed around * to a function that can operate with locks of any kind. */ -#define QEMU_MAKE_LOCKABLE_NONNULL(x) \ - QEMU_GENERIC(x, \ - (QemuLockable *, (x)), \ - QEMU_MAKE_LOCKABLE_(x)) +#define QEMU_MAKE_LOCKABLE_NONNULL(x) \ + _Generic((x), QemuLockable *: (x), \ + QemuMutex *: QML_OBJ_(x, mutex), \ + QemuRecMutex *: QML_OBJ_(x, rec_mutex), \ + CoMutex *: QML_OBJ_(x, co_mutex), \ + QemuSpin *: QML_OBJ_(x, spin)) static inline void qemu_lockable_lock(QemuLockable *x) { diff --git a/include/qemu/main-loop.h b/include/qemu/main-loop.h index 19389b0923..6846f80787 100644 --- a/include/qemu/main-loop.h +++ b/include/qemu/main-loop.h @@ -234,24 +234,6 @@ void event_notifier_set_handler(EventNotifier *e, GSource *iohandler_get_g_source(void); AioContext *iohandler_get_aio_context(void); -#ifdef CONFIG_POSIX -/** - * qemu_add_child_watch: Register a child process for reaping. - * - * Under POSIX systems, a parent process must read the exit status of - * its child processes using waitpid, or the operating system will not - * free some of the resources attached to that process. - * - * This function directs the QEMU main loop to observe a child process - * and call waitpid as soon as it exits; the watch is then removed - * automatically. It is useful whenever QEMU forks a child process - * but will find out about its termination by other means such as a - * "broken pipe". - * - * @pid: The pid that QEMU should observe. - */ -int qemu_add_child_watch(pid_t pid); -#endif /** * qemu_mutex_iothread_locked: Return lock status of the main loop mutex. @@ -312,7 +294,9 @@ void qemu_cond_timedwait_iothread(QemuCond *cond, int ms); void qemu_fd_register(int fd); -QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque); +#define qemu_bh_new(cb, opaque) \ + qemu_bh_new_full((cb), (opaque), (stringify(cb))) +QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name); void qemu_bh_schedule_idle(QEMUBH *bh); enum { diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h index 456ff87df1..90d0eee705 100644 --- a/include/qemu/mmap-alloc.h +++ b/include/qemu/mmap-alloc.h @@ -7,18 +7,22 @@ size_t qemu_fd_getpagesize(int fd); size_t qemu_mempath_getpagesize(const char *mem_path); /** - * qemu_ram_mmap: mmap the specified file or device. + * qemu_ram_mmap: mmap anonymous memory, the specified file or device. + * + * mmap() abstraction to map guest RAM, simplifying flag handling, taking + * care of alignment requirements and installing guard pages. * * Parameters: * @fd: the file or the device to mmap * @size: the number of bytes to be mmaped * @align: if not zero, specify the alignment of the starting mapping address; * otherwise, the alignment in use will be determined by QEMU. - * @readonly: true for a read-only mapping, false for read/write. - * @shared: map has RAM_SHARED flag. - * @is_pmem: map has RAM_PMEM flag. + * @qemu_map_flags: QEMU_MAP_* flags * @map_offset: map starts at offset of map_offset from the start of fd * + * Internally, MAP_PRIVATE, MAP_ANONYMOUS and MAP_SHARED_VALIDATE are set + * implicitly based on other parameters. + * * Return: * On success, return a pointer to the mapped area. * On failure, return MAP_FAILED. @@ -26,9 +30,7 @@ size_t qemu_mempath_getpagesize(const char *mem_path); void *qemu_ram_mmap(int fd, size_t size, size_t align, - bool readonly, - bool shared, - bool is_pmem, + uint32_t qemu_map_flags, off_t map_offset); void qemu_ram_munmap(int fd, void *ptr, size_t size); diff --git a/include/qemu/module.h b/include/qemu/module.h index 944d403cbd..3deac0078b 100644 --- a/include/qemu/module.h +++ b/include/qemu/module.h @@ -72,5 +72,84 @@ void module_call_init(module_init_type type); bool module_load_one(const char *prefix, const char *lib_name, bool mayfail); void module_load_qom_one(const char *type); void module_load_qom_all(void); +void module_allow_arch(const char *arch); + +/** + * DOC: module info annotation macros + * + * `scripts/modinfo-collect.py` will collect module info, + * using the preprocessor and -DQEMU_MODINFO. + * + * `scripts/modinfo-generate.py` will create a module meta-data database + * from the collected information so qemu knows about module + * dependencies and QOM objects implemented by modules. + * + * See `*.modinfo` and `modinfo.c` in the build directory to check the + * script results. + */ +#ifdef QEMU_MODINFO +# define modinfo(kind, value) \ + MODINFO_START kind value MODINFO_END +#else +# define modinfo(kind, value) +#endif + +/** + * module_obj + * + * @name: QOM type. + * + * This module implements QOM type @name. + */ +#define module_obj(name) modinfo(obj, name) + +/** + * module_dep + * + * @name: module name + * + * This module depends on module @name. + */ +#define module_dep(name) modinfo(dep, name) + +/** + * module_arch + * + * @name: target architecture + * + * This module is for target architecture @arch. + * + * Note that target-dependent modules are tagged automatically, so + * this is only needed in case target-independent modules should be + * restricted. Use case example: the ccw bus is implemented by s390x + * only. + */ +#define module_arch(name) modinfo(arch, name) + +/** + * module_opts + * + * @name: QemuOpts name + * + * This module registers QemuOpts @name. + */ +#define module_opts(name) modinfo(opts, name) + +/* + * module info database + * + * scripts/modinfo-generate.c will build this using the data collected + * by scripts/modinfo-collect.py + */ +typedef struct QemuModinfo QemuModinfo; +struct QemuModinfo { + const char *name; + const char *arch; + const char **objs; + const char **deps; + const char **opts; +}; +extern const QemuModinfo qemu_modinfo[]; +void module_init_info(const QemuModinfo *info); #endif diff --git a/include/qemu/option.h b/include/qemu/option.h index f73e0dc7d9..306bf07575 100644 --- a/include/qemu/option.h +++ b/include/qemu/option.h @@ -119,7 +119,6 @@ QemuOpts *qemu_opts_create(QemuOptsList *list, const char *id, int fail_if_exists, Error **errp); void qemu_opts_reset(QemuOptsList *list); void qemu_opts_loc_restore(QemuOpts *opts); -bool qemu_opts_set(QemuOptsList *list, const char *name, const char *value, Error **errp); const char *qemu_opts_id(QemuOpts *opts); void qemu_opts_set_id(QemuOpts *opts, char *id); void qemu_opts_del(QemuOpts *opts); @@ -130,8 +129,6 @@ QemuOpts *qemu_opts_parse_noisily(QemuOptsList *list, const char *params, bool permit_abbrev); QemuOpts *qemu_opts_parse(QemuOptsList *list, const char *params, bool permit_abbrev, Error **errp); -void qemu_opts_set_defaults(QemuOptsList *list, const char *params, - int permit_abbrev); QemuOpts *qemu_opts_from_qdict(QemuOptsList *list, const QDict *qdict, Error **errp); QDict *qemu_opts_to_qdict_filtered(QemuOpts *opts, QDict *qdict, @@ -147,7 +144,10 @@ void qemu_opts_print_help(QemuOptsList *list, bool print_caption); void qemu_opts_free(QemuOptsList *list); QemuOptsList *qemu_opts_append(QemuOptsList *dst, QemuOptsList *list); +QDict *keyval_parse_into(QDict *qdict, const char *params, const char *implied_key, + bool *p_help, Error **errp); QDict *keyval_parse(const char *params, const char *implied_key, bool *help, Error **errp); +void keyval_merge(QDict *old, const QDict *new, Error **errp); #endif diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h index cb2a07e472..60718fc342 100644 --- a/include/qemu/osdep.h +++ b/include/qemu/osdep.h @@ -131,10 +131,6 @@ QEMU_EXTERN_C int daemon(int, int); */ #include "glib-compat.h" -#ifdef __cplusplus -extern "C" { -#endif - #ifdef _WIN32 #include "sysemu/os-win32.h" #endif @@ -143,6 +139,10 @@ extern "C" { #include "sysemu/os-posix.h" #endif +#ifdef __cplusplus +extern "C" { +#endif + #include "qemu/typedefs.h" /* @@ -195,6 +195,9 @@ extern "C" { #ifndef MAP_FIXED_NOREPLACE #define MAP_FIXED_NOREPLACE 0 #endif +#ifndef MAP_NORESERVE +#define MAP_NORESERVE 0 +#endif #ifndef ENOMEDIUM #define ENOMEDIUM ENODEV #endif @@ -253,7 +256,7 @@ extern "C" { /* Mac OSX has a bug that incorrectly defines SIZE_MAX with * the wrong type. Our replacement isn't usable in preprocessor * expressions, but it is sufficient for our needs. */ -#if defined(HAVE_BROKEN_SIZE_MAX) && HAVE_BROKEN_SIZE_MAX +#ifdef HAVE_BROKEN_SIZE_MAX #undef SIZE_MAX #define SIZE_MAX ((size_t)-1) #endif @@ -316,11 +319,16 @@ extern "C" { }) #endif -/* Round number down to multiple */ +/* + * Round number down to multiple. Safe when m is not a power of 2 (see + * ROUND_DOWN for a faster version when a power of 2 is guaranteed). + */ #define QEMU_ALIGN_DOWN(n, m) ((n) / (m) * (m)) -/* Round number up to multiple. Safe when m is not a power of 2 (see - * ROUND_UP for a faster version when a power of 2 is guaranteed) */ +/* + * Round number up to multiple. Safe when m is not a power of 2 (see + * ROUND_UP for a faster version when a power of 2 is guaranteed). + */ #define QEMU_ALIGN_UP(n, m) QEMU_ALIGN_DOWN((n) + (m) - 1, (m)) /* Check if n is a multiple of m */ @@ -337,11 +345,22 @@ extern "C" { /* Check if pointer p is n-bytes aligned */ #define QEMU_PTR_IS_ALIGNED(p, n) QEMU_IS_ALIGNED((uintptr_t)(p), (n)) -/* Round number up to multiple. Requires that d be a power of 2 (see +/* + * Round number down to multiple. Requires that d be a power of 2 (see * QEMU_ALIGN_UP for a safer but slower version on arbitrary - * numbers); works even if d is a smaller type than n. */ + * numbers); works even if d is a smaller type than n. + */ +#ifndef ROUND_DOWN +#define ROUND_DOWN(n, d) ((n) & -(0 ? (n) : (d))) +#endif + +/* + * Round number up to multiple. Requires that d be a power of 2 (see + * QEMU_ALIGN_UP for a safer but slower version on arbitrary + * numbers); works even if d is a smaller type than n. + */ #ifndef ROUND_UP -#define ROUND_UP(n, d) (((n) + (d) - 1) & -(0 ? (n) : (d))) +#define ROUND_UP(n, d) ROUND_DOWN((n) + (d) - 1, (d)) #endif #ifndef DIV_ROUND_UP @@ -362,10 +381,50 @@ extern "C" { int qemu_daemon(int nochdir, int noclose); void *qemu_try_memalign(size_t alignment, size_t size); void *qemu_memalign(size_t alignment, size_t size); -void *qemu_anon_ram_alloc(size_t size, uint64_t *align, bool shared); +void *qemu_anon_ram_alloc(size_t size, uint64_t *align, bool shared, + bool noreserve); void qemu_vfree(void *ptr); void qemu_anon_ram_free(void *ptr, size_t size); +/* + * It's an analog of GLIB's g_autoptr_cleanup_generic_gfree(), used to define + * g_autofree macro. + */ +static inline void qemu_cleanup_generic_vfree(void *p) +{ + void **pp = (void **)p; + qemu_vfree(*pp); +} + +/* + * Analog of g_autofree, but qemu_vfree is called on cleanup instead of g_free. + */ +#define QEMU_AUTO_VFREE __attribute__((cleanup(qemu_cleanup_generic_vfree))) + +/* + * Abstraction of PROT_ and MAP_ flags as passed to mmap(), for example, + * consumed by qemu_ram_mmap(). + */ + +/* Map PROT_READ instead of PROT_READ | PROT_WRITE. */ +#define QEMU_MAP_READONLY (1 << 0) + +/* Use MAP_SHARED instead of MAP_PRIVATE. */ +#define QEMU_MAP_SHARED (1 << 1) + +/* + * Use MAP_SYNC | MAP_SHARED_VALIDATE if supported. Ignored without + * QEMU_MAP_SHARED. If mapping fails, warn and fallback to !QEMU_MAP_SYNC. + */ +#define QEMU_MAP_SYNC (1 << 2) + +/* + * Use MAP_NORESERVE to skip reservation of swap space (or huge pages if + * applicable). Bail out if not supported/effective. + */ +#define QEMU_MAP_NORESERVE (1 << 3) + + #define QEMU_MADV_INVALID -1 #if defined(CONFIG_MADVISE) @@ -410,7 +469,7 @@ void qemu_anon_ram_free(void *ptr, size_t size); #ifdef MADV_REMOVE #define QEMU_MADV_REMOVE MADV_REMOVE #else -#define QEMU_MADV_REMOVE QEMU_MADV_INVALID +#define QEMU_MADV_REMOVE QEMU_MADV_DONTNEED #endif #elif defined(CONFIG_POSIX_MADVISE) @@ -424,7 +483,7 @@ void qemu_anon_ram_free(void *ptr, size_t size); #define QEMU_MADV_DONTDUMP QEMU_MADV_INVALID #define QEMU_MADV_HUGEPAGE QEMU_MADV_INVALID #define QEMU_MADV_NOHUGEPAGE QEMU_MADV_INVALID -#define QEMU_MADV_REMOVE QEMU_MADV_INVALID +#define QEMU_MADV_REMOVE QEMU_MADV_DONTNEED #else /* no-op */ @@ -512,6 +571,7 @@ void sigaction_invoke(struct sigaction *action, #endif int qemu_madvise(void *addr, size_t len, int advice); +int qemu_mprotect_rw(void *addr, size_t size); int qemu_mprotect_rwx(void *addr, size_t size); int qemu_mprotect_none(void *addr, size_t size); diff --git a/include/qemu/plugin-memory.h b/include/qemu/plugin-memory.h index fbbe99474b..0f59226727 100644 --- a/include/qemu/plugin-memory.h +++ b/include/qemu/plugin-memory.h @@ -6,8 +6,8 @@ * SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _PLUGIN_MEMORY_H_ -#define _PLUGIN_MEMORY_H_ +#ifndef PLUGIN_MEMORY_H +#define PLUGIN_MEMORY_H struct qemu_plugin_hwaddr { bool is_io; @@ -18,7 +18,7 @@ struct qemu_plugin_hwaddr { hwaddr offset; } io; struct { - uint64_t hostaddr; + void *hostaddr; } ram; } v; }; diff --git a/include/qemu/plugin.h b/include/qemu/plugin.h index c5a79a89f0..9a8438f683 100644 --- a/include/qemu/plugin.h +++ b/include/qemu/plugin.h @@ -79,7 +79,6 @@ enum plugin_dyn_cb_subtype { struct qemu_plugin_dyn_cb { union qemu_plugin_cb_sig f; void *userp; - unsigned tcg_flags; enum plugin_dyn_cb_subtype type; /* @rw applies to mem callbacks only (both regular and inline) */ enum qemu_plugin_mem_rw rw; @@ -191,6 +190,16 @@ void qemu_plugin_add_dyn_cb_arr(GArray *arr); void qemu_plugin_disable_mem_helpers(CPUState *cpu); +/** + * qemu_plugin_user_exit(): clean-up callbacks before calling exit callbacks + * + * This is a user-mode only helper that ensure we have fully cleared + * callbacks from all threads before calling the exit callbacks. This + * is so the plugins themselves don't have to jump through hoops to + * guard against race conditions. + */ +void qemu_plugin_user_exit(void); + #else /* !CONFIG_PLUGIN */ static inline void qemu_plugin_add_opts(void) @@ -251,6 +260,8 @@ void qemu_plugin_add_dyn_cb_arr(GArray *arr) static inline void qemu_plugin_disable_mem_helpers(CPUState *cpu) { } +static inline void qemu_plugin_user_exit(void) +{ } #endif /* !CONFIG_PLUGIN */ #endif /* QEMU_PLUGIN_H */ diff --git a/include/qemu/progress_meter.h b/include/qemu/progress_meter.h index 9a23ff071c..dadf822bbf 100644 --- a/include/qemu/progress_meter.h +++ b/include/qemu/progress_meter.h @@ -27,6 +27,8 @@ #ifndef QEMU_PROGRESS_METER_H #define QEMU_PROGRESS_METER_H +#include "qemu/lockable.h" + typedef struct ProgressMeter { /** * Current progress. The unit is arbitrary as long as the ratio between @@ -37,22 +39,24 @@ typedef struct ProgressMeter { /** Estimated current value at the completion of the process */ uint64_t total; + + QemuMutex lock; /* protects concurrent access to above fields */ } ProgressMeter; -static inline void progress_work_done(ProgressMeter *pm, uint64_t done) -{ - pm->current += done; -} +void progress_init(ProgressMeter *pm); +void progress_destroy(ProgressMeter *pm); -static inline void progress_set_remaining(ProgressMeter *pm, uint64_t remaining) -{ - pm->total = pm->current + remaining; -} +/* Get a snapshot of internal current and total values */ +void progress_get_snapshot(ProgressMeter *pm, uint64_t *current, + uint64_t *total); -static inline void progress_increase_remaining(ProgressMeter *pm, - uint64_t delta) -{ - pm->total += delta; -} +/* Increases the amount of work done so far by @done */ +void progress_work_done(ProgressMeter *pm, uint64_t done); + +/* Sets how much work has to be done to complete to @remaining */ +void progress_set_remaining(ProgressMeter *pm, uint64_t remaining); + +/* Increases the total work to do by @delta */ +void progress_increase_remaining(ProgressMeter *pm, uint64_t delta); #endif /* QEMU_PROGRESS_METER_H */ diff --git a/qemu-options.h b/include/qemu/qemu-options.h similarity index 88% rename from qemu-options.h rename to include/qemu/qemu-options.h index b4ee63cd60..4a62c83c45 100644 --- a/qemu-options.h +++ b/include/qemu/qemu-options.h @@ -29,8 +29,13 @@ #define QEMU_OPTIONS_H enum { -#define QEMU_OPTIONS_GENERATE_ENUM -#include "qemu-options-wrapper.h" + +#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask) \ + opt_enum, +#define DEFHEADING(text) +#define ARCHHEADING(text, arch_mask) + +#include "qemu-options.def" }; #endif diff --git a/include/qemu/qemu-plugin.h b/include/qemu/qemu-plugin.h index 97cdfd7761..e6e815abc5 100644 --- a/include/qemu/qemu-plugin.h +++ b/include/qemu/qemu-plugin.h @@ -525,6 +525,15 @@ qemu_plugin_register_vcpu_syscall_ret_cb(qemu_plugin_id_t id, char *qemu_plugin_insn_disas(const struct qemu_plugin_insn *insn); +/** + * qemu_plugin_insn_symbol() - best effort symbol lookup + * @insn: instruction reference + * + * Return a static string referring to the symbol. This is dependent + * on the binary QEMU is running having provided a symbol table. + */ +const char *qemu_plugin_insn_symbol(const struct qemu_plugin_insn *insn); + /** * qemu_plugin_vcpu_for_each() - iterate over the existing vCPU * @id: plugin ID @@ -540,6 +549,19 @@ void qemu_plugin_vcpu_for_each(qemu_plugin_id_t id, void qemu_plugin_register_flush_cb(qemu_plugin_id_t id, qemu_plugin_simple_cb_t cb); +/** + * qemu_plugin_register_atexit_cb() - register exit callback + * @id: plugin ID + * @cb: callback + * @userdata: user data for callback + * + * The @cb function is called once execution has finished. Plugins + * should be able to free all their resources at this point much like + * after a reset/uninstall callback is called. + * + * In user-mode it is possible a few un-instrumented instructions from + * child threads may run before the host kernel reaps the threads. + */ void qemu_plugin_register_atexit_cb(qemu_plugin_id_t id, qemu_plugin_udata_cb_t cb, void *userdata); diff --git a/include/qemu/ratelimit.h b/include/qemu/ratelimit.h index 01da8d63f1..48bf59e857 100644 --- a/include/qemu/ratelimit.h +++ b/include/qemu/ratelimit.h @@ -14,9 +14,11 @@ #ifndef QEMU_RATELIMIT_H #define QEMU_RATELIMIT_H +#include "qemu/lockable.h" #include "qemu/timer.h" typedef struct { + QemuMutex lock; int64_t slice_start_time; int64_t slice_end_time; uint64_t slice_quota; @@ -40,7 +42,12 @@ static inline int64_t ratelimit_calculate_delay(RateLimit *limit, uint64_t n) int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); double delay_slices; - assert(limit->slice_quota && limit->slice_ns); + QEMU_LOCK_GUARD(&limit->lock); + if (!limit->slice_quota) { + /* Throttling disabled. */ + return 0; + } + assert(limit->slice_ns); if (limit->slice_end_time < now) { /* Previous, possibly extended, time slice finished; reset the @@ -65,11 +72,26 @@ static inline int64_t ratelimit_calculate_delay(RateLimit *limit, uint64_t n) return limit->slice_end_time - now; } +static inline void ratelimit_init(RateLimit *limit) +{ + qemu_mutex_init(&limit->lock); +} + +static inline void ratelimit_destroy(RateLimit *limit) +{ + qemu_mutex_destroy(&limit->lock); +} + static inline void ratelimit_set_speed(RateLimit *limit, uint64_t speed, uint64_t slice_ns) { + QEMU_LOCK_GUARD(&limit->lock); limit->slice_ns = slice_ns; - limit->slice_quota = MAX(((double)speed * slice_ns) / 1000000000ULL, 1); + if (speed == 0) { + limit->slice_quota = 0; + } else { + limit->slice_quota = MAX(((double)speed * slice_ns) / 1000000000ULL, 1); + } } #endif diff --git a/include/qemu/selfmap.h b/include/qemu/selfmap.h index 8382c4c779..80cf920fba 100644 --- a/include/qemu/selfmap.h +++ b/include/qemu/selfmap.h @@ -6,8 +6,8 @@ * SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _SELFMAP_H_ -#define _SELFMAP_H_ +#ifndef SELFMAP_H +#define SELFMAP_H typedef struct { unsigned long start; diff --git a/include/qemu/sockets.h b/include/qemu/sockets.h index 7d1f813576..0c34bf2398 100644 --- a/include/qemu/sockets.h +++ b/include/qemu/sockets.h @@ -111,4 +111,15 @@ SocketAddress *socket_remote_address(int fd, Error **errp); */ SocketAddress *socket_address_flatten(SocketAddressLegacy *addr); +/** + * socket_address_parse_named_fd: + * + * Modify @addr, replacing a named fd by its corresponding number. + * Needed for callers that plan to pass @addr to a context where the + * current monitor is not available. + * + * Return 0 on success. + */ +int socket_address_parse_named_fd(SocketAddress *addr, Error **errp); + #endif /* QEMU_SOCKETS_H */ diff --git a/include/qemu/stats64.h b/include/qemu/stats64.h index fdd3d1b8f9..802402254b 100644 --- a/include/qemu/stats64.h +++ b/include/qemu/stats64.h @@ -21,7 +21,7 @@ typedef struct Stat64 { #ifdef CONFIG_ATOMIC64 - uint64_t value; + aligned_uint64_t value; #else uint32_t low, high; uint32_t lock; diff --git a/include/qemu/thread-posix.h b/include/qemu/thread-posix.h index c903525062..b792e6ef37 100644 --- a/include/qemu/thread-posix.h +++ b/include/qemu/thread-posix.h @@ -4,12 +4,6 @@ #include #include -typedef QemuMutex QemuRecMutex; -#define qemu_rec_mutex_destroy qemu_mutex_destroy -#define qemu_rec_mutex_lock_impl qemu_mutex_lock_impl -#define qemu_rec_mutex_trylock_impl qemu_mutex_trylock_impl -#define qemu_rec_mutex_unlock qemu_mutex_unlock - struct QemuMutex { pthread_mutex_t lock; #ifdef CONFIG_DEBUG_MUTEX @@ -19,6 +13,14 @@ struct QemuMutex { bool initialized; }; +/* + * QemuRecMutex cannot be a typedef of QemuMutex lest we have two + * compatible cases in _Generic. See qemu/lockable.h. + */ +typedef struct QemuRecMutex { + QemuMutex m; +} QemuRecMutex; + struct QemuCond { pthread_cond_t cond; bool initialized; diff --git a/include/qemu/thread-win32.h b/include/qemu/thread-win32.h index d0a1a9597e..d95af4498f 100644 --- a/include/qemu/thread-win32.h +++ b/include/qemu/thread-win32.h @@ -18,12 +18,6 @@ struct QemuRecMutex { bool initialized; }; -void qemu_rec_mutex_destroy(QemuRecMutex *mutex); -void qemu_rec_mutex_lock_impl(QemuRecMutex *mutex, const char *file, int line); -int qemu_rec_mutex_trylock_impl(QemuRecMutex *mutex, const char *file, - int line); -void qemu_rec_mutex_unlock(QemuRecMutex *mutex); - struct QemuCond { CONDITION_VARIABLE var; bool initialized; diff --git a/include/qemu/thread.h b/include/qemu/thread.h index 5435763184..460568d67d 100644 --- a/include/qemu/thread.h +++ b/include/qemu/thread.h @@ -28,6 +28,12 @@ int qemu_mutex_trylock_impl(QemuMutex *mutex, const char *file, const int line); void qemu_mutex_lock_impl(QemuMutex *mutex, const char *file, const int line); void qemu_mutex_unlock_impl(QemuMutex *mutex, const char *file, const int line); +void qemu_rec_mutex_init(QemuRecMutex *mutex); +void qemu_rec_mutex_destroy(QemuRecMutex *mutex); +void qemu_rec_mutex_lock_impl(QemuRecMutex *mutex, const char *file, int line); +int qemu_rec_mutex_trylock_impl(QemuRecMutex *mutex, const char *file, int line); +void qemu_rec_mutex_unlock_impl(QemuRecMutex *mutex, const char *file, int line); + typedef void (*QemuMutexLockFunc)(QemuMutex *m, const char *f, int l); typedef int (*QemuMutexTrylockFunc)(QemuMutex *m, const char *f, int l); typedef void (*QemuRecMutexLockFunc)(QemuRecMutex *m, const char *f, int l); @@ -104,6 +110,9 @@ extern QemuCondTimedWaitFunc qemu_cond_timedwait_func; #define qemu_mutex_unlock(mutex) \ qemu_mutex_unlock_impl(mutex, __FILE__, __LINE__) +#define qemu_rec_mutex_unlock(mutex) \ + qemu_rec_mutex_unlock_impl(mutex, __FILE__, __LINE__) + static inline void (qemu_mutex_lock)(QemuMutex *mutex) { qemu_mutex_lock(mutex); @@ -129,8 +138,10 @@ static inline int (qemu_rec_mutex_trylock)(QemuRecMutex *mutex) return qemu_rec_mutex_trylock(mutex); } -/* Prototypes for other functions are in thread-posix.h/thread-win32.h. */ -void qemu_rec_mutex_init(QemuRecMutex *mutex); +static inline void (qemu_rec_mutex_unlock)(QemuRecMutex *mutex) +{ + qemu_rec_mutex_unlock(mutex); +} void qemu_cond_init(QemuCond *cond); void qemu_cond_destroy(QemuCond *cond); diff --git a/include/qemu/transactions.h b/include/qemu/transactions.h new file mode 100644 index 0000000000..92c5965235 --- /dev/null +++ b/include/qemu/transactions.h @@ -0,0 +1,63 @@ +/* + * Simple transactions API + * + * Copyright (c) 2021 Virtuozzo International GmbH. + * + * Author: + * Vladimir Sementsov-Ogievskiy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + * + * + * = Generic transaction API = + * + * The intended usage is the following: you create "prepare" functions, which + * represents the actions. They will usually have Transaction* argument, and + * call tran_add() to register finalization callbacks. For finalization + * callbacks, prepare corresponding TransactionActionDrv structures. + * + * Then, when you need to make a transaction, create an empty Transaction by + * tran_create(), call your "prepare" functions on it, and finally call + * tran_abort() or tran_commit() to finalize the transaction by corresponding + * finalization actions in reverse order. + */ + +#ifndef QEMU_TRANSACTIONS_H +#define QEMU_TRANSACTIONS_H + +#include + +typedef struct TransactionActionDrv { + void (*abort)(void *opaque); + void (*commit)(void *opaque); + void (*clean)(void *opaque); +} TransactionActionDrv; + +typedef struct Transaction Transaction; + +Transaction *tran_new(void); +void tran_add(Transaction *tran, TransactionActionDrv *drv, void *opaque); +void tran_abort(Transaction *tran); +void tran_commit(Transaction *tran); + +static inline void tran_finalize(Transaction *tran, int ret) +{ + if (ret < 0) { + tran_abort(tran); + } else { + tran_commit(tran); + } +} + +#endif /* QEMU_TRANSACTIONS_H */ diff --git a/include/qom/object.h b/include/qom/object.h index 3ddc4b34dc..14072b91cf 100644 --- a/include/qom/object.h +++ b/include/qom/object.h @@ -866,6 +866,29 @@ static void do_qemu_init_ ## type_array(void) \ } \ type_init(do_qemu_init_ ## type_array) +/** + * type_print_class_properties: + * @type: a QOM class name + * + * Print the object's class properties to stdout or the monitor. + * Return whether an object was found. + */ +bool type_print_class_properties(const char *type); + +/** + * object_set_properties_from_keyval: + * @obj: a QOM object + * @qdict: a dictionary with the properties to be set + * @from_json: true if leaf values of @qdict are typed, false if they + * are strings + * @errp: pointer to error object + * + * For each key in the dictionary, parse the value string if needed, + * then set the corresponding property in @obj. + */ +void object_set_properties_from_keyval(Object *obj, const QDict *qdict, + bool from_json, Error **errp); + /** * object_class_dynamic_cast_assert: * @klass: The #ObjectClass to attempt to cast. diff --git a/include/standard-headers/asm-x86/kvm_para.h b/include/standard-headers/asm-x86/kvm_para.h index 215d01b4ec..204cfb8640 100644 --- a/include/standard-headers/asm-x86/kvm_para.h +++ b/include/standard-headers/asm-x86/kvm_para.h @@ -33,6 +33,8 @@ #define KVM_FEATURE_PV_SCHED_YIELD 13 #define KVM_FEATURE_ASYNC_PF_INT 14 #define KVM_FEATURE_MSI_EXT_DEST_ID 15 +#define KVM_FEATURE_HC_MAP_GPA_RANGE 16 +#define KVM_FEATURE_MIGRATION_CONTROL 17 #define KVM_HINTS_REALTIME 0 @@ -54,6 +56,7 @@ #define MSR_KVM_POLL_CONTROL 0x4b564d05 #define MSR_KVM_ASYNC_PF_INT 0x4b564d06 #define MSR_KVM_ASYNC_PF_ACK 0x4b564d07 +#define MSR_KVM_MIGRATION_CONTROL 0x4b564d08 struct kvm_steal_time { uint64_t steal; @@ -90,6 +93,16 @@ struct kvm_clock_pairing { /* MSR_KVM_ASYNC_PF_INT */ #define KVM_ASYNC_PF_VEC_MASK GENMASK(7, 0) +/* MSR_KVM_MIGRATION_CONTROL */ +#define KVM_MIGRATION_READY (1 << 0) + +/* KVM_HC_MAP_GPA_RANGE */ +#define KVM_MAP_GPA_RANGE_PAGE_SZ_4K 0 +#define KVM_MAP_GPA_RANGE_PAGE_SZ_2M (1 << 0) +#define KVM_MAP_GPA_RANGE_PAGE_SZ_1G (1 << 1) +#define KVM_MAP_GPA_RANGE_ENC_STAT(n) (n << 4) +#define KVM_MAP_GPA_RANGE_ENCRYPTED KVM_MAP_GPA_RANGE_ENC_STAT(1) +#define KVM_MAP_GPA_RANGE_DECRYPTED KVM_MAP_GPA_RANGE_ENC_STAT(0) /* Operations for KVM_HC_MMU_OP */ #define KVM_MMU_OP_WRITE_PTE 1 diff --git a/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h index 1677208a41..94d41b202c 100644 --- a/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h +++ b/include/standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h @@ -70,30 +70,6 @@ enum pvrdma_mtu { PVRDMA_MTU_4096 = 5, }; -static inline int pvrdma_mtu_enum_to_int(enum pvrdma_mtu mtu) -{ - switch (mtu) { - case PVRDMA_MTU_256: return 256; - case PVRDMA_MTU_512: return 512; - case PVRDMA_MTU_1024: return 1024; - case PVRDMA_MTU_2048: return 2048; - case PVRDMA_MTU_4096: return 4096; - default: return -1; - } -} - -static inline enum pvrdma_mtu pvrdma_mtu_int_to_enum(int mtu) -{ - switch (mtu) { - case 256: return PVRDMA_MTU_256; - case 512: return PVRDMA_MTU_512; - case 1024: return PVRDMA_MTU_1024; - case 2048: return PVRDMA_MTU_2048; - case 4096: - default: return PVRDMA_MTU_4096; - } -} - enum pvrdma_port_state { PVRDMA_PORT_NOP = 0, PVRDMA_PORT_DOWN = 1, @@ -138,17 +114,6 @@ enum pvrdma_port_width { PVRDMA_WIDTH_12X = 8, }; -static inline int pvrdma_width_enum_to_int(enum pvrdma_port_width width) -{ - switch (width) { - case PVRDMA_WIDTH_1X: return 1; - case PVRDMA_WIDTH_4X: return 4; - case PVRDMA_WIDTH_8X: return 8; - case PVRDMA_WIDTH_12X: return 12; - default: return -1; - } -} - enum pvrdma_port_speed { PVRDMA_SPEED_SDR = 1, PVRDMA_SPEED_DDR = 2, diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h index c47e19810c..352b51fd0a 100644 --- a/include/standard-headers/drm/drm_fourcc.h +++ b/include/standard-headers/drm/drm_fourcc.h @@ -167,6 +167,13 @@ extern "C" { #define DRM_FORMAT_RGBA1010102 fourcc_code('R', 'A', '3', '0') /* [31:0] R:G:B:A 10:10:10:2 little endian */ #define DRM_FORMAT_BGRA1010102 fourcc_code('B', 'A', '3', '0') /* [31:0] B:G:R:A 10:10:10:2 little endian */ +/* 64 bpp RGB */ +#define DRM_FORMAT_XRGB16161616 fourcc_code('X', 'R', '4', '8') /* [63:0] x:R:G:B 16:16:16:16 little endian */ +#define DRM_FORMAT_XBGR16161616 fourcc_code('X', 'B', '4', '8') /* [63:0] x:B:G:R 16:16:16:16 little endian */ + +#define DRM_FORMAT_ARGB16161616 fourcc_code('A', 'R', '4', '8') /* [63:0] A:R:G:B 16:16:16:16 little endian */ +#define DRM_FORMAT_ABGR16161616 fourcc_code('A', 'B', '4', '8') /* [63:0] A:B:G:R 16:16:16:16 little endian */ + /* * Floating point 64bpp RGB * IEEE 754-2008 binary16 half-precision float @@ -526,6 +533,25 @@ extern "C" { */ #define I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS fourcc_mod_code(INTEL, 7) +/* + * Intel Color Control Surface with Clear Color (CCS) for Gen-12 render + * compression. + * + * The main surface is Y-tiled and is at plane index 0 whereas CCS is linear + * and at index 1. The clear color is stored at index 2, and the pitch should + * be ignored. The clear color structure is 256 bits. The first 128 bits + * represents Raw Clear Color Red, Green, Blue and Alpha color each represented + * by 32 bits. The raw clear color is consumed by the 3d engine and generates + * the converted clear color of size 64 bits. The first 32 bits store the Lower + * Converted Clear Color value and the next 32 bits store the Higher Converted + * Clear Color value when applicable. The Converted Clear Color values are + * consumed by the DE. The last 64 bits are used to store Color Discard Enable + * and Depth Clear Value Valid which are ignored by the DE. A CCS cache line + * corresponds to an area of 4x1 tiles in the main surface. The main surface + * pitch is required to be a multiple of 4 tile widths. + */ +#define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC fourcc_mod_code(INTEL, 8) + /* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * @@ -1035,9 +1061,9 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier) * Not all combinations are valid, and different SoCs may support different * combinations of layout and options. */ -#define __fourcc_mod_amlogic_layout_mask 0xf +#define __fourcc_mod_amlogic_layout_mask 0xff #define __fourcc_mod_amlogic_options_shift 8 -#define __fourcc_mod_amlogic_options_mask 0xf +#define __fourcc_mod_amlogic_options_mask 0xff #define DRM_FORMAT_MOD_AMLOGIC_FBC(__layout, __options) \ fourcc_mod_code(AMLOGIC, \ diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index 8bfd01d230..053d3fafdf 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -26,6 +26,14 @@ * have the same layout for 32-bit and 64-bit userland. */ +/* Note on reserved space. + * Reserved fields must not be accessed directly by user space because + * they may be replaced by a different field in the future. They must + * be initialized to zero before making the request, e.g. via memset + * of the entire structure or implicitly by not being set in a structure + * initializer. + */ + /** * struct ethtool_cmd - DEPRECATED, link control and status * This structure is DEPRECATED, please use struct ethtool_link_settings. @@ -67,6 +75,7 @@ * and other link features that the link partner advertised * through autonegotiation; 0 if unknown or not applicable. * Read-only. + * @reserved: Reserved for future use; see the note on reserved space. * * The link speed in Mbps is split between @speed and @speed_hi. Use * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to @@ -155,6 +164,7 @@ static inline uint32_t ethtool_cmd_speed(const struct ethtool_cmd *ep) * @bus_info: Device bus address. This should match the dev_name() * string for the underlying bus device, if there is one. May be * an empty string. + * @reserved2: Reserved for future use; see the note on reserved space. * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and * %ETHTOOL_SPFLAGS commands; also the number of strings in the * %ETH_SS_PRIV_FLAGS set @@ -223,7 +233,7 @@ enum tunable_id { ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ /* * Add your fresh new tunable attribute above and remember to update - * tunable_strings[] in net/core/ethtool.c + * tunable_strings[] in net/ethtool/common.c */ __ETHTOOL_TUNABLE_COUNT, }; @@ -287,7 +297,7 @@ enum phy_tunable_id { ETHTOOL_PHY_EDPD, /* * Add your fresh new phy tunable attribute above and remember to update - * phy_tunable_strings[] in net/core/ethtool.c + * phy_tunable_strings[] in net/ethtool/common.c */ __ETHTOOL_PHY_TUNABLE_COUNT, }; @@ -356,6 +366,7 @@ struct ethtool_eeprom { * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting * its tx lpi (after reaching 'idle' state). Effective only when eee * was negotiated and tx_lpi_enabled was set. + * @reserved: Reserved for future use; see the note on reserved space. */ struct ethtool_eee { uint32_t cmd; @@ -374,6 +385,7 @@ struct ethtool_eee { * @cmd: %ETHTOOL_GMODULEINFO * @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx * @eeprom_len: Length of the eeprom + * @reserved: Reserved for future use; see the note on reserved space. * * This structure is used to return the information to * properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM. @@ -579,9 +591,7 @@ struct ethtool_pauseparam { uint32_t tx_pause; }; -/** - * enum ethtool_link_ext_state - link extended state - */ +/* Link extended state */ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_AUTONEG, ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE, @@ -595,10 +605,7 @@ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_OVERHEAT, }; -/** - * enum ethtool_link_ext_substate_autoneg - more information in addition to - * ETHTOOL_LINK_EXT_STATE_AUTONEG. - */ +/* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */ enum ethtool_link_ext_substate_autoneg { ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1, ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED, @@ -608,9 +615,7 @@ enum ethtool_link_ext_substate_autoneg { ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD, }; -/** - * enum ethtool_link_ext_substate_link_training - more information in addition to - * ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE. +/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE. */ enum ethtool_link_ext_substate_link_training { ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1, @@ -619,9 +624,7 @@ enum ethtool_link_ext_substate_link_training { ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT, }; -/** - * enum ethtool_link_ext_substate_logical_mismatch - more information in addition - * to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH. +/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH. */ enum ethtool_link_ext_substate_link_logical_mismatch { ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1, @@ -631,19 +634,14 @@ enum ethtool_link_ext_substate_link_logical_mismatch { ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED, }; -/** - * enum ethtool_link_ext_substate_bad_signal_integrity - more information in - * addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY. +/* More information in addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY. */ enum ethtool_link_ext_substate_bad_signal_integrity { ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1, ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE, }; -/** - * enum ethtool_link_ext_substate_cable_issue - more information in - * addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. - */ +/* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */ enum ethtool_link_ext_substate_cable_issue { ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1, ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE, @@ -661,6 +659,7 @@ enum ethtool_link_ext_substate_cable_issue { * now deprecated * @ETH_SS_FEATURES: Device feature names * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names + * @ETH_SS_TUNABLES: tunable names * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS * @ETH_SS_PHY_TUNABLES: PHY tunable names * @ETH_SS_LINK_MODES: link mode names @@ -670,6 +669,13 @@ enum ethtool_link_ext_substate_cable_issue { * @ETH_SS_TS_TX_TYPES: timestamping Tx types * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types + * @ETH_SS_STATS_STD: standardized stats + * @ETH_SS_STATS_ETH_PHY: names of IEEE 802.3 PHY statistics + * @ETH_SS_STATS_ETH_MAC: names of IEEE 802.3 MAC statistics + * @ETH_SS_STATS_ETH_CTRL: names of IEEE 802.3 MAC Control statistics + * @ETH_SS_STATS_RMON: names of RMON statistics + * + * @ETH_SS_COUNT: number of defined string sets */ enum ethtool_stringset { ETH_SS_TEST = 0, @@ -688,6 +694,11 @@ enum ethtool_stringset { ETH_SS_TS_TX_TYPES, ETH_SS_TS_RX_FILTERS, ETH_SS_UDP_TUNNEL_TYPES, + ETH_SS_STATS_STD, + ETH_SS_STATS_ETH_PHY, + ETH_SS_STATS_ETH_MAC, + ETH_SS_STATS_ETH_CTRL, + ETH_SS_STATS_RMON, /* add new constants above here */ ETH_SS_COUNT @@ -715,6 +726,7 @@ struct ethtool_gstrings { /** * struct ethtool_sset_info - string set information * @cmd: Command number = %ETHTOOL_GSSET_INFO + * @reserved: Reserved for future use; see the note on reserved space. * @sset_mask: On entry, a bitmask of string sets to query, with bits * numbered according to &enum ethtool_stringset. On return, a * bitmask of those string sets queried that are supported. @@ -759,6 +771,7 @@ enum ethtool_test_flags { * @flags: A bitmask of flags from &enum ethtool_test_flags. Some * flags may be set by the user on entry; others may be set by * the driver on return. + * @reserved: Reserved for future use; see the note on reserved space. * @len: On return, the number of test results * @data: Array of test results * @@ -959,6 +972,7 @@ union ethtool_flow_union { * @vlan_etype: VLAN EtherType * @vlan_tci: VLAN tag control information * @data: user defined data + * @padding: Reserved for future use; see the note on reserved space. * * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT * is set in &struct ethtool_rx_flow_spec @flow_type. @@ -1134,7 +1148,8 @@ struct ethtool_rxfh_indir { * hardware hash key. * @hfunc: Defines the current RSS hash function used by HW (or to be set to). * Valid values are one of the %ETH_RSS_HASH_*. - * @rsvd: Reserved for future extensions. + * @rsvd8: Reserved for future use; see the note on reserved space. + * @rsvd32: Reserved for future use; see the note on reserved space. * @rss_config: RX ring/queue index for each hash value i.e., indirection table * of @indir_size uint32_t elements, followed by hash key of @key_size * bytes. @@ -1302,7 +1317,9 @@ struct ethtool_sfeatures { * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags * @phc_index: device index of the associated PHC, or -1 if there is none * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values + * @tx_reserved: Reserved for future use; see the note on reserved space. * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values + * @rx_reserved: Reserved for future use; see the note on reserved space. * * The bits in the 'tx_types' and 'rx_filters' fields correspond to * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values, @@ -1376,15 +1393,33 @@ struct ethtool_per_queue_op { }; /** - * struct ethtool_fecparam - Ethernet forward error correction(fec) parameters + * struct ethtool_fecparam - Ethernet Forward Error Correction parameters * @cmd: Command number = %ETHTOOL_GFECPARAM or %ETHTOOL_SFECPARAM - * @active_fec: FEC mode which is active on porte - * @fec: Bitmask of supported/configured FEC modes - * @rsvd: Reserved for future extensions. i.e FEC bypass feature. + * @active_fec: FEC mode which is active on the port, single bit set, GET only. + * @fec: Bitmask of configured FEC modes. + * @reserved: Reserved for future extensions, ignore on GET, write 0 for SET. * - * Drivers should reject a non-zero setting of @autoneg when - * autoneogotiation is disabled (or not supported) for the link. + * Note that @reserved was never validated on input and ethtool user space + * left it uninitialized when calling SET. Hence going forward it can only be + * used to return a value to userspace with GET. * + * FEC modes supported by the device can be read via %ETHTOOL_GLINKSETTINGS. + * FEC settings are configured by link autonegotiation whenever it's enabled. + * With autoneg on %ETHTOOL_GFECPARAM can be used to read the current mode. + * + * When autoneg is disabled %ETHTOOL_SFECPARAM controls the FEC settings. + * It is recommended that drivers only accept a single bit set in @fec. + * When multiple bits are set in @fec drivers may pick mode in an implementation + * dependent way. Drivers should reject mixing %ETHTOOL_FEC_AUTO_BIT with other + * FEC modes, because it's unclear whether in this case other modes constrain + * AUTO or are independent choices. + * Drivers must reject SET requests if they support none of the requested modes. + * + * If device does not support FEC drivers may use %ETHTOOL_FEC_NONE instead + * of returning %EOPNOTSUPP from %ETHTOOL_GFECPARAM. + * + * See enum ethtool_fec_config_bits for definition of valid bits for both + * @fec and @active_fec. */ struct ethtool_fecparam { uint32_t cmd; @@ -1396,11 +1431,16 @@ struct ethtool_fecparam { /** * enum ethtool_fec_config_bits - flags definition of ethtool_fec_configuration - * @ETHTOOL_FEC_NONE: FEC mode configuration is not supported - * @ETHTOOL_FEC_AUTO: Default/Best FEC mode provided by driver - * @ETHTOOL_FEC_OFF: No FEC Mode - * @ETHTOOL_FEC_RS: Reed-Solomon Forward Error Detection mode - * @ETHTOOL_FEC_BASER: Base-R/Reed-Solomon Forward Error Detection mode + * @ETHTOOL_FEC_NONE_BIT: FEC mode configuration is not supported. Should not + * be used together with other bits. GET only. + * @ETHTOOL_FEC_AUTO_BIT: Select default/best FEC mode automatically, usually + * based link mode and SFP parameters read from module's + * EEPROM. This bit does _not_ mean autonegotiation. + * @ETHTOOL_FEC_OFF_BIT: No FEC Mode + * @ETHTOOL_FEC_RS_BIT: Reed-Solomon FEC Mode + * @ETHTOOL_FEC_BASER_BIT: Base-R/Reed-Solomon FEC Mode + * @ETHTOOL_FEC_LLRS_BIT: Low Latency Reed Solomon FEC Mode (25G/50G Ethernet + * Consortium) */ enum ethtool_fec_config_bits { ETHTOOL_FEC_NONE_BIT, @@ -1958,6 +1998,11 @@ enum ethtool_reset_flags { * autonegotiation; 0 if unknown or not applicable. Read-only. * @transceiver: Used to distinguish different possible PHY types, * reported consistently by PHYLIB. Read-only. + * @master_slave_cfg: Master/slave port mode. + * @master_slave_state: Master/slave port state. + * @reserved: Reserved for future use; see the note on reserved space. + * @reserved1: Reserved for future use; see the note on reserved space. + * @link_mode_masks: Variable length bitmaps. * * If autonegotiation is disabled, the speed and @duplex represent the * fixed link mode and are writable if the driver supports multiple diff --git a/include/standard-headers/linux/fuse.h b/include/standard-headers/linux/fuse.h index 950d7edb7e..cce105bfba 100644 --- a/include/standard-headers/linux/fuse.h +++ b/include/standard-headers/linux/fuse.h @@ -179,6 +179,8 @@ * 7.33 * - add FUSE_HANDLE_KILLPRIV_V2, FUSE_WRITE_KILL_SUIDGID, FATTR_KILL_SUIDGID * - add FUSE_OPEN_KILL_SUIDGID + * - extend fuse_setxattr_in, add FUSE_SETXATTR_EXT + * - add FUSE_SETXATTR_ACL_KILL_SGID */ #ifndef _LINUX_FUSE_H @@ -326,6 +328,7 @@ struct fuse_file_lock { * does not have CAP_FSETID. Additionally upon * write/truncate sgid is killed only if file has group * execute permission. (Same as Linux VFS behavior). + * FUSE_SETXATTR_EXT: Server supports extended struct fuse_setxattr_in */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -356,6 +359,7 @@ struct fuse_file_lock { #define FUSE_MAP_ALIGNMENT (1 << 26) #define FUSE_SUBMOUNTS (1 << 27) #define FUSE_HANDLE_KILLPRIV_V2 (1 << 28) +#define FUSE_SETXATTR_EXT (1 << 29) /** * CUSE INIT request/reply flags @@ -447,6 +451,12 @@ struct fuse_file_lock { */ #define FUSE_OPEN_KILL_SUIDGID (1 << 0) +/** + * setxattr flags + * FUSE_SETXATTR_ACL_KILL_SGID: Clear SGID when system.posix_acl_access is set + */ +#define FUSE_SETXATTR_ACL_KILL_SGID (1 << 0) + enum fuse_opcode { FUSE_LOOKUP = 1, FUSE_FORGET = 2, /* no reply */ @@ -677,9 +687,13 @@ struct fuse_fsync_in { uint32_t padding; }; +#define FUSE_COMPAT_SETXATTR_IN_SIZE 8 + struct fuse_setxattr_in { uint32_t size; uint32_t flags; + uint32_t setxattr_flags; + uint32_t padding; }; struct fuse_getxattr_in { @@ -899,7 +913,8 @@ struct fuse_notify_retrieve_in { }; /* Device ioctls: */ -#define FUSE_DEV_IOC_CLONE _IOR(229, 0, uint32_t) +#define FUSE_DEV_IOC_MAGIC 229 +#define FUSE_DEV_IOC_CLONE _IOR(FUSE_DEV_IOC_MAGIC, 0, uint32_t) struct fuse_lseek_in { uint64_t fh; diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h index c403b9cb0d..b5e86b40ab 100644 --- a/include/standard-headers/linux/input-event-codes.h +++ b/include/standard-headers/linux/input-event-codes.h @@ -611,6 +611,7 @@ #define KEY_VOICECOMMAND 0x246 /* Listening Voice Command */ #define KEY_ASSISTANT 0x247 /* AL Context-aware desktop assistant */ #define KEY_KBD_LAYOUT_NEXT 0x248 /* AC Next Keyboard Layout Select */ +#define KEY_EMOJI_PICKER 0x249 /* Show/hide emoji picker (HUTRR101) */ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h index f89c986190..7822c24178 100644 --- a/include/standard-headers/linux/input.h +++ b/include/standard-headers/linux/input.h @@ -81,7 +81,7 @@ struct input_id { * in units per radian. * When INPUT_PROP_ACCELEROMETER is set the resolution changes. * The main axes (ABS_X, ABS_Y, ABS_Z) are then reported in - * in units per g (units/g) and in units per degree per second + * units per g (units/g) and in units per degree per second * (units/deg/s) for rotational axes (ABS_RX, ABS_RY, ABS_RZ). */ struct input_absinfo { diff --git a/include/standard-headers/linux/udmabuf.h b/include/standard-headers/linux/udmabuf.h new file mode 100644 index 0000000000..e19eb5b5ce --- /dev/null +++ b/include/standard-headers/linux/udmabuf.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_UDMABUF_H +#define _LINUX_UDMABUF_H + +#include "standard-headers/linux/types.h" + +#define UDMABUF_FLAGS_CLOEXEC 0x01 + +struct udmabuf_create { + uint32_t memfd; + uint32_t flags; + uint64_t offset; + uint64_t size; +}; + +struct udmabuf_create_item { + uint32_t memfd; + uint32_t __pad; + uint64_t offset; + uint64_t size; +}; + +struct udmabuf_create_list { + uint32_t flags; + uint32_t count; + struct udmabuf_create_item list[]; +}; + +#define UDMABUF_CREATE _IOW('u', 0x42, struct udmabuf_create) +#define UDMABUF_CREATE_LIST _IOW('u', 0x43, struct udmabuf_create_list) + +#endif /* _LINUX_UDMABUF_H */ diff --git a/include/standard-headers/linux/virtio_bt.h b/include/standard-headers/linux/virtio_bt.h new file mode 100644 index 0000000000..245e1eff4b --- /dev/null +++ b/include/standard-headers/linux/virtio_bt.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ + +#ifndef _LINUX_VIRTIO_BT_H +#define _LINUX_VIRTIO_BT_H + +#include "standard-headers/linux/virtio_types.h" + +/* Feature bits */ +#define VIRTIO_BT_F_VND_HCI 0 /* Indicates vendor command support */ +#define VIRTIO_BT_F_MSFT_EXT 1 /* Indicates MSFT vendor support */ +#define VIRTIO_BT_F_AOSP_EXT 2 /* Indicates AOSP vendor support */ + +enum virtio_bt_config_type { + VIRTIO_BT_CONFIG_TYPE_PRIMARY = 0, + VIRTIO_BT_CONFIG_TYPE_AMP = 1, +}; + +enum virtio_bt_config_vendor { + VIRTIO_BT_CONFIG_VENDOR_NONE = 0, + VIRTIO_BT_CONFIG_VENDOR_ZEPHYR = 1, + VIRTIO_BT_CONFIG_VENDOR_INTEL = 2, + VIRTIO_BT_CONFIG_VENDOR_REALTEK = 3, +}; + +struct virtio_bt_config { + uint8_t type; + uint16_t vendor; + uint16_t msft_opcode; +} QEMU_PACKED; + +#endif /* _LINUX_VIRTIO_BT_H */ diff --git a/include/standard-headers/linux/virtio_ids.h b/include/standard-headers/linux/virtio_ids.h index bc1c0621f5..4fe842c3a3 100644 --- a/include/standard-headers/linux/virtio_ids.h +++ b/include/standard-headers/linux/virtio_ids.h @@ -51,8 +51,10 @@ #define VIRTIO_ID_PSTORE 22 /* virtio pstore device */ #define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */ #define VIRTIO_ID_MEM 24 /* virtio mem */ +#define VIRTIO_ID_SOUND 25 /* virtio sound */ #define VIRTIO_ID_FS 26 /* virtio filesystem */ #define VIRTIO_ID_PMEM 27 /* virtio pmem */ #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ +#define VIRTIO_ID_BT 40 /* virtio bluetooth */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/include/standard-headers/linux/virtio_snd.h b/include/standard-headers/linux/virtio_snd.h new file mode 100644 index 0000000000..1af96b9fc6 --- /dev/null +++ b/include/standard-headers/linux/virtio_snd.h @@ -0,0 +1,334 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* + * Copyright (C) 2021 OpenSynergy GmbH + */ +#ifndef VIRTIO_SND_IF_H +#define VIRTIO_SND_IF_H + +#include "standard-headers/linux/virtio_types.h" + +/******************************************************************************* + * CONFIGURATION SPACE + */ +struct virtio_snd_config { + /* # of available physical jacks */ + uint32_t jacks; + /* # of available PCM streams */ + uint32_t streams; + /* # of available channel maps */ + uint32_t chmaps; +}; + +enum { + /* device virtqueue indexes */ + VIRTIO_SND_VQ_CONTROL = 0, + VIRTIO_SND_VQ_EVENT, + VIRTIO_SND_VQ_TX, + VIRTIO_SND_VQ_RX, + /* # of device virtqueues */ + VIRTIO_SND_VQ_MAX +}; + +/******************************************************************************* + * COMMON DEFINITIONS + */ + +/* supported dataflow directions */ +enum { + VIRTIO_SND_D_OUTPUT = 0, + VIRTIO_SND_D_INPUT +}; + +enum { + /* jack control request types */ + VIRTIO_SND_R_JACK_INFO = 1, + VIRTIO_SND_R_JACK_REMAP, + + /* PCM control request types */ + VIRTIO_SND_R_PCM_INFO = 0x0100, + VIRTIO_SND_R_PCM_SET_PARAMS, + VIRTIO_SND_R_PCM_PREPARE, + VIRTIO_SND_R_PCM_RELEASE, + VIRTIO_SND_R_PCM_START, + VIRTIO_SND_R_PCM_STOP, + + /* channel map control request types */ + VIRTIO_SND_R_CHMAP_INFO = 0x0200, + + /* jack event types */ + VIRTIO_SND_EVT_JACK_CONNECTED = 0x1000, + VIRTIO_SND_EVT_JACK_DISCONNECTED, + + /* PCM event types */ + VIRTIO_SND_EVT_PCM_PERIOD_ELAPSED = 0x1100, + VIRTIO_SND_EVT_PCM_XRUN, + + /* common status codes */ + VIRTIO_SND_S_OK = 0x8000, + VIRTIO_SND_S_BAD_MSG, + VIRTIO_SND_S_NOT_SUPP, + VIRTIO_SND_S_IO_ERR +}; + +/* common header */ +struct virtio_snd_hdr { + uint32_t code; +}; + +/* event notification */ +struct virtio_snd_event { + /* VIRTIO_SND_EVT_XXX */ + struct virtio_snd_hdr hdr; + /* optional event data */ + uint32_t data; +}; + +/* common control request to query an item information */ +struct virtio_snd_query_info { + /* VIRTIO_SND_R_XXX_INFO */ + struct virtio_snd_hdr hdr; + /* item start identifier */ + uint32_t start_id; + /* item count to query */ + uint32_t count; + /* item information size in bytes */ + uint32_t size; +}; + +/* common item information header */ +struct virtio_snd_info { + /* function group node id (High Definition Audio Specification 7.1.2) */ + uint32_t hda_fn_nid; +}; + +/******************************************************************************* + * JACK CONTROL MESSAGES + */ +struct virtio_snd_jack_hdr { + /* VIRTIO_SND_R_JACK_XXX */ + struct virtio_snd_hdr hdr; + /* 0 ... virtio_snd_config::jacks - 1 */ + uint32_t jack_id; +}; + +/* supported jack features */ +enum { + VIRTIO_SND_JACK_F_REMAP = 0 +}; + +struct virtio_snd_jack_info { + /* common header */ + struct virtio_snd_info hdr; + /* supported feature bit map (1 << VIRTIO_SND_JACK_F_XXX) */ + uint32_t features; + /* pin configuration (High Definition Audio Specification 7.3.3.31) */ + uint32_t hda_reg_defconf; + /* pin capabilities (High Definition Audio Specification 7.3.4.9) */ + uint32_t hda_reg_caps; + /* current jack connection status (0: disconnected, 1: connected) */ + uint8_t connected; + + uint8_t padding[7]; +}; + +/* jack remapping control request */ +struct virtio_snd_jack_remap { + /* .code = VIRTIO_SND_R_JACK_REMAP */ + struct virtio_snd_jack_hdr hdr; + /* selected association number */ + uint32_t association; + /* selected sequence number */ + uint32_t sequence; +}; + +/******************************************************************************* + * PCM CONTROL MESSAGES + */ +struct virtio_snd_pcm_hdr { + /* VIRTIO_SND_R_PCM_XXX */ + struct virtio_snd_hdr hdr; + /* 0 ... virtio_snd_config::streams - 1 */ + uint32_t stream_id; +}; + +/* supported PCM stream features */ +enum { + VIRTIO_SND_PCM_F_SHMEM_HOST = 0, + VIRTIO_SND_PCM_F_SHMEM_GUEST, + VIRTIO_SND_PCM_F_MSG_POLLING, + VIRTIO_SND_PCM_F_EVT_SHMEM_PERIODS, + VIRTIO_SND_PCM_F_EVT_XRUNS +}; + +/* supported PCM sample formats */ +enum { + /* analog formats (width / physical width) */ + VIRTIO_SND_PCM_FMT_IMA_ADPCM = 0, /* 4 / 4 bits */ + VIRTIO_SND_PCM_FMT_MU_LAW, /* 8 / 8 bits */ + VIRTIO_SND_PCM_FMT_A_LAW, /* 8 / 8 bits */ + VIRTIO_SND_PCM_FMT_S8, /* 8 / 8 bits */ + VIRTIO_SND_PCM_FMT_U8, /* 8 / 8 bits */ + VIRTIO_SND_PCM_FMT_S16, /* 16 / 16 bits */ + VIRTIO_SND_PCM_FMT_U16, /* 16 / 16 bits */ + VIRTIO_SND_PCM_FMT_S18_3, /* 18 / 24 bits */ + VIRTIO_SND_PCM_FMT_U18_3, /* 18 / 24 bits */ + VIRTIO_SND_PCM_FMT_S20_3, /* 20 / 24 bits */ + VIRTIO_SND_PCM_FMT_U20_3, /* 20 / 24 bits */ + VIRTIO_SND_PCM_FMT_S24_3, /* 24 / 24 bits */ + VIRTIO_SND_PCM_FMT_U24_3, /* 24 / 24 bits */ + VIRTIO_SND_PCM_FMT_S20, /* 20 / 32 bits */ + VIRTIO_SND_PCM_FMT_U20, /* 20 / 32 bits */ + VIRTIO_SND_PCM_FMT_S24, /* 24 / 32 bits */ + VIRTIO_SND_PCM_FMT_U24, /* 24 / 32 bits */ + VIRTIO_SND_PCM_FMT_S32, /* 32 / 32 bits */ + VIRTIO_SND_PCM_FMT_U32, /* 32 / 32 bits */ + VIRTIO_SND_PCM_FMT_FLOAT, /* 32 / 32 bits */ + VIRTIO_SND_PCM_FMT_FLOAT64, /* 64 / 64 bits */ + /* digital formats (width / physical width) */ + VIRTIO_SND_PCM_FMT_DSD_U8, /* 8 / 8 bits */ + VIRTIO_SND_PCM_FMT_DSD_U16, /* 16 / 16 bits */ + VIRTIO_SND_PCM_FMT_DSD_U32, /* 32 / 32 bits */ + VIRTIO_SND_PCM_FMT_IEC958_SUBFRAME /* 32 / 32 bits */ +}; + +/* supported PCM frame rates */ +enum { + VIRTIO_SND_PCM_RATE_5512 = 0, + VIRTIO_SND_PCM_RATE_8000, + VIRTIO_SND_PCM_RATE_11025, + VIRTIO_SND_PCM_RATE_16000, + VIRTIO_SND_PCM_RATE_22050, + VIRTIO_SND_PCM_RATE_32000, + VIRTIO_SND_PCM_RATE_44100, + VIRTIO_SND_PCM_RATE_48000, + VIRTIO_SND_PCM_RATE_64000, + VIRTIO_SND_PCM_RATE_88200, + VIRTIO_SND_PCM_RATE_96000, + VIRTIO_SND_PCM_RATE_176400, + VIRTIO_SND_PCM_RATE_192000, + VIRTIO_SND_PCM_RATE_384000 +}; + +struct virtio_snd_pcm_info { + /* common header */ + struct virtio_snd_info hdr; + /* supported feature bit map (1 << VIRTIO_SND_PCM_F_XXX) */ + uint32_t features; + /* supported sample format bit map (1 << VIRTIO_SND_PCM_FMT_XXX) */ + uint64_t formats; + /* supported frame rate bit map (1 << VIRTIO_SND_PCM_RATE_XXX) */ + uint64_t rates; + /* dataflow direction (VIRTIO_SND_D_XXX) */ + uint8_t direction; + /* minimum # of supported channels */ + uint8_t channels_min; + /* maximum # of supported channels */ + uint8_t channels_max; + + uint8_t padding[5]; +}; + +/* set PCM stream format */ +struct virtio_snd_pcm_set_params { + /* .code = VIRTIO_SND_R_PCM_SET_PARAMS */ + struct virtio_snd_pcm_hdr hdr; + /* size of the hardware buffer */ + uint32_t buffer_bytes; + /* size of the hardware period */ + uint32_t period_bytes; + /* selected feature bit map (1 << VIRTIO_SND_PCM_F_XXX) */ + uint32_t features; + /* selected # of channels */ + uint8_t channels; + /* selected sample format (VIRTIO_SND_PCM_FMT_XXX) */ + uint8_t format; + /* selected frame rate (VIRTIO_SND_PCM_RATE_XXX) */ + uint8_t rate; + + uint8_t padding; +}; + +/******************************************************************************* + * PCM I/O MESSAGES + */ + +/* I/O request header */ +struct virtio_snd_pcm_xfer { + /* 0 ... virtio_snd_config::streams - 1 */ + uint32_t stream_id; +}; + +/* I/O request status */ +struct virtio_snd_pcm_status { + /* VIRTIO_SND_S_XXX */ + uint32_t status; + /* current device latency */ + uint32_t latency_bytes; +}; + +/******************************************************************************* + * CHANNEL MAP CONTROL MESSAGES + */ +struct virtio_snd_chmap_hdr { + /* VIRTIO_SND_R_CHMAP_XXX */ + struct virtio_snd_hdr hdr; + /* 0 ... virtio_snd_config::chmaps - 1 */ + uint32_t chmap_id; +}; + +/* standard channel position definition */ +enum { + VIRTIO_SND_CHMAP_NONE = 0, /* undefined */ + VIRTIO_SND_CHMAP_NA, /* silent */ + VIRTIO_SND_CHMAP_MONO, /* mono stream */ + VIRTIO_SND_CHMAP_FL, /* front left */ + VIRTIO_SND_CHMAP_FR, /* front right */ + VIRTIO_SND_CHMAP_RL, /* rear left */ + VIRTIO_SND_CHMAP_RR, /* rear right */ + VIRTIO_SND_CHMAP_FC, /* front center */ + VIRTIO_SND_CHMAP_LFE, /* low frequency (LFE) */ + VIRTIO_SND_CHMAP_SL, /* side left */ + VIRTIO_SND_CHMAP_SR, /* side right */ + VIRTIO_SND_CHMAP_RC, /* rear center */ + VIRTIO_SND_CHMAP_FLC, /* front left center */ + VIRTIO_SND_CHMAP_FRC, /* front right center */ + VIRTIO_SND_CHMAP_RLC, /* rear left center */ + VIRTIO_SND_CHMAP_RRC, /* rear right center */ + VIRTIO_SND_CHMAP_FLW, /* front left wide */ + VIRTIO_SND_CHMAP_FRW, /* front right wide */ + VIRTIO_SND_CHMAP_FLH, /* front left high */ + VIRTIO_SND_CHMAP_FCH, /* front center high */ + VIRTIO_SND_CHMAP_FRH, /* front right high */ + VIRTIO_SND_CHMAP_TC, /* top center */ + VIRTIO_SND_CHMAP_TFL, /* top front left */ + VIRTIO_SND_CHMAP_TFR, /* top front right */ + VIRTIO_SND_CHMAP_TFC, /* top front center */ + VIRTIO_SND_CHMAP_TRL, /* top rear left */ + VIRTIO_SND_CHMAP_TRR, /* top rear right */ + VIRTIO_SND_CHMAP_TRC, /* top rear center */ + VIRTIO_SND_CHMAP_TFLC, /* top front left center */ + VIRTIO_SND_CHMAP_TFRC, /* top front right center */ + VIRTIO_SND_CHMAP_TSL, /* top side left */ + VIRTIO_SND_CHMAP_TSR, /* top side right */ + VIRTIO_SND_CHMAP_LLFE, /* left LFE */ + VIRTIO_SND_CHMAP_RLFE, /* right LFE */ + VIRTIO_SND_CHMAP_BC, /* bottom center */ + VIRTIO_SND_CHMAP_BLC, /* bottom left center */ + VIRTIO_SND_CHMAP_BRC /* bottom right center */ +}; + +/* maximum possible number of channels */ +#define VIRTIO_SND_CHMAP_MAX_SIZE 18 + +struct virtio_snd_chmap_info { + /* common header */ + struct virtio_snd_info hdr; + /* dataflow direction (VIRTIO_SND_D_XXX) */ + uint8_t direction; + /* # of valid channel position values */ + uint8_t channels; + /* channel position values (VIRTIO_SND_CHMAP_XXX) */ + uint8_t positions[VIRTIO_SND_CHMAP_MAX_SIZE]; +}; + +#endif /* VIRTIO_SND_IF_H */ diff --git a/include/standard-headers/linux/virtio_vsock.h b/include/standard-headers/linux/virtio_vsock.h index be443211ce..3a23488e42 100644 --- a/include/standard-headers/linux/virtio_vsock.h +++ b/include/standard-headers/linux/virtio_vsock.h @@ -38,6 +38,9 @@ #include "standard-headers/linux/virtio_ids.h" #include "standard-headers/linux/virtio_config.h" +/* The feature bitmap for virtio vsock */ +#define VIRTIO_VSOCK_F_SEQPACKET 1 /* SOCK_SEQPACKET supported */ + struct virtio_vsock_config { uint64_t guest_cid; } QEMU_PACKED; @@ -65,6 +68,7 @@ struct virtio_vsock_hdr { enum virtio_vsock_type { VIRTIO_VSOCK_TYPE_STREAM = 1, + VIRTIO_VSOCK_TYPE_SEQPACKET = 2, }; enum virtio_vsock_op { @@ -91,4 +95,9 @@ enum virtio_vsock_shutdown { VIRTIO_VSOCK_SHUTDOWN_SEND = 2, }; +/* VIRTIO_VSOCK_OP_RW flags values */ +enum virtio_vsock_rw { + VIRTIO_VSOCK_SEQ_EOR = 1, +}; + #endif /* _LINUX_VIRTIO_VSOCK_H */ diff --git a/include/standard-headers/rdma/vmw_pvrdma-abi.h b/include/standard-headers/rdma/vmw_pvrdma-abi.h index 0989426a3f..c30182a7ae 100644 --- a/include/standard-headers/rdma/vmw_pvrdma-abi.h +++ b/include/standard-headers/rdma/vmw_pvrdma-abi.h @@ -133,6 +133,13 @@ enum pvrdma_wc_flags { PVRDMA_WC_FLAGS_MAX = PVRDMA_WC_WITH_NETWORK_HDR_TYPE, }; +enum pvrdma_network_type { + PVRDMA_NETWORK_IB, + PVRDMA_NETWORK_ROCE_V1 = PVRDMA_NETWORK_IB, + PVRDMA_NETWORK_IPV4, + PVRDMA_NETWORK_IPV6 +}; + struct pvrdma_alloc_ucontext_resp { uint32_t qp_tab_size; uint32_t reserved; diff --git a/include/sysemu/arch_init.h b/include/sysemu/arch_init.h index 16da279696..e723c467eb 100644 --- a/include/sysemu/arch_init.h +++ b/include/sysemu/arch_init.h @@ -9,7 +9,6 @@ enum { QEMU_ARCH_CRIS = (1 << 2), QEMU_ARCH_I386 = (1 << 3), QEMU_ARCH_M68K = (1 << 4), - QEMU_ARCH_LM32 = (1 << 5), QEMU_ARCH_MICROBLAZE = (1 << 6), QEMU_ARCH_MIPS = (1 << 7), QEMU_ARCH_PPC = (1 << 8), @@ -18,8 +17,6 @@ enum { QEMU_ARCH_SPARC = (1 << 11), QEMU_ARCH_XTENSA = (1 << 12), QEMU_ARCH_OPENRISC = (1 << 13), - QEMU_ARCH_UNICORE32 = (1 << 14), - QEMU_ARCH_MOXIE = (1 << 15), QEMU_ARCH_TRICORE = (1 << 16), QEMU_ARCH_NIOS2 = (1 << 17), QEMU_ARCH_HPPA = (1 << 18), diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index 880e903293..9ac5f7bbd3 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -66,6 +66,10 @@ typedef struct BlockDevOps { * Runs when the backend's last drain request ends. */ void (*drained_end)(void *opaque); + /* + * Is the device still busy? + */ + bool (*drained_poll)(void *opaque); } BlockDevOps; /* This struct is embedded in (the private) BlockBackend struct and contains @@ -204,6 +208,7 @@ void blk_eject(BlockBackend *blk, bool eject_flag); int blk_get_flags(BlockBackend *blk); uint32_t blk_get_request_alignment(BlockBackend *blk); uint32_t blk_get_max_transfer(BlockBackend *blk); +uint64_t blk_get_max_hw_transfer(BlockBackend *blk); int blk_get_max_iov(BlockBackend *blk); void blk_set_guest_block_size(BlockBackend *blk, int align); void *blk_try_blockalign(BlockBackend *blk, size_t size); diff --git a/include/sysemu/hax.h b/include/sysemu/hax.h index 12fb54f990..247f0661d1 100644 --- a/include/sysemu/hax.h +++ b/include/sysemu/hax.h @@ -24,6 +24,8 @@ int hax_sync_vcpus(void); +#ifdef NEED_CPU_H + #ifdef CONFIG_HAX int hax_enabled(void); @@ -34,4 +36,6 @@ int hax_enabled(void); #endif /* CONFIG_HAX */ +#endif /* NEED_CPU_H */ + #endif /* QEMU_HAX_H */ diff --git a/include/sysemu/hostmem.h b/include/sysemu/hostmem.h index df5644723a..9ff5c16963 100644 --- a/include/sysemu/hostmem.h +++ b/include/sysemu/hostmem.h @@ -64,7 +64,7 @@ struct HostMemoryBackend { /* protected */ uint64_t size; bool merge, dump, use_canonical_path; - bool prealloc, is_mapped, share; + bool prealloc, is_mapped, share, reserve; uint32_t prealloc_threads; DECLARE_BITMAP(host_nodes, MAX_NODES + 1); HostMemPolicy policy; diff --git a/include/sysemu/hvf.h b/include/sysemu/hvf.h index c98636bc81..bb70082e45 100644 --- a/include/sysemu/hvf.h +++ b/include/sysemu/hvf.h @@ -16,6 +16,8 @@ #include "qemu/accel.h" #include "qom/object.h" +#ifdef NEED_CPU_H + #ifdef CONFIG_HVF uint32_t hvf_get_supported_cpuid(uint32_t func, uint32_t idx, int reg); @@ -26,6 +28,8 @@ extern bool hvf_allowed; #define hvf_get_supported_cpuid(func, idx, reg) 0 #endif /* !CONFIG_HVF */ +#endif /* NEED_CPU_H */ + #define TYPE_HVF_ACCEL ACCEL_CLASS_NAME("hvf") typedef struct HVFState HVFState; diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h new file mode 100644 index 0000000000..8b66a4e7d0 --- /dev/null +++ b/include/sysemu/hvf_int.h @@ -0,0 +1,58 @@ +/* + * QEMU Hypervisor.framework (HVF) support + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +/* header to be included in HVF-specific code */ + +#ifndef HVF_INT_H +#define HVF_INT_H + +#include + +/* hvf_slot flags */ +#define HVF_SLOT_LOG (1 << 0) + +typedef struct hvf_slot { + uint64_t start; + uint64_t size; + uint8_t *mem; + int slot_id; + uint32_t flags; + MemoryRegion *region; +} hvf_slot; + +typedef struct hvf_vcpu_caps { + uint64_t vmx_cap_pinbased; + uint64_t vmx_cap_procbased; + uint64_t vmx_cap_procbased2; + uint64_t vmx_cap_entry; + uint64_t vmx_cap_exit; + uint64_t vmx_cap_preemption_timer; +} hvf_vcpu_caps; + +struct HVFState { + AccelState parent; + hvf_slot slots[32]; + int num_slots; + + hvf_vcpu_caps *hvf_caps; +}; +extern HVFState *hvf_state; + +struct hvf_vcpu_state { + int fd; +}; + +void assert_hvf_ok(hv_return_t ret); +int hvf_arch_init_vcpu(CPUState *cpu); +void hvf_arch_vcpu_destroy(CPUState *cpu); +int hvf_vcpu_exec(CPUState *); +hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t); +int hvf_put_registers(CPUState *); +int hvf_get_registers(CPUState *); + +#endif diff --git a/include/sysemu/hw_accel.h b/include/sysemu/hw_accel.h index 61672f9b32..01b5ebf442 100644 --- a/include/sysemu/hw_accel.h +++ b/include/sysemu/hw_accel.h @@ -16,6 +16,7 @@ #include "sysemu/kvm.h" #include "sysemu/hvf.h" #include "sysemu/whpx.h" +#include "sysemu/nvmm.h" void cpu_synchronize_state(CPUState *cpu); void cpu_synchronize_post_reset(CPUState *cpu); diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h index f177142f16..7f714bd136 100644 --- a/include/sysemu/iothread.h +++ b/include/sysemu/iothread.h @@ -37,6 +37,9 @@ struct IOThread { int64_t poll_max_ns; int64_t poll_grow; int64_t poll_shrink; + + /* AioContext AIO engine parameters */ + int64_t aio_max_batch; }; typedef struct IOThread IOThread; diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index ccb8869f01..c788452cd9 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -23,12 +23,15 @@ typedef struct KVMSlot int old_flags; /* Dirty bitmap cache for the slot */ unsigned long *dirty_bmap; + unsigned long dirty_bmap_size; + /* Cache of the address space ID */ + int as_id; + /* Cache of the offset in ram address space */ + ram_addr_t ram_start_offset; } KVMSlot; typedef struct KVMMemoryListener { MemoryListener listener; - /* Protects the slots and all inside them */ - QemuMutex slots_lock; KVMSlot *slots; int as_id; } KVMMemoryListener; diff --git a/include/sysemu/nvmm.h b/include/sysemu/nvmm.h new file mode 100644 index 0000000000..6d216599b0 --- /dev/null +++ b/include/sysemu/nvmm.h @@ -0,0 +1,26 @@ +/* + * Copyright (c) 2018-2019 Maxime Villard, All rights reserved. + * + * NetBSD Virtual Machine Monitor (NVMM) accelerator support. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef QEMU_NVMM_H +#define QEMU_NVMM_H + +#include "config-host.h" +#include "qemu-common.h" + +#ifdef CONFIG_NVMM + +int nvmm_enabled(void); + +#else /* CONFIG_NVMM */ + +#define nvmm_enabled() (0) + +#endif /* CONFIG_NVMM */ + +#endif /* CONFIG_NVMM */ diff --git a/include/sysemu/os-posix.h b/include/sysemu/os-posix.h index 629c8c648b..2edf33658a 100644 --- a/include/sysemu/os-posix.h +++ b/include/sysemu/os-posix.h @@ -38,6 +38,10 @@ #include #endif +#ifdef __cplusplus +extern "C" { +#endif + void os_set_line_buffering(void); void os_set_proc_name(const char *s); void os_setup_signal_handling(void); @@ -92,4 +96,8 @@ static inline void qemu_funlockfile(FILE *f) funlockfile(f); } +#ifdef __cplusplus +} +#endif + #endif diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h index 5346d51e89..43f569b5c2 100644 --- a/include/sysemu/os-win32.h +++ b/include/sysemu/os-win32.h @@ -30,6 +30,10 @@ #include #include +#ifdef __cplusplus +extern "C" { +#endif + #if defined(_WIN64) /* On w64, setjmp is implemented by _setjmp which needs a second parameter. * If this parameter is NULL, longjump does no stack unwinding. @@ -194,4 +198,8 @@ ssize_t qemu_recv_wrap(int sockfd, void *buf, size_t len, int flags); ssize_t qemu_recvfrom_wrap(int sockfd, void *buf, size_t len, int flags, struct sockaddr *addr, socklen_t *addrlen); +#ifdef __cplusplus +} +#endif + #endif diff --git a/include/sysemu/tcg.h b/include/sysemu/tcg.h index 00349fb18a..53352450ff 100644 --- a/include/sysemu/tcg.h +++ b/include/sysemu/tcg.h @@ -8,8 +8,6 @@ #ifndef SYSEMU_TCG_H #define SYSEMU_TCG_H -void tcg_exec_init(unsigned long tb_size, int splitwx); - #ifdef CONFIG_TCG extern bool tcg_allowed; #define tcg_enabled() (tcg_allowed) diff --git a/include/sysemu/tpm.h b/include/sysemu/tpm.h index 1a85564e47..68b2206463 100644 --- a/include/sysemu/tpm.h +++ b/include/sysemu/tpm.h @@ -15,6 +15,8 @@ #include "qapi/qapi-types-tpm.h" #include "qom/object.h" +#ifdef CONFIG_TPM + int tpm_config_parse(QemuOptsList *opts_list, const char *optarg); int tpm_init(void); void tpm_cleanup(void); @@ -73,4 +75,11 @@ static inline TPMVersion tpm_get_version(TPMIf *ti) return TPM_IF_GET_CLASS(ti)->get_version(ti); } +#else /* CONFIG_TPM */ + +#define tpm_init() (0) +#define tpm_cleanup() + +#endif /* CONFIG_TPM */ + #endif /* QEMU_TPM_H */ diff --git a/include/sysemu/tpm_backend.h b/include/sysemu/tpm_backend.h index 6f078f5f48..8fd3269c11 100644 --- a/include/sysemu/tpm_backend.h +++ b/include/sysemu/tpm_backend.h @@ -18,6 +18,8 @@ #include "sysemu/tpm.h" #include "qapi/error.h" +#ifdef CONFIG_TPM + #define TYPE_TPM_BACKEND "tpm-backend" OBJECT_DECLARE_TYPE(TPMBackend, TPMBackendClass, TPM_BACKEND) @@ -209,4 +211,6 @@ TPMInfo *tpm_backend_query_tpm(TPMBackend *s); TPMBackend *qemu_find_tpm_be(const char *id); -#endif +#endif /* CONFIG_TPM */ + +#endif /* TPM_BACKEND_H */ diff --git a/include/sysemu/whpx.h b/include/sysemu/whpx.h index 8ca1c1c4ac..2889fa2278 100644 --- a/include/sysemu/whpx.h +++ b/include/sysemu/whpx.h @@ -13,6 +13,8 @@ #ifndef QEMU_WHPX_H #define QEMU_WHPX_H +#ifdef NEED_CPU_H + #ifdef CONFIG_WHPX int whpx_enabled(void); @@ -25,4 +27,6 @@ bool whpx_apic_in_platform(void); #endif /* CONFIG_WHPX */ +#endif /* NEED_CPU_H */ + #endif /* QEMU_WHPX_H */ diff --git a/include/tcg/tcg-cond.h b/include/tcg/tcg-cond.h new file mode 100644 index 0000000000..2a38a386d4 --- /dev/null +++ b/include/tcg/tcg-cond.h @@ -0,0 +1,101 @@ +/* + * Tiny Code Generator for QEMU + * + * Copyright (c) 2008 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef TCG_COND_H +#define TCG_COND_H + +/* + * Conditions. Note that these are laid out for easy manipulation by + * the functions below: + * bit 0 is used for inverting; + * bit 1 is signed, + * bit 2 is unsigned, + * bit 3 is used with bit 0 for swapping signed/unsigned. + */ +typedef enum { + /* non-signed */ + TCG_COND_NEVER = 0 | 0 | 0 | 0, + TCG_COND_ALWAYS = 0 | 0 | 0 | 1, + TCG_COND_EQ = 8 | 0 | 0 | 0, + TCG_COND_NE = 8 | 0 | 0 | 1, + /* signed */ + TCG_COND_LT = 0 | 0 | 2 | 0, + TCG_COND_GE = 0 | 0 | 2 | 1, + TCG_COND_LE = 8 | 0 | 2 | 0, + TCG_COND_GT = 8 | 0 | 2 | 1, + /* unsigned */ + TCG_COND_LTU = 0 | 4 | 0 | 0, + TCG_COND_GEU = 0 | 4 | 0 | 1, + TCG_COND_LEU = 8 | 4 | 0 | 0, + TCG_COND_GTU = 8 | 4 | 0 | 1, +} TCGCond; + +/* Invert the sense of the comparison. */ +static inline TCGCond tcg_invert_cond(TCGCond c) +{ + return (TCGCond)(c ^ 1); +} + +/* Swap the operands in a comparison. */ +static inline TCGCond tcg_swap_cond(TCGCond c) +{ + return c & 6 ? (TCGCond)(c ^ 9) : c; +} + +/* Create an "unsigned" version of a "signed" comparison. */ +static inline TCGCond tcg_unsigned_cond(TCGCond c) +{ + return c & 2 ? (TCGCond)(c ^ 6) : c; +} + +/* Create a "signed" version of an "unsigned" comparison. */ +static inline TCGCond tcg_signed_cond(TCGCond c) +{ + return c & 4 ? (TCGCond)(c ^ 6) : c; +} + +/* Must a comparison be considered unsigned? */ +static inline bool is_unsigned_cond(TCGCond c) +{ + return (c & 4) != 0; +} + +/* + * Create a "high" version of a double-word comparison. + * This removes equality from a LTE or GTE comparison. + */ +static inline TCGCond tcg_high_cond(TCGCond c) +{ + switch (c) { + case TCG_COND_GE: + case TCG_COND_LE: + case TCG_COND_GEU: + case TCG_COND_LEU: + return (TCGCond)(c ^ 8); + default: + return c; + } +} + +#endif /* TCG_COND_H */ diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h index c69a7de984..da55fed870 100644 --- a/include/tcg/tcg-op-gvec.h +++ b/include/tcg/tcg-op-gvec.h @@ -401,4 +401,47 @@ void tcg_gen_vec_sar16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t); void tcg_gen_vec_rotl8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c); void tcg_gen_vec_rotl16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c); +/* 32-bit vector operations. */ +void tcg_gen_vec_add8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); +void tcg_gen_vec_add16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); + +void tcg_gen_vec_sub8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); +void tcg_gen_vec_sub16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); + +void tcg_gen_vec_shl8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); +void tcg_gen_vec_shl16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); +void tcg_gen_vec_shr8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); +void tcg_gen_vec_shr16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); +void tcg_gen_vec_sar8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); +void tcg_gen_vec_sar16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t); + +#if TARGET_LONG_BITS == 64 +#define tcg_gen_vec_add8_tl tcg_gen_vec_add8_i64 +#define tcg_gen_vec_sub8_tl tcg_gen_vec_sub8_i64 +#define tcg_gen_vec_add16_tl tcg_gen_vec_add16_i64 +#define tcg_gen_vec_sub16_tl tcg_gen_vec_sub16_i64 +#define tcg_gen_vec_add32_tl tcg_gen_vec_add32_i64 +#define tcg_gen_vec_sub32_tl tcg_gen_vec_sub32_i64 +#define tcg_gen_vec_shl8i_tl tcg_gen_vec_shl8i_i64 +#define tcg_gen_vec_shr8i_tl tcg_gen_vec_shr8i_i64 +#define tcg_gen_vec_sar8i_tl tcg_gen_vec_sar8i_i64 +#define tcg_gen_vec_shl16i_tl tcg_gen_vec_shl16i_i64 +#define tcg_gen_vec_shr16i_tl tcg_gen_vec_shr16i_i64 +#define tcg_gen_vec_sar16i_tl tcg_gen_vec_sar16i_i64 + +#else +#define tcg_gen_vec_add8_tl tcg_gen_vec_add8_i32 +#define tcg_gen_vec_sub8_tl tcg_gen_vec_sub8_i32 +#define tcg_gen_vec_add16_tl tcg_gen_vec_add16_i32 +#define tcg_gen_vec_sub16_tl tcg_gen_vec_sub16_i32 +#define tcg_gen_vec_add32_tl tcg_gen_add_i32 +#define tcg_gen_vec_sub32_tl tcg_gen_sub_i32 +#define tcg_gen_vec_shl8i_tl tcg_gen_vec_shl8i_i32 +#define tcg_gen_vec_shr8i_tl tcg_gen_vec_shr8i_i32 +#define tcg_gen_vec_sar8i_tl tcg_gen_vec_sar8i_i32 +#define tcg_gen_vec_shl16i_tl tcg_gen_vec_shl16i_i32 +#define tcg_gen_vec_shr16i_tl tcg_gen_vec_shr16i_i32 +#define tcg_gen_vec_sar16i_tl tcg_gen_vec_sar16i_i32 +#endif + #endif diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h index 2cd1faf9c4..2a654f350c 100644 --- a/include/tcg/tcg-op.h +++ b/include/tcg/tcg-op.h @@ -330,7 +330,7 @@ void tcg_gen_ext8s_i32(TCGv_i32 ret, TCGv_i32 arg); void tcg_gen_ext16s_i32(TCGv_i32 ret, TCGv_i32 arg); void tcg_gen_ext8u_i32(TCGv_i32 ret, TCGv_i32 arg); void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg); -void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg); +void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg, int flags); void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg); void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); @@ -338,6 +338,9 @@ void tcg_gen_umin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_umax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_abs_i32(TCGv_i32, TCGv_i32); +/* Replicate a value of size @vece from @in to all the lanes in @out */ +void tcg_gen_dup_i32(unsigned vece, TCGv_i32 out, TCGv_i32 in); + static inline void tcg_gen_discard_i32(TCGv_i32 arg) { tcg_gen_op1_i32(INDEX_op_discard, arg); @@ -525,8 +528,8 @@ void tcg_gen_ext32s_i64(TCGv_i64 ret, TCGv_i64 arg); void tcg_gen_ext8u_i64(TCGv_i64 ret, TCGv_i64 arg); void tcg_gen_ext16u_i64(TCGv_i64 ret, TCGv_i64 arg); void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg); -void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg); +void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg, int flags); +void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags); void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg); void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); @@ -534,6 +537,9 @@ void tcg_gen_umin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_umax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_abs_i64(TCGv_i64, TCGv_i64); +/* Replicate a value of size @vece from @in to all the lanes in @out */ +void tcg_gen_dup_i64(unsigned vece, TCGv_i64 out, TCGv_i64 in); + #if TCG_TARGET_REG_BITS == 64 static inline void tcg_gen_discard_i64(TCGv_i64 arg) { @@ -1096,6 +1102,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_sextract_tl tcg_gen_sextract_i64 #define tcg_gen_extract2_tl tcg_gen_extract2_i64 #define tcg_const_tl tcg_const_i64 +#define tcg_constant_tl tcg_constant_i64 #define tcg_const_local_tl tcg_const_local_i64 #define tcg_gen_movcond_tl tcg_gen_movcond_i64 #define tcg_gen_add2_tl tcg_gen_add2_i64 @@ -1126,6 +1133,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_atomic_smax_fetch_tl tcg_gen_atomic_smax_fetch_i64 #define tcg_gen_atomic_umax_fetch_tl tcg_gen_atomic_umax_fetch_i64 #define tcg_gen_dup_tl_vec tcg_gen_dup_i64_vec +#define tcg_gen_dup_tl tcg_gen_dup_i64 #else #define tcg_gen_movi_tl tcg_gen_movi_i32 #define tcg_gen_mov_tl tcg_gen_mov_i32 @@ -1184,7 +1192,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_ext32u_tl tcg_gen_mov_i32 #define tcg_gen_ext32s_tl tcg_gen_mov_i32 #define tcg_gen_bswap16_tl tcg_gen_bswap16_i32 -#define tcg_gen_bswap32_tl tcg_gen_bswap32_i32 +#define tcg_gen_bswap32_tl(D, S, F) tcg_gen_bswap32_i32(D, S) #define tcg_gen_bswap_tl tcg_gen_bswap32_i32 #define tcg_gen_concat_tl_i64 tcg_gen_concat_i32_i64 #define tcg_gen_extr_i64_tl tcg_gen_extr_i64_i32 @@ -1209,6 +1217,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_sextract_tl tcg_gen_sextract_i32 #define tcg_gen_extract2_tl tcg_gen_extract2_i32 #define tcg_const_tl tcg_const_i32 +#define tcg_constant_tl tcg_constant_i32 #define tcg_const_local_tl tcg_const_local_i32 #define tcg_gen_movcond_tl tcg_gen_movcond_i32 #define tcg_gen_add2_tl tcg_gen_add2_i32 @@ -1239,6 +1248,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_atomic_smax_fetch_tl tcg_gen_atomic_smax_fetch_i32 #define tcg_gen_atomic_umax_fetch_tl tcg_gen_atomic_umax_fetch_i32 #define tcg_gen_dup_tl_vec tcg_gen_dup_i32_vec +#define tcg_gen_dup_tl tcg_gen_dup_i32 #endif #if UINTPTR_MAX == UINT32_MAX diff --git a/include/tcg/tcg-opc.h b/include/tcg/tcg-opc.h index bbb0884af8..675873e200 100644 --- a/include/tcg/tcg-opc.h +++ b/include/tcg/tcg-opc.h @@ -96,8 +96,8 @@ DEF(ext8s_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext8s_i32)) DEF(ext16s_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext16s_i32)) DEF(ext8u_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext8u_i32)) DEF(ext16u_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext16u_i32)) -DEF(bswap16_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_bswap16_i32)) -DEF(bswap32_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_bswap32_i32)) +DEF(bswap16_i32, 1, 1, 1, IMPL(TCG_TARGET_HAS_bswap16_i32)) +DEF(bswap32_i32, 1, 1, 1, IMPL(TCG_TARGET_HAS_bswap32_i32)) DEF(not_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_not_i32)) DEF(neg_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_neg_i32)) DEF(andc_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_andc_i32)) @@ -165,9 +165,9 @@ DEF(ext32s_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext32s_i64)) DEF(ext8u_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext8u_i64)) DEF(ext16u_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext16u_i64)) DEF(ext32u_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext32u_i64)) -DEF(bswap16_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_bswap16_i64)) -DEF(bswap32_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_bswap32_i64)) -DEF(bswap64_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_bswap64_i64)) +DEF(bswap16_i64, 1, 1, 1, IMPL64 | IMPL(TCG_TARGET_HAS_bswap16_i64)) +DEF(bswap32_i64, 1, 1, 1, IMPL64 | IMPL(TCG_TARGET_HAS_bswap32_i64)) +DEF(bswap64_i64, 1, 1, 1, IMPL64 | IMPL(TCG_TARGET_HAS_bswap64_i64)) DEF(not_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_not_i64)) DEF(neg_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_neg_i64)) DEF(andc_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_andc_i64)) @@ -194,8 +194,7 @@ DEF(insn_start, 0, 0, TLADDR_ARGS * TARGET_INSN_START_WORDS, TCG_OPF_NOT_PRESENT) DEF(exit_tb, 0, 0, 1, TCG_OPF_BB_EXIT | TCG_OPF_BB_END) DEF(goto_tb, 0, 0, 1, TCG_OPF_BB_EXIT | TCG_OPF_BB_END) -DEF(goto_ptr, 0, 1, 0, - TCG_OPF_BB_EXIT | TCG_OPF_BB_END | IMPL(TCG_TARGET_HAS_goto_ptr)) +DEF(goto_ptr, 0, 1, 0, TCG_OPF_BB_EXIT | TCG_OPF_BB_END) DEF(plugin_cb_start, 0, 0, 3, TCG_OPF_NOT_PRESENT) DEF(plugin_cb_end, 0, 0, 0, TCG_OPF_NOT_PRESENT) @@ -277,8 +276,8 @@ DEF(last_generic, 0, 0, 0, TCG_OPF_NOT_PRESENT) #ifdef TCG_TARGET_INTERPRETER /* These opcodes are only for use between the tci generator and interpreter. */ -DEF(tci_movi_i32, 1, 0, 1, TCG_OPF_NOT_PRESENT) -DEF(tci_movi_i64, 1, 0, 1, TCG_OPF_64BIT | TCG_OPF_NOT_PRESENT) +DEF(tci_movi, 1, 0, 1, TCG_OPF_NOT_PRESENT) +DEF(tci_movl, 1, 0, 1, TCG_OPF_NOT_PRESENT) #endif #undef TLADDR_ARGS diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index 577d452dbe..255ec1446f 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -27,13 +27,13 @@ #include "cpu.h" #include "exec/memop.h" -#include "exec/tb-context.h" #include "qemu/bitops.h" #include "qemu/plugin.h" #include "qemu/queue.h" #include "tcg/tcg-mo.h" #include "tcg-target.h" #include "qemu/int128.h" +#include "tcg/tcg-cond.h" /* XXX: make safe guess about sizes */ #define MAX_OP_PER_INSTR 266 @@ -53,6 +53,7 @@ #define MAX_OPC_PARAM (4 + (MAX_OPC_PARAM_PER_ARG * MAX_OPC_PARAM_ARGS)) #define CPU_TEMP_BUF_NLONGS 128 +#define TCG_STATIC_FRAME_SIZE (CPU_TEMP_BUF_NLONGS * sizeof(long)) /* Default target word size to pointer size. */ #ifndef TCG_TARGET_REG_BITS @@ -407,74 +408,17 @@ typedef TCGv_ptr TCGv_env; /* Used to align parameters. See the comment before tcgv_i32_temp. */ #define TCG_CALL_DUMMY_ARG ((TCGArg)0) -/* Conditions. Note that these are laid out for easy manipulation by - the functions below: - bit 0 is used for inverting; - bit 1 is signed, - bit 2 is unsigned, - bit 3 is used with bit 0 for swapping signed/unsigned. */ -typedef enum { - /* non-signed */ - TCG_COND_NEVER = 0 | 0 | 0 | 0, - TCG_COND_ALWAYS = 0 | 0 | 0 | 1, - TCG_COND_EQ = 8 | 0 | 0 | 0, - TCG_COND_NE = 8 | 0 | 0 | 1, - /* signed */ - TCG_COND_LT = 0 | 0 | 2 | 0, - TCG_COND_GE = 0 | 0 | 2 | 1, - TCG_COND_LE = 8 | 0 | 2 | 0, - TCG_COND_GT = 8 | 0 | 2 | 1, - /* unsigned */ - TCG_COND_LTU = 0 | 4 | 0 | 0, - TCG_COND_GEU = 0 | 4 | 0 | 1, - TCG_COND_LEU = 8 | 4 | 0 | 0, - TCG_COND_GTU = 8 | 4 | 0 | 1, -} TCGCond; - -/* Invert the sense of the comparison. */ -static inline TCGCond tcg_invert_cond(TCGCond c) -{ - return (TCGCond)(c ^ 1); -} - -/* Swap the operands in a comparison. */ -static inline TCGCond tcg_swap_cond(TCGCond c) -{ - return c & 6 ? (TCGCond)(c ^ 9) : c; -} - -/* Create an "unsigned" version of a "signed" comparison. */ -static inline TCGCond tcg_unsigned_cond(TCGCond c) -{ - return c & 2 ? (TCGCond)(c ^ 6) : c; -} - -/* Create a "signed" version of an "unsigned" comparison. */ -static inline TCGCond tcg_signed_cond(TCGCond c) -{ - return c & 4 ? (TCGCond)(c ^ 6) : c; -} - -/* Must a comparison be considered unsigned? */ -static inline bool is_unsigned_cond(TCGCond c) -{ - return (c & 4) != 0; -} - -/* Create a "high" version of a double-word comparison. - This removes equality from a LTE or GTE comparison. */ -static inline TCGCond tcg_high_cond(TCGCond c) -{ - switch (c) { - case TCG_COND_GE: - case TCG_COND_LE: - case TCG_COND_GEU: - case TCG_COND_LEU: - return (TCGCond)(c ^ 8); - default: - return c; - } -} +/* + * Flags for the bswap opcodes. + * If IZ, the input is zero-extended, otherwise unknown. + * If OZ or OS, the output is zero- or sign-extended respectively, + * otherwise the high bits are undefined. + */ +enum { + TCG_BSWAP_IZ = 1, + TCG_BSWAP_OZ = 2, + TCG_BSWAP_OS = 4, +}; typedef enum TCGTempVal { TEMP_VAL_DEAD, @@ -635,8 +579,6 @@ struct TCGContext { /* Threshold to flush the translated code buffer. */ void *code_gen_highwater; - size_t tb_phys_invalidate_count; - /* Track which vCPU triggers events */ CPUState *cpu; /* *_trans */ @@ -690,22 +632,12 @@ static inline bool temp_readonly(TCGTemp *ts) return ts->kind >= TEMP_FIXED; } -extern TCGContext tcg_init_ctx; extern __thread TCGContext *tcg_ctx; extern const void *tcg_code_gen_epilogue; extern uintptr_t tcg_splitwx_diff; extern TCGv_env cpu_env; -static inline bool in_code_gen_buffer(const void *p) -{ - const TCGContext *s = &tcg_init_ctx; - /* - * Much like it is valid to have a pointer to the byte past the - * end of an array (so long as you don't dereference it), allow - * a pointer to the byte past the end of the code gen buffer. - */ - return (size_t)(p - s->code_gen_buffer) <= s->code_gen_buffer_size; -} +bool in_code_gen_buffer(const void *p); #ifdef CONFIG_DEBUG_TCG const void *tcg_splitwx_to_rx(void *rw); @@ -874,8 +806,6 @@ void *tcg_malloc_internal(TCGContext *s, int size); void tcg_pool_reset(TCGContext *s); TranslationBlock *tcg_tb_alloc(TCGContext *s); -void tcg_region_init(void); -void tb_destroy(TranslationBlock *tb); void tcg_region_reset_all(void); size_t tcg_code_size(void); @@ -883,7 +813,6 @@ size_t tcg_code_capacity(void); void tcg_tb_insert(TranslationBlock *tb); void tcg_tb_remove(TranslationBlock *tb); -size_t tcg_tb_phys_invalidate_count(void); TranslationBlock *tcg_tb_lookup(uintptr_t tc_ptr); void tcg_tb_foreach(GTraverseFunc func, gpointer user_data); size_t tcg_nb_tbs(void); @@ -911,7 +840,7 @@ static inline void *tcg_malloc(int size) void tcg_register_init_ctx(void); #endif -void tcg_context_init(TCGContext *s); +void tcg_init(size_t tb_size, int splitwx, unsigned max_cpus); void tcg_register_thread(void); void tcg_prologue_init(TCGContext *s); void tcg_func_start(TCGContext *s); @@ -1087,6 +1016,16 @@ void tcg_op_remove(TCGContext *s, TCGOp *op); TCGOp *tcg_op_insert_before(TCGContext *s, TCGOp *op, TCGOpcode opc); TCGOp *tcg_op_insert_after(TCGContext *s, TCGOp *op, TCGOpcode opc); +/** + * tcg_remove_ops_after: + * @op: target operation + * + * Discard any opcodes emitted since @op. Expected usage is to save + * a starting point with tcg_last_op(), speculatively emit opcodes, + * then decide whether or not to keep those opcodes after the fact. + */ +void tcg_remove_ops_after(TCGOp *op); + void tcg_optimize(TCGContext *s); /* Allocate a new temporary and initialize it with a constant. */ @@ -1101,7 +1040,8 @@ TCGv_vec tcg_const_ones_vec_matching(TCGv_vec); /* * Locate or create a read-only temporary that is a constant. - * This kind of temporary need not and should not be freed. + * This kind of temporary need not be freed, but for convenience + * will be silently ignored by tcg_temp_free_*. */ TCGTemp *tcg_constant_internal(TCGType type, int64_t val); @@ -1336,7 +1276,6 @@ uint64_t dup_const(unsigned vece, uint64_t c); : (qemu_build_not_reached_always(), 0)) \ : dup_const(VECE, C)) - /* * Memory helpers that will be used by TCG generated code. */ @@ -1406,31 +1345,32 @@ void helper_be_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val, # define helper_ret_stl_mmu helper_le_stl_mmu # define helper_ret_stq_mmu helper_le_stq_mmu #endif +#endif /* CONFIG_SOFTMMU */ -uint32_t helper_atomic_cmpxchgb_mmu(CPUArchState *env, target_ulong addr, +uint32_t cpu_atomic_cmpxchgb_mmu(CPUArchState *env, target_ulong addr, + uint32_t cmpv, uint32_t newv, + TCGMemOpIdx oi, uintptr_t retaddr); +uint32_t cpu_atomic_cmpxchgw_le_mmu(CPUArchState *env, target_ulong addr, uint32_t cmpv, uint32_t newv, TCGMemOpIdx oi, uintptr_t retaddr); -uint32_t helper_atomic_cmpxchgw_le_mmu(CPUArchState *env, target_ulong addr, - uint32_t cmpv, uint32_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); -uint32_t helper_atomic_cmpxchgl_le_mmu(CPUArchState *env, target_ulong addr, - uint32_t cmpv, uint32_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); -uint64_t helper_atomic_cmpxchgq_le_mmu(CPUArchState *env, target_ulong addr, - uint64_t cmpv, uint64_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); -uint32_t helper_atomic_cmpxchgw_be_mmu(CPUArchState *env, target_ulong addr, - uint32_t cmpv, uint32_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); -uint32_t helper_atomic_cmpxchgl_be_mmu(CPUArchState *env, target_ulong addr, - uint32_t cmpv, uint32_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); -uint64_t helper_atomic_cmpxchgq_be_mmu(CPUArchState *env, target_ulong addr, - uint64_t cmpv, uint64_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); +uint32_t cpu_atomic_cmpxchgl_le_mmu(CPUArchState *env, target_ulong addr, + uint32_t cmpv, uint32_t newv, + TCGMemOpIdx oi, uintptr_t retaddr); +uint64_t cpu_atomic_cmpxchgq_le_mmu(CPUArchState *env, target_ulong addr, + uint64_t cmpv, uint64_t newv, + TCGMemOpIdx oi, uintptr_t retaddr); +uint32_t cpu_atomic_cmpxchgw_be_mmu(CPUArchState *env, target_ulong addr, + uint32_t cmpv, uint32_t newv, + TCGMemOpIdx oi, uintptr_t retaddr); +uint32_t cpu_atomic_cmpxchgl_be_mmu(CPUArchState *env, target_ulong addr, + uint32_t cmpv, uint32_t newv, + TCGMemOpIdx oi, uintptr_t retaddr); +uint64_t cpu_atomic_cmpxchgq_be_mmu(CPUArchState *env, target_ulong addr, + uint64_t cmpv, uint64_t newv, + TCGMemOpIdx oi, uintptr_t retaddr); #define GEN_ATOMIC_HELPER(NAME, TYPE, SUFFIX) \ -TYPE helper_atomic_ ## NAME ## SUFFIX ## _mmu \ +TYPE cpu_atomic_ ## NAME ## SUFFIX ## _mmu \ (CPUArchState *env, target_ulong addr, TYPE val, \ TCGMemOpIdx oi, uintptr_t retaddr); @@ -1476,31 +1416,22 @@ GEN_ATOMIC_HELPER_ALL(xchg) #undef GEN_ATOMIC_HELPER_ALL #undef GEN_ATOMIC_HELPER -#endif /* CONFIG_SOFTMMU */ -/* - * These aren't really a "proper" helpers because TCG cannot manage Int128. - * However, use the same format as the others, for use by the backends. - * - * The cmpxchg functions are only defined if HAVE_CMPXCHG128; - * the ld/st functions are only defined if HAVE_ATOMIC128, - * as defined by . - */ -Int128 helper_atomic_cmpxchgo_le_mmu(CPUArchState *env, target_ulong addr, - Int128 cmpv, Int128 newv, - TCGMemOpIdx oi, uintptr_t retaddr); -Int128 helper_atomic_cmpxchgo_be_mmu(CPUArchState *env, target_ulong addr, - Int128 cmpv, Int128 newv, - TCGMemOpIdx oi, uintptr_t retaddr); +Int128 cpu_atomic_cmpxchgo_le_mmu(CPUArchState *env, target_ulong addr, + Int128 cmpv, Int128 newv, + TCGMemOpIdx oi, uintptr_t retaddr); +Int128 cpu_atomic_cmpxchgo_be_mmu(CPUArchState *env, target_ulong addr, + Int128 cmpv, Int128 newv, + TCGMemOpIdx oi, uintptr_t retaddr); -Int128 helper_atomic_ldo_le_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -Int128 helper_atomic_ldo_be_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); -void helper_atomic_sto_le_mmu(CPUArchState *env, target_ulong addr, Int128 val, - TCGMemOpIdx oi, uintptr_t retaddr); -void helper_atomic_sto_be_mmu(CPUArchState *env, target_ulong addr, Int128 val, - TCGMemOpIdx oi, uintptr_t retaddr); +Int128 cpu_atomic_ldo_le_mmu(CPUArchState *env, target_ulong addr, + TCGMemOpIdx oi, uintptr_t retaddr); +Int128 cpu_atomic_ldo_be_mmu(CPUArchState *env, target_ulong addr, + TCGMemOpIdx oi, uintptr_t retaddr); +void cpu_atomic_sto_le_mmu(CPUArchState *env, target_ulong addr, Int128 val, + TCGMemOpIdx oi, uintptr_t retaddr); +void cpu_atomic_sto_be_mmu(CPUArchState *env, target_ulong addr, Int128 val, + TCGMemOpIdx oi, uintptr_t retaddr); #ifdef CONFIG_DEBUG_TCG void tcg_assert_listed_vecop(TCGOpcode); diff --git a/include/ui/clipboard.h b/include/ui/clipboard.h new file mode 100644 index 0000000000..b45b984c9f --- /dev/null +++ b/include/ui/clipboard.h @@ -0,0 +1,193 @@ +#ifndef QEMU_CLIPBOARD_H +#define QEMU_CLIPBOARD_H + +#include "qemu/notify.h" + +/** + * DOC: Introduction + * + * The header ``ui/clipboard.h`` declares the qemu clipboard interface. + * + * All qemu elements which want use the clipboard can register as + * clipboard peer. Subsequently they can set the clipboard content + * and get notifications for clipboard updates. + * + * Typical users are user interfaces (gtk), remote access protocols + * (vnc) and devices talking to the guest (vdagent). + * + * Even though the design allows different data types only plain text + * is supported for now. + */ + +typedef enum QemuClipboardType QemuClipboardType; +typedef enum QemuClipboardSelection QemuClipboardSelection; +typedef struct QemuClipboardPeer QemuClipboardPeer; +typedef struct QemuClipboardInfo QemuClipboardInfo; + +/** + * enum QemuClipboardType + * + * @QEMU_CLIPBOARD_TYPE_TEXT: text/plain; charset=utf-8 + * @QEMU_CLIPBOARD_TYPE__COUNT: type count. + */ +enum QemuClipboardType { + QEMU_CLIPBOARD_TYPE_TEXT, + QEMU_CLIPBOARD_TYPE__COUNT, +}; + +/* same as VD_AGENT_CLIPBOARD_SELECTION_* */ +/** + * enum QemuClipboardSelection + * + * @QEMU_CLIPBOARD_SELECTION_CLIPBOARD: clipboard (explitcit cut+paste). + * @QEMU_CLIPBOARD_SELECTION_PRIMARY: primary selection (select + middle mouse button). + * @QEMU_CLIPBOARD_SELECTION_SECONDARY: secondary selection (dunno). + * @QEMU_CLIPBOARD_SELECTION__COUNT: selection count. + */ +enum QemuClipboardSelection { + QEMU_CLIPBOARD_SELECTION_CLIPBOARD, + QEMU_CLIPBOARD_SELECTION_PRIMARY, + QEMU_CLIPBOARD_SELECTION_SECONDARY, + QEMU_CLIPBOARD_SELECTION__COUNT, +}; + +/** + * struct QemuClipboardPeer + * + * @name: peer name. + * @update: notifier for clipboard updates. + * @request: callback for clipboard data requests. + * + * Clipboard peer description. + */ +struct QemuClipboardPeer { + const char *name; + Notifier update; + void (*request)(QemuClipboardInfo *info, + QemuClipboardType type); +}; + +/** + * struct QemuClipboardInfo + * + * @refcount: reference counter. + * @owner: clipboard owner. + * @selection: clipboard selection. + * @types: clipboard data array (one entry per type). + * + * Clipboard content data and metadata. + */ +struct QemuClipboardInfo { + uint32_t refcount; + QemuClipboardPeer *owner; + QemuClipboardSelection selection; + struct { + bool available; + bool requested; + size_t size; + void *data; + } types[QEMU_CLIPBOARD_TYPE__COUNT]; +}; + +/** + * qemu_clipboard_peer_register + * + * @peer: peer information. + * + * Register clipboard peer. Registering is needed for both active + * (set+grab clipboard) and passive (watch clipboard for updates) + * interaction with the qemu clipboard. + */ +void qemu_clipboard_peer_register(QemuClipboardPeer *peer); + +/** + * qemu_clipboard_peer_unregister + * + * @peer: peer information. + * + * Unregister clipboard peer. + */ +void qemu_clipboard_peer_unregister(QemuClipboardPeer *peer); + +/** + * qemu_clipboard_info_new + * + * @owner: clipboard owner. + * @selection: clipboard selection. + * + * Allocate a new QemuClipboardInfo and initialize it with the given + * @owner and @selection. + * + * QemuClipboardInfo is a reference-counted struct. The new struct is + * returned with a reference already taken (i.e. reference count is + * one). + */ +QemuClipboardInfo *qemu_clipboard_info_new(QemuClipboardPeer *owner, + QemuClipboardSelection selection); +/** + * qemu_clipboard_info_ref + * + * @info: clipboard info. + * + * Increase @info reference count. + */ +QemuClipboardInfo *qemu_clipboard_info_ref(QemuClipboardInfo *info); + +/** + * qemu_clipboard_info_unref + * + * @info: clipboard info. + * + * Decrease @info reference count. When the count goes down to zero + * free the @info struct itself and all clipboard data. + */ +void qemu_clipboard_info_unref(QemuClipboardInfo *info); + +/** + * qemu_clipboard_update + * + * @info: clipboard info. + * + * Update the qemu clipboard. Notify all registered peers (including + * the clipboard owner) that the qemu clipboard has been updated. + * + * This is used for both new completely clipboard content and for + * clipboard data updates in response to qemu_clipboard_request() + * calls. + */ +void qemu_clipboard_update(QemuClipboardInfo *info); + +/** + * qemu_clipboard_request + * + * @info: clipboard info. + * @type: clipboard data type. + * + * Request clipboard content. Typically the clipboard owner only + * advertises the available data types and provides the actual data + * only on request. + */ +void qemu_clipboard_request(QemuClipboardInfo *info, + QemuClipboardType type); + +/** + * qemu_clipboard_set_data + * + * @peer: clipboard peer. + * @info: clipboard info. + * @type: clipboard data type. + * @size: data size. + * @data: data blob. + * @update: notify peers about the update. + * + * Set clipboard content for the given @type. This function will make + * a copy of the content data and store that. + */ +void qemu_clipboard_set_data(QemuClipboardPeer *peer, + QemuClipboardInfo *info, + QemuClipboardType type, + uint32_t size, + const void *data, + bool update); + +#endif /* QEMU_CLIPBOARD_H */ diff --git a/include/ui/console.h b/include/ui/console.h index 59983a03ea..61baa085a3 100644 --- a/include/ui/console.h +++ b/include/ui/console.h @@ -471,4 +471,7 @@ bool vnc_display_reload_certs(const char *id, Error **errp); /* input.c */ int index_from_key(const char *key, size_t key_length); +/* udmabuf.c */ +int udmabuf_fd(void); + #endif diff --git a/include/ui/gtk.h b/include/ui/gtk.h index 5ae0ad60a6..80d6bbd9b5 100644 --- a/include/ui/gtk.h +++ b/include/ui/gtk.h @@ -18,11 +18,18 @@ #include #endif +#include "ui/clipboard.h" +#include "ui/console.h" #include "ui/kbd-state.h" #if defined(CONFIG_OPENGL) #include "ui/egl-helpers.h" #include "ui/egl-context.h" #endif +#ifdef CONFIG_VTE +#include "qemu/fifo8.h" +#endif + +#define MAX_VCS 10 typedef struct GtkDisplayState GtkDisplayState; @@ -58,6 +65,7 @@ typedef struct VirtualVteConsole { GtkWidget *scrollbar; GtkWidget *terminal; Chardev *chr; + Fifo8 out_fifo; bool echo; } VirtualVteConsole; #endif @@ -83,6 +91,66 @@ typedef struct VirtualConsole { }; } VirtualConsole; +struct GtkDisplayState { + GtkWidget *window; + + GtkWidget *menu_bar; + + GtkAccelGroup *accel_group; + + GtkWidget *machine_menu_item; + GtkWidget *machine_menu; + GtkWidget *pause_item; + GtkWidget *reset_item; + GtkWidget *powerdown_item; + GtkWidget *quit_item; + + GtkWidget *view_menu_item; + GtkWidget *view_menu; + GtkWidget *full_screen_item; + GtkWidget *copy_item; + GtkWidget *zoom_in_item; + GtkWidget *zoom_out_item; + GtkWidget *zoom_fixed_item; + GtkWidget *zoom_fit_item; + GtkWidget *grab_item; + GtkWidget *grab_on_hover_item; + + int nb_vcs; + VirtualConsole vc[MAX_VCS]; + + GtkWidget *show_tabs_item; + GtkWidget *untabify_item; + GtkWidget *show_menubar_item; + + GtkWidget *vbox; + GtkWidget *notebook; + int button_mask; + gboolean last_set; + int last_x; + int last_y; + int grab_x_root; + int grab_y_root; + VirtualConsole *kbd_owner; + VirtualConsole *ptr_owner; + + gboolean full_screen; + + GdkCursor *null_cursor; + Notifier mouse_mode_notifier; + gboolean free_scale; + + bool external_pause_update; + + QemuClipboardPeer cbpeer; + QemuClipboardInfo *cbinfo[QEMU_CLIPBOARD_SELECTION__COUNT]; + uint32_t cbpending[QEMU_CLIPBOARD_SELECTION__COUNT]; + GtkClipboard *gtkcb[QEMU_CLIPBOARD_SELECTION__COUNT]; + bool cbowner[QEMU_CLIPBOARD_SELECTION__COUNT]; + + DisplayOptions *opts; +}; + extern bool gtk_use_gl_area; /* ui/gtk.c */ @@ -150,4 +218,7 @@ void gtk_gl_area_init(void); int gd_gl_area_make_current(DisplayChangeListener *dcl, QEMUGLContext ctx); +/* gtk-clipboard.c */ +void gd_clipboard_init(GtkDisplayState *gd); + #endif /* UI_GTK_H */ diff --git a/include/ui/qemu-pixman.h b/include/ui/qemu-pixman.h index 87737a6f16..806ddcd7cd 100644 --- a/include/ui/qemu-pixman.h +++ b/include/ui/qemu-pixman.h @@ -62,6 +62,7 @@ typedef struct PixelFormat { PixelFormat qemu_pixelformat_from_pixman(pixman_format_code_t format); pixman_format_code_t qemu_default_pixman_format(int bpp, bool native_endian); pixman_format_code_t qemu_drm_format_to_pixman(uint32_t drm_format); +uint32_t qemu_pixman_to_drm_format(pixman_format_code_t pixman); int qemu_pixman_get_type(int rshift, int gshift, int bshift); pixman_format_code_t qemu_pixman_get_format(PixelFormat *pf); bool qemu_pixman_check_format(DisplayChangeListener *dcl, diff --git a/include/user/syscall-trace.h b/include/user/syscall-trace.h index 42e3b48b03..614cfacfa5 100644 --- a/include/user/syscall-trace.h +++ b/include/user/syscall-trace.h @@ -7,8 +7,8 @@ * SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _SYSCALL_TRACE_H_ -#define _SYSCALL_TRACE_H_ +#ifndef SYSCALL_TRACE_H +#define SYSCALL_TRACE_H #include "trace/trace-root.h" diff --git a/io/channel-socket.c b/io/channel-socket.c index de259f7eed..606ec97cf7 100644 --- a/io/channel-socket.c +++ b/io/channel-socket.c @@ -487,15 +487,15 @@ static ssize_t qio_channel_socket_readv(QIOChannel *ioc, memset(control, 0, CMSG_SPACE(sizeof(int) * SOCKET_MAX_FDS)); -#ifdef MSG_CMSG_CLOEXEC - sflags |= MSG_CMSG_CLOEXEC; -#endif - msg.msg_iov = (struct iovec *)iov; msg.msg_iovlen = niov; if (fds && nfds) { msg.msg_control = control; msg.msg_controllen = sizeof(control); +#ifdef MSG_CMSG_CLOEXEC + sflags |= MSG_CMSG_CLOEXEC; +#endif + } retry: diff --git a/io/channel-websock.c b/io/channel-websock.c index 03c1f7cb62..70889bb54d 100644 --- a/io/channel-websock.c +++ b/io/channel-websock.c @@ -177,15 +177,9 @@ qio_channel_websock_handshake_send_res(QIOChannelWebsock *ioc, static gchar *qio_channel_websock_date_str(void) { - struct tm tm; - time_t now = time(NULL); - char datebuf[128]; + g_autoptr(GDateTime) now = g_date_time_new_now_utc(); - gmtime_r(&now, &tm); - - strftime(datebuf, sizeof(datebuf), "%a, %d %b %Y %H:%M:%S GMT", &tm); - - return g_strdup(datebuf); + return g_date_time_format(now, "%a, %d %b %Y %H:%M:%S GMT"); } static void qio_channel_websock_handshake_send_res_err(QIOChannelWebsock *ioc, diff --git a/io/dns-resolver.c b/io/dns-resolver.c index 743a0efc87..a5946a93bf 100644 --- a/io/dns-resolver.c +++ b/io/dns-resolver.c @@ -122,6 +122,10 @@ static int qio_dns_resolver_lookup_sync_inet(QIODNSResolver *resolver, .ipv4 = iaddr->ipv4, .has_ipv6 = iaddr->has_ipv6, .ipv6 = iaddr->ipv6, +#ifdef IPPROTO_MPTCP + .has_mptcp = iaddr->has_mptcp, + .mptcp = iaddr->mptcp, +#endif }; (*addrs)[i] = newaddr; diff --git a/io/net-listener.c b/io/net-listener.c index 46c2643d00..1c984d69c6 100644 --- a/io/net-listener.c +++ b/io/net-listener.c @@ -292,6 +292,9 @@ static void qio_net_listener_finalize(Object *obj) QIONetListener *listener = QIO_NET_LISTENER(obj); size_t i; + if (listener->io_notify) { + listener->io_notify(listener->io_data); + } qio_net_listener_disconnect(listener); for (i = 0; i < listener->nsioc; i++) { diff --git a/io/trace-events b/io/trace-events index d7bc70b966..c5e814eb44 100644 --- a/io/trace-events +++ b/io/trace-events @@ -1,4 +1,4 @@ -# See docs/devel/tracing.txt for syntax documentation. +# See docs/devel/tracing.rst for syntax documentation. # task.c qio_task_new(void *task, void *source, void *func, void *opaque) "Task new task=%p source=%p func=%p opaque=%p" diff --git a/iothread.c b/iothread.c index 7f086387be..ddbbde61f7 100644 --- a/iothread.c +++ b/iothread.c @@ -39,13 +39,6 @@ DECLARE_CLASS_CHECKERS(IOThreadClass, IOTHREAD, #define IOTHREAD_POLL_MAX_NS_DEFAULT 0ULL #endif -static __thread IOThread *my_iothread; - -AioContext *qemu_get_current_aio_context(void) -{ - return my_iothread ? my_iothread->ctx : qemu_get_aio_context(); -} - static void *iothread_run(void *opaque) { IOThread *iothread = opaque; @@ -56,7 +49,7 @@ static void *iothread_run(void *opaque) * in this new thread uses glib. */ g_main_context_push_thread_default(iothread->worker_context); - my_iothread = iothread; + qemu_set_current_aio_context(iothread->ctx); iothread->thread_id = qemu_get_thread_id(); qemu_sem_post(&iothread->init_done_sem); @@ -159,6 +152,24 @@ static void iothread_init_gcontext(IOThread *iothread) iothread->main_loop = g_main_loop_new(iothread->worker_context, TRUE); } +static void iothread_set_aio_context_params(IOThread *iothread, Error **errp) +{ + ERRP_GUARD(); + + aio_context_set_poll_params(iothread->ctx, + iothread->poll_max_ns, + iothread->poll_grow, + iothread->poll_shrink, + errp); + if (*errp) { + return; + } + + aio_context_set_aio_params(iothread->ctx, + iothread->aio_max_batch, + errp); +} + static void iothread_complete(UserCreatable *obj, Error **errp) { Error *local_error = NULL; @@ -178,11 +189,7 @@ static void iothread_complete(UserCreatable *obj, Error **errp) */ iothread_init_gcontext(iothread); - aio_context_set_poll_params(iothread->ctx, - iothread->poll_max_ns, - iothread->poll_grow, - iothread->poll_shrink, - &local_error); + iothread_set_aio_context_params(iothread, &local_error); if (local_error) { error_propagate(errp, local_error); aio_context_unref(iothread->ctx); @@ -219,8 +226,11 @@ static PollParamInfo poll_grow_info = { static PollParamInfo poll_shrink_info = { "poll-shrink", offsetof(IOThread, poll_shrink), }; +static PollParamInfo aio_max_batch_info = { + "aio-max-batch", offsetof(IOThread, aio_max_batch), +}; -static void iothread_get_poll_param(Object *obj, Visitor *v, +static void iothread_get_param(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { IOThread *iothread = IOTHREAD(obj); @@ -230,7 +240,7 @@ static void iothread_get_poll_param(Object *obj, Visitor *v, visit_type_int64(v, name, field, errp); } -static void iothread_set_poll_param(Object *obj, Visitor *v, +static bool iothread_set_param(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { IOThread *iothread = IOTHREAD(obj); @@ -239,17 +249,36 @@ static void iothread_set_poll_param(Object *obj, Visitor *v, int64_t value; if (!visit_type_int64(v, name, &value, errp)) { - return; + return false; } if (value < 0) { error_setg(errp, "%s value must be in range [0, %" PRId64 "]", info->name, INT64_MAX); - return; + return false; } *field = value; + return true; +} + +static void iothread_get_poll_param(Object *obj, Visitor *v, + const char *name, void *opaque, Error **errp) +{ + + iothread_get_param(obj, v, name, opaque, errp); +} + +static void iothread_set_poll_param(Object *obj, Visitor *v, + const char *name, void *opaque, Error **errp) +{ + IOThread *iothread = IOTHREAD(obj); + + if (!iothread_set_param(obj, v, name, opaque, errp)) { + return; + } + if (iothread->ctx) { aio_context_set_poll_params(iothread->ctx, iothread->poll_max_ns, @@ -259,6 +288,29 @@ static void iothread_set_poll_param(Object *obj, Visitor *v, } } +static void iothread_get_aio_param(Object *obj, Visitor *v, + const char *name, void *opaque, Error **errp) +{ + + iothread_get_param(obj, v, name, opaque, errp); +} + +static void iothread_set_aio_param(Object *obj, Visitor *v, + const char *name, void *opaque, Error **errp) +{ + IOThread *iothread = IOTHREAD(obj); + + if (!iothread_set_param(obj, v, name, opaque, errp)) { + return; + } + + if (iothread->ctx) { + aio_context_set_aio_params(iothread->ctx, + iothread->aio_max_batch, + errp); + } +} + static void iothread_class_init(ObjectClass *klass, void *class_data) { UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); @@ -276,6 +328,10 @@ static void iothread_class_init(ObjectClass *klass, void *class_data) iothread_get_poll_param, iothread_set_poll_param, NULL, &poll_shrink_info); + object_class_property_add(klass, "aio-max-batch", "int", + iothread_get_aio_param, + iothread_set_aio_param, + NULL, &aio_max_batch_info); } static const TypeInfo iothread_info = { @@ -325,6 +381,7 @@ static int query_one_iothread(Object *object, void *opaque) info->poll_max_ns = iothread->poll_max_ns; info->poll_grow = iothread->poll_grow; info->poll_shrink = iothread->poll_shrink; + info->aio_max_batch = iothread->aio_max_batch; QAPI_LIST_APPEND(*tail, info); return 0; diff --git a/job-qmp.c b/job-qmp.c index 34c4da094f..829a28aa70 100644 --- a/job-qmp.c +++ b/job-qmp.c @@ -144,16 +144,20 @@ void qmp_job_dismiss(const char *id, Error **errp) static JobInfo *job_query_single(Job *job, Error **errp) { JobInfo *info; + uint64_t progress_current; + uint64_t progress_total; assert(!job_is_internal(job)); + progress_get_snapshot(&job->progress, &progress_current, + &progress_total); info = g_new(JobInfo, 1); *info = (JobInfo) { .id = g_strdup(job->id), .type = job_type(job), .status = job->status, - .current_progress = job->progress.current, - .total_progress = job->progress.total, + .current_progress = progress_current, + .total_progress = progress_total, .has_error = !!job->err, .error = job->err ? \ g_strdup(error_get_pretty(job->err)) : NULL, diff --git a/job.c b/job.c index 4aff13d95a..e7a5d28854 100644 --- a/job.c +++ b/job.c @@ -339,6 +339,8 @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn, job->cb = cb; job->opaque = opaque; + progress_init(&job->progress); + notifier_list_init(&job->on_finalize_cancelled); notifier_list_init(&job->on_finalize_completed); notifier_list_init(&job->on_pending); @@ -382,6 +384,7 @@ void job_unref(Job *job) QLIST_REMOVE(job, job_list); + progress_destroy(&job->progress); error_free(job->err); g_free(job->id); g_free(job); @@ -716,7 +719,7 @@ static int job_finalize_single(Job *job) static void job_cancel_async(Job *job, bool force) { if (job->driver->cancel) { - job->driver->cancel(job); + job->driver->cancel(job, force); } if (job->user_paused) { /* Do not call job_enter here, the caller will handle it. */ diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h index b6a0eaa32a..3d2ce9912d 100644 --- a/linux-headers/asm-arm64/kvm.h +++ b/linux-headers/asm-arm64/kvm.h @@ -184,6 +184,17 @@ struct kvm_vcpu_events { __u32 reserved[12]; }; +struct kvm_arm_copy_mte_tags { + __u64 guest_ipa; + __u64 length; + void *addr; + __u64 flags; + __u64 reserved[2]; +}; + +#define KVM_ARM_TAGS_TO_GUEST 0 +#define KVM_ARM_TAGS_FROM_GUEST 1 + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/linux-headers/asm-generic/mman-common.h b/linux-headers/asm-generic/mman-common.h index f94f65d429..1567a3294c 100644 --- a/linux-headers/asm-generic/mman-common.h +++ b/linux-headers/asm-generic/mman-common.h @@ -72,6 +72,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/linux-headers/asm-generic/unistd.h b/linux-headers/asm-generic/unistd.h index 7287529177..f211961ce1 100644 --- a/linux-headers/asm-generic/unistd.h +++ b/linux-headers/asm-generic/unistd.h @@ -861,9 +861,20 @@ __SYSCALL(__NR_faccessat2, sys_faccessat2) __SYSCALL(__NR_process_madvise, sys_process_madvise) #define __NR_epoll_pwait2 441 __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) +#define __NR_mount_setattr 442 +__SYSCALL(__NR_mount_setattr, sys_mount_setattr) +#define __NR_quotactl_fd 443 +__SYSCALL(__NR_quotactl_fd, sys_quotactl_fd) + +#define __NR_landlock_create_ruleset 444 +__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) +#define __NR_landlock_add_rule 445 +__SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule) +#define __NR_landlock_restrict_self 446 +__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) #undef __NR_syscalls -#define __NR_syscalls 442 +#define __NR_syscalls 447 /* * 32 bit systems traditionally used different diff --git a/linux-headers/asm-mips/mman.h b/linux-headers/asm-mips/mman.h index 57dc2ac4f8..40b210c65a 100644 --- a/linux-headers/asm-mips/mman.h +++ b/linux-headers/asm-mips/mman.h @@ -98,6 +98,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/linux-headers/asm-mips/unistd_n32.h b/linux-headers/asm-mips/unistd_n32.h index 59e53b6e07..09cd297698 100644 --- a/linux-headers/asm-mips/unistd_n32.h +++ b/linux-headers/asm-mips/unistd_n32.h @@ -1,376 +1,380 @@ -#ifndef _ASM_MIPS_UNISTD_N32_H -#define _ASM_MIPS_UNISTD_N32_H +#ifndef _ASM_UNISTD_N32_H +#define _ASM_UNISTD_N32_H -#define __NR_read (__NR_Linux + 0) -#define __NR_write (__NR_Linux + 1) -#define __NR_open (__NR_Linux + 2) -#define __NR_close (__NR_Linux + 3) -#define __NR_stat (__NR_Linux + 4) -#define __NR_fstat (__NR_Linux + 5) -#define __NR_lstat (__NR_Linux + 6) -#define __NR_poll (__NR_Linux + 7) -#define __NR_lseek (__NR_Linux + 8) -#define __NR_mmap (__NR_Linux + 9) -#define __NR_mprotect (__NR_Linux + 10) -#define __NR_munmap (__NR_Linux + 11) -#define __NR_brk (__NR_Linux + 12) -#define __NR_rt_sigaction (__NR_Linux + 13) -#define __NR_rt_sigprocmask (__NR_Linux + 14) -#define __NR_ioctl (__NR_Linux + 15) -#define __NR_pread64 (__NR_Linux + 16) -#define __NR_pwrite64 (__NR_Linux + 17) -#define __NR_readv (__NR_Linux + 18) -#define __NR_writev (__NR_Linux + 19) -#define __NR_access (__NR_Linux + 20) -#define __NR_pipe (__NR_Linux + 21) -#define __NR__newselect (__NR_Linux + 22) -#define __NR_sched_yield (__NR_Linux + 23) -#define __NR_mremap (__NR_Linux + 24) -#define __NR_msync (__NR_Linux + 25) -#define __NR_mincore (__NR_Linux + 26) -#define __NR_madvise (__NR_Linux + 27) -#define __NR_shmget (__NR_Linux + 28) -#define __NR_shmat (__NR_Linux + 29) -#define __NR_shmctl (__NR_Linux + 30) -#define __NR_dup (__NR_Linux + 31) -#define __NR_dup2 (__NR_Linux + 32) -#define __NR_pause (__NR_Linux + 33) -#define __NR_nanosleep (__NR_Linux + 34) -#define __NR_getitimer (__NR_Linux + 35) -#define __NR_setitimer (__NR_Linux + 36) -#define __NR_alarm (__NR_Linux + 37) -#define __NR_getpid (__NR_Linux + 38) -#define __NR_sendfile (__NR_Linux + 39) -#define __NR_socket (__NR_Linux + 40) -#define __NR_connect (__NR_Linux + 41) -#define __NR_accept (__NR_Linux + 42) -#define __NR_sendto (__NR_Linux + 43) -#define __NR_recvfrom (__NR_Linux + 44) -#define __NR_sendmsg (__NR_Linux + 45) -#define __NR_recvmsg (__NR_Linux + 46) -#define __NR_shutdown (__NR_Linux + 47) -#define __NR_bind (__NR_Linux + 48) -#define __NR_listen (__NR_Linux + 49) -#define __NR_getsockname (__NR_Linux + 50) -#define __NR_getpeername (__NR_Linux + 51) -#define __NR_socketpair (__NR_Linux + 52) -#define __NR_setsockopt (__NR_Linux + 53) -#define __NR_getsockopt (__NR_Linux + 54) -#define __NR_clone (__NR_Linux + 55) -#define __NR_fork (__NR_Linux + 56) -#define __NR_execve (__NR_Linux + 57) -#define __NR_exit (__NR_Linux + 58) -#define __NR_wait4 (__NR_Linux + 59) -#define __NR_kill (__NR_Linux + 60) -#define __NR_uname (__NR_Linux + 61) -#define __NR_semget (__NR_Linux + 62) -#define __NR_semop (__NR_Linux + 63) -#define __NR_semctl (__NR_Linux + 64) -#define __NR_shmdt (__NR_Linux + 65) -#define __NR_msgget (__NR_Linux + 66) -#define __NR_msgsnd (__NR_Linux + 67) -#define __NR_msgrcv (__NR_Linux + 68) -#define __NR_msgctl (__NR_Linux + 69) -#define __NR_fcntl (__NR_Linux + 70) -#define __NR_flock (__NR_Linux + 71) -#define __NR_fsync (__NR_Linux + 72) -#define __NR_fdatasync (__NR_Linux + 73) -#define __NR_truncate (__NR_Linux + 74) -#define __NR_ftruncate (__NR_Linux + 75) -#define __NR_getdents (__NR_Linux + 76) -#define __NR_getcwd (__NR_Linux + 77) -#define __NR_chdir (__NR_Linux + 78) -#define __NR_fchdir (__NR_Linux + 79) -#define __NR_rename (__NR_Linux + 80) -#define __NR_mkdir (__NR_Linux + 81) -#define __NR_rmdir (__NR_Linux + 82) -#define __NR_creat (__NR_Linux + 83) -#define __NR_link (__NR_Linux + 84) -#define __NR_unlink (__NR_Linux + 85) -#define __NR_symlink (__NR_Linux + 86) -#define __NR_readlink (__NR_Linux + 87) -#define __NR_chmod (__NR_Linux + 88) -#define __NR_fchmod (__NR_Linux + 89) -#define __NR_chown (__NR_Linux + 90) -#define __NR_fchown (__NR_Linux + 91) -#define __NR_lchown (__NR_Linux + 92) -#define __NR_umask (__NR_Linux + 93) -#define __NR_gettimeofday (__NR_Linux + 94) -#define __NR_getrlimit (__NR_Linux + 95) -#define __NR_getrusage (__NR_Linux + 96) -#define __NR_sysinfo (__NR_Linux + 97) -#define __NR_times (__NR_Linux + 98) -#define __NR_ptrace (__NR_Linux + 99) -#define __NR_getuid (__NR_Linux + 100) -#define __NR_syslog (__NR_Linux + 101) -#define __NR_getgid (__NR_Linux + 102) -#define __NR_setuid (__NR_Linux + 103) -#define __NR_setgid (__NR_Linux + 104) -#define __NR_geteuid (__NR_Linux + 105) -#define __NR_getegid (__NR_Linux + 106) -#define __NR_setpgid (__NR_Linux + 107) -#define __NR_getppid (__NR_Linux + 108) -#define __NR_getpgrp (__NR_Linux + 109) -#define __NR_setsid (__NR_Linux + 110) -#define __NR_setreuid (__NR_Linux + 111) -#define __NR_setregid (__NR_Linux + 112) -#define __NR_getgroups (__NR_Linux + 113) -#define __NR_setgroups (__NR_Linux + 114) -#define __NR_setresuid (__NR_Linux + 115) -#define __NR_getresuid (__NR_Linux + 116) -#define __NR_setresgid (__NR_Linux + 117) -#define __NR_getresgid (__NR_Linux + 118) -#define __NR_getpgid (__NR_Linux + 119) -#define __NR_setfsuid (__NR_Linux + 120) -#define __NR_setfsgid (__NR_Linux + 121) -#define __NR_getsid (__NR_Linux + 122) -#define __NR_capget (__NR_Linux + 123) -#define __NR_capset (__NR_Linux + 124) -#define __NR_rt_sigpending (__NR_Linux + 125) -#define __NR_rt_sigtimedwait (__NR_Linux + 126) -#define __NR_rt_sigqueueinfo (__NR_Linux + 127) -#define __NR_rt_sigsuspend (__NR_Linux + 128) -#define __NR_sigaltstack (__NR_Linux + 129) -#define __NR_utime (__NR_Linux + 130) -#define __NR_mknod (__NR_Linux + 131) -#define __NR_personality (__NR_Linux + 132) -#define __NR_ustat (__NR_Linux + 133) -#define __NR_statfs (__NR_Linux + 134) -#define __NR_fstatfs (__NR_Linux + 135) -#define __NR_sysfs (__NR_Linux + 136) -#define __NR_getpriority (__NR_Linux + 137) -#define __NR_setpriority (__NR_Linux + 138) -#define __NR_sched_setparam (__NR_Linux + 139) -#define __NR_sched_getparam (__NR_Linux + 140) -#define __NR_sched_setscheduler (__NR_Linux + 141) -#define __NR_sched_getscheduler (__NR_Linux + 142) -#define __NR_sched_get_priority_max (__NR_Linux + 143) -#define __NR_sched_get_priority_min (__NR_Linux + 144) -#define __NR_sched_rr_get_interval (__NR_Linux + 145) -#define __NR_mlock (__NR_Linux + 146) -#define __NR_munlock (__NR_Linux + 147) -#define __NR_mlockall (__NR_Linux + 148) -#define __NR_munlockall (__NR_Linux + 149) -#define __NR_vhangup (__NR_Linux + 150) -#define __NR_pivot_root (__NR_Linux + 151) -#define __NR__sysctl (__NR_Linux + 152) -#define __NR_prctl (__NR_Linux + 153) -#define __NR_adjtimex (__NR_Linux + 154) -#define __NR_setrlimit (__NR_Linux + 155) -#define __NR_chroot (__NR_Linux + 156) -#define __NR_sync (__NR_Linux + 157) -#define __NR_acct (__NR_Linux + 158) -#define __NR_settimeofday (__NR_Linux + 159) -#define __NR_mount (__NR_Linux + 160) -#define __NR_umount2 (__NR_Linux + 161) -#define __NR_swapon (__NR_Linux + 162) -#define __NR_swapoff (__NR_Linux + 163) -#define __NR_reboot (__NR_Linux + 164) -#define __NR_sethostname (__NR_Linux + 165) -#define __NR_setdomainname (__NR_Linux + 166) -#define __NR_create_module (__NR_Linux + 167) -#define __NR_init_module (__NR_Linux + 168) -#define __NR_delete_module (__NR_Linux + 169) -#define __NR_get_kernel_syms (__NR_Linux + 170) -#define __NR_query_module (__NR_Linux + 171) -#define __NR_quotactl (__NR_Linux + 172) -#define __NR_nfsservctl (__NR_Linux + 173) -#define __NR_getpmsg (__NR_Linux + 174) -#define __NR_putpmsg (__NR_Linux + 175) -#define __NR_afs_syscall (__NR_Linux + 176) -#define __NR_reserved177 (__NR_Linux + 177) -#define __NR_gettid (__NR_Linux + 178) -#define __NR_readahead (__NR_Linux + 179) -#define __NR_setxattr (__NR_Linux + 180) -#define __NR_lsetxattr (__NR_Linux + 181) -#define __NR_fsetxattr (__NR_Linux + 182) -#define __NR_getxattr (__NR_Linux + 183) -#define __NR_lgetxattr (__NR_Linux + 184) -#define __NR_fgetxattr (__NR_Linux + 185) -#define __NR_listxattr (__NR_Linux + 186) -#define __NR_llistxattr (__NR_Linux + 187) -#define __NR_flistxattr (__NR_Linux + 188) -#define __NR_removexattr (__NR_Linux + 189) -#define __NR_lremovexattr (__NR_Linux + 190) -#define __NR_fremovexattr (__NR_Linux + 191) -#define __NR_tkill (__NR_Linux + 192) -#define __NR_reserved193 (__NR_Linux + 193) -#define __NR_futex (__NR_Linux + 194) -#define __NR_sched_setaffinity (__NR_Linux + 195) -#define __NR_sched_getaffinity (__NR_Linux + 196) -#define __NR_cacheflush (__NR_Linux + 197) -#define __NR_cachectl (__NR_Linux + 198) -#define __NR_sysmips (__NR_Linux + 199) -#define __NR_io_setup (__NR_Linux + 200) -#define __NR_io_destroy (__NR_Linux + 201) -#define __NR_io_getevents (__NR_Linux + 202) -#define __NR_io_submit (__NR_Linux + 203) -#define __NR_io_cancel (__NR_Linux + 204) -#define __NR_exit_group (__NR_Linux + 205) -#define __NR_lookup_dcookie (__NR_Linux + 206) -#define __NR_epoll_create (__NR_Linux + 207) -#define __NR_epoll_ctl (__NR_Linux + 208) -#define __NR_epoll_wait (__NR_Linux + 209) -#define __NR_remap_file_pages (__NR_Linux + 210) -#define __NR_rt_sigreturn (__NR_Linux + 211) -#define __NR_fcntl64 (__NR_Linux + 212) -#define __NR_set_tid_address (__NR_Linux + 213) -#define __NR_restart_syscall (__NR_Linux + 214) -#define __NR_semtimedop (__NR_Linux + 215) -#define __NR_fadvise64 (__NR_Linux + 216) -#define __NR_statfs64 (__NR_Linux + 217) -#define __NR_fstatfs64 (__NR_Linux + 218) -#define __NR_sendfile64 (__NR_Linux + 219) -#define __NR_timer_create (__NR_Linux + 220) -#define __NR_timer_settime (__NR_Linux + 221) -#define __NR_timer_gettime (__NR_Linux + 222) -#define __NR_timer_getoverrun (__NR_Linux + 223) -#define __NR_timer_delete (__NR_Linux + 224) -#define __NR_clock_settime (__NR_Linux + 225) -#define __NR_clock_gettime (__NR_Linux + 226) -#define __NR_clock_getres (__NR_Linux + 227) -#define __NR_clock_nanosleep (__NR_Linux + 228) -#define __NR_tgkill (__NR_Linux + 229) -#define __NR_utimes (__NR_Linux + 230) -#define __NR_mbind (__NR_Linux + 231) -#define __NR_get_mempolicy (__NR_Linux + 232) -#define __NR_set_mempolicy (__NR_Linux + 233) -#define __NR_mq_open (__NR_Linux + 234) -#define __NR_mq_unlink (__NR_Linux + 235) -#define __NR_mq_timedsend (__NR_Linux + 236) -#define __NR_mq_timedreceive (__NR_Linux + 237) -#define __NR_mq_notify (__NR_Linux + 238) -#define __NR_mq_getsetattr (__NR_Linux + 239) -#define __NR_vserver (__NR_Linux + 240) -#define __NR_waitid (__NR_Linux + 241) -#define __NR_add_key (__NR_Linux + 243) -#define __NR_request_key (__NR_Linux + 244) -#define __NR_keyctl (__NR_Linux + 245) -#define __NR_set_thread_area (__NR_Linux + 246) -#define __NR_inotify_init (__NR_Linux + 247) -#define __NR_inotify_add_watch (__NR_Linux + 248) -#define __NR_inotify_rm_watch (__NR_Linux + 249) -#define __NR_migrate_pages (__NR_Linux + 250) -#define __NR_openat (__NR_Linux + 251) -#define __NR_mkdirat (__NR_Linux + 252) -#define __NR_mknodat (__NR_Linux + 253) -#define __NR_fchownat (__NR_Linux + 254) -#define __NR_futimesat (__NR_Linux + 255) -#define __NR_newfstatat (__NR_Linux + 256) -#define __NR_unlinkat (__NR_Linux + 257) -#define __NR_renameat (__NR_Linux + 258) -#define __NR_linkat (__NR_Linux + 259) -#define __NR_symlinkat (__NR_Linux + 260) -#define __NR_readlinkat (__NR_Linux + 261) -#define __NR_fchmodat (__NR_Linux + 262) -#define __NR_faccessat (__NR_Linux + 263) -#define __NR_pselect6 (__NR_Linux + 264) -#define __NR_ppoll (__NR_Linux + 265) -#define __NR_unshare (__NR_Linux + 266) -#define __NR_splice (__NR_Linux + 267) -#define __NR_sync_file_range (__NR_Linux + 268) -#define __NR_tee (__NR_Linux + 269) -#define __NR_vmsplice (__NR_Linux + 270) -#define __NR_move_pages (__NR_Linux + 271) -#define __NR_set_robust_list (__NR_Linux + 272) -#define __NR_get_robust_list (__NR_Linux + 273) -#define __NR_kexec_load (__NR_Linux + 274) -#define __NR_getcpu (__NR_Linux + 275) -#define __NR_epoll_pwait (__NR_Linux + 276) -#define __NR_ioprio_set (__NR_Linux + 277) -#define __NR_ioprio_get (__NR_Linux + 278) -#define __NR_utimensat (__NR_Linux + 279) -#define __NR_signalfd (__NR_Linux + 280) -#define __NR_timerfd (__NR_Linux + 281) -#define __NR_eventfd (__NR_Linux + 282) -#define __NR_fallocate (__NR_Linux + 283) -#define __NR_timerfd_create (__NR_Linux + 284) -#define __NR_timerfd_gettime (__NR_Linux + 285) -#define __NR_timerfd_settime (__NR_Linux + 286) -#define __NR_signalfd4 (__NR_Linux + 287) -#define __NR_eventfd2 (__NR_Linux + 288) -#define __NR_epoll_create1 (__NR_Linux + 289) -#define __NR_dup3 (__NR_Linux + 290) -#define __NR_pipe2 (__NR_Linux + 291) -#define __NR_inotify_init1 (__NR_Linux + 292) -#define __NR_preadv (__NR_Linux + 293) -#define __NR_pwritev (__NR_Linux + 294) -#define __NR_rt_tgsigqueueinfo (__NR_Linux + 295) -#define __NR_perf_event_open (__NR_Linux + 296) -#define __NR_accept4 (__NR_Linux + 297) -#define __NR_recvmmsg (__NR_Linux + 298) -#define __NR_getdents64 (__NR_Linux + 299) -#define __NR_fanotify_init (__NR_Linux + 300) -#define __NR_fanotify_mark (__NR_Linux + 301) -#define __NR_prlimit64 (__NR_Linux + 302) -#define __NR_name_to_handle_at (__NR_Linux + 303) -#define __NR_open_by_handle_at (__NR_Linux + 304) -#define __NR_clock_adjtime (__NR_Linux + 305) -#define __NR_syncfs (__NR_Linux + 306) -#define __NR_sendmmsg (__NR_Linux + 307) -#define __NR_setns (__NR_Linux + 308) -#define __NR_process_vm_readv (__NR_Linux + 309) -#define __NR_process_vm_writev (__NR_Linux + 310) -#define __NR_kcmp (__NR_Linux + 311) -#define __NR_finit_module (__NR_Linux + 312) -#define __NR_sched_setattr (__NR_Linux + 313) -#define __NR_sched_getattr (__NR_Linux + 314) -#define __NR_renameat2 (__NR_Linux + 315) -#define __NR_seccomp (__NR_Linux + 316) -#define __NR_getrandom (__NR_Linux + 317) -#define __NR_memfd_create (__NR_Linux + 318) -#define __NR_bpf (__NR_Linux + 319) -#define __NR_execveat (__NR_Linux + 320) -#define __NR_userfaultfd (__NR_Linux + 321) -#define __NR_membarrier (__NR_Linux + 322) -#define __NR_mlock2 (__NR_Linux + 323) -#define __NR_copy_file_range (__NR_Linux + 324) -#define __NR_preadv2 (__NR_Linux + 325) -#define __NR_pwritev2 (__NR_Linux + 326) -#define __NR_pkey_mprotect (__NR_Linux + 327) -#define __NR_pkey_alloc (__NR_Linux + 328) -#define __NR_pkey_free (__NR_Linux + 329) -#define __NR_statx (__NR_Linux + 330) -#define __NR_rseq (__NR_Linux + 331) -#define __NR_io_pgetevents (__NR_Linux + 332) -#define __NR_clock_gettime64 (__NR_Linux + 403) -#define __NR_clock_settime64 (__NR_Linux + 404) -#define __NR_clock_adjtime64 (__NR_Linux + 405) -#define __NR_clock_getres_time64 (__NR_Linux + 406) -#define __NR_clock_nanosleep_time64 (__NR_Linux + 407) -#define __NR_timer_gettime64 (__NR_Linux + 408) -#define __NR_timer_settime64 (__NR_Linux + 409) -#define __NR_timerfd_gettime64 (__NR_Linux + 410) -#define __NR_timerfd_settime64 (__NR_Linux + 411) -#define __NR_utimensat_time64 (__NR_Linux + 412) -#define __NR_pselect6_time64 (__NR_Linux + 413) -#define __NR_ppoll_time64 (__NR_Linux + 414) -#define __NR_io_pgetevents_time64 (__NR_Linux + 416) -#define __NR_recvmmsg_time64 (__NR_Linux + 417) -#define __NR_mq_timedsend_time64 (__NR_Linux + 418) -#define __NR_mq_timedreceive_time64 (__NR_Linux + 419) -#define __NR_semtimedop_time64 (__NR_Linux + 420) -#define __NR_rt_sigtimedwait_time64 (__NR_Linux + 421) -#define __NR_futex_time64 (__NR_Linux + 422) -#define __NR_sched_rr_get_interval_time64 (__NR_Linux + 423) -#define __NR_pidfd_send_signal (__NR_Linux + 424) -#define __NR_io_uring_setup (__NR_Linux + 425) -#define __NR_io_uring_enter (__NR_Linux + 426) -#define __NR_io_uring_register (__NR_Linux + 427) -#define __NR_open_tree (__NR_Linux + 428) -#define __NR_move_mount (__NR_Linux + 429) -#define __NR_fsopen (__NR_Linux + 430) -#define __NR_fsconfig (__NR_Linux + 431) -#define __NR_fsmount (__NR_Linux + 432) -#define __NR_fspick (__NR_Linux + 433) -#define __NR_pidfd_open (__NR_Linux + 434) -#define __NR_clone3 (__NR_Linux + 435) -#define __NR_close_range (__NR_Linux + 436) -#define __NR_openat2 (__NR_Linux + 437) -#define __NR_pidfd_getfd (__NR_Linux + 438) -#define __NR_faccessat2 (__NR_Linux + 439) -#define __NR_process_madvise (__NR_Linux + 440) -#define __NR_epoll_pwait2 (__NR_Linux + 441) +#define __NR_read (__NR_Linux + 0) +#define __NR_write (__NR_Linux + 1) +#define __NR_open (__NR_Linux + 2) +#define __NR_close (__NR_Linux + 3) +#define __NR_stat (__NR_Linux + 4) +#define __NR_fstat (__NR_Linux + 5) +#define __NR_lstat (__NR_Linux + 6) +#define __NR_poll (__NR_Linux + 7) +#define __NR_lseek (__NR_Linux + 8) +#define __NR_mmap (__NR_Linux + 9) +#define __NR_mprotect (__NR_Linux + 10) +#define __NR_munmap (__NR_Linux + 11) +#define __NR_brk (__NR_Linux + 12) +#define __NR_rt_sigaction (__NR_Linux + 13) +#define __NR_rt_sigprocmask (__NR_Linux + 14) +#define __NR_ioctl (__NR_Linux + 15) +#define __NR_pread64 (__NR_Linux + 16) +#define __NR_pwrite64 (__NR_Linux + 17) +#define __NR_readv (__NR_Linux + 18) +#define __NR_writev (__NR_Linux + 19) +#define __NR_access (__NR_Linux + 20) +#define __NR_pipe (__NR_Linux + 21) +#define __NR__newselect (__NR_Linux + 22) +#define __NR_sched_yield (__NR_Linux + 23) +#define __NR_mremap (__NR_Linux + 24) +#define __NR_msync (__NR_Linux + 25) +#define __NR_mincore (__NR_Linux + 26) +#define __NR_madvise (__NR_Linux + 27) +#define __NR_shmget (__NR_Linux + 28) +#define __NR_shmat (__NR_Linux + 29) +#define __NR_shmctl (__NR_Linux + 30) +#define __NR_dup (__NR_Linux + 31) +#define __NR_dup2 (__NR_Linux + 32) +#define __NR_pause (__NR_Linux + 33) +#define __NR_nanosleep (__NR_Linux + 34) +#define __NR_getitimer (__NR_Linux + 35) +#define __NR_setitimer (__NR_Linux + 36) +#define __NR_alarm (__NR_Linux + 37) +#define __NR_getpid (__NR_Linux + 38) +#define __NR_sendfile (__NR_Linux + 39) +#define __NR_socket (__NR_Linux + 40) +#define __NR_connect (__NR_Linux + 41) +#define __NR_accept (__NR_Linux + 42) +#define __NR_sendto (__NR_Linux + 43) +#define __NR_recvfrom (__NR_Linux + 44) +#define __NR_sendmsg (__NR_Linux + 45) +#define __NR_recvmsg (__NR_Linux + 46) +#define __NR_shutdown (__NR_Linux + 47) +#define __NR_bind (__NR_Linux + 48) +#define __NR_listen (__NR_Linux + 49) +#define __NR_getsockname (__NR_Linux + 50) +#define __NR_getpeername (__NR_Linux + 51) +#define __NR_socketpair (__NR_Linux + 52) +#define __NR_setsockopt (__NR_Linux + 53) +#define __NR_getsockopt (__NR_Linux + 54) +#define __NR_clone (__NR_Linux + 55) +#define __NR_fork (__NR_Linux + 56) +#define __NR_execve (__NR_Linux + 57) +#define __NR_exit (__NR_Linux + 58) +#define __NR_wait4 (__NR_Linux + 59) +#define __NR_kill (__NR_Linux + 60) +#define __NR_uname (__NR_Linux + 61) +#define __NR_semget (__NR_Linux + 62) +#define __NR_semop (__NR_Linux + 63) +#define __NR_semctl (__NR_Linux + 64) +#define __NR_shmdt (__NR_Linux + 65) +#define __NR_msgget (__NR_Linux + 66) +#define __NR_msgsnd (__NR_Linux + 67) +#define __NR_msgrcv (__NR_Linux + 68) +#define __NR_msgctl (__NR_Linux + 69) +#define __NR_fcntl (__NR_Linux + 70) +#define __NR_flock (__NR_Linux + 71) +#define __NR_fsync (__NR_Linux + 72) +#define __NR_fdatasync (__NR_Linux + 73) +#define __NR_truncate (__NR_Linux + 74) +#define __NR_ftruncate (__NR_Linux + 75) +#define __NR_getdents (__NR_Linux + 76) +#define __NR_getcwd (__NR_Linux + 77) +#define __NR_chdir (__NR_Linux + 78) +#define __NR_fchdir (__NR_Linux + 79) +#define __NR_rename (__NR_Linux + 80) +#define __NR_mkdir (__NR_Linux + 81) +#define __NR_rmdir (__NR_Linux + 82) +#define __NR_creat (__NR_Linux + 83) +#define __NR_link (__NR_Linux + 84) +#define __NR_unlink (__NR_Linux + 85) +#define __NR_symlink (__NR_Linux + 86) +#define __NR_readlink (__NR_Linux + 87) +#define __NR_chmod (__NR_Linux + 88) +#define __NR_fchmod (__NR_Linux + 89) +#define __NR_chown (__NR_Linux + 90) +#define __NR_fchown (__NR_Linux + 91) +#define __NR_lchown (__NR_Linux + 92) +#define __NR_umask (__NR_Linux + 93) +#define __NR_gettimeofday (__NR_Linux + 94) +#define __NR_getrlimit (__NR_Linux + 95) +#define __NR_getrusage (__NR_Linux + 96) +#define __NR_sysinfo (__NR_Linux + 97) +#define __NR_times (__NR_Linux + 98) +#define __NR_ptrace (__NR_Linux + 99) +#define __NR_getuid (__NR_Linux + 100) +#define __NR_syslog (__NR_Linux + 101) +#define __NR_getgid (__NR_Linux + 102) +#define __NR_setuid (__NR_Linux + 103) +#define __NR_setgid (__NR_Linux + 104) +#define __NR_geteuid (__NR_Linux + 105) +#define __NR_getegid (__NR_Linux + 106) +#define __NR_setpgid (__NR_Linux + 107) +#define __NR_getppid (__NR_Linux + 108) +#define __NR_getpgrp (__NR_Linux + 109) +#define __NR_setsid (__NR_Linux + 110) +#define __NR_setreuid (__NR_Linux + 111) +#define __NR_setregid (__NR_Linux + 112) +#define __NR_getgroups (__NR_Linux + 113) +#define __NR_setgroups (__NR_Linux + 114) +#define __NR_setresuid (__NR_Linux + 115) +#define __NR_getresuid (__NR_Linux + 116) +#define __NR_setresgid (__NR_Linux + 117) +#define __NR_getresgid (__NR_Linux + 118) +#define __NR_getpgid (__NR_Linux + 119) +#define __NR_setfsuid (__NR_Linux + 120) +#define __NR_setfsgid (__NR_Linux + 121) +#define __NR_getsid (__NR_Linux + 122) +#define __NR_capget (__NR_Linux + 123) +#define __NR_capset (__NR_Linux + 124) +#define __NR_rt_sigpending (__NR_Linux + 125) +#define __NR_rt_sigtimedwait (__NR_Linux + 126) +#define __NR_rt_sigqueueinfo (__NR_Linux + 127) +#define __NR_rt_sigsuspend (__NR_Linux + 128) +#define __NR_sigaltstack (__NR_Linux + 129) +#define __NR_utime (__NR_Linux + 130) +#define __NR_mknod (__NR_Linux + 131) +#define __NR_personality (__NR_Linux + 132) +#define __NR_ustat (__NR_Linux + 133) +#define __NR_statfs (__NR_Linux + 134) +#define __NR_fstatfs (__NR_Linux + 135) +#define __NR_sysfs (__NR_Linux + 136) +#define __NR_getpriority (__NR_Linux + 137) +#define __NR_setpriority (__NR_Linux + 138) +#define __NR_sched_setparam (__NR_Linux + 139) +#define __NR_sched_getparam (__NR_Linux + 140) +#define __NR_sched_setscheduler (__NR_Linux + 141) +#define __NR_sched_getscheduler (__NR_Linux + 142) +#define __NR_sched_get_priority_max (__NR_Linux + 143) +#define __NR_sched_get_priority_min (__NR_Linux + 144) +#define __NR_sched_rr_get_interval (__NR_Linux + 145) +#define __NR_mlock (__NR_Linux + 146) +#define __NR_munlock (__NR_Linux + 147) +#define __NR_mlockall (__NR_Linux + 148) +#define __NR_munlockall (__NR_Linux + 149) +#define __NR_vhangup (__NR_Linux + 150) +#define __NR_pivot_root (__NR_Linux + 151) +#define __NR__sysctl (__NR_Linux + 152) +#define __NR_prctl (__NR_Linux + 153) +#define __NR_adjtimex (__NR_Linux + 154) +#define __NR_setrlimit (__NR_Linux + 155) +#define __NR_chroot (__NR_Linux + 156) +#define __NR_sync (__NR_Linux + 157) +#define __NR_acct (__NR_Linux + 158) +#define __NR_settimeofday (__NR_Linux + 159) +#define __NR_mount (__NR_Linux + 160) +#define __NR_umount2 (__NR_Linux + 161) +#define __NR_swapon (__NR_Linux + 162) +#define __NR_swapoff (__NR_Linux + 163) +#define __NR_reboot (__NR_Linux + 164) +#define __NR_sethostname (__NR_Linux + 165) +#define __NR_setdomainname (__NR_Linux + 166) +#define __NR_create_module (__NR_Linux + 167) +#define __NR_init_module (__NR_Linux + 168) +#define __NR_delete_module (__NR_Linux + 169) +#define __NR_get_kernel_syms (__NR_Linux + 170) +#define __NR_query_module (__NR_Linux + 171) +#define __NR_quotactl (__NR_Linux + 172) +#define __NR_nfsservctl (__NR_Linux + 173) +#define __NR_getpmsg (__NR_Linux + 174) +#define __NR_putpmsg (__NR_Linux + 175) +#define __NR_afs_syscall (__NR_Linux + 176) +#define __NR_reserved177 (__NR_Linux + 177) +#define __NR_gettid (__NR_Linux + 178) +#define __NR_readahead (__NR_Linux + 179) +#define __NR_setxattr (__NR_Linux + 180) +#define __NR_lsetxattr (__NR_Linux + 181) +#define __NR_fsetxattr (__NR_Linux + 182) +#define __NR_getxattr (__NR_Linux + 183) +#define __NR_lgetxattr (__NR_Linux + 184) +#define __NR_fgetxattr (__NR_Linux + 185) +#define __NR_listxattr (__NR_Linux + 186) +#define __NR_llistxattr (__NR_Linux + 187) +#define __NR_flistxattr (__NR_Linux + 188) +#define __NR_removexattr (__NR_Linux + 189) +#define __NR_lremovexattr (__NR_Linux + 190) +#define __NR_fremovexattr (__NR_Linux + 191) +#define __NR_tkill (__NR_Linux + 192) +#define __NR_reserved193 (__NR_Linux + 193) +#define __NR_futex (__NR_Linux + 194) +#define __NR_sched_setaffinity (__NR_Linux + 195) +#define __NR_sched_getaffinity (__NR_Linux + 196) +#define __NR_cacheflush (__NR_Linux + 197) +#define __NR_cachectl (__NR_Linux + 198) +#define __NR_sysmips (__NR_Linux + 199) +#define __NR_io_setup (__NR_Linux + 200) +#define __NR_io_destroy (__NR_Linux + 201) +#define __NR_io_getevents (__NR_Linux + 202) +#define __NR_io_submit (__NR_Linux + 203) +#define __NR_io_cancel (__NR_Linux + 204) +#define __NR_exit_group (__NR_Linux + 205) +#define __NR_lookup_dcookie (__NR_Linux + 206) +#define __NR_epoll_create (__NR_Linux + 207) +#define __NR_epoll_ctl (__NR_Linux + 208) +#define __NR_epoll_wait (__NR_Linux + 209) +#define __NR_remap_file_pages (__NR_Linux + 210) +#define __NR_rt_sigreturn (__NR_Linux + 211) +#define __NR_fcntl64 (__NR_Linux + 212) +#define __NR_set_tid_address (__NR_Linux + 213) +#define __NR_restart_syscall (__NR_Linux + 214) +#define __NR_semtimedop (__NR_Linux + 215) +#define __NR_fadvise64 (__NR_Linux + 216) +#define __NR_statfs64 (__NR_Linux + 217) +#define __NR_fstatfs64 (__NR_Linux + 218) +#define __NR_sendfile64 (__NR_Linux + 219) +#define __NR_timer_create (__NR_Linux + 220) +#define __NR_timer_settime (__NR_Linux + 221) +#define __NR_timer_gettime (__NR_Linux + 222) +#define __NR_timer_getoverrun (__NR_Linux + 223) +#define __NR_timer_delete (__NR_Linux + 224) +#define __NR_clock_settime (__NR_Linux + 225) +#define __NR_clock_gettime (__NR_Linux + 226) +#define __NR_clock_getres (__NR_Linux + 227) +#define __NR_clock_nanosleep (__NR_Linux + 228) +#define __NR_tgkill (__NR_Linux + 229) +#define __NR_utimes (__NR_Linux + 230) +#define __NR_mbind (__NR_Linux + 231) +#define __NR_get_mempolicy (__NR_Linux + 232) +#define __NR_set_mempolicy (__NR_Linux + 233) +#define __NR_mq_open (__NR_Linux + 234) +#define __NR_mq_unlink (__NR_Linux + 235) +#define __NR_mq_timedsend (__NR_Linux + 236) +#define __NR_mq_timedreceive (__NR_Linux + 237) +#define __NR_mq_notify (__NR_Linux + 238) +#define __NR_mq_getsetattr (__NR_Linux + 239) +#define __NR_vserver (__NR_Linux + 240) +#define __NR_waitid (__NR_Linux + 241) +#define __NR_add_key (__NR_Linux + 243) +#define __NR_request_key (__NR_Linux + 244) +#define __NR_keyctl (__NR_Linux + 245) +#define __NR_set_thread_area (__NR_Linux + 246) +#define __NR_inotify_init (__NR_Linux + 247) +#define __NR_inotify_add_watch (__NR_Linux + 248) +#define __NR_inotify_rm_watch (__NR_Linux + 249) +#define __NR_migrate_pages (__NR_Linux + 250) +#define __NR_openat (__NR_Linux + 251) +#define __NR_mkdirat (__NR_Linux + 252) +#define __NR_mknodat (__NR_Linux + 253) +#define __NR_fchownat (__NR_Linux + 254) +#define __NR_futimesat (__NR_Linux + 255) +#define __NR_newfstatat (__NR_Linux + 256) +#define __NR_unlinkat (__NR_Linux + 257) +#define __NR_renameat (__NR_Linux + 258) +#define __NR_linkat (__NR_Linux + 259) +#define __NR_symlinkat (__NR_Linux + 260) +#define __NR_readlinkat (__NR_Linux + 261) +#define __NR_fchmodat (__NR_Linux + 262) +#define __NR_faccessat (__NR_Linux + 263) +#define __NR_pselect6 (__NR_Linux + 264) +#define __NR_ppoll (__NR_Linux + 265) +#define __NR_unshare (__NR_Linux + 266) +#define __NR_splice (__NR_Linux + 267) +#define __NR_sync_file_range (__NR_Linux + 268) +#define __NR_tee (__NR_Linux + 269) +#define __NR_vmsplice (__NR_Linux + 270) +#define __NR_move_pages (__NR_Linux + 271) +#define __NR_set_robust_list (__NR_Linux + 272) +#define __NR_get_robust_list (__NR_Linux + 273) +#define __NR_kexec_load (__NR_Linux + 274) +#define __NR_getcpu (__NR_Linux + 275) +#define __NR_epoll_pwait (__NR_Linux + 276) +#define __NR_ioprio_set (__NR_Linux + 277) +#define __NR_ioprio_get (__NR_Linux + 278) +#define __NR_utimensat (__NR_Linux + 279) +#define __NR_signalfd (__NR_Linux + 280) +#define __NR_timerfd (__NR_Linux + 281) +#define __NR_eventfd (__NR_Linux + 282) +#define __NR_fallocate (__NR_Linux + 283) +#define __NR_timerfd_create (__NR_Linux + 284) +#define __NR_timerfd_gettime (__NR_Linux + 285) +#define __NR_timerfd_settime (__NR_Linux + 286) +#define __NR_signalfd4 (__NR_Linux + 287) +#define __NR_eventfd2 (__NR_Linux + 288) +#define __NR_epoll_create1 (__NR_Linux + 289) +#define __NR_dup3 (__NR_Linux + 290) +#define __NR_pipe2 (__NR_Linux + 291) +#define __NR_inotify_init1 (__NR_Linux + 292) +#define __NR_preadv (__NR_Linux + 293) +#define __NR_pwritev (__NR_Linux + 294) +#define __NR_rt_tgsigqueueinfo (__NR_Linux + 295) +#define __NR_perf_event_open (__NR_Linux + 296) +#define __NR_accept4 (__NR_Linux + 297) +#define __NR_recvmmsg (__NR_Linux + 298) +#define __NR_getdents64 (__NR_Linux + 299) +#define __NR_fanotify_init (__NR_Linux + 300) +#define __NR_fanotify_mark (__NR_Linux + 301) +#define __NR_prlimit64 (__NR_Linux + 302) +#define __NR_name_to_handle_at (__NR_Linux + 303) +#define __NR_open_by_handle_at (__NR_Linux + 304) +#define __NR_clock_adjtime (__NR_Linux + 305) +#define __NR_syncfs (__NR_Linux + 306) +#define __NR_sendmmsg (__NR_Linux + 307) +#define __NR_setns (__NR_Linux + 308) +#define __NR_process_vm_readv (__NR_Linux + 309) +#define __NR_process_vm_writev (__NR_Linux + 310) +#define __NR_kcmp (__NR_Linux + 311) +#define __NR_finit_module (__NR_Linux + 312) +#define __NR_sched_setattr (__NR_Linux + 313) +#define __NR_sched_getattr (__NR_Linux + 314) +#define __NR_renameat2 (__NR_Linux + 315) +#define __NR_seccomp (__NR_Linux + 316) +#define __NR_getrandom (__NR_Linux + 317) +#define __NR_memfd_create (__NR_Linux + 318) +#define __NR_bpf (__NR_Linux + 319) +#define __NR_execveat (__NR_Linux + 320) +#define __NR_userfaultfd (__NR_Linux + 321) +#define __NR_membarrier (__NR_Linux + 322) +#define __NR_mlock2 (__NR_Linux + 323) +#define __NR_copy_file_range (__NR_Linux + 324) +#define __NR_preadv2 (__NR_Linux + 325) +#define __NR_pwritev2 (__NR_Linux + 326) +#define __NR_pkey_mprotect (__NR_Linux + 327) +#define __NR_pkey_alloc (__NR_Linux + 328) +#define __NR_pkey_free (__NR_Linux + 329) +#define __NR_statx (__NR_Linux + 330) +#define __NR_rseq (__NR_Linux + 331) +#define __NR_io_pgetevents (__NR_Linux + 332) +#define __NR_clock_gettime64 (__NR_Linux + 403) +#define __NR_clock_settime64 (__NR_Linux + 404) +#define __NR_clock_adjtime64 (__NR_Linux + 405) +#define __NR_clock_getres_time64 (__NR_Linux + 406) +#define __NR_clock_nanosleep_time64 (__NR_Linux + 407) +#define __NR_timer_gettime64 (__NR_Linux + 408) +#define __NR_timer_settime64 (__NR_Linux + 409) +#define __NR_timerfd_gettime64 (__NR_Linux + 410) +#define __NR_timerfd_settime64 (__NR_Linux + 411) +#define __NR_utimensat_time64 (__NR_Linux + 412) +#define __NR_pselect6_time64 (__NR_Linux + 413) +#define __NR_ppoll_time64 (__NR_Linux + 414) +#define __NR_io_pgetevents_time64 (__NR_Linux + 416) +#define __NR_recvmmsg_time64 (__NR_Linux + 417) +#define __NR_mq_timedsend_time64 (__NR_Linux + 418) +#define __NR_mq_timedreceive_time64 (__NR_Linux + 419) +#define __NR_semtimedop_time64 (__NR_Linux + 420) +#define __NR_rt_sigtimedwait_time64 (__NR_Linux + 421) +#define __NR_futex_time64 (__NR_Linux + 422) +#define __NR_sched_rr_get_interval_time64 (__NR_Linux + 423) +#define __NR_pidfd_send_signal (__NR_Linux + 424) +#define __NR_io_uring_setup (__NR_Linux + 425) +#define __NR_io_uring_enter (__NR_Linux + 426) +#define __NR_io_uring_register (__NR_Linux + 427) +#define __NR_open_tree (__NR_Linux + 428) +#define __NR_move_mount (__NR_Linux + 429) +#define __NR_fsopen (__NR_Linux + 430) +#define __NR_fsconfig (__NR_Linux + 431) +#define __NR_fsmount (__NR_Linux + 432) +#define __NR_fspick (__NR_Linux + 433) +#define __NR_pidfd_open (__NR_Linux + 434) +#define __NR_clone3 (__NR_Linux + 435) +#define __NR_close_range (__NR_Linux + 436) +#define __NR_openat2 (__NR_Linux + 437) +#define __NR_pidfd_getfd (__NR_Linux + 438) +#define __NR_faccessat2 (__NR_Linux + 439) +#define __NR_process_madvise (__NR_Linux + 440) +#define __NR_epoll_pwait2 (__NR_Linux + 441) +#define __NR_mount_setattr (__NR_Linux + 442) +#define __NR_quotactl_fd (__NR_Linux + 443) +#define __NR_landlock_create_ruleset (__NR_Linux + 444) +#define __NR_landlock_add_rule (__NR_Linux + 445) +#define __NR_landlock_restrict_self (__NR_Linux + 446) - -#endif /* _ASM_MIPS_UNISTD_N32_H */ +#endif /* _ASM_UNISTD_N32_H */ diff --git a/linux-headers/asm-mips/unistd_n64.h b/linux-headers/asm-mips/unistd_n64.h index 683558a7f8..780e0cead6 100644 --- a/linux-headers/asm-mips/unistd_n64.h +++ b/linux-headers/asm-mips/unistd_n64.h @@ -1,352 +1,356 @@ -#ifndef _ASM_MIPS_UNISTD_N64_H -#define _ASM_MIPS_UNISTD_N64_H +#ifndef _ASM_UNISTD_N64_H +#define _ASM_UNISTD_N64_H -#define __NR_read (__NR_Linux + 0) -#define __NR_write (__NR_Linux + 1) -#define __NR_open (__NR_Linux + 2) -#define __NR_close (__NR_Linux + 3) -#define __NR_stat (__NR_Linux + 4) -#define __NR_fstat (__NR_Linux + 5) -#define __NR_lstat (__NR_Linux + 6) -#define __NR_poll (__NR_Linux + 7) -#define __NR_lseek (__NR_Linux + 8) -#define __NR_mmap (__NR_Linux + 9) -#define __NR_mprotect (__NR_Linux + 10) -#define __NR_munmap (__NR_Linux + 11) -#define __NR_brk (__NR_Linux + 12) -#define __NR_rt_sigaction (__NR_Linux + 13) -#define __NR_rt_sigprocmask (__NR_Linux + 14) -#define __NR_ioctl (__NR_Linux + 15) -#define __NR_pread64 (__NR_Linux + 16) -#define __NR_pwrite64 (__NR_Linux + 17) -#define __NR_readv (__NR_Linux + 18) -#define __NR_writev (__NR_Linux + 19) -#define __NR_access (__NR_Linux + 20) -#define __NR_pipe (__NR_Linux + 21) -#define __NR__newselect (__NR_Linux + 22) -#define __NR_sched_yield (__NR_Linux + 23) -#define __NR_mremap (__NR_Linux + 24) -#define __NR_msync (__NR_Linux + 25) -#define __NR_mincore (__NR_Linux + 26) -#define __NR_madvise (__NR_Linux + 27) -#define __NR_shmget (__NR_Linux + 28) -#define __NR_shmat (__NR_Linux + 29) -#define __NR_shmctl (__NR_Linux + 30) -#define __NR_dup (__NR_Linux + 31) -#define __NR_dup2 (__NR_Linux + 32) -#define __NR_pause (__NR_Linux + 33) -#define __NR_nanosleep (__NR_Linux + 34) -#define __NR_getitimer (__NR_Linux + 35) -#define __NR_setitimer (__NR_Linux + 36) -#define __NR_alarm (__NR_Linux + 37) -#define __NR_getpid (__NR_Linux + 38) -#define __NR_sendfile (__NR_Linux + 39) -#define __NR_socket (__NR_Linux + 40) -#define __NR_connect (__NR_Linux + 41) -#define __NR_accept (__NR_Linux + 42) -#define __NR_sendto (__NR_Linux + 43) -#define __NR_recvfrom (__NR_Linux + 44) -#define __NR_sendmsg (__NR_Linux + 45) -#define __NR_recvmsg (__NR_Linux + 46) -#define __NR_shutdown (__NR_Linux + 47) -#define __NR_bind (__NR_Linux + 48) -#define __NR_listen (__NR_Linux + 49) -#define __NR_getsockname (__NR_Linux + 50) -#define __NR_getpeername (__NR_Linux + 51) -#define __NR_socketpair (__NR_Linux + 52) -#define __NR_setsockopt (__NR_Linux + 53) -#define __NR_getsockopt (__NR_Linux + 54) -#define __NR_clone (__NR_Linux + 55) -#define __NR_fork (__NR_Linux + 56) -#define __NR_execve (__NR_Linux + 57) -#define __NR_exit (__NR_Linux + 58) -#define __NR_wait4 (__NR_Linux + 59) -#define __NR_kill (__NR_Linux + 60) -#define __NR_uname (__NR_Linux + 61) -#define __NR_semget (__NR_Linux + 62) -#define __NR_semop (__NR_Linux + 63) -#define __NR_semctl (__NR_Linux + 64) -#define __NR_shmdt (__NR_Linux + 65) -#define __NR_msgget (__NR_Linux + 66) -#define __NR_msgsnd (__NR_Linux + 67) -#define __NR_msgrcv (__NR_Linux + 68) -#define __NR_msgctl (__NR_Linux + 69) -#define __NR_fcntl (__NR_Linux + 70) -#define __NR_flock (__NR_Linux + 71) -#define __NR_fsync (__NR_Linux + 72) -#define __NR_fdatasync (__NR_Linux + 73) -#define __NR_truncate (__NR_Linux + 74) -#define __NR_ftruncate (__NR_Linux + 75) -#define __NR_getdents (__NR_Linux + 76) -#define __NR_getcwd (__NR_Linux + 77) -#define __NR_chdir (__NR_Linux + 78) -#define __NR_fchdir (__NR_Linux + 79) -#define __NR_rename (__NR_Linux + 80) -#define __NR_mkdir (__NR_Linux + 81) -#define __NR_rmdir (__NR_Linux + 82) -#define __NR_creat (__NR_Linux + 83) -#define __NR_link (__NR_Linux + 84) -#define __NR_unlink (__NR_Linux + 85) -#define __NR_symlink (__NR_Linux + 86) -#define __NR_readlink (__NR_Linux + 87) -#define __NR_chmod (__NR_Linux + 88) -#define __NR_fchmod (__NR_Linux + 89) -#define __NR_chown (__NR_Linux + 90) -#define __NR_fchown (__NR_Linux + 91) -#define __NR_lchown (__NR_Linux + 92) -#define __NR_umask (__NR_Linux + 93) -#define __NR_gettimeofday (__NR_Linux + 94) -#define __NR_getrlimit (__NR_Linux + 95) -#define __NR_getrusage (__NR_Linux + 96) -#define __NR_sysinfo (__NR_Linux + 97) -#define __NR_times (__NR_Linux + 98) -#define __NR_ptrace (__NR_Linux + 99) -#define __NR_getuid (__NR_Linux + 100) -#define __NR_syslog (__NR_Linux + 101) -#define __NR_getgid (__NR_Linux + 102) -#define __NR_setuid (__NR_Linux + 103) -#define __NR_setgid (__NR_Linux + 104) -#define __NR_geteuid (__NR_Linux + 105) -#define __NR_getegid (__NR_Linux + 106) -#define __NR_setpgid (__NR_Linux + 107) -#define __NR_getppid (__NR_Linux + 108) -#define __NR_getpgrp (__NR_Linux + 109) -#define __NR_setsid (__NR_Linux + 110) -#define __NR_setreuid (__NR_Linux + 111) -#define __NR_setregid (__NR_Linux + 112) -#define __NR_getgroups (__NR_Linux + 113) -#define __NR_setgroups (__NR_Linux + 114) -#define __NR_setresuid (__NR_Linux + 115) -#define __NR_getresuid (__NR_Linux + 116) -#define __NR_setresgid (__NR_Linux + 117) -#define __NR_getresgid (__NR_Linux + 118) -#define __NR_getpgid (__NR_Linux + 119) -#define __NR_setfsuid (__NR_Linux + 120) -#define __NR_setfsgid (__NR_Linux + 121) -#define __NR_getsid (__NR_Linux + 122) -#define __NR_capget (__NR_Linux + 123) -#define __NR_capset (__NR_Linux + 124) -#define __NR_rt_sigpending (__NR_Linux + 125) -#define __NR_rt_sigtimedwait (__NR_Linux + 126) -#define __NR_rt_sigqueueinfo (__NR_Linux + 127) -#define __NR_rt_sigsuspend (__NR_Linux + 128) -#define __NR_sigaltstack (__NR_Linux + 129) -#define __NR_utime (__NR_Linux + 130) -#define __NR_mknod (__NR_Linux + 131) -#define __NR_personality (__NR_Linux + 132) -#define __NR_ustat (__NR_Linux + 133) -#define __NR_statfs (__NR_Linux + 134) -#define __NR_fstatfs (__NR_Linux + 135) -#define __NR_sysfs (__NR_Linux + 136) -#define __NR_getpriority (__NR_Linux + 137) -#define __NR_setpriority (__NR_Linux + 138) -#define __NR_sched_setparam (__NR_Linux + 139) -#define __NR_sched_getparam (__NR_Linux + 140) -#define __NR_sched_setscheduler (__NR_Linux + 141) -#define __NR_sched_getscheduler (__NR_Linux + 142) -#define __NR_sched_get_priority_max (__NR_Linux + 143) -#define __NR_sched_get_priority_min (__NR_Linux + 144) -#define __NR_sched_rr_get_interval (__NR_Linux + 145) -#define __NR_mlock (__NR_Linux + 146) -#define __NR_munlock (__NR_Linux + 147) -#define __NR_mlockall (__NR_Linux + 148) -#define __NR_munlockall (__NR_Linux + 149) -#define __NR_vhangup (__NR_Linux + 150) -#define __NR_pivot_root (__NR_Linux + 151) -#define __NR__sysctl (__NR_Linux + 152) -#define __NR_prctl (__NR_Linux + 153) -#define __NR_adjtimex (__NR_Linux + 154) -#define __NR_setrlimit (__NR_Linux + 155) -#define __NR_chroot (__NR_Linux + 156) -#define __NR_sync (__NR_Linux + 157) -#define __NR_acct (__NR_Linux + 158) -#define __NR_settimeofday (__NR_Linux + 159) -#define __NR_mount (__NR_Linux + 160) -#define __NR_umount2 (__NR_Linux + 161) -#define __NR_swapon (__NR_Linux + 162) -#define __NR_swapoff (__NR_Linux + 163) -#define __NR_reboot (__NR_Linux + 164) -#define __NR_sethostname (__NR_Linux + 165) -#define __NR_setdomainname (__NR_Linux + 166) -#define __NR_create_module (__NR_Linux + 167) -#define __NR_init_module (__NR_Linux + 168) -#define __NR_delete_module (__NR_Linux + 169) -#define __NR_get_kernel_syms (__NR_Linux + 170) -#define __NR_query_module (__NR_Linux + 171) -#define __NR_quotactl (__NR_Linux + 172) -#define __NR_nfsservctl (__NR_Linux + 173) -#define __NR_getpmsg (__NR_Linux + 174) -#define __NR_putpmsg (__NR_Linux + 175) -#define __NR_afs_syscall (__NR_Linux + 176) -#define __NR_reserved177 (__NR_Linux + 177) -#define __NR_gettid (__NR_Linux + 178) -#define __NR_readahead (__NR_Linux + 179) -#define __NR_setxattr (__NR_Linux + 180) -#define __NR_lsetxattr (__NR_Linux + 181) -#define __NR_fsetxattr (__NR_Linux + 182) -#define __NR_getxattr (__NR_Linux + 183) -#define __NR_lgetxattr (__NR_Linux + 184) -#define __NR_fgetxattr (__NR_Linux + 185) -#define __NR_listxattr (__NR_Linux + 186) -#define __NR_llistxattr (__NR_Linux + 187) -#define __NR_flistxattr (__NR_Linux + 188) -#define __NR_removexattr (__NR_Linux + 189) -#define __NR_lremovexattr (__NR_Linux + 190) -#define __NR_fremovexattr (__NR_Linux + 191) -#define __NR_tkill (__NR_Linux + 192) -#define __NR_reserved193 (__NR_Linux + 193) -#define __NR_futex (__NR_Linux + 194) -#define __NR_sched_setaffinity (__NR_Linux + 195) -#define __NR_sched_getaffinity (__NR_Linux + 196) -#define __NR_cacheflush (__NR_Linux + 197) -#define __NR_cachectl (__NR_Linux + 198) -#define __NR_sysmips (__NR_Linux + 199) -#define __NR_io_setup (__NR_Linux + 200) -#define __NR_io_destroy (__NR_Linux + 201) -#define __NR_io_getevents (__NR_Linux + 202) -#define __NR_io_submit (__NR_Linux + 203) -#define __NR_io_cancel (__NR_Linux + 204) -#define __NR_exit_group (__NR_Linux + 205) -#define __NR_lookup_dcookie (__NR_Linux + 206) -#define __NR_epoll_create (__NR_Linux + 207) -#define __NR_epoll_ctl (__NR_Linux + 208) -#define __NR_epoll_wait (__NR_Linux + 209) -#define __NR_remap_file_pages (__NR_Linux + 210) -#define __NR_rt_sigreturn (__NR_Linux + 211) -#define __NR_set_tid_address (__NR_Linux + 212) -#define __NR_restart_syscall (__NR_Linux + 213) -#define __NR_semtimedop (__NR_Linux + 214) -#define __NR_fadvise64 (__NR_Linux + 215) -#define __NR_timer_create (__NR_Linux + 216) -#define __NR_timer_settime (__NR_Linux + 217) -#define __NR_timer_gettime (__NR_Linux + 218) -#define __NR_timer_getoverrun (__NR_Linux + 219) -#define __NR_timer_delete (__NR_Linux + 220) -#define __NR_clock_settime (__NR_Linux + 221) -#define __NR_clock_gettime (__NR_Linux + 222) -#define __NR_clock_getres (__NR_Linux + 223) -#define __NR_clock_nanosleep (__NR_Linux + 224) -#define __NR_tgkill (__NR_Linux + 225) -#define __NR_utimes (__NR_Linux + 226) -#define __NR_mbind (__NR_Linux + 227) -#define __NR_get_mempolicy (__NR_Linux + 228) -#define __NR_set_mempolicy (__NR_Linux + 229) -#define __NR_mq_open (__NR_Linux + 230) -#define __NR_mq_unlink (__NR_Linux + 231) -#define __NR_mq_timedsend (__NR_Linux + 232) -#define __NR_mq_timedreceive (__NR_Linux + 233) -#define __NR_mq_notify (__NR_Linux + 234) -#define __NR_mq_getsetattr (__NR_Linux + 235) -#define __NR_vserver (__NR_Linux + 236) -#define __NR_waitid (__NR_Linux + 237) -#define __NR_add_key (__NR_Linux + 239) -#define __NR_request_key (__NR_Linux + 240) -#define __NR_keyctl (__NR_Linux + 241) -#define __NR_set_thread_area (__NR_Linux + 242) -#define __NR_inotify_init (__NR_Linux + 243) -#define __NR_inotify_add_watch (__NR_Linux + 244) -#define __NR_inotify_rm_watch (__NR_Linux + 245) -#define __NR_migrate_pages (__NR_Linux + 246) -#define __NR_openat (__NR_Linux + 247) -#define __NR_mkdirat (__NR_Linux + 248) -#define __NR_mknodat (__NR_Linux + 249) -#define __NR_fchownat (__NR_Linux + 250) -#define __NR_futimesat (__NR_Linux + 251) -#define __NR_newfstatat (__NR_Linux + 252) -#define __NR_unlinkat (__NR_Linux + 253) -#define __NR_renameat (__NR_Linux + 254) -#define __NR_linkat (__NR_Linux + 255) -#define __NR_symlinkat (__NR_Linux + 256) -#define __NR_readlinkat (__NR_Linux + 257) -#define __NR_fchmodat (__NR_Linux + 258) -#define __NR_faccessat (__NR_Linux + 259) -#define __NR_pselect6 (__NR_Linux + 260) -#define __NR_ppoll (__NR_Linux + 261) -#define __NR_unshare (__NR_Linux + 262) -#define __NR_splice (__NR_Linux + 263) -#define __NR_sync_file_range (__NR_Linux + 264) -#define __NR_tee (__NR_Linux + 265) -#define __NR_vmsplice (__NR_Linux + 266) -#define __NR_move_pages (__NR_Linux + 267) -#define __NR_set_robust_list (__NR_Linux + 268) -#define __NR_get_robust_list (__NR_Linux + 269) -#define __NR_kexec_load (__NR_Linux + 270) -#define __NR_getcpu (__NR_Linux + 271) -#define __NR_epoll_pwait (__NR_Linux + 272) -#define __NR_ioprio_set (__NR_Linux + 273) -#define __NR_ioprio_get (__NR_Linux + 274) -#define __NR_utimensat (__NR_Linux + 275) -#define __NR_signalfd (__NR_Linux + 276) -#define __NR_timerfd (__NR_Linux + 277) -#define __NR_eventfd (__NR_Linux + 278) -#define __NR_fallocate (__NR_Linux + 279) -#define __NR_timerfd_create (__NR_Linux + 280) -#define __NR_timerfd_gettime (__NR_Linux + 281) -#define __NR_timerfd_settime (__NR_Linux + 282) -#define __NR_signalfd4 (__NR_Linux + 283) -#define __NR_eventfd2 (__NR_Linux + 284) -#define __NR_epoll_create1 (__NR_Linux + 285) -#define __NR_dup3 (__NR_Linux + 286) -#define __NR_pipe2 (__NR_Linux + 287) -#define __NR_inotify_init1 (__NR_Linux + 288) -#define __NR_preadv (__NR_Linux + 289) -#define __NR_pwritev (__NR_Linux + 290) -#define __NR_rt_tgsigqueueinfo (__NR_Linux + 291) -#define __NR_perf_event_open (__NR_Linux + 292) -#define __NR_accept4 (__NR_Linux + 293) -#define __NR_recvmmsg (__NR_Linux + 294) -#define __NR_fanotify_init (__NR_Linux + 295) -#define __NR_fanotify_mark (__NR_Linux + 296) -#define __NR_prlimit64 (__NR_Linux + 297) -#define __NR_name_to_handle_at (__NR_Linux + 298) -#define __NR_open_by_handle_at (__NR_Linux + 299) -#define __NR_clock_adjtime (__NR_Linux + 300) -#define __NR_syncfs (__NR_Linux + 301) -#define __NR_sendmmsg (__NR_Linux + 302) -#define __NR_setns (__NR_Linux + 303) -#define __NR_process_vm_readv (__NR_Linux + 304) -#define __NR_process_vm_writev (__NR_Linux + 305) -#define __NR_kcmp (__NR_Linux + 306) -#define __NR_finit_module (__NR_Linux + 307) -#define __NR_getdents64 (__NR_Linux + 308) -#define __NR_sched_setattr (__NR_Linux + 309) -#define __NR_sched_getattr (__NR_Linux + 310) -#define __NR_renameat2 (__NR_Linux + 311) -#define __NR_seccomp (__NR_Linux + 312) -#define __NR_getrandom (__NR_Linux + 313) -#define __NR_memfd_create (__NR_Linux + 314) -#define __NR_bpf (__NR_Linux + 315) -#define __NR_execveat (__NR_Linux + 316) -#define __NR_userfaultfd (__NR_Linux + 317) -#define __NR_membarrier (__NR_Linux + 318) -#define __NR_mlock2 (__NR_Linux + 319) -#define __NR_copy_file_range (__NR_Linux + 320) -#define __NR_preadv2 (__NR_Linux + 321) -#define __NR_pwritev2 (__NR_Linux + 322) -#define __NR_pkey_mprotect (__NR_Linux + 323) -#define __NR_pkey_alloc (__NR_Linux + 324) -#define __NR_pkey_free (__NR_Linux + 325) -#define __NR_statx (__NR_Linux + 326) -#define __NR_rseq (__NR_Linux + 327) -#define __NR_io_pgetevents (__NR_Linux + 328) -#define __NR_pidfd_send_signal (__NR_Linux + 424) -#define __NR_io_uring_setup (__NR_Linux + 425) -#define __NR_io_uring_enter (__NR_Linux + 426) -#define __NR_io_uring_register (__NR_Linux + 427) -#define __NR_open_tree (__NR_Linux + 428) -#define __NR_move_mount (__NR_Linux + 429) -#define __NR_fsopen (__NR_Linux + 430) -#define __NR_fsconfig (__NR_Linux + 431) -#define __NR_fsmount (__NR_Linux + 432) -#define __NR_fspick (__NR_Linux + 433) -#define __NR_pidfd_open (__NR_Linux + 434) -#define __NR_clone3 (__NR_Linux + 435) -#define __NR_close_range (__NR_Linux + 436) -#define __NR_openat2 (__NR_Linux + 437) -#define __NR_pidfd_getfd (__NR_Linux + 438) -#define __NR_faccessat2 (__NR_Linux + 439) -#define __NR_process_madvise (__NR_Linux + 440) -#define __NR_epoll_pwait2 (__NR_Linux + 441) +#define __NR_read (__NR_Linux + 0) +#define __NR_write (__NR_Linux + 1) +#define __NR_open (__NR_Linux + 2) +#define __NR_close (__NR_Linux + 3) +#define __NR_stat (__NR_Linux + 4) +#define __NR_fstat (__NR_Linux + 5) +#define __NR_lstat (__NR_Linux + 6) +#define __NR_poll (__NR_Linux + 7) +#define __NR_lseek (__NR_Linux + 8) +#define __NR_mmap (__NR_Linux + 9) +#define __NR_mprotect (__NR_Linux + 10) +#define __NR_munmap (__NR_Linux + 11) +#define __NR_brk (__NR_Linux + 12) +#define __NR_rt_sigaction (__NR_Linux + 13) +#define __NR_rt_sigprocmask (__NR_Linux + 14) +#define __NR_ioctl (__NR_Linux + 15) +#define __NR_pread64 (__NR_Linux + 16) +#define __NR_pwrite64 (__NR_Linux + 17) +#define __NR_readv (__NR_Linux + 18) +#define __NR_writev (__NR_Linux + 19) +#define __NR_access (__NR_Linux + 20) +#define __NR_pipe (__NR_Linux + 21) +#define __NR__newselect (__NR_Linux + 22) +#define __NR_sched_yield (__NR_Linux + 23) +#define __NR_mremap (__NR_Linux + 24) +#define __NR_msync (__NR_Linux + 25) +#define __NR_mincore (__NR_Linux + 26) +#define __NR_madvise (__NR_Linux + 27) +#define __NR_shmget (__NR_Linux + 28) +#define __NR_shmat (__NR_Linux + 29) +#define __NR_shmctl (__NR_Linux + 30) +#define __NR_dup (__NR_Linux + 31) +#define __NR_dup2 (__NR_Linux + 32) +#define __NR_pause (__NR_Linux + 33) +#define __NR_nanosleep (__NR_Linux + 34) +#define __NR_getitimer (__NR_Linux + 35) +#define __NR_setitimer (__NR_Linux + 36) +#define __NR_alarm (__NR_Linux + 37) +#define __NR_getpid (__NR_Linux + 38) +#define __NR_sendfile (__NR_Linux + 39) +#define __NR_socket (__NR_Linux + 40) +#define __NR_connect (__NR_Linux + 41) +#define __NR_accept (__NR_Linux + 42) +#define __NR_sendto (__NR_Linux + 43) +#define __NR_recvfrom (__NR_Linux + 44) +#define __NR_sendmsg (__NR_Linux + 45) +#define __NR_recvmsg (__NR_Linux + 46) +#define __NR_shutdown (__NR_Linux + 47) +#define __NR_bind (__NR_Linux + 48) +#define __NR_listen (__NR_Linux + 49) +#define __NR_getsockname (__NR_Linux + 50) +#define __NR_getpeername (__NR_Linux + 51) +#define __NR_socketpair (__NR_Linux + 52) +#define __NR_setsockopt (__NR_Linux + 53) +#define __NR_getsockopt (__NR_Linux + 54) +#define __NR_clone (__NR_Linux + 55) +#define __NR_fork (__NR_Linux + 56) +#define __NR_execve (__NR_Linux + 57) +#define __NR_exit (__NR_Linux + 58) +#define __NR_wait4 (__NR_Linux + 59) +#define __NR_kill (__NR_Linux + 60) +#define __NR_uname (__NR_Linux + 61) +#define __NR_semget (__NR_Linux + 62) +#define __NR_semop (__NR_Linux + 63) +#define __NR_semctl (__NR_Linux + 64) +#define __NR_shmdt (__NR_Linux + 65) +#define __NR_msgget (__NR_Linux + 66) +#define __NR_msgsnd (__NR_Linux + 67) +#define __NR_msgrcv (__NR_Linux + 68) +#define __NR_msgctl (__NR_Linux + 69) +#define __NR_fcntl (__NR_Linux + 70) +#define __NR_flock (__NR_Linux + 71) +#define __NR_fsync (__NR_Linux + 72) +#define __NR_fdatasync (__NR_Linux + 73) +#define __NR_truncate (__NR_Linux + 74) +#define __NR_ftruncate (__NR_Linux + 75) +#define __NR_getdents (__NR_Linux + 76) +#define __NR_getcwd (__NR_Linux + 77) +#define __NR_chdir (__NR_Linux + 78) +#define __NR_fchdir (__NR_Linux + 79) +#define __NR_rename (__NR_Linux + 80) +#define __NR_mkdir (__NR_Linux + 81) +#define __NR_rmdir (__NR_Linux + 82) +#define __NR_creat (__NR_Linux + 83) +#define __NR_link (__NR_Linux + 84) +#define __NR_unlink (__NR_Linux + 85) +#define __NR_symlink (__NR_Linux + 86) +#define __NR_readlink (__NR_Linux + 87) +#define __NR_chmod (__NR_Linux + 88) +#define __NR_fchmod (__NR_Linux + 89) +#define __NR_chown (__NR_Linux + 90) +#define __NR_fchown (__NR_Linux + 91) +#define __NR_lchown (__NR_Linux + 92) +#define __NR_umask (__NR_Linux + 93) +#define __NR_gettimeofday (__NR_Linux + 94) +#define __NR_getrlimit (__NR_Linux + 95) +#define __NR_getrusage (__NR_Linux + 96) +#define __NR_sysinfo (__NR_Linux + 97) +#define __NR_times (__NR_Linux + 98) +#define __NR_ptrace (__NR_Linux + 99) +#define __NR_getuid (__NR_Linux + 100) +#define __NR_syslog (__NR_Linux + 101) +#define __NR_getgid (__NR_Linux + 102) +#define __NR_setuid (__NR_Linux + 103) +#define __NR_setgid (__NR_Linux + 104) +#define __NR_geteuid (__NR_Linux + 105) +#define __NR_getegid (__NR_Linux + 106) +#define __NR_setpgid (__NR_Linux + 107) +#define __NR_getppid (__NR_Linux + 108) +#define __NR_getpgrp (__NR_Linux + 109) +#define __NR_setsid (__NR_Linux + 110) +#define __NR_setreuid (__NR_Linux + 111) +#define __NR_setregid (__NR_Linux + 112) +#define __NR_getgroups (__NR_Linux + 113) +#define __NR_setgroups (__NR_Linux + 114) +#define __NR_setresuid (__NR_Linux + 115) +#define __NR_getresuid (__NR_Linux + 116) +#define __NR_setresgid (__NR_Linux + 117) +#define __NR_getresgid (__NR_Linux + 118) +#define __NR_getpgid (__NR_Linux + 119) +#define __NR_setfsuid (__NR_Linux + 120) +#define __NR_setfsgid (__NR_Linux + 121) +#define __NR_getsid (__NR_Linux + 122) +#define __NR_capget (__NR_Linux + 123) +#define __NR_capset (__NR_Linux + 124) +#define __NR_rt_sigpending (__NR_Linux + 125) +#define __NR_rt_sigtimedwait (__NR_Linux + 126) +#define __NR_rt_sigqueueinfo (__NR_Linux + 127) +#define __NR_rt_sigsuspend (__NR_Linux + 128) +#define __NR_sigaltstack (__NR_Linux + 129) +#define __NR_utime (__NR_Linux + 130) +#define __NR_mknod (__NR_Linux + 131) +#define __NR_personality (__NR_Linux + 132) +#define __NR_ustat (__NR_Linux + 133) +#define __NR_statfs (__NR_Linux + 134) +#define __NR_fstatfs (__NR_Linux + 135) +#define __NR_sysfs (__NR_Linux + 136) +#define __NR_getpriority (__NR_Linux + 137) +#define __NR_setpriority (__NR_Linux + 138) +#define __NR_sched_setparam (__NR_Linux + 139) +#define __NR_sched_getparam (__NR_Linux + 140) +#define __NR_sched_setscheduler (__NR_Linux + 141) +#define __NR_sched_getscheduler (__NR_Linux + 142) +#define __NR_sched_get_priority_max (__NR_Linux + 143) +#define __NR_sched_get_priority_min (__NR_Linux + 144) +#define __NR_sched_rr_get_interval (__NR_Linux + 145) +#define __NR_mlock (__NR_Linux + 146) +#define __NR_munlock (__NR_Linux + 147) +#define __NR_mlockall (__NR_Linux + 148) +#define __NR_munlockall (__NR_Linux + 149) +#define __NR_vhangup (__NR_Linux + 150) +#define __NR_pivot_root (__NR_Linux + 151) +#define __NR__sysctl (__NR_Linux + 152) +#define __NR_prctl (__NR_Linux + 153) +#define __NR_adjtimex (__NR_Linux + 154) +#define __NR_setrlimit (__NR_Linux + 155) +#define __NR_chroot (__NR_Linux + 156) +#define __NR_sync (__NR_Linux + 157) +#define __NR_acct (__NR_Linux + 158) +#define __NR_settimeofday (__NR_Linux + 159) +#define __NR_mount (__NR_Linux + 160) +#define __NR_umount2 (__NR_Linux + 161) +#define __NR_swapon (__NR_Linux + 162) +#define __NR_swapoff (__NR_Linux + 163) +#define __NR_reboot (__NR_Linux + 164) +#define __NR_sethostname (__NR_Linux + 165) +#define __NR_setdomainname (__NR_Linux + 166) +#define __NR_create_module (__NR_Linux + 167) +#define __NR_init_module (__NR_Linux + 168) +#define __NR_delete_module (__NR_Linux + 169) +#define __NR_get_kernel_syms (__NR_Linux + 170) +#define __NR_query_module (__NR_Linux + 171) +#define __NR_quotactl (__NR_Linux + 172) +#define __NR_nfsservctl (__NR_Linux + 173) +#define __NR_getpmsg (__NR_Linux + 174) +#define __NR_putpmsg (__NR_Linux + 175) +#define __NR_afs_syscall (__NR_Linux + 176) +#define __NR_reserved177 (__NR_Linux + 177) +#define __NR_gettid (__NR_Linux + 178) +#define __NR_readahead (__NR_Linux + 179) +#define __NR_setxattr (__NR_Linux + 180) +#define __NR_lsetxattr (__NR_Linux + 181) +#define __NR_fsetxattr (__NR_Linux + 182) +#define __NR_getxattr (__NR_Linux + 183) +#define __NR_lgetxattr (__NR_Linux + 184) +#define __NR_fgetxattr (__NR_Linux + 185) +#define __NR_listxattr (__NR_Linux + 186) +#define __NR_llistxattr (__NR_Linux + 187) +#define __NR_flistxattr (__NR_Linux + 188) +#define __NR_removexattr (__NR_Linux + 189) +#define __NR_lremovexattr (__NR_Linux + 190) +#define __NR_fremovexattr (__NR_Linux + 191) +#define __NR_tkill (__NR_Linux + 192) +#define __NR_reserved193 (__NR_Linux + 193) +#define __NR_futex (__NR_Linux + 194) +#define __NR_sched_setaffinity (__NR_Linux + 195) +#define __NR_sched_getaffinity (__NR_Linux + 196) +#define __NR_cacheflush (__NR_Linux + 197) +#define __NR_cachectl (__NR_Linux + 198) +#define __NR_sysmips (__NR_Linux + 199) +#define __NR_io_setup (__NR_Linux + 200) +#define __NR_io_destroy (__NR_Linux + 201) +#define __NR_io_getevents (__NR_Linux + 202) +#define __NR_io_submit (__NR_Linux + 203) +#define __NR_io_cancel (__NR_Linux + 204) +#define __NR_exit_group (__NR_Linux + 205) +#define __NR_lookup_dcookie (__NR_Linux + 206) +#define __NR_epoll_create (__NR_Linux + 207) +#define __NR_epoll_ctl (__NR_Linux + 208) +#define __NR_epoll_wait (__NR_Linux + 209) +#define __NR_remap_file_pages (__NR_Linux + 210) +#define __NR_rt_sigreturn (__NR_Linux + 211) +#define __NR_set_tid_address (__NR_Linux + 212) +#define __NR_restart_syscall (__NR_Linux + 213) +#define __NR_semtimedop (__NR_Linux + 214) +#define __NR_fadvise64 (__NR_Linux + 215) +#define __NR_timer_create (__NR_Linux + 216) +#define __NR_timer_settime (__NR_Linux + 217) +#define __NR_timer_gettime (__NR_Linux + 218) +#define __NR_timer_getoverrun (__NR_Linux + 219) +#define __NR_timer_delete (__NR_Linux + 220) +#define __NR_clock_settime (__NR_Linux + 221) +#define __NR_clock_gettime (__NR_Linux + 222) +#define __NR_clock_getres (__NR_Linux + 223) +#define __NR_clock_nanosleep (__NR_Linux + 224) +#define __NR_tgkill (__NR_Linux + 225) +#define __NR_utimes (__NR_Linux + 226) +#define __NR_mbind (__NR_Linux + 227) +#define __NR_get_mempolicy (__NR_Linux + 228) +#define __NR_set_mempolicy (__NR_Linux + 229) +#define __NR_mq_open (__NR_Linux + 230) +#define __NR_mq_unlink (__NR_Linux + 231) +#define __NR_mq_timedsend (__NR_Linux + 232) +#define __NR_mq_timedreceive (__NR_Linux + 233) +#define __NR_mq_notify (__NR_Linux + 234) +#define __NR_mq_getsetattr (__NR_Linux + 235) +#define __NR_vserver (__NR_Linux + 236) +#define __NR_waitid (__NR_Linux + 237) +#define __NR_add_key (__NR_Linux + 239) +#define __NR_request_key (__NR_Linux + 240) +#define __NR_keyctl (__NR_Linux + 241) +#define __NR_set_thread_area (__NR_Linux + 242) +#define __NR_inotify_init (__NR_Linux + 243) +#define __NR_inotify_add_watch (__NR_Linux + 244) +#define __NR_inotify_rm_watch (__NR_Linux + 245) +#define __NR_migrate_pages (__NR_Linux + 246) +#define __NR_openat (__NR_Linux + 247) +#define __NR_mkdirat (__NR_Linux + 248) +#define __NR_mknodat (__NR_Linux + 249) +#define __NR_fchownat (__NR_Linux + 250) +#define __NR_futimesat (__NR_Linux + 251) +#define __NR_newfstatat (__NR_Linux + 252) +#define __NR_unlinkat (__NR_Linux + 253) +#define __NR_renameat (__NR_Linux + 254) +#define __NR_linkat (__NR_Linux + 255) +#define __NR_symlinkat (__NR_Linux + 256) +#define __NR_readlinkat (__NR_Linux + 257) +#define __NR_fchmodat (__NR_Linux + 258) +#define __NR_faccessat (__NR_Linux + 259) +#define __NR_pselect6 (__NR_Linux + 260) +#define __NR_ppoll (__NR_Linux + 261) +#define __NR_unshare (__NR_Linux + 262) +#define __NR_splice (__NR_Linux + 263) +#define __NR_sync_file_range (__NR_Linux + 264) +#define __NR_tee (__NR_Linux + 265) +#define __NR_vmsplice (__NR_Linux + 266) +#define __NR_move_pages (__NR_Linux + 267) +#define __NR_set_robust_list (__NR_Linux + 268) +#define __NR_get_robust_list (__NR_Linux + 269) +#define __NR_kexec_load (__NR_Linux + 270) +#define __NR_getcpu (__NR_Linux + 271) +#define __NR_epoll_pwait (__NR_Linux + 272) +#define __NR_ioprio_set (__NR_Linux + 273) +#define __NR_ioprio_get (__NR_Linux + 274) +#define __NR_utimensat (__NR_Linux + 275) +#define __NR_signalfd (__NR_Linux + 276) +#define __NR_timerfd (__NR_Linux + 277) +#define __NR_eventfd (__NR_Linux + 278) +#define __NR_fallocate (__NR_Linux + 279) +#define __NR_timerfd_create (__NR_Linux + 280) +#define __NR_timerfd_gettime (__NR_Linux + 281) +#define __NR_timerfd_settime (__NR_Linux + 282) +#define __NR_signalfd4 (__NR_Linux + 283) +#define __NR_eventfd2 (__NR_Linux + 284) +#define __NR_epoll_create1 (__NR_Linux + 285) +#define __NR_dup3 (__NR_Linux + 286) +#define __NR_pipe2 (__NR_Linux + 287) +#define __NR_inotify_init1 (__NR_Linux + 288) +#define __NR_preadv (__NR_Linux + 289) +#define __NR_pwritev (__NR_Linux + 290) +#define __NR_rt_tgsigqueueinfo (__NR_Linux + 291) +#define __NR_perf_event_open (__NR_Linux + 292) +#define __NR_accept4 (__NR_Linux + 293) +#define __NR_recvmmsg (__NR_Linux + 294) +#define __NR_fanotify_init (__NR_Linux + 295) +#define __NR_fanotify_mark (__NR_Linux + 296) +#define __NR_prlimit64 (__NR_Linux + 297) +#define __NR_name_to_handle_at (__NR_Linux + 298) +#define __NR_open_by_handle_at (__NR_Linux + 299) +#define __NR_clock_adjtime (__NR_Linux + 300) +#define __NR_syncfs (__NR_Linux + 301) +#define __NR_sendmmsg (__NR_Linux + 302) +#define __NR_setns (__NR_Linux + 303) +#define __NR_process_vm_readv (__NR_Linux + 304) +#define __NR_process_vm_writev (__NR_Linux + 305) +#define __NR_kcmp (__NR_Linux + 306) +#define __NR_finit_module (__NR_Linux + 307) +#define __NR_getdents64 (__NR_Linux + 308) +#define __NR_sched_setattr (__NR_Linux + 309) +#define __NR_sched_getattr (__NR_Linux + 310) +#define __NR_renameat2 (__NR_Linux + 311) +#define __NR_seccomp (__NR_Linux + 312) +#define __NR_getrandom (__NR_Linux + 313) +#define __NR_memfd_create (__NR_Linux + 314) +#define __NR_bpf (__NR_Linux + 315) +#define __NR_execveat (__NR_Linux + 316) +#define __NR_userfaultfd (__NR_Linux + 317) +#define __NR_membarrier (__NR_Linux + 318) +#define __NR_mlock2 (__NR_Linux + 319) +#define __NR_copy_file_range (__NR_Linux + 320) +#define __NR_preadv2 (__NR_Linux + 321) +#define __NR_pwritev2 (__NR_Linux + 322) +#define __NR_pkey_mprotect (__NR_Linux + 323) +#define __NR_pkey_alloc (__NR_Linux + 324) +#define __NR_pkey_free (__NR_Linux + 325) +#define __NR_statx (__NR_Linux + 326) +#define __NR_rseq (__NR_Linux + 327) +#define __NR_io_pgetevents (__NR_Linux + 328) +#define __NR_pidfd_send_signal (__NR_Linux + 424) +#define __NR_io_uring_setup (__NR_Linux + 425) +#define __NR_io_uring_enter (__NR_Linux + 426) +#define __NR_io_uring_register (__NR_Linux + 427) +#define __NR_open_tree (__NR_Linux + 428) +#define __NR_move_mount (__NR_Linux + 429) +#define __NR_fsopen (__NR_Linux + 430) +#define __NR_fsconfig (__NR_Linux + 431) +#define __NR_fsmount (__NR_Linux + 432) +#define __NR_fspick (__NR_Linux + 433) +#define __NR_pidfd_open (__NR_Linux + 434) +#define __NR_clone3 (__NR_Linux + 435) +#define __NR_close_range (__NR_Linux + 436) +#define __NR_openat2 (__NR_Linux + 437) +#define __NR_pidfd_getfd (__NR_Linux + 438) +#define __NR_faccessat2 (__NR_Linux + 439) +#define __NR_process_madvise (__NR_Linux + 440) +#define __NR_epoll_pwait2 (__NR_Linux + 441) +#define __NR_mount_setattr (__NR_Linux + 442) +#define __NR_quotactl_fd (__NR_Linux + 443) +#define __NR_landlock_create_ruleset (__NR_Linux + 444) +#define __NR_landlock_add_rule (__NR_Linux + 445) +#define __NR_landlock_restrict_self (__NR_Linux + 446) - -#endif /* _ASM_MIPS_UNISTD_N64_H */ +#endif /* _ASM_UNISTD_N64_H */ diff --git a/linux-headers/asm-mips/unistd_o32.h b/linux-headers/asm-mips/unistd_o32.h index ca6a7e5c0b..06a2b3b55e 100644 --- a/linux-headers/asm-mips/unistd_o32.h +++ b/linux-headers/asm-mips/unistd_o32.h @@ -1,422 +1,426 @@ -#ifndef _ASM_MIPS_UNISTD_O32_H -#define _ASM_MIPS_UNISTD_O32_H +#ifndef _ASM_UNISTD_O32_H +#define _ASM_UNISTD_O32_H -#define __NR_syscall (__NR_Linux + 0) -#define __NR_exit (__NR_Linux + 1) -#define __NR_fork (__NR_Linux + 2) -#define __NR_read (__NR_Linux + 3) -#define __NR_write (__NR_Linux + 4) -#define __NR_open (__NR_Linux + 5) -#define __NR_close (__NR_Linux + 6) -#define __NR_waitpid (__NR_Linux + 7) -#define __NR_creat (__NR_Linux + 8) -#define __NR_link (__NR_Linux + 9) -#define __NR_unlink (__NR_Linux + 10) -#define __NR_execve (__NR_Linux + 11) -#define __NR_chdir (__NR_Linux + 12) -#define __NR_time (__NR_Linux + 13) -#define __NR_mknod (__NR_Linux + 14) -#define __NR_chmod (__NR_Linux + 15) -#define __NR_lchown (__NR_Linux + 16) -#define __NR_break (__NR_Linux + 17) -#define __NR_unused18 (__NR_Linux + 18) -#define __NR_lseek (__NR_Linux + 19) -#define __NR_getpid (__NR_Linux + 20) -#define __NR_mount (__NR_Linux + 21) -#define __NR_umount (__NR_Linux + 22) -#define __NR_setuid (__NR_Linux + 23) -#define __NR_getuid (__NR_Linux + 24) -#define __NR_stime (__NR_Linux + 25) -#define __NR_ptrace (__NR_Linux + 26) -#define __NR_alarm (__NR_Linux + 27) -#define __NR_unused28 (__NR_Linux + 28) -#define __NR_pause (__NR_Linux + 29) -#define __NR_utime (__NR_Linux + 30) -#define __NR_stty (__NR_Linux + 31) -#define __NR_gtty (__NR_Linux + 32) -#define __NR_access (__NR_Linux + 33) -#define __NR_nice (__NR_Linux + 34) -#define __NR_ftime (__NR_Linux + 35) -#define __NR_sync (__NR_Linux + 36) -#define __NR_kill (__NR_Linux + 37) -#define __NR_rename (__NR_Linux + 38) -#define __NR_mkdir (__NR_Linux + 39) -#define __NR_rmdir (__NR_Linux + 40) -#define __NR_dup (__NR_Linux + 41) -#define __NR_pipe (__NR_Linux + 42) -#define __NR_times (__NR_Linux + 43) -#define __NR_prof (__NR_Linux + 44) -#define __NR_brk (__NR_Linux + 45) -#define __NR_setgid (__NR_Linux + 46) -#define __NR_getgid (__NR_Linux + 47) -#define __NR_signal (__NR_Linux + 48) -#define __NR_geteuid (__NR_Linux + 49) -#define __NR_getegid (__NR_Linux + 50) -#define __NR_acct (__NR_Linux + 51) -#define __NR_umount2 (__NR_Linux + 52) -#define __NR_lock (__NR_Linux + 53) -#define __NR_ioctl (__NR_Linux + 54) -#define __NR_fcntl (__NR_Linux + 55) -#define __NR_mpx (__NR_Linux + 56) -#define __NR_setpgid (__NR_Linux + 57) -#define __NR_ulimit (__NR_Linux + 58) -#define __NR_unused59 (__NR_Linux + 59) -#define __NR_umask (__NR_Linux + 60) -#define __NR_chroot (__NR_Linux + 61) -#define __NR_ustat (__NR_Linux + 62) -#define __NR_dup2 (__NR_Linux + 63) -#define __NR_getppid (__NR_Linux + 64) -#define __NR_getpgrp (__NR_Linux + 65) -#define __NR_setsid (__NR_Linux + 66) -#define __NR_sigaction (__NR_Linux + 67) -#define __NR_sgetmask (__NR_Linux + 68) -#define __NR_ssetmask (__NR_Linux + 69) -#define __NR_setreuid (__NR_Linux + 70) -#define __NR_setregid (__NR_Linux + 71) -#define __NR_sigsuspend (__NR_Linux + 72) -#define __NR_sigpending (__NR_Linux + 73) -#define __NR_sethostname (__NR_Linux + 74) -#define __NR_setrlimit (__NR_Linux + 75) -#define __NR_getrlimit (__NR_Linux + 76) -#define __NR_getrusage (__NR_Linux + 77) -#define __NR_gettimeofday (__NR_Linux + 78) -#define __NR_settimeofday (__NR_Linux + 79) -#define __NR_getgroups (__NR_Linux + 80) -#define __NR_setgroups (__NR_Linux + 81) -#define __NR_reserved82 (__NR_Linux + 82) -#define __NR_symlink (__NR_Linux + 83) -#define __NR_unused84 (__NR_Linux + 84) -#define __NR_readlink (__NR_Linux + 85) -#define __NR_uselib (__NR_Linux + 86) -#define __NR_swapon (__NR_Linux + 87) -#define __NR_reboot (__NR_Linux + 88) -#define __NR_readdir (__NR_Linux + 89) -#define __NR_mmap (__NR_Linux + 90) -#define __NR_munmap (__NR_Linux + 91) -#define __NR_truncate (__NR_Linux + 92) -#define __NR_ftruncate (__NR_Linux + 93) -#define __NR_fchmod (__NR_Linux + 94) -#define __NR_fchown (__NR_Linux + 95) -#define __NR_getpriority (__NR_Linux + 96) -#define __NR_setpriority (__NR_Linux + 97) -#define __NR_profil (__NR_Linux + 98) -#define __NR_statfs (__NR_Linux + 99) -#define __NR_fstatfs (__NR_Linux + 100) -#define __NR_ioperm (__NR_Linux + 101) -#define __NR_socketcall (__NR_Linux + 102) -#define __NR_syslog (__NR_Linux + 103) -#define __NR_setitimer (__NR_Linux + 104) -#define __NR_getitimer (__NR_Linux + 105) -#define __NR_stat (__NR_Linux + 106) -#define __NR_lstat (__NR_Linux + 107) -#define __NR_fstat (__NR_Linux + 108) -#define __NR_unused109 (__NR_Linux + 109) -#define __NR_iopl (__NR_Linux + 110) -#define __NR_vhangup (__NR_Linux + 111) -#define __NR_idle (__NR_Linux + 112) -#define __NR_vm86 (__NR_Linux + 113) -#define __NR_wait4 (__NR_Linux + 114) -#define __NR_swapoff (__NR_Linux + 115) -#define __NR_sysinfo (__NR_Linux + 116) -#define __NR_ipc (__NR_Linux + 117) -#define __NR_fsync (__NR_Linux + 118) -#define __NR_sigreturn (__NR_Linux + 119) -#define __NR_clone (__NR_Linux + 120) -#define __NR_setdomainname (__NR_Linux + 121) -#define __NR_uname (__NR_Linux + 122) -#define __NR_modify_ldt (__NR_Linux + 123) -#define __NR_adjtimex (__NR_Linux + 124) -#define __NR_mprotect (__NR_Linux + 125) -#define __NR_sigprocmask (__NR_Linux + 126) -#define __NR_create_module (__NR_Linux + 127) -#define __NR_init_module (__NR_Linux + 128) -#define __NR_delete_module (__NR_Linux + 129) -#define __NR_get_kernel_syms (__NR_Linux + 130) -#define __NR_quotactl (__NR_Linux + 131) -#define __NR_getpgid (__NR_Linux + 132) -#define __NR_fchdir (__NR_Linux + 133) -#define __NR_bdflush (__NR_Linux + 134) -#define __NR_sysfs (__NR_Linux + 135) -#define __NR_personality (__NR_Linux + 136) -#define __NR_afs_syscall (__NR_Linux + 137) -#define __NR_setfsuid (__NR_Linux + 138) -#define __NR_setfsgid (__NR_Linux + 139) -#define __NR__llseek (__NR_Linux + 140) -#define __NR_getdents (__NR_Linux + 141) -#define __NR__newselect (__NR_Linux + 142) -#define __NR_flock (__NR_Linux + 143) -#define __NR_msync (__NR_Linux + 144) -#define __NR_readv (__NR_Linux + 145) -#define __NR_writev (__NR_Linux + 146) -#define __NR_cacheflush (__NR_Linux + 147) -#define __NR_cachectl (__NR_Linux + 148) -#define __NR_sysmips (__NR_Linux + 149) -#define __NR_unused150 (__NR_Linux + 150) -#define __NR_getsid (__NR_Linux + 151) -#define __NR_fdatasync (__NR_Linux + 152) -#define __NR__sysctl (__NR_Linux + 153) -#define __NR_mlock (__NR_Linux + 154) -#define __NR_munlock (__NR_Linux + 155) -#define __NR_mlockall (__NR_Linux + 156) -#define __NR_munlockall (__NR_Linux + 157) -#define __NR_sched_setparam (__NR_Linux + 158) -#define __NR_sched_getparam (__NR_Linux + 159) -#define __NR_sched_setscheduler (__NR_Linux + 160) -#define __NR_sched_getscheduler (__NR_Linux + 161) -#define __NR_sched_yield (__NR_Linux + 162) -#define __NR_sched_get_priority_max (__NR_Linux + 163) -#define __NR_sched_get_priority_min (__NR_Linux + 164) -#define __NR_sched_rr_get_interval (__NR_Linux + 165) -#define __NR_nanosleep (__NR_Linux + 166) -#define __NR_mremap (__NR_Linux + 167) -#define __NR_accept (__NR_Linux + 168) -#define __NR_bind (__NR_Linux + 169) -#define __NR_connect (__NR_Linux + 170) -#define __NR_getpeername (__NR_Linux + 171) -#define __NR_getsockname (__NR_Linux + 172) -#define __NR_getsockopt (__NR_Linux + 173) -#define __NR_listen (__NR_Linux + 174) -#define __NR_recv (__NR_Linux + 175) -#define __NR_recvfrom (__NR_Linux + 176) -#define __NR_recvmsg (__NR_Linux + 177) -#define __NR_send (__NR_Linux + 178) -#define __NR_sendmsg (__NR_Linux + 179) -#define __NR_sendto (__NR_Linux + 180) -#define __NR_setsockopt (__NR_Linux + 181) -#define __NR_shutdown (__NR_Linux + 182) -#define __NR_socket (__NR_Linux + 183) -#define __NR_socketpair (__NR_Linux + 184) -#define __NR_setresuid (__NR_Linux + 185) -#define __NR_getresuid (__NR_Linux + 186) -#define __NR_query_module (__NR_Linux + 187) -#define __NR_poll (__NR_Linux + 188) -#define __NR_nfsservctl (__NR_Linux + 189) -#define __NR_setresgid (__NR_Linux + 190) -#define __NR_getresgid (__NR_Linux + 191) -#define __NR_prctl (__NR_Linux + 192) -#define __NR_rt_sigreturn (__NR_Linux + 193) -#define __NR_rt_sigaction (__NR_Linux + 194) -#define __NR_rt_sigprocmask (__NR_Linux + 195) -#define __NR_rt_sigpending (__NR_Linux + 196) -#define __NR_rt_sigtimedwait (__NR_Linux + 197) -#define __NR_rt_sigqueueinfo (__NR_Linux + 198) -#define __NR_rt_sigsuspend (__NR_Linux + 199) -#define __NR_pread64 (__NR_Linux + 200) -#define __NR_pwrite64 (__NR_Linux + 201) -#define __NR_chown (__NR_Linux + 202) -#define __NR_getcwd (__NR_Linux + 203) -#define __NR_capget (__NR_Linux + 204) -#define __NR_capset (__NR_Linux + 205) -#define __NR_sigaltstack (__NR_Linux + 206) -#define __NR_sendfile (__NR_Linux + 207) -#define __NR_getpmsg (__NR_Linux + 208) -#define __NR_putpmsg (__NR_Linux + 209) -#define __NR_mmap2 (__NR_Linux + 210) -#define __NR_truncate64 (__NR_Linux + 211) -#define __NR_ftruncate64 (__NR_Linux + 212) -#define __NR_stat64 (__NR_Linux + 213) -#define __NR_lstat64 (__NR_Linux + 214) -#define __NR_fstat64 (__NR_Linux + 215) -#define __NR_pivot_root (__NR_Linux + 216) -#define __NR_mincore (__NR_Linux + 217) -#define __NR_madvise (__NR_Linux + 218) -#define __NR_getdents64 (__NR_Linux + 219) -#define __NR_fcntl64 (__NR_Linux + 220) -#define __NR_reserved221 (__NR_Linux + 221) -#define __NR_gettid (__NR_Linux + 222) -#define __NR_readahead (__NR_Linux + 223) -#define __NR_setxattr (__NR_Linux + 224) -#define __NR_lsetxattr (__NR_Linux + 225) -#define __NR_fsetxattr (__NR_Linux + 226) -#define __NR_getxattr (__NR_Linux + 227) -#define __NR_lgetxattr (__NR_Linux + 228) -#define __NR_fgetxattr (__NR_Linux + 229) -#define __NR_listxattr (__NR_Linux + 230) -#define __NR_llistxattr (__NR_Linux + 231) -#define __NR_flistxattr (__NR_Linux + 232) -#define __NR_removexattr (__NR_Linux + 233) -#define __NR_lremovexattr (__NR_Linux + 234) -#define __NR_fremovexattr (__NR_Linux + 235) -#define __NR_tkill (__NR_Linux + 236) -#define __NR_sendfile64 (__NR_Linux + 237) -#define __NR_futex (__NR_Linux + 238) -#define __NR_sched_setaffinity (__NR_Linux + 239) -#define __NR_sched_getaffinity (__NR_Linux + 240) -#define __NR_io_setup (__NR_Linux + 241) -#define __NR_io_destroy (__NR_Linux + 242) -#define __NR_io_getevents (__NR_Linux + 243) -#define __NR_io_submit (__NR_Linux + 244) -#define __NR_io_cancel (__NR_Linux + 245) -#define __NR_exit_group (__NR_Linux + 246) -#define __NR_lookup_dcookie (__NR_Linux + 247) -#define __NR_epoll_create (__NR_Linux + 248) -#define __NR_epoll_ctl (__NR_Linux + 249) -#define __NR_epoll_wait (__NR_Linux + 250) -#define __NR_remap_file_pages (__NR_Linux + 251) -#define __NR_set_tid_address (__NR_Linux + 252) -#define __NR_restart_syscall (__NR_Linux + 253) -#define __NR_fadvise64 (__NR_Linux + 254) -#define __NR_statfs64 (__NR_Linux + 255) -#define __NR_fstatfs64 (__NR_Linux + 256) -#define __NR_timer_create (__NR_Linux + 257) -#define __NR_timer_settime (__NR_Linux + 258) -#define __NR_timer_gettime (__NR_Linux + 259) -#define __NR_timer_getoverrun (__NR_Linux + 260) -#define __NR_timer_delete (__NR_Linux + 261) -#define __NR_clock_settime (__NR_Linux + 262) -#define __NR_clock_gettime (__NR_Linux + 263) -#define __NR_clock_getres (__NR_Linux + 264) -#define __NR_clock_nanosleep (__NR_Linux + 265) -#define __NR_tgkill (__NR_Linux + 266) -#define __NR_utimes (__NR_Linux + 267) -#define __NR_mbind (__NR_Linux + 268) -#define __NR_get_mempolicy (__NR_Linux + 269) -#define __NR_set_mempolicy (__NR_Linux + 270) -#define __NR_mq_open (__NR_Linux + 271) -#define __NR_mq_unlink (__NR_Linux + 272) -#define __NR_mq_timedsend (__NR_Linux + 273) -#define __NR_mq_timedreceive (__NR_Linux + 274) -#define __NR_mq_notify (__NR_Linux + 275) -#define __NR_mq_getsetattr (__NR_Linux + 276) -#define __NR_vserver (__NR_Linux + 277) -#define __NR_waitid (__NR_Linux + 278) -#define __NR_add_key (__NR_Linux + 280) -#define __NR_request_key (__NR_Linux + 281) -#define __NR_keyctl (__NR_Linux + 282) -#define __NR_set_thread_area (__NR_Linux + 283) -#define __NR_inotify_init (__NR_Linux + 284) -#define __NR_inotify_add_watch (__NR_Linux + 285) -#define __NR_inotify_rm_watch (__NR_Linux + 286) -#define __NR_migrate_pages (__NR_Linux + 287) -#define __NR_openat (__NR_Linux + 288) -#define __NR_mkdirat (__NR_Linux + 289) -#define __NR_mknodat (__NR_Linux + 290) -#define __NR_fchownat (__NR_Linux + 291) -#define __NR_futimesat (__NR_Linux + 292) -#define __NR_fstatat64 (__NR_Linux + 293) -#define __NR_unlinkat (__NR_Linux + 294) -#define __NR_renameat (__NR_Linux + 295) -#define __NR_linkat (__NR_Linux + 296) -#define __NR_symlinkat (__NR_Linux + 297) -#define __NR_readlinkat (__NR_Linux + 298) -#define __NR_fchmodat (__NR_Linux + 299) -#define __NR_faccessat (__NR_Linux + 300) -#define __NR_pselect6 (__NR_Linux + 301) -#define __NR_ppoll (__NR_Linux + 302) -#define __NR_unshare (__NR_Linux + 303) -#define __NR_splice (__NR_Linux + 304) -#define __NR_sync_file_range (__NR_Linux + 305) -#define __NR_tee (__NR_Linux + 306) -#define __NR_vmsplice (__NR_Linux + 307) -#define __NR_move_pages (__NR_Linux + 308) -#define __NR_set_robust_list (__NR_Linux + 309) -#define __NR_get_robust_list (__NR_Linux + 310) -#define __NR_kexec_load (__NR_Linux + 311) -#define __NR_getcpu (__NR_Linux + 312) -#define __NR_epoll_pwait (__NR_Linux + 313) -#define __NR_ioprio_set (__NR_Linux + 314) -#define __NR_ioprio_get (__NR_Linux + 315) -#define __NR_utimensat (__NR_Linux + 316) -#define __NR_signalfd (__NR_Linux + 317) -#define __NR_timerfd (__NR_Linux + 318) -#define __NR_eventfd (__NR_Linux + 319) -#define __NR_fallocate (__NR_Linux + 320) -#define __NR_timerfd_create (__NR_Linux + 321) -#define __NR_timerfd_gettime (__NR_Linux + 322) -#define __NR_timerfd_settime (__NR_Linux + 323) -#define __NR_signalfd4 (__NR_Linux + 324) -#define __NR_eventfd2 (__NR_Linux + 325) -#define __NR_epoll_create1 (__NR_Linux + 326) -#define __NR_dup3 (__NR_Linux + 327) -#define __NR_pipe2 (__NR_Linux + 328) -#define __NR_inotify_init1 (__NR_Linux + 329) -#define __NR_preadv (__NR_Linux + 330) -#define __NR_pwritev (__NR_Linux + 331) -#define __NR_rt_tgsigqueueinfo (__NR_Linux + 332) -#define __NR_perf_event_open (__NR_Linux + 333) -#define __NR_accept4 (__NR_Linux + 334) -#define __NR_recvmmsg (__NR_Linux + 335) -#define __NR_fanotify_init (__NR_Linux + 336) -#define __NR_fanotify_mark (__NR_Linux + 337) -#define __NR_prlimit64 (__NR_Linux + 338) -#define __NR_name_to_handle_at (__NR_Linux + 339) -#define __NR_open_by_handle_at (__NR_Linux + 340) -#define __NR_clock_adjtime (__NR_Linux + 341) -#define __NR_syncfs (__NR_Linux + 342) -#define __NR_sendmmsg (__NR_Linux + 343) -#define __NR_setns (__NR_Linux + 344) -#define __NR_process_vm_readv (__NR_Linux + 345) -#define __NR_process_vm_writev (__NR_Linux + 346) -#define __NR_kcmp (__NR_Linux + 347) -#define __NR_finit_module (__NR_Linux + 348) -#define __NR_sched_setattr (__NR_Linux + 349) -#define __NR_sched_getattr (__NR_Linux + 350) -#define __NR_renameat2 (__NR_Linux + 351) -#define __NR_seccomp (__NR_Linux + 352) -#define __NR_getrandom (__NR_Linux + 353) -#define __NR_memfd_create (__NR_Linux + 354) -#define __NR_bpf (__NR_Linux + 355) -#define __NR_execveat (__NR_Linux + 356) -#define __NR_userfaultfd (__NR_Linux + 357) -#define __NR_membarrier (__NR_Linux + 358) -#define __NR_mlock2 (__NR_Linux + 359) -#define __NR_copy_file_range (__NR_Linux + 360) -#define __NR_preadv2 (__NR_Linux + 361) -#define __NR_pwritev2 (__NR_Linux + 362) -#define __NR_pkey_mprotect (__NR_Linux + 363) -#define __NR_pkey_alloc (__NR_Linux + 364) -#define __NR_pkey_free (__NR_Linux + 365) -#define __NR_statx (__NR_Linux + 366) -#define __NR_rseq (__NR_Linux + 367) -#define __NR_io_pgetevents (__NR_Linux + 368) -#define __NR_semget (__NR_Linux + 393) -#define __NR_semctl (__NR_Linux + 394) -#define __NR_shmget (__NR_Linux + 395) -#define __NR_shmctl (__NR_Linux + 396) -#define __NR_shmat (__NR_Linux + 397) -#define __NR_shmdt (__NR_Linux + 398) -#define __NR_msgget (__NR_Linux + 399) -#define __NR_msgsnd (__NR_Linux + 400) -#define __NR_msgrcv (__NR_Linux + 401) -#define __NR_msgctl (__NR_Linux + 402) -#define __NR_clock_gettime64 (__NR_Linux + 403) -#define __NR_clock_settime64 (__NR_Linux + 404) -#define __NR_clock_adjtime64 (__NR_Linux + 405) -#define __NR_clock_getres_time64 (__NR_Linux + 406) -#define __NR_clock_nanosleep_time64 (__NR_Linux + 407) -#define __NR_timer_gettime64 (__NR_Linux + 408) -#define __NR_timer_settime64 (__NR_Linux + 409) -#define __NR_timerfd_gettime64 (__NR_Linux + 410) -#define __NR_timerfd_settime64 (__NR_Linux + 411) -#define __NR_utimensat_time64 (__NR_Linux + 412) -#define __NR_pselect6_time64 (__NR_Linux + 413) -#define __NR_ppoll_time64 (__NR_Linux + 414) -#define __NR_io_pgetevents_time64 (__NR_Linux + 416) -#define __NR_recvmmsg_time64 (__NR_Linux + 417) -#define __NR_mq_timedsend_time64 (__NR_Linux + 418) -#define __NR_mq_timedreceive_time64 (__NR_Linux + 419) -#define __NR_semtimedop_time64 (__NR_Linux + 420) -#define __NR_rt_sigtimedwait_time64 (__NR_Linux + 421) -#define __NR_futex_time64 (__NR_Linux + 422) -#define __NR_sched_rr_get_interval_time64 (__NR_Linux + 423) -#define __NR_pidfd_send_signal (__NR_Linux + 424) -#define __NR_io_uring_setup (__NR_Linux + 425) -#define __NR_io_uring_enter (__NR_Linux + 426) -#define __NR_io_uring_register (__NR_Linux + 427) -#define __NR_open_tree (__NR_Linux + 428) -#define __NR_move_mount (__NR_Linux + 429) -#define __NR_fsopen (__NR_Linux + 430) -#define __NR_fsconfig (__NR_Linux + 431) -#define __NR_fsmount (__NR_Linux + 432) -#define __NR_fspick (__NR_Linux + 433) -#define __NR_pidfd_open (__NR_Linux + 434) -#define __NR_clone3 (__NR_Linux + 435) -#define __NR_close_range (__NR_Linux + 436) -#define __NR_openat2 (__NR_Linux + 437) -#define __NR_pidfd_getfd (__NR_Linux + 438) -#define __NR_faccessat2 (__NR_Linux + 439) -#define __NR_process_madvise (__NR_Linux + 440) -#define __NR_epoll_pwait2 (__NR_Linux + 441) +#define __NR_syscall (__NR_Linux + 0) +#define __NR_exit (__NR_Linux + 1) +#define __NR_fork (__NR_Linux + 2) +#define __NR_read (__NR_Linux + 3) +#define __NR_write (__NR_Linux + 4) +#define __NR_open (__NR_Linux + 5) +#define __NR_close (__NR_Linux + 6) +#define __NR_waitpid (__NR_Linux + 7) +#define __NR_creat (__NR_Linux + 8) +#define __NR_link (__NR_Linux + 9) +#define __NR_unlink (__NR_Linux + 10) +#define __NR_execve (__NR_Linux + 11) +#define __NR_chdir (__NR_Linux + 12) +#define __NR_time (__NR_Linux + 13) +#define __NR_mknod (__NR_Linux + 14) +#define __NR_chmod (__NR_Linux + 15) +#define __NR_lchown (__NR_Linux + 16) +#define __NR_break (__NR_Linux + 17) +#define __NR_unused18 (__NR_Linux + 18) +#define __NR_lseek (__NR_Linux + 19) +#define __NR_getpid (__NR_Linux + 20) +#define __NR_mount (__NR_Linux + 21) +#define __NR_umount (__NR_Linux + 22) +#define __NR_setuid (__NR_Linux + 23) +#define __NR_getuid (__NR_Linux + 24) +#define __NR_stime (__NR_Linux + 25) +#define __NR_ptrace (__NR_Linux + 26) +#define __NR_alarm (__NR_Linux + 27) +#define __NR_unused28 (__NR_Linux + 28) +#define __NR_pause (__NR_Linux + 29) +#define __NR_utime (__NR_Linux + 30) +#define __NR_stty (__NR_Linux + 31) +#define __NR_gtty (__NR_Linux + 32) +#define __NR_access (__NR_Linux + 33) +#define __NR_nice (__NR_Linux + 34) +#define __NR_ftime (__NR_Linux + 35) +#define __NR_sync (__NR_Linux + 36) +#define __NR_kill (__NR_Linux + 37) +#define __NR_rename (__NR_Linux + 38) +#define __NR_mkdir (__NR_Linux + 39) +#define __NR_rmdir (__NR_Linux + 40) +#define __NR_dup (__NR_Linux + 41) +#define __NR_pipe (__NR_Linux + 42) +#define __NR_times (__NR_Linux + 43) +#define __NR_prof (__NR_Linux + 44) +#define __NR_brk (__NR_Linux + 45) +#define __NR_setgid (__NR_Linux + 46) +#define __NR_getgid (__NR_Linux + 47) +#define __NR_signal (__NR_Linux + 48) +#define __NR_geteuid (__NR_Linux + 49) +#define __NR_getegid (__NR_Linux + 50) +#define __NR_acct (__NR_Linux + 51) +#define __NR_umount2 (__NR_Linux + 52) +#define __NR_lock (__NR_Linux + 53) +#define __NR_ioctl (__NR_Linux + 54) +#define __NR_fcntl (__NR_Linux + 55) +#define __NR_mpx (__NR_Linux + 56) +#define __NR_setpgid (__NR_Linux + 57) +#define __NR_ulimit (__NR_Linux + 58) +#define __NR_unused59 (__NR_Linux + 59) +#define __NR_umask (__NR_Linux + 60) +#define __NR_chroot (__NR_Linux + 61) +#define __NR_ustat (__NR_Linux + 62) +#define __NR_dup2 (__NR_Linux + 63) +#define __NR_getppid (__NR_Linux + 64) +#define __NR_getpgrp (__NR_Linux + 65) +#define __NR_setsid (__NR_Linux + 66) +#define __NR_sigaction (__NR_Linux + 67) +#define __NR_sgetmask (__NR_Linux + 68) +#define __NR_ssetmask (__NR_Linux + 69) +#define __NR_setreuid (__NR_Linux + 70) +#define __NR_setregid (__NR_Linux + 71) +#define __NR_sigsuspend (__NR_Linux + 72) +#define __NR_sigpending (__NR_Linux + 73) +#define __NR_sethostname (__NR_Linux + 74) +#define __NR_setrlimit (__NR_Linux + 75) +#define __NR_getrlimit (__NR_Linux + 76) +#define __NR_getrusage (__NR_Linux + 77) +#define __NR_gettimeofday (__NR_Linux + 78) +#define __NR_settimeofday (__NR_Linux + 79) +#define __NR_getgroups (__NR_Linux + 80) +#define __NR_setgroups (__NR_Linux + 81) +#define __NR_reserved82 (__NR_Linux + 82) +#define __NR_symlink (__NR_Linux + 83) +#define __NR_unused84 (__NR_Linux + 84) +#define __NR_readlink (__NR_Linux + 85) +#define __NR_uselib (__NR_Linux + 86) +#define __NR_swapon (__NR_Linux + 87) +#define __NR_reboot (__NR_Linux + 88) +#define __NR_readdir (__NR_Linux + 89) +#define __NR_mmap (__NR_Linux + 90) +#define __NR_munmap (__NR_Linux + 91) +#define __NR_truncate (__NR_Linux + 92) +#define __NR_ftruncate (__NR_Linux + 93) +#define __NR_fchmod (__NR_Linux + 94) +#define __NR_fchown (__NR_Linux + 95) +#define __NR_getpriority (__NR_Linux + 96) +#define __NR_setpriority (__NR_Linux + 97) +#define __NR_profil (__NR_Linux + 98) +#define __NR_statfs (__NR_Linux + 99) +#define __NR_fstatfs (__NR_Linux + 100) +#define __NR_ioperm (__NR_Linux + 101) +#define __NR_socketcall (__NR_Linux + 102) +#define __NR_syslog (__NR_Linux + 103) +#define __NR_setitimer (__NR_Linux + 104) +#define __NR_getitimer (__NR_Linux + 105) +#define __NR_stat (__NR_Linux + 106) +#define __NR_lstat (__NR_Linux + 107) +#define __NR_fstat (__NR_Linux + 108) +#define __NR_unused109 (__NR_Linux + 109) +#define __NR_iopl (__NR_Linux + 110) +#define __NR_vhangup (__NR_Linux + 111) +#define __NR_idle (__NR_Linux + 112) +#define __NR_vm86 (__NR_Linux + 113) +#define __NR_wait4 (__NR_Linux + 114) +#define __NR_swapoff (__NR_Linux + 115) +#define __NR_sysinfo (__NR_Linux + 116) +#define __NR_ipc (__NR_Linux + 117) +#define __NR_fsync (__NR_Linux + 118) +#define __NR_sigreturn (__NR_Linux + 119) +#define __NR_clone (__NR_Linux + 120) +#define __NR_setdomainname (__NR_Linux + 121) +#define __NR_uname (__NR_Linux + 122) +#define __NR_modify_ldt (__NR_Linux + 123) +#define __NR_adjtimex (__NR_Linux + 124) +#define __NR_mprotect (__NR_Linux + 125) +#define __NR_sigprocmask (__NR_Linux + 126) +#define __NR_create_module (__NR_Linux + 127) +#define __NR_init_module (__NR_Linux + 128) +#define __NR_delete_module (__NR_Linux + 129) +#define __NR_get_kernel_syms (__NR_Linux + 130) +#define __NR_quotactl (__NR_Linux + 131) +#define __NR_getpgid (__NR_Linux + 132) +#define __NR_fchdir (__NR_Linux + 133) +#define __NR_bdflush (__NR_Linux + 134) +#define __NR_sysfs (__NR_Linux + 135) +#define __NR_personality (__NR_Linux + 136) +#define __NR_afs_syscall (__NR_Linux + 137) +#define __NR_setfsuid (__NR_Linux + 138) +#define __NR_setfsgid (__NR_Linux + 139) +#define __NR__llseek (__NR_Linux + 140) +#define __NR_getdents (__NR_Linux + 141) +#define __NR__newselect (__NR_Linux + 142) +#define __NR_flock (__NR_Linux + 143) +#define __NR_msync (__NR_Linux + 144) +#define __NR_readv (__NR_Linux + 145) +#define __NR_writev (__NR_Linux + 146) +#define __NR_cacheflush (__NR_Linux + 147) +#define __NR_cachectl (__NR_Linux + 148) +#define __NR_sysmips (__NR_Linux + 149) +#define __NR_unused150 (__NR_Linux + 150) +#define __NR_getsid (__NR_Linux + 151) +#define __NR_fdatasync (__NR_Linux + 152) +#define __NR__sysctl (__NR_Linux + 153) +#define __NR_mlock (__NR_Linux + 154) +#define __NR_munlock (__NR_Linux + 155) +#define __NR_mlockall (__NR_Linux + 156) +#define __NR_munlockall (__NR_Linux + 157) +#define __NR_sched_setparam (__NR_Linux + 158) +#define __NR_sched_getparam (__NR_Linux + 159) +#define __NR_sched_setscheduler (__NR_Linux + 160) +#define __NR_sched_getscheduler (__NR_Linux + 161) +#define __NR_sched_yield (__NR_Linux + 162) +#define __NR_sched_get_priority_max (__NR_Linux + 163) +#define __NR_sched_get_priority_min (__NR_Linux + 164) +#define __NR_sched_rr_get_interval (__NR_Linux + 165) +#define __NR_nanosleep (__NR_Linux + 166) +#define __NR_mremap (__NR_Linux + 167) +#define __NR_accept (__NR_Linux + 168) +#define __NR_bind (__NR_Linux + 169) +#define __NR_connect (__NR_Linux + 170) +#define __NR_getpeername (__NR_Linux + 171) +#define __NR_getsockname (__NR_Linux + 172) +#define __NR_getsockopt (__NR_Linux + 173) +#define __NR_listen (__NR_Linux + 174) +#define __NR_recv (__NR_Linux + 175) +#define __NR_recvfrom (__NR_Linux + 176) +#define __NR_recvmsg (__NR_Linux + 177) +#define __NR_send (__NR_Linux + 178) +#define __NR_sendmsg (__NR_Linux + 179) +#define __NR_sendto (__NR_Linux + 180) +#define __NR_setsockopt (__NR_Linux + 181) +#define __NR_shutdown (__NR_Linux + 182) +#define __NR_socket (__NR_Linux + 183) +#define __NR_socketpair (__NR_Linux + 184) +#define __NR_setresuid (__NR_Linux + 185) +#define __NR_getresuid (__NR_Linux + 186) +#define __NR_query_module (__NR_Linux + 187) +#define __NR_poll (__NR_Linux + 188) +#define __NR_nfsservctl (__NR_Linux + 189) +#define __NR_setresgid (__NR_Linux + 190) +#define __NR_getresgid (__NR_Linux + 191) +#define __NR_prctl (__NR_Linux + 192) +#define __NR_rt_sigreturn (__NR_Linux + 193) +#define __NR_rt_sigaction (__NR_Linux + 194) +#define __NR_rt_sigprocmask (__NR_Linux + 195) +#define __NR_rt_sigpending (__NR_Linux + 196) +#define __NR_rt_sigtimedwait (__NR_Linux + 197) +#define __NR_rt_sigqueueinfo (__NR_Linux + 198) +#define __NR_rt_sigsuspend (__NR_Linux + 199) +#define __NR_pread64 (__NR_Linux + 200) +#define __NR_pwrite64 (__NR_Linux + 201) +#define __NR_chown (__NR_Linux + 202) +#define __NR_getcwd (__NR_Linux + 203) +#define __NR_capget (__NR_Linux + 204) +#define __NR_capset (__NR_Linux + 205) +#define __NR_sigaltstack (__NR_Linux + 206) +#define __NR_sendfile (__NR_Linux + 207) +#define __NR_getpmsg (__NR_Linux + 208) +#define __NR_putpmsg (__NR_Linux + 209) +#define __NR_mmap2 (__NR_Linux + 210) +#define __NR_truncate64 (__NR_Linux + 211) +#define __NR_ftruncate64 (__NR_Linux + 212) +#define __NR_stat64 (__NR_Linux + 213) +#define __NR_lstat64 (__NR_Linux + 214) +#define __NR_fstat64 (__NR_Linux + 215) +#define __NR_pivot_root (__NR_Linux + 216) +#define __NR_mincore (__NR_Linux + 217) +#define __NR_madvise (__NR_Linux + 218) +#define __NR_getdents64 (__NR_Linux + 219) +#define __NR_fcntl64 (__NR_Linux + 220) +#define __NR_reserved221 (__NR_Linux + 221) +#define __NR_gettid (__NR_Linux + 222) +#define __NR_readahead (__NR_Linux + 223) +#define __NR_setxattr (__NR_Linux + 224) +#define __NR_lsetxattr (__NR_Linux + 225) +#define __NR_fsetxattr (__NR_Linux + 226) +#define __NR_getxattr (__NR_Linux + 227) +#define __NR_lgetxattr (__NR_Linux + 228) +#define __NR_fgetxattr (__NR_Linux + 229) +#define __NR_listxattr (__NR_Linux + 230) +#define __NR_llistxattr (__NR_Linux + 231) +#define __NR_flistxattr (__NR_Linux + 232) +#define __NR_removexattr (__NR_Linux + 233) +#define __NR_lremovexattr (__NR_Linux + 234) +#define __NR_fremovexattr (__NR_Linux + 235) +#define __NR_tkill (__NR_Linux + 236) +#define __NR_sendfile64 (__NR_Linux + 237) +#define __NR_futex (__NR_Linux + 238) +#define __NR_sched_setaffinity (__NR_Linux + 239) +#define __NR_sched_getaffinity (__NR_Linux + 240) +#define __NR_io_setup (__NR_Linux + 241) +#define __NR_io_destroy (__NR_Linux + 242) +#define __NR_io_getevents (__NR_Linux + 243) +#define __NR_io_submit (__NR_Linux + 244) +#define __NR_io_cancel (__NR_Linux + 245) +#define __NR_exit_group (__NR_Linux + 246) +#define __NR_lookup_dcookie (__NR_Linux + 247) +#define __NR_epoll_create (__NR_Linux + 248) +#define __NR_epoll_ctl (__NR_Linux + 249) +#define __NR_epoll_wait (__NR_Linux + 250) +#define __NR_remap_file_pages (__NR_Linux + 251) +#define __NR_set_tid_address (__NR_Linux + 252) +#define __NR_restart_syscall (__NR_Linux + 253) +#define __NR_fadvise64 (__NR_Linux + 254) +#define __NR_statfs64 (__NR_Linux + 255) +#define __NR_fstatfs64 (__NR_Linux + 256) +#define __NR_timer_create (__NR_Linux + 257) +#define __NR_timer_settime (__NR_Linux + 258) +#define __NR_timer_gettime (__NR_Linux + 259) +#define __NR_timer_getoverrun (__NR_Linux + 260) +#define __NR_timer_delete (__NR_Linux + 261) +#define __NR_clock_settime (__NR_Linux + 262) +#define __NR_clock_gettime (__NR_Linux + 263) +#define __NR_clock_getres (__NR_Linux + 264) +#define __NR_clock_nanosleep (__NR_Linux + 265) +#define __NR_tgkill (__NR_Linux + 266) +#define __NR_utimes (__NR_Linux + 267) +#define __NR_mbind (__NR_Linux + 268) +#define __NR_get_mempolicy (__NR_Linux + 269) +#define __NR_set_mempolicy (__NR_Linux + 270) +#define __NR_mq_open (__NR_Linux + 271) +#define __NR_mq_unlink (__NR_Linux + 272) +#define __NR_mq_timedsend (__NR_Linux + 273) +#define __NR_mq_timedreceive (__NR_Linux + 274) +#define __NR_mq_notify (__NR_Linux + 275) +#define __NR_mq_getsetattr (__NR_Linux + 276) +#define __NR_vserver (__NR_Linux + 277) +#define __NR_waitid (__NR_Linux + 278) +#define __NR_add_key (__NR_Linux + 280) +#define __NR_request_key (__NR_Linux + 281) +#define __NR_keyctl (__NR_Linux + 282) +#define __NR_set_thread_area (__NR_Linux + 283) +#define __NR_inotify_init (__NR_Linux + 284) +#define __NR_inotify_add_watch (__NR_Linux + 285) +#define __NR_inotify_rm_watch (__NR_Linux + 286) +#define __NR_migrate_pages (__NR_Linux + 287) +#define __NR_openat (__NR_Linux + 288) +#define __NR_mkdirat (__NR_Linux + 289) +#define __NR_mknodat (__NR_Linux + 290) +#define __NR_fchownat (__NR_Linux + 291) +#define __NR_futimesat (__NR_Linux + 292) +#define __NR_fstatat64 (__NR_Linux + 293) +#define __NR_unlinkat (__NR_Linux + 294) +#define __NR_renameat (__NR_Linux + 295) +#define __NR_linkat (__NR_Linux + 296) +#define __NR_symlinkat (__NR_Linux + 297) +#define __NR_readlinkat (__NR_Linux + 298) +#define __NR_fchmodat (__NR_Linux + 299) +#define __NR_faccessat (__NR_Linux + 300) +#define __NR_pselect6 (__NR_Linux + 301) +#define __NR_ppoll (__NR_Linux + 302) +#define __NR_unshare (__NR_Linux + 303) +#define __NR_splice (__NR_Linux + 304) +#define __NR_sync_file_range (__NR_Linux + 305) +#define __NR_tee (__NR_Linux + 306) +#define __NR_vmsplice (__NR_Linux + 307) +#define __NR_move_pages (__NR_Linux + 308) +#define __NR_set_robust_list (__NR_Linux + 309) +#define __NR_get_robust_list (__NR_Linux + 310) +#define __NR_kexec_load (__NR_Linux + 311) +#define __NR_getcpu (__NR_Linux + 312) +#define __NR_epoll_pwait (__NR_Linux + 313) +#define __NR_ioprio_set (__NR_Linux + 314) +#define __NR_ioprio_get (__NR_Linux + 315) +#define __NR_utimensat (__NR_Linux + 316) +#define __NR_signalfd (__NR_Linux + 317) +#define __NR_timerfd (__NR_Linux + 318) +#define __NR_eventfd (__NR_Linux + 319) +#define __NR_fallocate (__NR_Linux + 320) +#define __NR_timerfd_create (__NR_Linux + 321) +#define __NR_timerfd_gettime (__NR_Linux + 322) +#define __NR_timerfd_settime (__NR_Linux + 323) +#define __NR_signalfd4 (__NR_Linux + 324) +#define __NR_eventfd2 (__NR_Linux + 325) +#define __NR_epoll_create1 (__NR_Linux + 326) +#define __NR_dup3 (__NR_Linux + 327) +#define __NR_pipe2 (__NR_Linux + 328) +#define __NR_inotify_init1 (__NR_Linux + 329) +#define __NR_preadv (__NR_Linux + 330) +#define __NR_pwritev (__NR_Linux + 331) +#define __NR_rt_tgsigqueueinfo (__NR_Linux + 332) +#define __NR_perf_event_open (__NR_Linux + 333) +#define __NR_accept4 (__NR_Linux + 334) +#define __NR_recvmmsg (__NR_Linux + 335) +#define __NR_fanotify_init (__NR_Linux + 336) +#define __NR_fanotify_mark (__NR_Linux + 337) +#define __NR_prlimit64 (__NR_Linux + 338) +#define __NR_name_to_handle_at (__NR_Linux + 339) +#define __NR_open_by_handle_at (__NR_Linux + 340) +#define __NR_clock_adjtime (__NR_Linux + 341) +#define __NR_syncfs (__NR_Linux + 342) +#define __NR_sendmmsg (__NR_Linux + 343) +#define __NR_setns (__NR_Linux + 344) +#define __NR_process_vm_readv (__NR_Linux + 345) +#define __NR_process_vm_writev (__NR_Linux + 346) +#define __NR_kcmp (__NR_Linux + 347) +#define __NR_finit_module (__NR_Linux + 348) +#define __NR_sched_setattr (__NR_Linux + 349) +#define __NR_sched_getattr (__NR_Linux + 350) +#define __NR_renameat2 (__NR_Linux + 351) +#define __NR_seccomp (__NR_Linux + 352) +#define __NR_getrandom (__NR_Linux + 353) +#define __NR_memfd_create (__NR_Linux + 354) +#define __NR_bpf (__NR_Linux + 355) +#define __NR_execveat (__NR_Linux + 356) +#define __NR_userfaultfd (__NR_Linux + 357) +#define __NR_membarrier (__NR_Linux + 358) +#define __NR_mlock2 (__NR_Linux + 359) +#define __NR_copy_file_range (__NR_Linux + 360) +#define __NR_preadv2 (__NR_Linux + 361) +#define __NR_pwritev2 (__NR_Linux + 362) +#define __NR_pkey_mprotect (__NR_Linux + 363) +#define __NR_pkey_alloc (__NR_Linux + 364) +#define __NR_pkey_free (__NR_Linux + 365) +#define __NR_statx (__NR_Linux + 366) +#define __NR_rseq (__NR_Linux + 367) +#define __NR_io_pgetevents (__NR_Linux + 368) +#define __NR_semget (__NR_Linux + 393) +#define __NR_semctl (__NR_Linux + 394) +#define __NR_shmget (__NR_Linux + 395) +#define __NR_shmctl (__NR_Linux + 396) +#define __NR_shmat (__NR_Linux + 397) +#define __NR_shmdt (__NR_Linux + 398) +#define __NR_msgget (__NR_Linux + 399) +#define __NR_msgsnd (__NR_Linux + 400) +#define __NR_msgrcv (__NR_Linux + 401) +#define __NR_msgctl (__NR_Linux + 402) +#define __NR_clock_gettime64 (__NR_Linux + 403) +#define __NR_clock_settime64 (__NR_Linux + 404) +#define __NR_clock_adjtime64 (__NR_Linux + 405) +#define __NR_clock_getres_time64 (__NR_Linux + 406) +#define __NR_clock_nanosleep_time64 (__NR_Linux + 407) +#define __NR_timer_gettime64 (__NR_Linux + 408) +#define __NR_timer_settime64 (__NR_Linux + 409) +#define __NR_timerfd_gettime64 (__NR_Linux + 410) +#define __NR_timerfd_settime64 (__NR_Linux + 411) +#define __NR_utimensat_time64 (__NR_Linux + 412) +#define __NR_pselect6_time64 (__NR_Linux + 413) +#define __NR_ppoll_time64 (__NR_Linux + 414) +#define __NR_io_pgetevents_time64 (__NR_Linux + 416) +#define __NR_recvmmsg_time64 (__NR_Linux + 417) +#define __NR_mq_timedsend_time64 (__NR_Linux + 418) +#define __NR_mq_timedreceive_time64 (__NR_Linux + 419) +#define __NR_semtimedop_time64 (__NR_Linux + 420) +#define __NR_rt_sigtimedwait_time64 (__NR_Linux + 421) +#define __NR_futex_time64 (__NR_Linux + 422) +#define __NR_sched_rr_get_interval_time64 (__NR_Linux + 423) +#define __NR_pidfd_send_signal (__NR_Linux + 424) +#define __NR_io_uring_setup (__NR_Linux + 425) +#define __NR_io_uring_enter (__NR_Linux + 426) +#define __NR_io_uring_register (__NR_Linux + 427) +#define __NR_open_tree (__NR_Linux + 428) +#define __NR_move_mount (__NR_Linux + 429) +#define __NR_fsopen (__NR_Linux + 430) +#define __NR_fsconfig (__NR_Linux + 431) +#define __NR_fsmount (__NR_Linux + 432) +#define __NR_fspick (__NR_Linux + 433) +#define __NR_pidfd_open (__NR_Linux + 434) +#define __NR_clone3 (__NR_Linux + 435) +#define __NR_close_range (__NR_Linux + 436) +#define __NR_openat2 (__NR_Linux + 437) +#define __NR_pidfd_getfd (__NR_Linux + 438) +#define __NR_faccessat2 (__NR_Linux + 439) +#define __NR_process_madvise (__NR_Linux + 440) +#define __NR_epoll_pwait2 (__NR_Linux + 441) +#define __NR_mount_setattr (__NR_Linux + 442) +#define __NR_quotactl_fd (__NR_Linux + 443) +#define __NR_landlock_create_ruleset (__NR_Linux + 444) +#define __NR_landlock_add_rule (__NR_Linux + 445) +#define __NR_landlock_restrict_self (__NR_Linux + 446) - -#endif /* _ASM_MIPS_UNISTD_O32_H */ +#endif /* _ASM_UNISTD_O32_H */ diff --git a/linux-headers/asm-powerpc/kvm.h b/linux-headers/asm-powerpc/kvm.h index c3af3f324c..9f18fa090f 100644 --- a/linux-headers/asm-powerpc/kvm.h +++ b/linux-headers/asm-powerpc/kvm.h @@ -644,6 +644,8 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_MMCR3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc1) #define KVM_REG_PPC_SIER2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc2) #define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3) +#define KVM_REG_PPC_DAWR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4) +#define KVM_REG_PPC_DAWRX1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5) /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs diff --git a/linux-headers/asm-powerpc/unistd_32.h b/linux-headers/asm-powerpc/unistd_32.h index 4624c90043..cd5a8a41b2 100644 --- a/linux-headers/asm-powerpc/unistd_32.h +++ b/linux-headers/asm-powerpc/unistd_32.h @@ -1,429 +1,434 @@ -#ifndef _ASM_POWERPC_UNISTD_32_H -#define _ASM_POWERPC_UNISTD_32_H +#ifndef _ASM_UNISTD_32_H +#define _ASM_UNISTD_32_H -#define __NR_restart_syscall 0 -#define __NR_exit 1 -#define __NR_fork 2 -#define __NR_read 3 -#define __NR_write 4 -#define __NR_open 5 -#define __NR_close 6 -#define __NR_waitpid 7 -#define __NR_creat 8 -#define __NR_link 9 -#define __NR_unlink 10 -#define __NR_execve 11 -#define __NR_chdir 12 -#define __NR_time 13 -#define __NR_mknod 14 -#define __NR_chmod 15 -#define __NR_lchown 16 -#define __NR_break 17 -#define __NR_oldstat 18 -#define __NR_lseek 19 -#define __NR_getpid 20 -#define __NR_mount 21 -#define __NR_umount 22 -#define __NR_setuid 23 -#define __NR_getuid 24 -#define __NR_stime 25 -#define __NR_ptrace 26 -#define __NR_alarm 27 -#define __NR_oldfstat 28 -#define __NR_pause 29 -#define __NR_utime 30 -#define __NR_stty 31 -#define __NR_gtty 32 -#define __NR_access 33 -#define __NR_nice 34 -#define __NR_ftime 35 -#define __NR_sync 36 -#define __NR_kill 37 -#define __NR_rename 38 -#define __NR_mkdir 39 -#define __NR_rmdir 40 -#define __NR_dup 41 -#define __NR_pipe 42 -#define __NR_times 43 -#define __NR_prof 44 -#define __NR_brk 45 -#define __NR_setgid 46 -#define __NR_getgid 47 -#define __NR_signal 48 -#define __NR_geteuid 49 -#define __NR_getegid 50 -#define __NR_acct 51 -#define __NR_umount2 52 -#define __NR_lock 53 -#define __NR_ioctl 54 -#define __NR_fcntl 55 -#define __NR_mpx 56 -#define __NR_setpgid 57 -#define __NR_ulimit 58 -#define __NR_oldolduname 59 -#define __NR_umask 60 -#define __NR_chroot 61 -#define __NR_ustat 62 -#define __NR_dup2 63 -#define __NR_getppid 64 -#define __NR_getpgrp 65 -#define __NR_setsid 66 -#define __NR_sigaction 67 -#define __NR_sgetmask 68 -#define __NR_ssetmask 69 -#define __NR_setreuid 70 -#define __NR_setregid 71 -#define __NR_sigsuspend 72 -#define __NR_sigpending 73 -#define __NR_sethostname 74 -#define __NR_setrlimit 75 -#define __NR_getrlimit 76 -#define __NR_getrusage 77 -#define __NR_gettimeofday 78 -#define __NR_settimeofday 79 -#define __NR_getgroups 80 -#define __NR_setgroups 81 -#define __NR_select 82 -#define __NR_symlink 83 -#define __NR_oldlstat 84 -#define __NR_readlink 85 -#define __NR_uselib 86 -#define __NR_swapon 87 -#define __NR_reboot 88 -#define __NR_readdir 89 -#define __NR_mmap 90 -#define __NR_munmap 91 -#define __NR_truncate 92 -#define __NR_ftruncate 93 -#define __NR_fchmod 94 -#define __NR_fchown 95 -#define __NR_getpriority 96 -#define __NR_setpriority 97 -#define __NR_profil 98 -#define __NR_statfs 99 -#define __NR_fstatfs 100 -#define __NR_ioperm 101 -#define __NR_socketcall 102 -#define __NR_syslog 103 -#define __NR_setitimer 104 -#define __NR_getitimer 105 -#define __NR_stat 106 -#define __NR_lstat 107 -#define __NR_fstat 108 -#define __NR_olduname 109 -#define __NR_iopl 110 -#define __NR_vhangup 111 -#define __NR_idle 112 -#define __NR_vm86 113 -#define __NR_wait4 114 -#define __NR_swapoff 115 -#define __NR_sysinfo 116 -#define __NR_ipc 117 -#define __NR_fsync 118 -#define __NR_sigreturn 119 -#define __NR_clone 120 -#define __NR_setdomainname 121 -#define __NR_uname 122 -#define __NR_modify_ldt 123 -#define __NR_adjtimex 124 -#define __NR_mprotect 125 -#define __NR_sigprocmask 126 -#define __NR_create_module 127 -#define __NR_init_module 128 -#define __NR_delete_module 129 -#define __NR_get_kernel_syms 130 -#define __NR_quotactl 131 -#define __NR_getpgid 132 -#define __NR_fchdir 133 -#define __NR_bdflush 134 -#define __NR_sysfs 135 -#define __NR_personality 136 -#define __NR_afs_syscall 137 -#define __NR_setfsuid 138 -#define __NR_setfsgid 139 -#define __NR__llseek 140 -#define __NR_getdents 141 -#define __NR__newselect 142 -#define __NR_flock 143 -#define __NR_msync 144 -#define __NR_readv 145 -#define __NR_writev 146 -#define __NR_getsid 147 -#define __NR_fdatasync 148 -#define __NR__sysctl 149 -#define __NR_mlock 150 -#define __NR_munlock 151 -#define __NR_mlockall 152 -#define __NR_munlockall 153 -#define __NR_sched_setparam 154 -#define __NR_sched_getparam 155 -#define __NR_sched_setscheduler 156 -#define __NR_sched_getscheduler 157 -#define __NR_sched_yield 158 -#define __NR_sched_get_priority_max 159 -#define __NR_sched_get_priority_min 160 -#define __NR_sched_rr_get_interval 161 -#define __NR_nanosleep 162 -#define __NR_mremap 163 -#define __NR_setresuid 164 -#define __NR_getresuid 165 -#define __NR_query_module 166 -#define __NR_poll 167 -#define __NR_nfsservctl 168 -#define __NR_setresgid 169 -#define __NR_getresgid 170 -#define __NR_prctl 171 -#define __NR_rt_sigreturn 172 -#define __NR_rt_sigaction 173 -#define __NR_rt_sigprocmask 174 -#define __NR_rt_sigpending 175 -#define __NR_rt_sigtimedwait 176 -#define __NR_rt_sigqueueinfo 177 -#define __NR_rt_sigsuspend 178 -#define __NR_pread64 179 -#define __NR_pwrite64 180 -#define __NR_chown 181 -#define __NR_getcwd 182 -#define __NR_capget 183 -#define __NR_capset 184 -#define __NR_sigaltstack 185 -#define __NR_sendfile 186 -#define __NR_getpmsg 187 -#define __NR_putpmsg 188 -#define __NR_vfork 189 -#define __NR_ugetrlimit 190 -#define __NR_readahead 191 -#define __NR_mmap2 192 -#define __NR_truncate64 193 -#define __NR_ftruncate64 194 -#define __NR_stat64 195 -#define __NR_lstat64 196 -#define __NR_fstat64 197 -#define __NR_pciconfig_read 198 -#define __NR_pciconfig_write 199 -#define __NR_pciconfig_iobase 200 -#define __NR_multiplexer 201 -#define __NR_getdents64 202 -#define __NR_pivot_root 203 -#define __NR_fcntl64 204 -#define __NR_madvise 205 -#define __NR_mincore 206 -#define __NR_gettid 207 -#define __NR_tkill 208 -#define __NR_setxattr 209 -#define __NR_lsetxattr 210 -#define __NR_fsetxattr 211 -#define __NR_getxattr 212 -#define __NR_lgetxattr 213 -#define __NR_fgetxattr 214 -#define __NR_listxattr 215 -#define __NR_llistxattr 216 -#define __NR_flistxattr 217 -#define __NR_removexattr 218 -#define __NR_lremovexattr 219 -#define __NR_fremovexattr 220 -#define __NR_futex 221 -#define __NR_sched_setaffinity 222 -#define __NR_sched_getaffinity 223 -#define __NR_tuxcall 225 -#define __NR_sendfile64 226 -#define __NR_io_setup 227 -#define __NR_io_destroy 228 -#define __NR_io_getevents 229 -#define __NR_io_submit 230 -#define __NR_io_cancel 231 -#define __NR_set_tid_address 232 -#define __NR_fadvise64 233 -#define __NR_exit_group 234 -#define __NR_lookup_dcookie 235 -#define __NR_epoll_create 236 -#define __NR_epoll_ctl 237 -#define __NR_epoll_wait 238 -#define __NR_remap_file_pages 239 -#define __NR_timer_create 240 -#define __NR_timer_settime 241 -#define __NR_timer_gettime 242 -#define __NR_timer_getoverrun 243 -#define __NR_timer_delete 244 -#define __NR_clock_settime 245 -#define __NR_clock_gettime 246 -#define __NR_clock_getres 247 -#define __NR_clock_nanosleep 248 -#define __NR_swapcontext 249 -#define __NR_tgkill 250 -#define __NR_utimes 251 -#define __NR_statfs64 252 -#define __NR_fstatfs64 253 -#define __NR_fadvise64_64 254 -#define __NR_rtas 255 -#define __NR_sys_debug_setcontext 256 -#define __NR_migrate_pages 258 -#define __NR_mbind 259 -#define __NR_get_mempolicy 260 -#define __NR_set_mempolicy 261 -#define __NR_mq_open 262 -#define __NR_mq_unlink 263 -#define __NR_mq_timedsend 264 -#define __NR_mq_timedreceive 265 -#define __NR_mq_notify 266 -#define __NR_mq_getsetattr 267 -#define __NR_kexec_load 268 -#define __NR_add_key 269 -#define __NR_request_key 270 -#define __NR_keyctl 271 -#define __NR_waitid 272 -#define __NR_ioprio_set 273 -#define __NR_ioprio_get 274 -#define __NR_inotify_init 275 -#define __NR_inotify_add_watch 276 -#define __NR_inotify_rm_watch 277 -#define __NR_spu_run 278 -#define __NR_spu_create 279 -#define __NR_pselect6 280 -#define __NR_ppoll 281 -#define __NR_unshare 282 -#define __NR_splice 283 -#define __NR_tee 284 -#define __NR_vmsplice 285 -#define __NR_openat 286 -#define __NR_mkdirat 287 -#define __NR_mknodat 288 -#define __NR_fchownat 289 -#define __NR_futimesat 290 -#define __NR_fstatat64 291 -#define __NR_unlinkat 292 -#define __NR_renameat 293 -#define __NR_linkat 294 -#define __NR_symlinkat 295 -#define __NR_readlinkat 296 -#define __NR_fchmodat 297 -#define __NR_faccessat 298 -#define __NR_get_robust_list 299 -#define __NR_set_robust_list 300 -#define __NR_move_pages 301 -#define __NR_getcpu 302 -#define __NR_epoll_pwait 303 -#define __NR_utimensat 304 -#define __NR_signalfd 305 -#define __NR_timerfd_create 306 -#define __NR_eventfd 307 -#define __NR_sync_file_range2 308 -#define __NR_fallocate 309 -#define __NR_subpage_prot 310 -#define __NR_timerfd_settime 311 -#define __NR_timerfd_gettime 312 -#define __NR_signalfd4 313 -#define __NR_eventfd2 314 -#define __NR_epoll_create1 315 -#define __NR_dup3 316 -#define __NR_pipe2 317 -#define __NR_inotify_init1 318 -#define __NR_perf_event_open 319 -#define __NR_preadv 320 -#define __NR_pwritev 321 -#define __NR_rt_tgsigqueueinfo 322 -#define __NR_fanotify_init 323 -#define __NR_fanotify_mark 324 -#define __NR_prlimit64 325 -#define __NR_socket 326 -#define __NR_bind 327 -#define __NR_connect 328 -#define __NR_listen 329 -#define __NR_accept 330 -#define __NR_getsockname 331 -#define __NR_getpeername 332 -#define __NR_socketpair 333 -#define __NR_send 334 -#define __NR_sendto 335 -#define __NR_recv 336 -#define __NR_recvfrom 337 -#define __NR_shutdown 338 -#define __NR_setsockopt 339 -#define __NR_getsockopt 340 -#define __NR_sendmsg 341 -#define __NR_recvmsg 342 -#define __NR_recvmmsg 343 -#define __NR_accept4 344 -#define __NR_name_to_handle_at 345 -#define __NR_open_by_handle_at 346 -#define __NR_clock_adjtime 347 -#define __NR_syncfs 348 -#define __NR_sendmmsg 349 -#define __NR_setns 350 -#define __NR_process_vm_readv 351 -#define __NR_process_vm_writev 352 -#define __NR_finit_module 353 -#define __NR_kcmp 354 -#define __NR_sched_setattr 355 -#define __NR_sched_getattr 356 -#define __NR_renameat2 357 -#define __NR_seccomp 358 -#define __NR_getrandom 359 -#define __NR_memfd_create 360 -#define __NR_bpf 361 -#define __NR_execveat 362 -#define __NR_switch_endian 363 -#define __NR_userfaultfd 364 -#define __NR_membarrier 365 -#define __NR_mlock2 378 -#define __NR_copy_file_range 379 -#define __NR_preadv2 380 -#define __NR_pwritev2 381 -#define __NR_kexec_file_load 382 -#define __NR_statx 383 -#define __NR_pkey_alloc 384 -#define __NR_pkey_free 385 -#define __NR_pkey_mprotect 386 -#define __NR_rseq 387 -#define __NR_io_pgetevents 388 -#define __NR_semget 393 -#define __NR_semctl 394 -#define __NR_shmget 395 -#define __NR_shmctl 396 -#define __NR_shmat 397 -#define __NR_shmdt 398 -#define __NR_msgget 399 -#define __NR_msgsnd 400 -#define __NR_msgrcv 401 -#define __NR_msgctl 402 -#define __NR_clock_gettime64 403 -#define __NR_clock_settime64 404 -#define __NR_clock_adjtime64 405 -#define __NR_clock_getres_time64 406 -#define __NR_clock_nanosleep_time64 407 -#define __NR_timer_gettime64 408 -#define __NR_timer_settime64 409 -#define __NR_timerfd_gettime64 410 -#define __NR_timerfd_settime64 411 -#define __NR_utimensat_time64 412 -#define __NR_pselect6_time64 413 -#define __NR_ppoll_time64 414 -#define __NR_io_pgetevents_time64 416 -#define __NR_recvmmsg_time64 417 -#define __NR_mq_timedsend_time64 418 -#define __NR_mq_timedreceive_time64 419 -#define __NR_semtimedop_time64 420 -#define __NR_rt_sigtimedwait_time64 421 -#define __NR_futex_time64 422 -#define __NR_sched_rr_get_interval_time64 423 -#define __NR_pidfd_send_signal 424 -#define __NR_io_uring_setup 425 -#define __NR_io_uring_enter 426 -#define __NR_io_uring_register 427 -#define __NR_open_tree 428 -#define __NR_move_mount 429 -#define __NR_fsopen 430 -#define __NR_fsconfig 431 -#define __NR_fsmount 432 -#define __NR_fspick 433 -#define __NR_pidfd_open 434 -#define __NR_clone3 435 -#define __NR_close_range 436 -#define __NR_openat2 437 -#define __NR_pidfd_getfd 438 -#define __NR_faccessat2 439 -#define __NR_process_madvise 440 -#define __NR_epoll_pwait2 441 +#define __NR_restart_syscall 0 +#define __NR_exit 1 +#define __NR_fork 2 +#define __NR_read 3 +#define __NR_write 4 +#define __NR_open 5 +#define __NR_close 6 +#define __NR_waitpid 7 +#define __NR_creat 8 +#define __NR_link 9 +#define __NR_unlink 10 +#define __NR_execve 11 +#define __NR_chdir 12 +#define __NR_time 13 +#define __NR_mknod 14 +#define __NR_chmod 15 +#define __NR_lchown 16 +#define __NR_break 17 +#define __NR_oldstat 18 +#define __NR_lseek 19 +#define __NR_getpid 20 +#define __NR_mount 21 +#define __NR_umount 22 +#define __NR_setuid 23 +#define __NR_getuid 24 +#define __NR_stime 25 +#define __NR_ptrace 26 +#define __NR_alarm 27 +#define __NR_oldfstat 28 +#define __NR_pause 29 +#define __NR_utime 30 +#define __NR_stty 31 +#define __NR_gtty 32 +#define __NR_access 33 +#define __NR_nice 34 +#define __NR_ftime 35 +#define __NR_sync 36 +#define __NR_kill 37 +#define __NR_rename 38 +#define __NR_mkdir 39 +#define __NR_rmdir 40 +#define __NR_dup 41 +#define __NR_pipe 42 +#define __NR_times 43 +#define __NR_prof 44 +#define __NR_brk 45 +#define __NR_setgid 46 +#define __NR_getgid 47 +#define __NR_signal 48 +#define __NR_geteuid 49 +#define __NR_getegid 50 +#define __NR_acct 51 +#define __NR_umount2 52 +#define __NR_lock 53 +#define __NR_ioctl 54 +#define __NR_fcntl 55 +#define __NR_mpx 56 +#define __NR_setpgid 57 +#define __NR_ulimit 58 +#define __NR_oldolduname 59 +#define __NR_umask 60 +#define __NR_chroot 61 +#define __NR_ustat 62 +#define __NR_dup2 63 +#define __NR_getppid 64 +#define __NR_getpgrp 65 +#define __NR_setsid 66 +#define __NR_sigaction 67 +#define __NR_sgetmask 68 +#define __NR_ssetmask 69 +#define __NR_setreuid 70 +#define __NR_setregid 71 +#define __NR_sigsuspend 72 +#define __NR_sigpending 73 +#define __NR_sethostname 74 +#define __NR_setrlimit 75 +#define __NR_getrlimit 76 +#define __NR_getrusage 77 +#define __NR_gettimeofday 78 +#define __NR_settimeofday 79 +#define __NR_getgroups 80 +#define __NR_setgroups 81 +#define __NR_select 82 +#define __NR_symlink 83 +#define __NR_oldlstat 84 +#define __NR_readlink 85 +#define __NR_uselib 86 +#define __NR_swapon 87 +#define __NR_reboot 88 +#define __NR_readdir 89 +#define __NR_mmap 90 +#define __NR_munmap 91 +#define __NR_truncate 92 +#define __NR_ftruncate 93 +#define __NR_fchmod 94 +#define __NR_fchown 95 +#define __NR_getpriority 96 +#define __NR_setpriority 97 +#define __NR_profil 98 +#define __NR_statfs 99 +#define __NR_fstatfs 100 +#define __NR_ioperm 101 +#define __NR_socketcall 102 +#define __NR_syslog 103 +#define __NR_setitimer 104 +#define __NR_getitimer 105 +#define __NR_stat 106 +#define __NR_lstat 107 +#define __NR_fstat 108 +#define __NR_olduname 109 +#define __NR_iopl 110 +#define __NR_vhangup 111 +#define __NR_idle 112 +#define __NR_vm86 113 +#define __NR_wait4 114 +#define __NR_swapoff 115 +#define __NR_sysinfo 116 +#define __NR_ipc 117 +#define __NR_fsync 118 +#define __NR_sigreturn 119 +#define __NR_clone 120 +#define __NR_setdomainname 121 +#define __NR_uname 122 +#define __NR_modify_ldt 123 +#define __NR_adjtimex 124 +#define __NR_mprotect 125 +#define __NR_sigprocmask 126 +#define __NR_create_module 127 +#define __NR_init_module 128 +#define __NR_delete_module 129 +#define __NR_get_kernel_syms 130 +#define __NR_quotactl 131 +#define __NR_getpgid 132 +#define __NR_fchdir 133 +#define __NR_bdflush 134 +#define __NR_sysfs 135 +#define __NR_personality 136 +#define __NR_afs_syscall 137 +#define __NR_setfsuid 138 +#define __NR_setfsgid 139 +#define __NR__llseek 140 +#define __NR_getdents 141 +#define __NR__newselect 142 +#define __NR_flock 143 +#define __NR_msync 144 +#define __NR_readv 145 +#define __NR_writev 146 +#define __NR_getsid 147 +#define __NR_fdatasync 148 +#define __NR__sysctl 149 +#define __NR_mlock 150 +#define __NR_munlock 151 +#define __NR_mlockall 152 +#define __NR_munlockall 153 +#define __NR_sched_setparam 154 +#define __NR_sched_getparam 155 +#define __NR_sched_setscheduler 156 +#define __NR_sched_getscheduler 157 +#define __NR_sched_yield 158 +#define __NR_sched_get_priority_max 159 +#define __NR_sched_get_priority_min 160 +#define __NR_sched_rr_get_interval 161 +#define __NR_nanosleep 162 +#define __NR_mremap 163 +#define __NR_setresuid 164 +#define __NR_getresuid 165 +#define __NR_query_module 166 +#define __NR_poll 167 +#define __NR_nfsservctl 168 +#define __NR_setresgid 169 +#define __NR_getresgid 170 +#define __NR_prctl 171 +#define __NR_rt_sigreturn 172 +#define __NR_rt_sigaction 173 +#define __NR_rt_sigprocmask 174 +#define __NR_rt_sigpending 175 +#define __NR_rt_sigtimedwait 176 +#define __NR_rt_sigqueueinfo 177 +#define __NR_rt_sigsuspend 178 +#define __NR_pread64 179 +#define __NR_pwrite64 180 +#define __NR_chown 181 +#define __NR_getcwd 182 +#define __NR_capget 183 +#define __NR_capset 184 +#define __NR_sigaltstack 185 +#define __NR_sendfile 186 +#define __NR_getpmsg 187 +#define __NR_putpmsg 188 +#define __NR_vfork 189 +#define __NR_ugetrlimit 190 +#define __NR_readahead 191 +#define __NR_mmap2 192 +#define __NR_truncate64 193 +#define __NR_ftruncate64 194 +#define __NR_stat64 195 +#define __NR_lstat64 196 +#define __NR_fstat64 197 +#define __NR_pciconfig_read 198 +#define __NR_pciconfig_write 199 +#define __NR_pciconfig_iobase 200 +#define __NR_multiplexer 201 +#define __NR_getdents64 202 +#define __NR_pivot_root 203 +#define __NR_fcntl64 204 +#define __NR_madvise 205 +#define __NR_mincore 206 +#define __NR_gettid 207 +#define __NR_tkill 208 +#define __NR_setxattr 209 +#define __NR_lsetxattr 210 +#define __NR_fsetxattr 211 +#define __NR_getxattr 212 +#define __NR_lgetxattr 213 +#define __NR_fgetxattr 214 +#define __NR_listxattr 215 +#define __NR_llistxattr 216 +#define __NR_flistxattr 217 +#define __NR_removexattr 218 +#define __NR_lremovexattr 219 +#define __NR_fremovexattr 220 +#define __NR_futex 221 +#define __NR_sched_setaffinity 222 +#define __NR_sched_getaffinity 223 +#define __NR_tuxcall 225 +#define __NR_sendfile64 226 +#define __NR_io_setup 227 +#define __NR_io_destroy 228 +#define __NR_io_getevents 229 +#define __NR_io_submit 230 +#define __NR_io_cancel 231 +#define __NR_set_tid_address 232 +#define __NR_fadvise64 233 +#define __NR_exit_group 234 +#define __NR_lookup_dcookie 235 +#define __NR_epoll_create 236 +#define __NR_epoll_ctl 237 +#define __NR_epoll_wait 238 +#define __NR_remap_file_pages 239 +#define __NR_timer_create 240 +#define __NR_timer_settime 241 +#define __NR_timer_gettime 242 +#define __NR_timer_getoverrun 243 +#define __NR_timer_delete 244 +#define __NR_clock_settime 245 +#define __NR_clock_gettime 246 +#define __NR_clock_getres 247 +#define __NR_clock_nanosleep 248 +#define __NR_swapcontext 249 +#define __NR_tgkill 250 +#define __NR_utimes 251 +#define __NR_statfs64 252 +#define __NR_fstatfs64 253 +#define __NR_fadvise64_64 254 +#define __NR_rtas 255 +#define __NR_sys_debug_setcontext 256 +#define __NR_migrate_pages 258 +#define __NR_mbind 259 +#define __NR_get_mempolicy 260 +#define __NR_set_mempolicy 261 +#define __NR_mq_open 262 +#define __NR_mq_unlink 263 +#define __NR_mq_timedsend 264 +#define __NR_mq_timedreceive 265 +#define __NR_mq_notify 266 +#define __NR_mq_getsetattr 267 +#define __NR_kexec_load 268 +#define __NR_add_key 269 +#define __NR_request_key 270 +#define __NR_keyctl 271 +#define __NR_waitid 272 +#define __NR_ioprio_set 273 +#define __NR_ioprio_get 274 +#define __NR_inotify_init 275 +#define __NR_inotify_add_watch 276 +#define __NR_inotify_rm_watch 277 +#define __NR_spu_run 278 +#define __NR_spu_create 279 +#define __NR_pselect6 280 +#define __NR_ppoll 281 +#define __NR_unshare 282 +#define __NR_splice 283 +#define __NR_tee 284 +#define __NR_vmsplice 285 +#define __NR_openat 286 +#define __NR_mkdirat 287 +#define __NR_mknodat 288 +#define __NR_fchownat 289 +#define __NR_futimesat 290 +#define __NR_fstatat64 291 +#define __NR_unlinkat 292 +#define __NR_renameat 293 +#define __NR_linkat 294 +#define __NR_symlinkat 295 +#define __NR_readlinkat 296 +#define __NR_fchmodat 297 +#define __NR_faccessat 298 +#define __NR_get_robust_list 299 +#define __NR_set_robust_list 300 +#define __NR_move_pages 301 +#define __NR_getcpu 302 +#define __NR_epoll_pwait 303 +#define __NR_utimensat 304 +#define __NR_signalfd 305 +#define __NR_timerfd_create 306 +#define __NR_eventfd 307 +#define __NR_sync_file_range2 308 +#define __NR_fallocate 309 +#define __NR_subpage_prot 310 +#define __NR_timerfd_settime 311 +#define __NR_timerfd_gettime 312 +#define __NR_signalfd4 313 +#define __NR_eventfd2 314 +#define __NR_epoll_create1 315 +#define __NR_dup3 316 +#define __NR_pipe2 317 +#define __NR_inotify_init1 318 +#define __NR_perf_event_open 319 +#define __NR_preadv 320 +#define __NR_pwritev 321 +#define __NR_rt_tgsigqueueinfo 322 +#define __NR_fanotify_init 323 +#define __NR_fanotify_mark 324 +#define __NR_prlimit64 325 +#define __NR_socket 326 +#define __NR_bind 327 +#define __NR_connect 328 +#define __NR_listen 329 +#define __NR_accept 330 +#define __NR_getsockname 331 +#define __NR_getpeername 332 +#define __NR_socketpair 333 +#define __NR_send 334 +#define __NR_sendto 335 +#define __NR_recv 336 +#define __NR_recvfrom 337 +#define __NR_shutdown 338 +#define __NR_setsockopt 339 +#define __NR_getsockopt 340 +#define __NR_sendmsg 341 +#define __NR_recvmsg 342 +#define __NR_recvmmsg 343 +#define __NR_accept4 344 +#define __NR_name_to_handle_at 345 +#define __NR_open_by_handle_at 346 +#define __NR_clock_adjtime 347 +#define __NR_syncfs 348 +#define __NR_sendmmsg 349 +#define __NR_setns 350 +#define __NR_process_vm_readv 351 +#define __NR_process_vm_writev 352 +#define __NR_finit_module 353 +#define __NR_kcmp 354 +#define __NR_sched_setattr 355 +#define __NR_sched_getattr 356 +#define __NR_renameat2 357 +#define __NR_seccomp 358 +#define __NR_getrandom 359 +#define __NR_memfd_create 360 +#define __NR_bpf 361 +#define __NR_execveat 362 +#define __NR_switch_endian 363 +#define __NR_userfaultfd 364 +#define __NR_membarrier 365 +#define __NR_mlock2 378 +#define __NR_copy_file_range 379 +#define __NR_preadv2 380 +#define __NR_pwritev2 381 +#define __NR_kexec_file_load 382 +#define __NR_statx 383 +#define __NR_pkey_alloc 384 +#define __NR_pkey_free 385 +#define __NR_pkey_mprotect 386 +#define __NR_rseq 387 +#define __NR_io_pgetevents 388 +#define __NR_semget 393 +#define __NR_semctl 394 +#define __NR_shmget 395 +#define __NR_shmctl 396 +#define __NR_shmat 397 +#define __NR_shmdt 398 +#define __NR_msgget 399 +#define __NR_msgsnd 400 +#define __NR_msgrcv 401 +#define __NR_msgctl 402 +#define __NR_clock_gettime64 403 +#define __NR_clock_settime64 404 +#define __NR_clock_adjtime64 405 +#define __NR_clock_getres_time64 406 +#define __NR_clock_nanosleep_time64 407 +#define __NR_timer_gettime64 408 +#define __NR_timer_settime64 409 +#define __NR_timerfd_gettime64 410 +#define __NR_timerfd_settime64 411 +#define __NR_utimensat_time64 412 +#define __NR_pselect6_time64 413 +#define __NR_ppoll_time64 414 +#define __NR_io_pgetevents_time64 416 +#define __NR_recvmmsg_time64 417 +#define __NR_mq_timedsend_time64 418 +#define __NR_mq_timedreceive_time64 419 +#define __NR_semtimedop_time64 420 +#define __NR_rt_sigtimedwait_time64 421 +#define __NR_futex_time64 422 +#define __NR_sched_rr_get_interval_time64 423 +#define __NR_pidfd_send_signal 424 +#define __NR_io_uring_setup 425 +#define __NR_io_uring_enter 426 +#define __NR_io_uring_register 427 +#define __NR_open_tree 428 +#define __NR_move_mount 429 +#define __NR_fsopen 430 +#define __NR_fsconfig 431 +#define __NR_fsmount 432 +#define __NR_fspick 433 +#define __NR_pidfd_open 434 +#define __NR_clone3 435 +#define __NR_close_range 436 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 +#define __NR_faccessat2 439 +#define __NR_process_madvise 440 +#define __NR_epoll_pwait2 441 +#define __NR_mount_setattr 442 +#define __NR_quotactl_fd 443 +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 -#endif /* _ASM_POWERPC_UNISTD_32_H */ +#endif /* _ASM_UNISTD_32_H */ diff --git a/linux-headers/asm-powerpc/unistd_64.h b/linux-headers/asm-powerpc/unistd_64.h index 7e851b30bb..8458effa8d 100644 --- a/linux-headers/asm-powerpc/unistd_64.h +++ b/linux-headers/asm-powerpc/unistd_64.h @@ -1,401 +1,406 @@ -#ifndef _ASM_POWERPC_UNISTD_64_H -#define _ASM_POWERPC_UNISTD_64_H +#ifndef _ASM_UNISTD_64_H +#define _ASM_UNISTD_64_H -#define __NR_restart_syscall 0 -#define __NR_exit 1 -#define __NR_fork 2 -#define __NR_read 3 -#define __NR_write 4 -#define __NR_open 5 -#define __NR_close 6 -#define __NR_waitpid 7 -#define __NR_creat 8 -#define __NR_link 9 -#define __NR_unlink 10 -#define __NR_execve 11 -#define __NR_chdir 12 -#define __NR_time 13 -#define __NR_mknod 14 -#define __NR_chmod 15 -#define __NR_lchown 16 -#define __NR_break 17 -#define __NR_oldstat 18 -#define __NR_lseek 19 -#define __NR_getpid 20 -#define __NR_mount 21 -#define __NR_umount 22 -#define __NR_setuid 23 -#define __NR_getuid 24 -#define __NR_stime 25 -#define __NR_ptrace 26 -#define __NR_alarm 27 -#define __NR_oldfstat 28 -#define __NR_pause 29 -#define __NR_utime 30 -#define __NR_stty 31 -#define __NR_gtty 32 -#define __NR_access 33 -#define __NR_nice 34 -#define __NR_ftime 35 -#define __NR_sync 36 -#define __NR_kill 37 -#define __NR_rename 38 -#define __NR_mkdir 39 -#define __NR_rmdir 40 -#define __NR_dup 41 -#define __NR_pipe 42 -#define __NR_times 43 -#define __NR_prof 44 -#define __NR_brk 45 -#define __NR_setgid 46 -#define __NR_getgid 47 -#define __NR_signal 48 -#define __NR_geteuid 49 -#define __NR_getegid 50 -#define __NR_acct 51 -#define __NR_umount2 52 -#define __NR_lock 53 -#define __NR_ioctl 54 -#define __NR_fcntl 55 -#define __NR_mpx 56 -#define __NR_setpgid 57 -#define __NR_ulimit 58 -#define __NR_oldolduname 59 -#define __NR_umask 60 -#define __NR_chroot 61 -#define __NR_ustat 62 -#define __NR_dup2 63 -#define __NR_getppid 64 -#define __NR_getpgrp 65 -#define __NR_setsid 66 -#define __NR_sigaction 67 -#define __NR_sgetmask 68 -#define __NR_ssetmask 69 -#define __NR_setreuid 70 -#define __NR_setregid 71 -#define __NR_sigsuspend 72 -#define __NR_sigpending 73 -#define __NR_sethostname 74 -#define __NR_setrlimit 75 -#define __NR_getrlimit 76 -#define __NR_getrusage 77 -#define __NR_gettimeofday 78 -#define __NR_settimeofday 79 -#define __NR_getgroups 80 -#define __NR_setgroups 81 -#define __NR_select 82 -#define __NR_symlink 83 -#define __NR_oldlstat 84 -#define __NR_readlink 85 -#define __NR_uselib 86 -#define __NR_swapon 87 -#define __NR_reboot 88 -#define __NR_readdir 89 -#define __NR_mmap 90 -#define __NR_munmap 91 -#define __NR_truncate 92 -#define __NR_ftruncate 93 -#define __NR_fchmod 94 -#define __NR_fchown 95 -#define __NR_getpriority 96 -#define __NR_setpriority 97 -#define __NR_profil 98 -#define __NR_statfs 99 -#define __NR_fstatfs 100 -#define __NR_ioperm 101 -#define __NR_socketcall 102 -#define __NR_syslog 103 -#define __NR_setitimer 104 -#define __NR_getitimer 105 -#define __NR_stat 106 -#define __NR_lstat 107 -#define __NR_fstat 108 -#define __NR_olduname 109 -#define __NR_iopl 110 -#define __NR_vhangup 111 -#define __NR_idle 112 -#define __NR_vm86 113 -#define __NR_wait4 114 -#define __NR_swapoff 115 -#define __NR_sysinfo 116 -#define __NR_ipc 117 -#define __NR_fsync 118 -#define __NR_sigreturn 119 -#define __NR_clone 120 -#define __NR_setdomainname 121 -#define __NR_uname 122 -#define __NR_modify_ldt 123 -#define __NR_adjtimex 124 -#define __NR_mprotect 125 -#define __NR_sigprocmask 126 -#define __NR_create_module 127 -#define __NR_init_module 128 -#define __NR_delete_module 129 -#define __NR_get_kernel_syms 130 -#define __NR_quotactl 131 -#define __NR_getpgid 132 -#define __NR_fchdir 133 -#define __NR_bdflush 134 -#define __NR_sysfs 135 -#define __NR_personality 136 -#define __NR_afs_syscall 137 -#define __NR_setfsuid 138 -#define __NR_setfsgid 139 -#define __NR__llseek 140 -#define __NR_getdents 141 -#define __NR__newselect 142 -#define __NR_flock 143 -#define __NR_msync 144 -#define __NR_readv 145 -#define __NR_writev 146 -#define __NR_getsid 147 -#define __NR_fdatasync 148 -#define __NR__sysctl 149 -#define __NR_mlock 150 -#define __NR_munlock 151 -#define __NR_mlockall 152 -#define __NR_munlockall 153 -#define __NR_sched_setparam 154 -#define __NR_sched_getparam 155 -#define __NR_sched_setscheduler 156 -#define __NR_sched_getscheduler 157 -#define __NR_sched_yield 158 -#define __NR_sched_get_priority_max 159 -#define __NR_sched_get_priority_min 160 -#define __NR_sched_rr_get_interval 161 -#define __NR_nanosleep 162 -#define __NR_mremap 163 -#define __NR_setresuid 164 -#define __NR_getresuid 165 -#define __NR_query_module 166 -#define __NR_poll 167 -#define __NR_nfsservctl 168 -#define __NR_setresgid 169 -#define __NR_getresgid 170 -#define __NR_prctl 171 -#define __NR_rt_sigreturn 172 -#define __NR_rt_sigaction 173 -#define __NR_rt_sigprocmask 174 -#define __NR_rt_sigpending 175 -#define __NR_rt_sigtimedwait 176 -#define __NR_rt_sigqueueinfo 177 -#define __NR_rt_sigsuspend 178 -#define __NR_pread64 179 -#define __NR_pwrite64 180 -#define __NR_chown 181 -#define __NR_getcwd 182 -#define __NR_capget 183 -#define __NR_capset 184 -#define __NR_sigaltstack 185 -#define __NR_sendfile 186 -#define __NR_getpmsg 187 -#define __NR_putpmsg 188 -#define __NR_vfork 189 -#define __NR_ugetrlimit 190 -#define __NR_readahead 191 -#define __NR_pciconfig_read 198 -#define __NR_pciconfig_write 199 -#define __NR_pciconfig_iobase 200 -#define __NR_multiplexer 201 -#define __NR_getdents64 202 -#define __NR_pivot_root 203 -#define __NR_madvise 205 -#define __NR_mincore 206 -#define __NR_gettid 207 -#define __NR_tkill 208 -#define __NR_setxattr 209 -#define __NR_lsetxattr 210 -#define __NR_fsetxattr 211 -#define __NR_getxattr 212 -#define __NR_lgetxattr 213 -#define __NR_fgetxattr 214 -#define __NR_listxattr 215 -#define __NR_llistxattr 216 -#define __NR_flistxattr 217 -#define __NR_removexattr 218 -#define __NR_lremovexattr 219 -#define __NR_fremovexattr 220 -#define __NR_futex 221 -#define __NR_sched_setaffinity 222 -#define __NR_sched_getaffinity 223 -#define __NR_tuxcall 225 -#define __NR_io_setup 227 -#define __NR_io_destroy 228 -#define __NR_io_getevents 229 -#define __NR_io_submit 230 -#define __NR_io_cancel 231 -#define __NR_set_tid_address 232 -#define __NR_fadvise64 233 -#define __NR_exit_group 234 -#define __NR_lookup_dcookie 235 -#define __NR_epoll_create 236 -#define __NR_epoll_ctl 237 -#define __NR_epoll_wait 238 -#define __NR_remap_file_pages 239 -#define __NR_timer_create 240 -#define __NR_timer_settime 241 -#define __NR_timer_gettime 242 -#define __NR_timer_getoverrun 243 -#define __NR_timer_delete 244 -#define __NR_clock_settime 245 -#define __NR_clock_gettime 246 -#define __NR_clock_getres 247 -#define __NR_clock_nanosleep 248 -#define __NR_swapcontext 249 -#define __NR_tgkill 250 -#define __NR_utimes 251 -#define __NR_statfs64 252 -#define __NR_fstatfs64 253 -#define __NR_rtas 255 -#define __NR_sys_debug_setcontext 256 -#define __NR_migrate_pages 258 -#define __NR_mbind 259 -#define __NR_get_mempolicy 260 -#define __NR_set_mempolicy 261 -#define __NR_mq_open 262 -#define __NR_mq_unlink 263 -#define __NR_mq_timedsend 264 -#define __NR_mq_timedreceive 265 -#define __NR_mq_notify 266 -#define __NR_mq_getsetattr 267 -#define __NR_kexec_load 268 -#define __NR_add_key 269 -#define __NR_request_key 270 -#define __NR_keyctl 271 -#define __NR_waitid 272 -#define __NR_ioprio_set 273 -#define __NR_ioprio_get 274 -#define __NR_inotify_init 275 -#define __NR_inotify_add_watch 276 -#define __NR_inotify_rm_watch 277 -#define __NR_spu_run 278 -#define __NR_spu_create 279 -#define __NR_pselect6 280 -#define __NR_ppoll 281 -#define __NR_unshare 282 -#define __NR_splice 283 -#define __NR_tee 284 -#define __NR_vmsplice 285 -#define __NR_openat 286 -#define __NR_mkdirat 287 -#define __NR_mknodat 288 -#define __NR_fchownat 289 -#define __NR_futimesat 290 -#define __NR_newfstatat 291 -#define __NR_unlinkat 292 -#define __NR_renameat 293 -#define __NR_linkat 294 -#define __NR_symlinkat 295 -#define __NR_readlinkat 296 -#define __NR_fchmodat 297 -#define __NR_faccessat 298 -#define __NR_get_robust_list 299 -#define __NR_set_robust_list 300 -#define __NR_move_pages 301 -#define __NR_getcpu 302 -#define __NR_epoll_pwait 303 -#define __NR_utimensat 304 -#define __NR_signalfd 305 -#define __NR_timerfd_create 306 -#define __NR_eventfd 307 -#define __NR_sync_file_range2 308 -#define __NR_fallocate 309 -#define __NR_subpage_prot 310 -#define __NR_timerfd_settime 311 -#define __NR_timerfd_gettime 312 -#define __NR_signalfd4 313 -#define __NR_eventfd2 314 -#define __NR_epoll_create1 315 -#define __NR_dup3 316 -#define __NR_pipe2 317 -#define __NR_inotify_init1 318 -#define __NR_perf_event_open 319 -#define __NR_preadv 320 -#define __NR_pwritev 321 -#define __NR_rt_tgsigqueueinfo 322 -#define __NR_fanotify_init 323 -#define __NR_fanotify_mark 324 -#define __NR_prlimit64 325 -#define __NR_socket 326 -#define __NR_bind 327 -#define __NR_connect 328 -#define __NR_listen 329 -#define __NR_accept 330 -#define __NR_getsockname 331 -#define __NR_getpeername 332 -#define __NR_socketpair 333 -#define __NR_send 334 -#define __NR_sendto 335 -#define __NR_recv 336 -#define __NR_recvfrom 337 -#define __NR_shutdown 338 -#define __NR_setsockopt 339 -#define __NR_getsockopt 340 -#define __NR_sendmsg 341 -#define __NR_recvmsg 342 -#define __NR_recvmmsg 343 -#define __NR_accept4 344 -#define __NR_name_to_handle_at 345 -#define __NR_open_by_handle_at 346 -#define __NR_clock_adjtime 347 -#define __NR_syncfs 348 -#define __NR_sendmmsg 349 -#define __NR_setns 350 -#define __NR_process_vm_readv 351 -#define __NR_process_vm_writev 352 -#define __NR_finit_module 353 -#define __NR_kcmp 354 -#define __NR_sched_setattr 355 -#define __NR_sched_getattr 356 -#define __NR_renameat2 357 -#define __NR_seccomp 358 -#define __NR_getrandom 359 -#define __NR_memfd_create 360 -#define __NR_bpf 361 -#define __NR_execveat 362 -#define __NR_switch_endian 363 -#define __NR_userfaultfd 364 -#define __NR_membarrier 365 -#define __NR_mlock2 378 -#define __NR_copy_file_range 379 -#define __NR_preadv2 380 -#define __NR_pwritev2 381 -#define __NR_kexec_file_load 382 -#define __NR_statx 383 -#define __NR_pkey_alloc 384 -#define __NR_pkey_free 385 -#define __NR_pkey_mprotect 386 -#define __NR_rseq 387 -#define __NR_io_pgetevents 388 -#define __NR_semtimedop 392 -#define __NR_semget 393 -#define __NR_semctl 394 -#define __NR_shmget 395 -#define __NR_shmctl 396 -#define __NR_shmat 397 -#define __NR_shmdt 398 -#define __NR_msgget 399 -#define __NR_msgsnd 400 -#define __NR_msgrcv 401 -#define __NR_msgctl 402 -#define __NR_pidfd_send_signal 424 -#define __NR_io_uring_setup 425 -#define __NR_io_uring_enter 426 -#define __NR_io_uring_register 427 -#define __NR_open_tree 428 -#define __NR_move_mount 429 -#define __NR_fsopen 430 -#define __NR_fsconfig 431 -#define __NR_fsmount 432 -#define __NR_fspick 433 -#define __NR_pidfd_open 434 -#define __NR_clone3 435 -#define __NR_close_range 436 -#define __NR_openat2 437 -#define __NR_pidfd_getfd 438 -#define __NR_faccessat2 439 -#define __NR_process_madvise 440 -#define __NR_epoll_pwait2 441 +#define __NR_restart_syscall 0 +#define __NR_exit 1 +#define __NR_fork 2 +#define __NR_read 3 +#define __NR_write 4 +#define __NR_open 5 +#define __NR_close 6 +#define __NR_waitpid 7 +#define __NR_creat 8 +#define __NR_link 9 +#define __NR_unlink 10 +#define __NR_execve 11 +#define __NR_chdir 12 +#define __NR_time 13 +#define __NR_mknod 14 +#define __NR_chmod 15 +#define __NR_lchown 16 +#define __NR_break 17 +#define __NR_oldstat 18 +#define __NR_lseek 19 +#define __NR_getpid 20 +#define __NR_mount 21 +#define __NR_umount 22 +#define __NR_setuid 23 +#define __NR_getuid 24 +#define __NR_stime 25 +#define __NR_ptrace 26 +#define __NR_alarm 27 +#define __NR_oldfstat 28 +#define __NR_pause 29 +#define __NR_utime 30 +#define __NR_stty 31 +#define __NR_gtty 32 +#define __NR_access 33 +#define __NR_nice 34 +#define __NR_ftime 35 +#define __NR_sync 36 +#define __NR_kill 37 +#define __NR_rename 38 +#define __NR_mkdir 39 +#define __NR_rmdir 40 +#define __NR_dup 41 +#define __NR_pipe 42 +#define __NR_times 43 +#define __NR_prof 44 +#define __NR_brk 45 +#define __NR_setgid 46 +#define __NR_getgid 47 +#define __NR_signal 48 +#define __NR_geteuid 49 +#define __NR_getegid 50 +#define __NR_acct 51 +#define __NR_umount2 52 +#define __NR_lock 53 +#define __NR_ioctl 54 +#define __NR_fcntl 55 +#define __NR_mpx 56 +#define __NR_setpgid 57 +#define __NR_ulimit 58 +#define __NR_oldolduname 59 +#define __NR_umask 60 +#define __NR_chroot 61 +#define __NR_ustat 62 +#define __NR_dup2 63 +#define __NR_getppid 64 +#define __NR_getpgrp 65 +#define __NR_setsid 66 +#define __NR_sigaction 67 +#define __NR_sgetmask 68 +#define __NR_ssetmask 69 +#define __NR_setreuid 70 +#define __NR_setregid 71 +#define __NR_sigsuspend 72 +#define __NR_sigpending 73 +#define __NR_sethostname 74 +#define __NR_setrlimit 75 +#define __NR_getrlimit 76 +#define __NR_getrusage 77 +#define __NR_gettimeofday 78 +#define __NR_settimeofday 79 +#define __NR_getgroups 80 +#define __NR_setgroups 81 +#define __NR_select 82 +#define __NR_symlink 83 +#define __NR_oldlstat 84 +#define __NR_readlink 85 +#define __NR_uselib 86 +#define __NR_swapon 87 +#define __NR_reboot 88 +#define __NR_readdir 89 +#define __NR_mmap 90 +#define __NR_munmap 91 +#define __NR_truncate 92 +#define __NR_ftruncate 93 +#define __NR_fchmod 94 +#define __NR_fchown 95 +#define __NR_getpriority 96 +#define __NR_setpriority 97 +#define __NR_profil 98 +#define __NR_statfs 99 +#define __NR_fstatfs 100 +#define __NR_ioperm 101 +#define __NR_socketcall 102 +#define __NR_syslog 103 +#define __NR_setitimer 104 +#define __NR_getitimer 105 +#define __NR_stat 106 +#define __NR_lstat 107 +#define __NR_fstat 108 +#define __NR_olduname 109 +#define __NR_iopl 110 +#define __NR_vhangup 111 +#define __NR_idle 112 +#define __NR_vm86 113 +#define __NR_wait4 114 +#define __NR_swapoff 115 +#define __NR_sysinfo 116 +#define __NR_ipc 117 +#define __NR_fsync 118 +#define __NR_sigreturn 119 +#define __NR_clone 120 +#define __NR_setdomainname 121 +#define __NR_uname 122 +#define __NR_modify_ldt 123 +#define __NR_adjtimex 124 +#define __NR_mprotect 125 +#define __NR_sigprocmask 126 +#define __NR_create_module 127 +#define __NR_init_module 128 +#define __NR_delete_module 129 +#define __NR_get_kernel_syms 130 +#define __NR_quotactl 131 +#define __NR_getpgid 132 +#define __NR_fchdir 133 +#define __NR_bdflush 134 +#define __NR_sysfs 135 +#define __NR_personality 136 +#define __NR_afs_syscall 137 +#define __NR_setfsuid 138 +#define __NR_setfsgid 139 +#define __NR__llseek 140 +#define __NR_getdents 141 +#define __NR__newselect 142 +#define __NR_flock 143 +#define __NR_msync 144 +#define __NR_readv 145 +#define __NR_writev 146 +#define __NR_getsid 147 +#define __NR_fdatasync 148 +#define __NR__sysctl 149 +#define __NR_mlock 150 +#define __NR_munlock 151 +#define __NR_mlockall 152 +#define __NR_munlockall 153 +#define __NR_sched_setparam 154 +#define __NR_sched_getparam 155 +#define __NR_sched_setscheduler 156 +#define __NR_sched_getscheduler 157 +#define __NR_sched_yield 158 +#define __NR_sched_get_priority_max 159 +#define __NR_sched_get_priority_min 160 +#define __NR_sched_rr_get_interval 161 +#define __NR_nanosleep 162 +#define __NR_mremap 163 +#define __NR_setresuid 164 +#define __NR_getresuid 165 +#define __NR_query_module 166 +#define __NR_poll 167 +#define __NR_nfsservctl 168 +#define __NR_setresgid 169 +#define __NR_getresgid 170 +#define __NR_prctl 171 +#define __NR_rt_sigreturn 172 +#define __NR_rt_sigaction 173 +#define __NR_rt_sigprocmask 174 +#define __NR_rt_sigpending 175 +#define __NR_rt_sigtimedwait 176 +#define __NR_rt_sigqueueinfo 177 +#define __NR_rt_sigsuspend 178 +#define __NR_pread64 179 +#define __NR_pwrite64 180 +#define __NR_chown 181 +#define __NR_getcwd 182 +#define __NR_capget 183 +#define __NR_capset 184 +#define __NR_sigaltstack 185 +#define __NR_sendfile 186 +#define __NR_getpmsg 187 +#define __NR_putpmsg 188 +#define __NR_vfork 189 +#define __NR_ugetrlimit 190 +#define __NR_readahead 191 +#define __NR_pciconfig_read 198 +#define __NR_pciconfig_write 199 +#define __NR_pciconfig_iobase 200 +#define __NR_multiplexer 201 +#define __NR_getdents64 202 +#define __NR_pivot_root 203 +#define __NR_madvise 205 +#define __NR_mincore 206 +#define __NR_gettid 207 +#define __NR_tkill 208 +#define __NR_setxattr 209 +#define __NR_lsetxattr 210 +#define __NR_fsetxattr 211 +#define __NR_getxattr 212 +#define __NR_lgetxattr 213 +#define __NR_fgetxattr 214 +#define __NR_listxattr 215 +#define __NR_llistxattr 216 +#define __NR_flistxattr 217 +#define __NR_removexattr 218 +#define __NR_lremovexattr 219 +#define __NR_fremovexattr 220 +#define __NR_futex 221 +#define __NR_sched_setaffinity 222 +#define __NR_sched_getaffinity 223 +#define __NR_tuxcall 225 +#define __NR_io_setup 227 +#define __NR_io_destroy 228 +#define __NR_io_getevents 229 +#define __NR_io_submit 230 +#define __NR_io_cancel 231 +#define __NR_set_tid_address 232 +#define __NR_fadvise64 233 +#define __NR_exit_group 234 +#define __NR_lookup_dcookie 235 +#define __NR_epoll_create 236 +#define __NR_epoll_ctl 237 +#define __NR_epoll_wait 238 +#define __NR_remap_file_pages 239 +#define __NR_timer_create 240 +#define __NR_timer_settime 241 +#define __NR_timer_gettime 242 +#define __NR_timer_getoverrun 243 +#define __NR_timer_delete 244 +#define __NR_clock_settime 245 +#define __NR_clock_gettime 246 +#define __NR_clock_getres 247 +#define __NR_clock_nanosleep 248 +#define __NR_swapcontext 249 +#define __NR_tgkill 250 +#define __NR_utimes 251 +#define __NR_statfs64 252 +#define __NR_fstatfs64 253 +#define __NR_rtas 255 +#define __NR_sys_debug_setcontext 256 +#define __NR_migrate_pages 258 +#define __NR_mbind 259 +#define __NR_get_mempolicy 260 +#define __NR_set_mempolicy 261 +#define __NR_mq_open 262 +#define __NR_mq_unlink 263 +#define __NR_mq_timedsend 264 +#define __NR_mq_timedreceive 265 +#define __NR_mq_notify 266 +#define __NR_mq_getsetattr 267 +#define __NR_kexec_load 268 +#define __NR_add_key 269 +#define __NR_request_key 270 +#define __NR_keyctl 271 +#define __NR_waitid 272 +#define __NR_ioprio_set 273 +#define __NR_ioprio_get 274 +#define __NR_inotify_init 275 +#define __NR_inotify_add_watch 276 +#define __NR_inotify_rm_watch 277 +#define __NR_spu_run 278 +#define __NR_spu_create 279 +#define __NR_pselect6 280 +#define __NR_ppoll 281 +#define __NR_unshare 282 +#define __NR_splice 283 +#define __NR_tee 284 +#define __NR_vmsplice 285 +#define __NR_openat 286 +#define __NR_mkdirat 287 +#define __NR_mknodat 288 +#define __NR_fchownat 289 +#define __NR_futimesat 290 +#define __NR_newfstatat 291 +#define __NR_unlinkat 292 +#define __NR_renameat 293 +#define __NR_linkat 294 +#define __NR_symlinkat 295 +#define __NR_readlinkat 296 +#define __NR_fchmodat 297 +#define __NR_faccessat 298 +#define __NR_get_robust_list 299 +#define __NR_set_robust_list 300 +#define __NR_move_pages 301 +#define __NR_getcpu 302 +#define __NR_epoll_pwait 303 +#define __NR_utimensat 304 +#define __NR_signalfd 305 +#define __NR_timerfd_create 306 +#define __NR_eventfd 307 +#define __NR_sync_file_range2 308 +#define __NR_fallocate 309 +#define __NR_subpage_prot 310 +#define __NR_timerfd_settime 311 +#define __NR_timerfd_gettime 312 +#define __NR_signalfd4 313 +#define __NR_eventfd2 314 +#define __NR_epoll_create1 315 +#define __NR_dup3 316 +#define __NR_pipe2 317 +#define __NR_inotify_init1 318 +#define __NR_perf_event_open 319 +#define __NR_preadv 320 +#define __NR_pwritev 321 +#define __NR_rt_tgsigqueueinfo 322 +#define __NR_fanotify_init 323 +#define __NR_fanotify_mark 324 +#define __NR_prlimit64 325 +#define __NR_socket 326 +#define __NR_bind 327 +#define __NR_connect 328 +#define __NR_listen 329 +#define __NR_accept 330 +#define __NR_getsockname 331 +#define __NR_getpeername 332 +#define __NR_socketpair 333 +#define __NR_send 334 +#define __NR_sendto 335 +#define __NR_recv 336 +#define __NR_recvfrom 337 +#define __NR_shutdown 338 +#define __NR_setsockopt 339 +#define __NR_getsockopt 340 +#define __NR_sendmsg 341 +#define __NR_recvmsg 342 +#define __NR_recvmmsg 343 +#define __NR_accept4 344 +#define __NR_name_to_handle_at 345 +#define __NR_open_by_handle_at 346 +#define __NR_clock_adjtime 347 +#define __NR_syncfs 348 +#define __NR_sendmmsg 349 +#define __NR_setns 350 +#define __NR_process_vm_readv 351 +#define __NR_process_vm_writev 352 +#define __NR_finit_module 353 +#define __NR_kcmp 354 +#define __NR_sched_setattr 355 +#define __NR_sched_getattr 356 +#define __NR_renameat2 357 +#define __NR_seccomp 358 +#define __NR_getrandom 359 +#define __NR_memfd_create 360 +#define __NR_bpf 361 +#define __NR_execveat 362 +#define __NR_switch_endian 363 +#define __NR_userfaultfd 364 +#define __NR_membarrier 365 +#define __NR_mlock2 378 +#define __NR_copy_file_range 379 +#define __NR_preadv2 380 +#define __NR_pwritev2 381 +#define __NR_kexec_file_load 382 +#define __NR_statx 383 +#define __NR_pkey_alloc 384 +#define __NR_pkey_free 385 +#define __NR_pkey_mprotect 386 +#define __NR_rseq 387 +#define __NR_io_pgetevents 388 +#define __NR_semtimedop 392 +#define __NR_semget 393 +#define __NR_semctl 394 +#define __NR_shmget 395 +#define __NR_shmctl 396 +#define __NR_shmat 397 +#define __NR_shmdt 398 +#define __NR_msgget 399 +#define __NR_msgsnd 400 +#define __NR_msgrcv 401 +#define __NR_msgctl 402 +#define __NR_pidfd_send_signal 424 +#define __NR_io_uring_setup 425 +#define __NR_io_uring_enter 426 +#define __NR_io_uring_register 427 +#define __NR_open_tree 428 +#define __NR_move_mount 429 +#define __NR_fsopen 430 +#define __NR_fsconfig 431 +#define __NR_fsmount 432 +#define __NR_fspick 433 +#define __NR_pidfd_open 434 +#define __NR_clone3 435 +#define __NR_close_range 436 +#define __NR_openat2 437 +#define __NR_pidfd_getfd 438 +#define __NR_faccessat2 439 +#define __NR_process_madvise 440 +#define __NR_epoll_pwait2 441 +#define __NR_mount_setattr 442 +#define __NR_quotactl_fd 443 +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 -#endif /* _ASM_POWERPC_UNISTD_64_H */ +#endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-s390/unistd_32.h b/linux-headers/asm-s390/unistd_32.h index c94d2c3a22..0c3cd299e4 100644 --- a/linux-headers/asm-s390/unistd_32.h +++ b/linux-headers/asm-s390/unistd_32.h @@ -414,5 +414,10 @@ #define __NR_faccessat2 439 #define __NR_process_madvise 440 #define __NR_epoll_pwait2 441 +#define __NR_mount_setattr 442 +#define __NR_quotactl_fd 443 +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 #endif /* _ASM_S390_UNISTD_32_H */ diff --git a/linux-headers/asm-s390/unistd_64.h b/linux-headers/asm-s390/unistd_64.h index 984a06b7eb..8dfc08b5e6 100644 --- a/linux-headers/asm-s390/unistd_64.h +++ b/linux-headers/asm-s390/unistd_64.h @@ -362,5 +362,10 @@ #define __NR_faccessat2 439 #define __NR_process_madvise 440 #define __NR_epoll_pwait2 441 +#define __NR_mount_setattr 442 +#define __NR_quotactl_fd 443 +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 #endif /* _ASM_S390_UNISTD_64_H */ diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h index 8e76d3701d..a6c327f8ad 100644 --- a/linux-headers/asm-x86/kvm.h +++ b/linux-headers/asm-x86/kvm.h @@ -112,6 +112,7 @@ struct kvm_ioapic_state { #define KVM_NR_IRQCHIPS 3 #define KVM_RUN_X86_SMM (1 << 0) +#define KVM_RUN_X86_BUS_LOCK (1 << 1) /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { @@ -158,6 +159,19 @@ struct kvm_sregs { __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64]; }; +struct kvm_sregs2 { + /* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */ + struct kvm_segment cs, ds, es, fs, gs, ss; + struct kvm_segment tr, ldt; + struct kvm_dtable gdt, idt; + __u64 cr0, cr2, cr3, cr4, cr8; + __u64 efer; + __u64 apic_base; + __u64 flags; + __u64 pdptrs[4]; +}; +#define KVM_SREGS2_FLAGS_PDPTRS_VALID 1 + /* for KVM_GET_FPU and KVM_SET_FPU */ struct kvm_fpu { __u8 fpr[8][16]; @@ -436,6 +450,8 @@ struct kvm_vmx_nested_state_hdr { __u16 flags; } smm; + __u16 pad; + __u32 flags; __u64 preemption_timer_deadline; }; diff --git a/linux-headers/asm-x86/unistd_32.h b/linux-headers/asm-x86/unistd_32.h index 18fb99dfa2..66e96c0c68 100644 --- a/linux-headers/asm-x86/unistd_32.h +++ b/linux-headers/asm-x86/unistd_32.h @@ -1,5 +1,5 @@ -#ifndef _ASM_X86_UNISTD_32_H -#define _ASM_X86_UNISTD_32_H 1 +#ifndef _ASM_UNISTD_32_H +#define _ASM_UNISTD_32_H #define __NR_restart_syscall 0 #define __NR_exit 1 @@ -432,6 +432,11 @@ #define __NR_faccessat2 439 #define __NR_process_madvise 440 #define __NR_epoll_pwait2 441 +#define __NR_mount_setattr 442 +#define __NR_quotactl_fd 443 +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 -#endif /* _ASM_X86_UNISTD_32_H */ +#endif /* _ASM_UNISTD_32_H */ diff --git a/linux-headers/asm-x86/unistd_64.h b/linux-headers/asm-x86/unistd_64.h index bde959328d..b8ff6f14ee 100644 --- a/linux-headers/asm-x86/unistd_64.h +++ b/linux-headers/asm-x86/unistd_64.h @@ -1,5 +1,5 @@ -#ifndef _ASM_X86_UNISTD_64_H -#define _ASM_X86_UNISTD_64_H 1 +#ifndef _ASM_UNISTD_64_H +#define _ASM_UNISTD_64_H #define __NR_read 0 #define __NR_write 1 @@ -354,6 +354,11 @@ #define __NR_faccessat2 439 #define __NR_process_madvise 440 #define __NR_epoll_pwait2 441 +#define __NR_mount_setattr 442 +#define __NR_quotactl_fd 443 +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 -#endif /* _ASM_X86_UNISTD_64_H */ +#endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h index 4ff6b17d3b..06a1097c15 100644 --- a/linux-headers/asm-x86/unistd_x32.h +++ b/linux-headers/asm-x86/unistd_x32.h @@ -1,5 +1,5 @@ -#ifndef _ASM_X86_UNISTD_X32_H -#define _ASM_X86_UNISTD_X32_H 1 +#ifndef _ASM_UNISTD_X32_H +#define _ASM_UNISTD_X32_H #define __NR_read (__X32_SYSCALL_BIT + 0) #define __NR_write (__X32_SYSCALL_BIT + 1) @@ -307,6 +307,11 @@ #define __NR_faccessat2 (__X32_SYSCALL_BIT + 439) #define __NR_process_madvise (__X32_SYSCALL_BIT + 440) #define __NR_epoll_pwait2 (__X32_SYSCALL_BIT + 441) +#define __NR_mount_setattr (__X32_SYSCALL_BIT + 442) +#define __NR_quotactl_fd (__X32_SYSCALL_BIT + 443) +#define __NR_landlock_create_ruleset (__X32_SYSCALL_BIT + 444) +#define __NR_landlock_add_rule (__X32_SYSCALL_BIT + 445) +#define __NR_landlock_restrict_self (__X32_SYSCALL_BIT + 446) #define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512) #define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513) #define __NR_ioctl (__X32_SYSCALL_BIT + 514) @@ -345,4 +350,4 @@ #define __NR_pwritev2 (__X32_SYSCALL_BIT + 547) -#endif /* _ASM_X86_UNISTD_X32_H */ +#endif /* _ASM_UNISTD_X32_H */ diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index 020b62a619..bcaf66cc4d 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include #include #include @@ -216,6 +217,20 @@ struct kvm_hyperv_exit { } u; }; +struct kvm_xen_exit { +#define KVM_EXIT_XEN_HCALL 1 + __u32 type; + union { + struct { + __u32 longmode; + __u32 cpl; + __u64 input; + __u64 result; + __u64 params[6]; + } hcall; + } u; +}; + #define KVM_S390_GET_SKEYS_NONE 1 #define KVM_S390_SKEYS_MAX 1048576 @@ -251,6 +266,9 @@ struct kvm_hyperv_exit { #define KVM_EXIT_X86_RDMSR 29 #define KVM_EXIT_X86_WRMSR 30 #define KVM_EXIT_DIRTY_RING_FULL 31 +#define KVM_EXIT_AP_RESET_HOLD 32 +#define KVM_EXIT_X86_BUS_LOCK 33 +#define KVM_EXIT_XEN 34 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -262,6 +280,9 @@ struct kvm_hyperv_exit { /* Encounter unexpected vm-exit reason */ #define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4 +/* Flags that describe what fields in emulation_failure hold valid data. */ +#define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ @@ -365,6 +386,25 @@ struct kvm_run { __u32 ndata; __u64 data[16]; } internal; + /* + * KVM_INTERNAL_ERROR_EMULATION + * + * "struct emulation_failure" is an overlay of "struct internal" + * that is used for the KVM_INTERNAL_ERROR_EMULATION sub-type of + * KVM_EXIT_INTERNAL_ERROR. Note, unlike other internal error + * sub-types, this struct is ABI! It also needs to be backwards + * compatible with "struct internal". Take special care that + * "ndata" is correct, that new fields are enumerated in "flags", + * and that each flag enumerates fields that are 64-bit aligned + * and sized (so that ndata+internal.data[] is valid/accurate). + */ + struct { + __u32 suberror; + __u32 ndata; + __u64 flags; + __u8 insn_size; + __u8 insn_bytes[15]; + } emulation_failure; /* KVM_EXIT_OSI */ struct { __u64 gprs[32]; @@ -427,6 +467,8 @@ struct kvm_run { __u32 index; /* kernel -> user */ __u64 data; /* kernel <-> user */ } msr; + /* KVM_EXIT_XEN */ + struct kvm_xen_exit xen; /* Fix the size of the union. */ char padding[256]; }; @@ -573,6 +615,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_CHECK_STOP 6 #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 +#define KVM_MP_STATE_AP_RESET_HOLD 9 struct kvm_mp_state { __u32 mp_state; @@ -1056,6 +1099,19 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 #define KVM_CAP_SYS_HYPERV_CPUID 191 #define KVM_CAP_DIRTY_LOG_RING 192 +#define KVM_CAP_X86_BUS_LOCK_EXIT 193 +#define KVM_CAP_PPC_DAWR1 194 +#define KVM_CAP_SET_GUEST_DEBUG2 195 +#define KVM_CAP_SGX_ATTRIBUTE 196 +#define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 +#define KVM_CAP_PTP_KVM 198 +#define KVM_CAP_HYPERV_ENFORCE_CPUID 199 +#define KVM_CAP_SREGS2 200 +#define KVM_CAP_EXIT_HYPERCALL 201 +#define KVM_CAP_PPC_RPT_INVALIDATE 202 +#define KVM_CAP_BINARY_STATS_FD 203 +#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 +#define KVM_CAP_ARM_MTE 205 #ifdef KVM_CAP_IRQ_ROUTING @@ -1129,6 +1185,11 @@ struct kvm_x86_mce { #endif #ifdef KVM_CAP_XEN_HVM +#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) +#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) + struct kvm_xen_hvm_config { __u32 flags; __u32 msr; @@ -1396,6 +1457,7 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_PMU_EVENT_FILTER */ #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) +#define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) @@ -1563,6 +1625,60 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_DIRTY_LOG_RING */ #define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7) +/* Per-VM Xen attributes */ +#define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) +#define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u8 long_mode; + __u8 vector; + struct { + __u64 gfn; + } shared_info; + __u64 pad[8]; + } u; +}; + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 +#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 + +/* Per-vCPU Xen attributes */ +#define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) +#define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) + +#define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) +#define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 gpa; + __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; + } u; +}; + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ @@ -1591,6 +1707,10 @@ enum sev_cmd_id { KVM_SEV_DBG_ENCRYPT, /* Guest certificates commands */ KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, KVM_SEV_NR_MAX, }; @@ -1643,6 +1763,51 @@ struct kvm_sev_dbg { __u32 len; }; +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; +}; + +struct kvm_sev_send_start { + __u32 policy; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) #define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) @@ -1748,8 +1913,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* @@ -1764,4 +1929,79 @@ struct kvm_dirty_gfn { __u64 offset; }; +#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) +#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) + +/** + * struct kvm_stats_header - Header of per vm/vcpu binary statistics data. + * @flags: Some extra information for header, always 0 for now. + * @name_size: The size in bytes of the memory which contains statistics + * name string including trailing '\0'. The memory is allocated + * at the send of statistics descriptor. + * @num_desc: The number of statistics the vm or vcpu has. + * @id_offset: The offset of the vm/vcpu stats' id string in the file pointed + * by vm/vcpu stats fd. + * @desc_offset: The offset of the vm/vcpu stats' descriptor block in the file + * pointd by vm/vcpu stats fd. + * @data_offset: The offset of the vm/vcpu stats' data block in the file + * pointed by vm/vcpu stats fd. + * + * This is the header userspace needs to read from stats fd before any other + * readings. It is used by userspace to discover all the information about the + * vm/vcpu's binary statistics. + * Userspace reads this header from the start of the vm/vcpu's stats fd. + */ +struct kvm_stats_header { + __u32 flags; + __u32 name_size; + __u32 num_desc; + __u32 id_offset; + __u32 desc_offset; + __u32 data_offset; +}; + +#define KVM_STATS_TYPE_SHIFT 0 +#define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_PEAK + +#define KVM_STATS_UNIT_SHIFT 4 +#define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES + +#define KVM_STATS_BASE_SHIFT 8 +#define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2 + +/** + * struct kvm_stats_desc - Descriptor of a KVM statistics. + * @flags: Annotations of the stats, like type, unit, etc. + * @exponent: Used together with @flags to determine the unit. + * @size: The number of data items for this stats. + * Every data item is of type __u64. + * @offset: The offset of the stats to the start of stat structure in + * struture kvm or kvm_vcpu. + * @unused: Unused field for future usage. Always 0 for now. + * @name: The name string for the stats. Its size is indicated by the + * &kvm_stats_header->name_size. + */ +struct kvm_stats_desc { + __u32 flags; + __s16 exponent; + __u16 size; + __u32 offset; + __u32 unused; + char name[]; +}; + +#define KVM_GET_STATS_FD _IO(KVMIO, 0xce) + #endif /* __LINUX_KVM_H */ diff --git a/linux-headers/linux/userfaultfd.h b/linux-headers/linux/userfaultfd.h index 1ba9a9feeb..8479af5f4c 100644 --- a/linux-headers/linux/userfaultfd.h +++ b/linux-headers/linux/userfaultfd.h @@ -19,15 +19,20 @@ * means the userland is reading). */ #define UFFD_API ((__u64)0xAA) +#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \ + UFFDIO_REGISTER_MODE_WP | \ + UFFDIO_REGISTER_MODE_MINOR) #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \ UFFD_FEATURE_EVENT_FORK | \ UFFD_FEATURE_EVENT_REMAP | \ - UFFD_FEATURE_EVENT_REMOVE | \ + UFFD_FEATURE_EVENT_REMOVE | \ UFFD_FEATURE_EVENT_UNMAP | \ UFFD_FEATURE_MISSING_HUGETLBFS | \ UFFD_FEATURE_MISSING_SHMEM | \ UFFD_FEATURE_SIGBUS | \ - UFFD_FEATURE_THREAD_ID) + UFFD_FEATURE_THREAD_ID | \ + UFFD_FEATURE_MINOR_HUGETLBFS | \ + UFFD_FEATURE_MINOR_SHMEM) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -36,10 +41,12 @@ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ (__u64)1 << _UFFDIO_ZEROPAGE | \ - (__u64)1 << _UFFDIO_WRITEPROTECT) + (__u64)1 << _UFFDIO_WRITEPROTECT | \ + (__u64)1 << _UFFDIO_CONTINUE) #define UFFD_API_RANGE_IOCTLS_BASIC \ ((__u64)1 << _UFFDIO_WAKE | \ - (__u64)1 << _UFFDIO_COPY) + (__u64)1 << _UFFDIO_COPY | \ + (__u64)1 << _UFFDIO_CONTINUE) /* * Valid ioctl command number range with this API is from 0x00 to @@ -55,6 +62,7 @@ #define _UFFDIO_COPY (0x03) #define _UFFDIO_ZEROPAGE (0x04) #define _UFFDIO_WRITEPROTECT (0x06) +#define _UFFDIO_CONTINUE (0x07) #define _UFFDIO_API (0x3F) /* userfaultfd ioctl ids */ @@ -73,6 +81,8 @@ struct uffdio_zeropage) #define UFFDIO_WRITEPROTECT _IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \ struct uffdio_writeprotect) +#define UFFDIO_CONTINUE _IOWR(UFFDIO, _UFFDIO_CONTINUE, \ + struct uffdio_continue) /* read() structure */ struct uffd_msg { @@ -127,6 +137,7 @@ struct uffd_msg { /* flags for UFFD_EVENT_PAGEFAULT */ #define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ #define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */ +#define UFFD_PAGEFAULT_FLAG_MINOR (1<<2) /* If reason is VM_UFFD_MINOR */ struct uffdio_api { /* userland asks for an API number and the features to enable */ @@ -171,6 +182,13 @@ struct uffdio_api { * * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will * be returned, if feature is not requested 0 will be returned. + * + * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults + * can be intercepted (via REGISTER_MODE_MINOR) for + * hugetlbfs-backed pages. + * + * UFFD_FEATURE_MINOR_SHMEM indicates the same support as + * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -181,6 +199,8 @@ struct uffdio_api { #define UFFD_FEATURE_EVENT_UNMAP (1<<6) #define UFFD_FEATURE_SIGBUS (1<<7) #define UFFD_FEATURE_THREAD_ID (1<<8) +#define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) +#define UFFD_FEATURE_MINOR_SHMEM (1<<10) __u64 features; __u64 ioctls; @@ -195,6 +215,7 @@ struct uffdio_register { struct uffdio_range range; #define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0) #define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1) +#define UFFDIO_REGISTER_MODE_MINOR ((__u64)1<<2) __u64 mode; /* @@ -257,6 +278,18 @@ struct uffdio_writeprotect { __u64 mode; }; +struct uffdio_continue { + struct uffdio_range range; +#define UFFDIO_CONTINUE_MODE_DONTWAKE ((__u64)1<<0) + __u64 mode; + + /* + * Fields below here are written by the ioctl and must be at the end: + * the copy_from_user will not read past here. + */ + __s64 mapped; +}; + /* * Flags for the userfaultfd(2) system call itself. */ diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h index 609099e455..e680594f27 100644 --- a/linux-headers/linux/vfio.h +++ b/linux-headers/linux/vfio.h @@ -46,6 +46,12 @@ */ #define VFIO_NOIOMMU_IOMMU 8 +/* Supports VFIO_DMA_UNMAP_FLAG_ALL */ +#define VFIO_UNMAP_ALL 9 + +/* Supports the vaddr flag for DMA map and unmap */ +#define VFIO_UPDATE_VADDR 10 + /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between @@ -329,6 +335,8 @@ struct vfio_region_info_cap_type { /* 10de vendor PCI sub-types */ /* * NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space. + * + * Deprecated, region no longer provided */ #define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM (1) @@ -336,6 +344,8 @@ struct vfio_region_info_cap_type { /* * IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU * to do TLB invalidation on a GPU. + * + * Deprecated, region no longer provided */ #define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD (1) @@ -635,6 +645,8 @@ struct vfio_device_migration_info { * Capability with compressed real address (aka SSA - small system address) * where GPU RAM is mapped on a system bus. Used by a GPU for DMA routing * and by the userspace to associate a NVLink bridge with a GPU. + * + * Deprecated, capability no longer provided */ #define VFIO_REGION_INFO_CAP_NVLINK2_SSATGT 4 @@ -649,6 +661,8 @@ struct vfio_region_info_cap_nvlink2_ssatgt { * property in the device tree. The value is fixed in the hardware * and failing to provide the correct value results in the link * not working with no indication from the driver why. + * + * Deprecated, capability no longer provided */ #define VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD 5 @@ -1074,12 +1088,22 @@ struct vfio_iommu_type1_info_dma_avail { * * Map process virtual addresses to IO virtual addresses using the * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required. + * + * If flags & VFIO_DMA_MAP_FLAG_VADDR, update the base vaddr for iova, and + * unblock translation of host virtual addresses in the iova range. The vaddr + * must have previously been invalidated with VFIO_DMA_UNMAP_FLAG_VADDR. To + * maintain memory consistency within the user application, the updated vaddr + * must address the same memory object as originally mapped. Failure to do so + * will result in user memory corruption and/or device misbehavior. iova and + * size must match those in the original MAP_DMA call. Protection is not + * changed, and the READ & WRITE flags must be 0. */ struct vfio_iommu_type1_dma_map { __u32 argsz; __u32 flags; #define VFIO_DMA_MAP_FLAG_READ (1 << 0) /* readable from device */ #define VFIO_DMA_MAP_FLAG_WRITE (1 << 1) /* writable from device */ +#define VFIO_DMA_MAP_FLAG_VADDR (1 << 2) __u64 vaddr; /* Process virtual address */ __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ @@ -1102,6 +1126,7 @@ struct vfio_bitmap { * field. No guarantee is made to the user that arbitrary unmaps of iova * or size different from those used in the original mapping call will * succeed. + * * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get the dirty bitmap * before unmapping IO virtual addresses. When this flag is set, the user must * provide a struct vfio_bitmap in data[]. User must provide zero-allocated @@ -1111,11 +1136,21 @@ struct vfio_bitmap { * indicates that the page at that offset from iova is dirty. A Bitmap of the * pages in the range of unmapped size is returned in the user-provided * vfio_bitmap.data. + * + * If flags & VFIO_DMA_UNMAP_FLAG_ALL, unmap all addresses. iova and size + * must be 0. This cannot be combined with the get-dirty-bitmap flag. + * + * If flags & VFIO_DMA_UNMAP_FLAG_VADDR, do not unmap, but invalidate host + * virtual addresses in the iova range. Tasks that attempt to translate an + * iova's vaddr will block. DMA to already-mapped pages continues. This + * cannot be combined with the get-dirty-bitmap flag. */ struct vfio_iommu_type1_dma_unmap { __u32 argsz; __u32 flags; #define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0) +#define VFIO_DMA_UNMAP_FLAG_ALL (1 << 1) +#define VFIO_DMA_UNMAP_FLAG_VADDR (1 << 2) __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ __u8 data[]; diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index b591790c22..662bcd1c4e 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -561,11 +561,7 @@ long do_rt_sigreturn(CPUARMState *env) goto badframe; } - if (do_sigaltstack(frame_addr + - offsetof(struct target_rt_sigframe, uc.tuc_stack), - 0, get_sp_from_cpustate(env)) == -EFAULT) { - goto badframe; - } + target_restore_altstack(&frame->uc.tuc_stack, env); unlock_user_struct(frame, frame_addr, 0); return -TARGET_QEMU_ESIGRETURN; diff --git a/linux-user/aarch64/syscall_nr.h b/linux-user/aarch64/syscall_nr.h index 6fd5b331e7..12ef002d60 100644 --- a/linux-user/aarch64/syscall_nr.h +++ b/linux-user/aarch64/syscall_nr.h @@ -302,6 +302,12 @@ #define TARGET_NR_openat2 437 #define TARGET_NR_pidfd_getfd 438 #define TARGET_NR_faccessat2 439 -#define TARGET_NR_syscalls 440 +#define TARGET_NR_process_madvise 440 +#define TARGET_NR_epoll_pwait2 441 +#define TARGET_NR_mount_setattr 442 +#define TARGET_NR_landlock_create_ruleset 444 +#define TARGET_NR_landlock_add_rule 445 +#define TARGET_NR_landlock_restrict_self 446 +#define TARGET_NR_syscalls 447 #endif /* LINUX_USER_AARCH64_SYSCALL_NR_H */ diff --git a/linux-user/aarch64/target_errno_defs.h b/linux-user/aarch64/target_errno_defs.h new file mode 100644 index 0000000000..461b547728 --- /dev/null +++ b/linux-user/aarch64/target_errno_defs.h @@ -0,0 +1,7 @@ +#ifndef AARCH64_TARGET_ERRNO_DEFS_H +#define AARCH64_TARGET_ERRNO_DEFS_H + +/* Target uses generic errno */ +#include "../generic/target_errno_defs.h" + +#endif diff --git a/linux-user/alpha/signal.c b/linux-user/alpha/signal.c index c5c27ce084..1129ffeea1 100644 --- a/linux-user/alpha/signal.c +++ b/linux-user/alpha/signal.c @@ -138,8 +138,8 @@ void setup_frame(int sig, struct target_sigaction *ka, setup_sigcontext(&frame->sc, env, frame_addr, set); - if (ka->sa_restorer) { - r26 = ka->sa_restorer; + if (ka->ka_restorer) { + r26 = ka->ka_restorer; } else { __put_user(INSN_MOV_R30_R16, &frame->retcode[0]); __put_user(INSN_LDI_R0 + TARGET_NR_sigreturn, @@ -192,15 +192,15 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, __put_user(set->sig[i], &frame->uc.tuc_sigmask.sig[i]); } - if (ka->sa_restorer) { - r26 = ka->sa_restorer; + if (ka->ka_restorer) { + r26 = ka->ka_restorer; } else { __put_user(INSN_MOV_R30_R16, &frame->retcode[0]); __put_user(INSN_LDI_R0 + TARGET_NR_rt_sigreturn, &frame->retcode[1]); __put_user(INSN_CALLSYS, &frame->retcode[2]); /* imb(); */ - r26 = frame_addr + offsetof(struct target_sigframe, retcode); + r26 = frame_addr + offsetof(struct target_rt_sigframe, retcode); } if (err) { @@ -257,11 +257,7 @@ long do_rt_sigreturn(CPUAlphaState *env) set_sigmask(&set); restore_sigcontext(env, &frame->uc.tuc_mcontext); - if (do_sigaltstack(frame_addr + offsetof(struct target_rt_sigframe, - uc.tuc_stack), - 0, env->ir[IR_SP]) == -EFAULT) { - goto badframe; - } + target_restore_altstack(&frame->uc.tuc_stack, env); unlock_user_struct(frame, frame_addr, 0); return -TARGET_QEMU_ESIGRETURN; diff --git a/linux-user/alpha/syscall.tbl b/linux-user/alpha/syscall.tbl index ec8bed9e7b..3000a2e8ee 100644 --- a/linux-user/alpha/syscall.tbl +++ b/linux-user/alpha/syscall.tbl @@ -479,3 +479,10 @@ 547 common openat2 sys_openat2 548 common pidfd_getfd sys_pidfd_getfd 549 common faccessat2 sys_faccessat2 +550 common process_madvise sys_process_madvise +551 common epoll_pwait2 sys_epoll_pwait2 +552 common mount_setattr sys_mount_setattr +# 553 reserved for quotactl_path +554 common landlock_create_ruleset sys_landlock_create_ruleset +555 common landlock_add_rule sys_landlock_add_rule +556 common landlock_restrict_self sys_landlock_restrict_self diff --git a/linux-user/alpha/target_errno_defs.h b/linux-user/alpha/target_errno_defs.h new file mode 100644 index 0000000000..07924b13aa --- /dev/null +++ b/linux-user/alpha/target_errno_defs.h @@ -0,0 +1,204 @@ +#ifndef ALPHA_TARGET_ERRNO_DEFS_H +#define ALPHA_TARGET_ERRNO_DEFS_H + +#include "../generic/target_errno_defs.h" + +/* + * Generic target errno overridden with definitions taken + * from asm-alpha/errno.h + */ +#undef TARGET_EWOULDBLOCK +#define TARGET_EWOULDBLOCK TARGET_EAGAIN +#undef TARGET_EDEADLK +#define TARGET_EDEADLK 11 +#undef TARGET_EAGAIN +#define TARGET_EAGAIN 35 +#undef TARGET_EINPROGRESS +#define TARGET_EINPROGRESS 36 +#undef TARGET_EALREADY +#define TARGET_EALREADY 37 +#undef TARGET_ENOTSOCK +#define TARGET_ENOTSOCK 38 +#undef TARGET_EDESTADDRREQ +#define TARGET_EDESTADDRREQ 39 +#undef TARGET_EMSGSIZE +#define TARGET_EMSGSIZE 40 +#undef TARGET_EPROTOTYPE +#define TARGET_EPROTOTYPE 41 +#undef TARGET_ENOPROTOOPT +#define TARGET_ENOPROTOOPT 42 +#undef TARGET_EPROTONOSUPPORT +#define TARGET_EPROTONOSUPPORT 43 +#undef TARGET_ESOCKTNOSUPPORT +#define TARGET_ESOCKTNOSUPPORT 44 +#undef TARGET_EOPNOTSUPP +#define TARGET_EOPNOTSUPP 45 +#undef TARGET_EPFNOSUPPORT +#define TARGET_EPFNOSUPPORT 46 +#undef TARGET_EAFNOSUPPORT +#define TARGET_EAFNOSUPPORT 47 +#undef TARGET_EADDRINUSE +#define TARGET_EADDRINUSE 48 +#undef TARGET_EADDRNOTAVAIL +#define TARGET_EADDRNOTAVAIL 49 +#undef TARGET_ENETDOWN +#define TARGET_ENETDOWN 50 +#undef TARGET_ENETUNREACH +#define TARGET_ENETUNREACH 51 +#undef TARGET_ENETRESET +#define TARGET_ENETRESET 52 +#undef TARGET_ECONNABORTED +#define TARGET_ECONNABORTED 53 +#undef TARGET_ECONNRESET +#define TARGET_ECONNRESET 54 +#undef TARGET_ENOBUFS +#define TARGET_ENOBUFS 55 +#undef TARGET_EISCONN +#define TARGET_EISCONN 56 +#undef TARGET_ENOTCONN +#define TARGET_ENOTCONN 57 +#undef TARGET_ESHUTDOWN +#define TARGET_ESHUTDOWN 58 +#undef TARGET_ETOOMANYREFS +#define TARGET_ETOOMANYREFS 59 +#undef TARGET_ETIMEDOUT +#define TARGET_ETIMEDOUT 60 +#undef TARGET_ECONNREFUSED +#define TARGET_ECONNREFUSED 61 +#undef TARGET_ELOOP +#define TARGET_ELOOP 62 +#undef TARGET_ENAMETOOLONG +#define TARGET_ENAMETOOLONG 63 +#undef TARGET_EHOSTDOWN +#define TARGET_EHOSTDOWN 64 +#undef TARGET_EHOSTUNREACH +#define TARGET_EHOSTUNREACH 65 +#undef TARGET_ENOTEMPTY +#define TARGET_ENOTEMPTY 66 +/* Unused 67 */ +#undef TARGET_EUSERS +#define TARGET_EUSERS 68 +#undef TARGET_EDQUOT +#define TARGET_EDQUOT 69 +#undef TARGET_ESTALE +#define TARGET_ESTALE 70 +#undef TARGET_EREMOTE +#define TARGET_EREMOTE 71 +/* Unused 72-76 */ +#undef TARGET_ENOLCK +#define TARGET_ENOLCK 77 +#undef TARGET_ENOSYS +#define TARGET_ENOSYS 78 +/* Unused 79 */ +#undef TARGET_ENOMSG +#define TARGET_ENOMSG 80 +#undef TARGET_EIDRM +#define TARGET_EIDRM 81 +#undef TARGET_ENOSR +#define TARGET_ENOSR 82 +#undef TARGET_ETIME +#define TARGET_ETIME 83 +#undef TARGET_EBADMSG +#define TARGET_EBADMSG 84 +#undef TARGET_EPROTO +#define TARGET_EPROTO 85 +#undef TARGET_ENODATA +#define TARGET_ENODATA 86 +#undef TARGET_ENOSTR +#define TARGET_ENOSTR 87 +#undef TARGET_ECHRNG +#define TARGET_ECHRNG 88 +#undef TARGET_EL2NSYNC +#define TARGET_EL2NSYNC 89 +#undef TARGET_EL3HLT +#define TARGET_EL3HLT 90 +#undef TARGET_EL3RST +#define TARGET_EL3RST 91 +#undef TARGET_ENOPKG +#define TARGET_ENOPKG 92 +#undef TARGET_ELNRNG +#define TARGET_ELNRNG 93 +#undef TARGET_EUNATCH +#define TARGET_EUNATCH 94 +#undef TARGET_ENOCSI +#define TARGET_ENOCSI 95 +#undef TARGET_EL2HLT +#define TARGET_EL2HLT 96 +#undef TARGET_EBADE +#define TARGET_EBADE 97 +#undef TARGET_EBADR +#define TARGET_EBADR 98 +#undef TARGET_EXFULL +#define TARGET_EXFULL 99 +#undef TARGET_ENOANO +#define TARGET_ENOANO 100 +#undef TARGET_EBADRQC +#define TARGET_EBADRQC 101 +#undef TARGET_EBADSLT +#define TARGET_EBADSLT 102 +/* Unused 103 */ +#undef TARGET_EBFONT +#define TARGET_EBFONT 104 +#undef TARGET_ENONET +#define TARGET_ENONET 105 +#undef TARGET_ENOLINK +#define TARGET_ENOLINK 106 +#undef TARGET_EADV +#define TARGET_EADV 107 +#undef TARGET_ESRMNT +#define TARGET_ESRMNT 108 +#undef TARGET_ECOMM +#define TARGET_ECOMM 109 +#undef TARGET_EMULTIHOP +#define TARGET_EMULTIHOP 110 +#undef TARGET_EDOTDOT +#define TARGET_EDOTDOT 111 +#undef TARGET_EOVERFLOW +#define TARGET_EOVERFLOW 112 +#undef TARGET_ENOTUNIQ +#define TARGET_ENOTUNIQ 113 +#undef TARGET_EBADFD +#define TARGET_EBADFD 114 +#undef TARGET_EREMCHG +#define TARGET_EREMCHG 115 +#undef TARGET_EILSEQ +#define TARGET_EILSEQ 116 +/* Same as default 117-121 */ +#undef TARGET_ELIBACC +#define TARGET_ELIBACC 122 +#undef TARGET_ELIBBAD +#define TARGET_ELIBBAD 123 +#undef TARGET_ELIBSCN +#define TARGET_ELIBSCN 124 +#undef TARGET_ELIBMAX +#define TARGET_ELIBMAX 125 +#undef TARGET_ELIBEXEC +#define TARGET_ELIBEXEC 126 +#undef TARGET_ERESTART +#define TARGET_ERESTART 127 +#undef TARGET_ESTRPIPE +#define TARGET_ESTRPIPE 128 +#undef TARGET_ENOMEDIUM +#define TARGET_ENOMEDIUM 129 +#undef TARGET_EMEDIUMTYPE +#define TARGET_EMEDIUMTYPE 130 +#undef TARGET_ECANCELED +#define TARGET_ECANCELED 131 +#undef TARGET_ENOKEY +#define TARGET_ENOKEY 132 +#undef TARGET_EKEYEXPIRED +#define TARGET_EKEYEXPIRED 133 +#undef TARGET_EKEYREVOKED +#define TARGET_EKEYREVOKED 134 +#undef TARGET_EKEYREJECTED +#define TARGET_EKEYREJECTED 135 +#undef TARGET_EOWNERDEAD +#define TARGET_EOWNERDEAD 136 +#undef TARGET_ENOTRECOVERABLE +#define TARGET_ENOTRECOVERABLE 137 +#undef TARGET_ERFKILL +#define TARGET_ERFKILL 138 +#undef TARGET_EHWPOISON +#define TARGET_EHWPOISON 139 + +#endif diff --git a/linux-user/alpha/target_signal.h b/linux-user/alpha/target_signal.h index 0b90d3a897..250642913e 100644 --- a/linux-user/alpha/target_signal.h +++ b/linux-user/alpha/target_signal.h @@ -92,6 +92,7 @@ typedef struct target_sigaltstack { #define TARGET_GEN_SUBRNG7 -25 #define TARGET_ARCH_HAS_SETUP_FRAME +#define TARGET_ARCH_HAS_KA_RESTORER /* bit-flags */ #define TARGET_SS_AUTODISARM (1U << 31) /* disable sas during sighandling */ diff --git a/linux-user/alpha/target_syscall.h b/linux-user/alpha/target_syscall.h index fd389422e3..03091bf0a8 100644 --- a/linux-user/alpha/target_syscall.h +++ b/linux-user/alpha/target_syscall.h @@ -44,200 +44,6 @@ struct target_pt_regs { #define UNAME_MACHINE "alpha" #define UNAME_MINIMUM_RELEASE "2.6.32" -#undef TARGET_EDEADLK -#define TARGET_EDEADLK 11 -#undef TARGET_EAGAIN -#define TARGET_EAGAIN 35 -#undef TARGET_EINPROGRESS -#define TARGET_EINPROGRESS 36 -#undef TARGET_EALREADY -#define TARGET_EALREADY 37 -#undef TARGET_ENOTSOCK -#define TARGET_ENOTSOCK 38 -#undef TARGET_EDESTADDRREQ -#define TARGET_EDESTADDRREQ 39 -#undef TARGET_EMSGSIZE -#define TARGET_EMSGSIZE 40 -#undef TARGET_EPROTOTYPE -#define TARGET_EPROTOTYPE 41 -#undef TARGET_ENOPROTOOPT -#define TARGET_ENOPROTOOPT 42 -#undef TARGET_EPROTONOSUPPORT -#define TARGET_EPROTONOSUPPORT 43 -#undef TARGET_ESOCKTNOSUPPORT -#define TARGET_ESOCKTNOSUPPORT 44 -#undef TARGET_EOPNOTSUPP -#define TARGET_EOPNOTSUPP 45 -#undef TARGET_EPFNOSUPPORT -#define TARGET_EPFNOSUPPORT 46 -#undef TARGET_EAFNOSUPPORT -#define TARGET_EAFNOSUPPORT 47 -#undef TARGET_EADDRINUSE -#define TARGET_EADDRINUSE 48 -#undef TARGET_EADDRNOTAVAIL -#define TARGET_EADDRNOTAVAIL 49 -#undef TARGET_ENETDOWN -#define TARGET_ENETDOWN 50 -#undef TARGET_ENETUNREACH -#define TARGET_ENETUNREACH 51 -#undef TARGET_ENETRESET -#define TARGET_ENETRESET 52 -#undef TARGET_ECONNABORTED -#define TARGET_ECONNABORTED 53 -#undef TARGET_ECONNRESET -#define TARGET_ECONNRESET 54 -#undef TARGET_ENOBUFS -#define TARGET_ENOBUFS 55 -#undef TARGET_EISCONN -#define TARGET_EISCONN 56 -#undef TARGET_ENOTCONN -#define TARGET_ENOTCONN 57 -#undef TARGET_ESHUTDOWN -#define TARGET_ESHUTDOWN 58 -#undef TARGET_ETOOMANYREFS -#define TARGET_ETOOMANYREFS 59 -#undef TARGET_ETIMEDOUT -#define TARGET_ETIMEDOUT 60 -#undef TARGET_ECONNREFUSED -#define TARGET_ECONNREFUSED 61 -#undef TARGET_ELOOP -#define TARGET_ELOOP 62 -#undef TARGET_ENAMETOOLONG -#define TARGET_ENAMETOOLONG 63 -#undef TARGET_EHOSTDOWN -#define TARGET_EHOSTDOWN 64 -#undef TARGET_EHOSTUNREACH -#define TARGET_EHOSTUNREACH 65 -#undef TARGET_ENOTEMPTY -#define TARGET_ENOTEMPTY 66 -// Unused 67 -#undef TARGET_EUSERS -#define TARGET_EUSERS 68 -#undef TARGET_EDQUOT -#define TARGET_EDQUOT 69 -#undef TARGET_ESTALE -#define TARGET_ESTALE 70 -#undef TARGET_EREMOTE -#define TARGET_EREMOTE 71 -// Unused 72-76 -#undef TARGET_ENOLCK -#define TARGET_ENOLCK 77 -#undef TARGET_ENOSYS -#define TARGET_ENOSYS 78 -// Unused 79 -#undef TARGET_ENOMSG -#define TARGET_ENOMSG 80 -#undef TARGET_EIDRM -#define TARGET_EIDRM 81 -#undef TARGET_ENOSR -#define TARGET_ENOSR 82 -#undef TARGET_ETIME -#define TARGET_ETIME 83 -#undef TARGET_EBADMSG -#define TARGET_EBADMSG 84 -#undef TARGET_EPROTO -#define TARGET_EPROTO 85 -#undef TARGET_ENODATA -#define TARGET_ENODATA 86 -#undef TARGET_ENOSTR -#define TARGET_ENOSTR 87 -#undef TARGET_ECHRNG -#define TARGET_ECHRNG 88 -#undef TARGET_EL2NSYNC -#define TARGET_EL2NSYNC 89 -#undef TARGET_EL3HLT -#define TARGET_EL3HLT 90 -#undef TARGET_EL3RST -#define TARGET_EL3RST 91 -#undef TARGET_ENOPKG -#define TARGET_ENOPKG 92 -#undef TARGET_ELNRNG -#define TARGET_ELNRNG 93 -#undef TARGET_EUNATCH -#define TARGET_EUNATCH 94 -#undef TARGET_ENOCSI -#define TARGET_ENOCSI 95 -#undef TARGET_EL2HLT -#define TARGET_EL2HLT 96 -#undef TARGET_EBADE -#define TARGET_EBADE 97 -#undef TARGET_EBADR -#define TARGET_EBADR 98 -#undef TARGET_EXFULL -#define TARGET_EXFULL 99 -#undef TARGET_ENOANO -#define TARGET_ENOANO 100 -#undef TARGET_EBADRQC -#define TARGET_EBADRQC 101 -#undef TARGET_EBADSLT -#define TARGET_EBADSLT 102 -// Unused 103 -#undef TARGET_EBFONT -#define TARGET_EBFONT 104 -#undef TARGET_ENONET -#define TARGET_ENONET 105 -#undef TARGET_ENOLINK -#define TARGET_ENOLINK 106 -#undef TARGET_EADV -#define TARGET_EADV 107 -#undef TARGET_ESRMNT -#define TARGET_ESRMNT 108 -#undef TARGET_ECOMM -#define TARGET_ECOMM 109 -#undef TARGET_EMULTIHOP -#define TARGET_EMULTIHOP 110 -#undef TARGET_EDOTDOT -#define TARGET_EDOTDOT 111 -#undef TARGET_EOVERFLOW -#define TARGET_EOVERFLOW 112 -#undef TARGET_ENOTUNIQ -#define TARGET_ENOTUNIQ 113 -#undef TARGET_EBADFD -#define TARGET_EBADFD 114 -#undef TARGET_EREMCHG -#define TARGET_EREMCHG 115 -#undef TARGET_EILSEQ -#define TARGET_EILSEQ 116 - -// Same as default 117-121 - -#undef TARGET_ELIBACC -#define TARGET_ELIBACC 122 -#undef TARGET_ELIBBAD -#define TARGET_ELIBBAD 123 -#undef TARGET_ELIBSCN -#define TARGET_ELIBSCN 124 -#undef TARGET_ELIBMAX -#define TARGET_ELIBMAX 125 -#undef TARGET_ELIBEXEC -#define TARGET_ELIBEXEC 126 -#undef TARGET_ERESTART -#define TARGET_ERESTART 127 -#undef TARGET_ESTRPIPE -#define TARGET_ESTRPIPE 128 -#undef TARGET_ENOMEDIUM -#define TARGET_ENOMEDIUM 129 -#undef TARGET_EMEDIUMTYPE -#define TARGET_EMEDIUMTYPE 130 -#undef TARGET_ECANCELED -#define TARGET_ECANCELED 131 -#undef TARGET_ENOKEY -#define TARGET_ENOKEY 132 -#undef TARGET_EKEYEXPIRED -#define TARGET_EKEYEXPIRED 133 -#undef TARGET_EKEYREVOKED -#define TARGET_EKEYREVOKED 134 -#undef TARGET_EKEYREJECTED -#define TARGET_EKEYREJECTED 135 -#undef TARGET_EOWNERDEAD -#define TARGET_EOWNERDEAD 136 -#undef TARGET_ENOTRECOVERABLE -#define TARGET_ENOTRECOVERABLE 137 -#undef TARGET_ERFKILL -#define TARGET_ERFKILL 138 -#undef TARGET_EHWPOISON -#define TARGET_EHWPOISON 139 - // For sys_osf_getsysinfo #define TARGET_GSI_UACPROC 8 #define TARGET_GSI_IEEE_FP_CONTROL 45 diff --git a/linux-user/arm/cpu_loop.c b/linux-user/arm/cpu_loop.c index 989d03cd89..69632d15be 100644 --- a/linux-user/arm/cpu_loop.c +++ b/linux-user/arm/cpu_loop.c @@ -224,6 +224,64 @@ static bool insn_is_linux_bkpt(uint32_t opcode, bool is_thumb) } } +static bool emulate_arm_fpa11(CPUARMState *env, uint32_t opcode) +{ + TaskState *ts = env_cpu(env)->opaque; + int rc = EmulateAll(opcode, &ts->fpa, env); + int raise, enabled; + + if (rc == 0) { + /* Illegal instruction */ + return false; + } + if (rc > 0) { + /* Everything ok. */ + env->regs[15] += 4; + return true; + } + + /* FP exception */ + rc = -rc; + raise = 0; + + /* Translate softfloat flags to FPSR flags */ + if (rc & float_flag_invalid) { + raise |= BIT_IOC; + } + if (rc & float_flag_divbyzero) { + raise |= BIT_DZC; + } + if (rc & float_flag_overflow) { + raise |= BIT_OFC; + } + if (rc & float_flag_underflow) { + raise |= BIT_UFC; + } + if (rc & float_flag_inexact) { + raise |= BIT_IXC; + } + + /* Accumulate unenabled exceptions */ + enabled = ts->fpa.fpsr >> 16; + ts->fpa.fpsr |= raise & ~enabled; + + if (raise & enabled) { + target_siginfo_t info = { }; + + /* + * The kernel's nwfpe emulator does not pass a real si_code. + * It merely uses send_sig(SIGFPE, current, 1). + */ + info.si_signo = TARGET_SIGFPE; + info.si_code = TARGET_SI_KERNEL; + + queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info); + } else { + env->regs[15] += 4; + } + return true; +} + void cpu_loop(CPUARMState *env) { CPUState *cs = env_cpu(env); @@ -244,9 +302,7 @@ void cpu_loop(CPUARMState *env) case EXCP_NOCP: case EXCP_INVSTATE: { - TaskState *ts = cs->opaque; uint32_t opcode; - int rc; /* we handle the FPU emulation here, as Linux */ /* we get the opcode */ @@ -263,64 +319,15 @@ void cpu_loop(CPUARMState *env) goto excp_debug; } - rc = EmulateAll(opcode, &ts->fpa, env); - if (rc == 0) { /* illegal instruction */ - info.si_signo = TARGET_SIGILL; - info.si_errno = 0; - info.si_code = TARGET_ILL_ILLOPN; - info._sifields._sigfault._addr = env->regs[15]; - queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info); - } else if (rc < 0) { /* FP exception */ - int arm_fpe=0; - - /* translate softfloat flags to FPSR flags */ - if (-rc & float_flag_invalid) - arm_fpe |= BIT_IOC; - if (-rc & float_flag_divbyzero) - arm_fpe |= BIT_DZC; - if (-rc & float_flag_overflow) - arm_fpe |= BIT_OFC; - if (-rc & float_flag_underflow) - arm_fpe |= BIT_UFC; - if (-rc & float_flag_inexact) - arm_fpe |= BIT_IXC; - - FPSR fpsr = ts->fpa.fpsr; - //printf("fpsr 0x%x, arm_fpe 0x%x\n",fpsr,arm_fpe); - - if (fpsr & (arm_fpe << 16)) { /* exception enabled? */ - info.si_signo = TARGET_SIGFPE; - info.si_errno = 0; - - /* ordered by priority, least first */ - if (arm_fpe & BIT_IXC) info.si_code = TARGET_FPE_FLTRES; - if (arm_fpe & BIT_UFC) info.si_code = TARGET_FPE_FLTUND; - if (arm_fpe & BIT_OFC) info.si_code = TARGET_FPE_FLTOVF; - if (arm_fpe & BIT_DZC) info.si_code = TARGET_FPE_FLTDIV; - if (arm_fpe & BIT_IOC) info.si_code = TARGET_FPE_FLTINV; - - info._sifields._sigfault._addr = env->regs[15]; - queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info); - } else { - env->regs[15] += 4; - } - - /* accumulate unenabled exceptions */ - if ((!(fpsr & BIT_IXE)) && (arm_fpe & BIT_IXC)) - fpsr |= BIT_IXC; - if ((!(fpsr & BIT_UFE)) && (arm_fpe & BIT_UFC)) - fpsr |= BIT_UFC; - if ((!(fpsr & BIT_OFE)) && (arm_fpe & BIT_OFC)) - fpsr |= BIT_OFC; - if ((!(fpsr & BIT_DZE)) && (arm_fpe & BIT_DZC)) - fpsr |= BIT_DZC; - if ((!(fpsr & BIT_IOE)) && (arm_fpe & BIT_IOC)) - fpsr |= BIT_IOC; - ts->fpa.fpsr=fpsr; - } else { /* everything OK */ - /* increment PC */ - env->regs[15] += 4; + if (!env->thumb && emulate_arm_fpa11(env, opcode)) { + break; } + + info.si_signo = TARGET_SIGILL; + info.si_errno = 0; + info.si_code = TARGET_ILL_ILLOPN; + info._sifields._sigfault._addr = env->regs[15]; + queue_signal(env, info.si_signo, QEMU_SI_FAULT, &info); } break; case EXCP_SWI: diff --git a/linux-user/arm/nwfpe/fpa11.c b/linux-user/arm/nwfpe/fpa11.c index f6f8163eab..9a93610d24 100644 --- a/linux-user/arm/nwfpe/fpa11.c +++ b/linux-user/arm/nwfpe/fpa11.c @@ -97,37 +97,38 @@ void SetRoundingMode(const unsigned int opcode) void SetRoundingPrecision(const unsigned int opcode) { - int rounding_precision; - FPA11 *fpa11 = GET_FPA11(); + FloatX80RoundPrec rounding_precision; + FPA11 *fpa11 = GET_FPA11(); #ifdef MAINTAIN_FPCR - fpa11->fpcr &= ~MASK_ROUNDING_PRECISION; + fpa11->fpcr &= ~MASK_ROUNDING_PRECISION; #endif - switch (opcode & MASK_ROUNDING_PRECISION) - { - case ROUND_SINGLE: - rounding_precision = 32; + switch (opcode & MASK_ROUNDING_PRECISION) { + case ROUND_SINGLE: + rounding_precision = floatx80_precision_s; #ifdef MAINTAIN_FPCR - fpa11->fpcr |= ROUND_SINGLE; + fpa11->fpcr |= ROUND_SINGLE; #endif - break; + break; - case ROUND_DOUBLE: - rounding_precision = 64; + case ROUND_DOUBLE: + rounding_precision = floatx80_precision_d; #ifdef MAINTAIN_FPCR - fpa11->fpcr |= ROUND_DOUBLE; + fpa11->fpcr |= ROUND_DOUBLE; #endif - break; + break; - case ROUND_EXTENDED: - rounding_precision = 80; + case ROUND_EXTENDED: + rounding_precision = floatx80_precision_x; #ifdef MAINTAIN_FPCR - fpa11->fpcr |= ROUND_EXTENDED; + fpa11->fpcr |= ROUND_EXTENDED; #endif - break; + break; - default: rounding_precision = 80; - } - set_floatx80_rounding_precision(rounding_precision, &fpa11->fp_status); + default: + rounding_precision = floatx80_precision_x; + break; + } + set_floatx80_rounding_precision(rounding_precision, &fpa11->fp_status); } /* Emulate the instruction in the opcode. */ diff --git a/linux-user/arm/signal.c b/linux-user/arm/signal.c index f21d1535e4..32b68ee302 100644 --- a/linux-user/arm/signal.c +++ b/linux-user/arm/signal.c @@ -685,11 +685,7 @@ static int do_sigframe_return_v2(CPUARMState *env, } } - if (do_sigaltstack(context_addr - + offsetof(struct target_ucontext_v2, tuc_stack), - 0, get_sp_from_cpustate(env)) == -EFAULT) { - return 1; - } + target_restore_altstack(&uc->tuc_stack, env); #if 0 /* Send SIGTRAP if we're single-stepping */ @@ -773,8 +769,7 @@ static long do_rt_sigreturn_v1(CPUARMState *env) goto badframe; } - if (do_sigaltstack(frame_addr + offsetof(struct rt_sigframe_v1, uc.tuc_stack), 0, get_sp_from_cpustate(env)) == -EFAULT) - goto badframe; + target_restore_altstack(&frame->uc.tuc_stack, env); #if 0 /* Send SIGTRAP if we're single-stepping */ diff --git a/linux-user/arm/syscall.tbl b/linux-user/arm/syscall.tbl index 171077cbf4..28e03b5fec 100644 --- a/linux-user/arm/syscall.tbl +++ b/linux-user/arm/syscall.tbl @@ -453,3 +453,10 @@ 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +# 443 reserved for quotactl_path +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/linux-user/arm/target_errno_defs.h b/linux-user/arm/target_errno_defs.h new file mode 100644 index 0000000000..fd84373238 --- /dev/null +++ b/linux-user/arm/target_errno_defs.h @@ -0,0 +1,7 @@ +#ifndef ARM_TARGET_ERRNO_DEFS_H +#define ARM_TARGET_ERRNO_DEFS_H + +/* Target uses generic errno */ +#include "../generic/target_errno_defs.h" + +#endif diff --git a/linux-user/cris/target_errno_defs.h b/linux-user/cris/target_errno_defs.h new file mode 100644 index 0000000000..1cf43b17a5 --- /dev/null +++ b/linux-user/cris/target_errno_defs.h @@ -0,0 +1,7 @@ +#ifndef CRIS_TARGET_ERRNO_DEFS_H +#define CRIS_TARGET_ERRNO_DEFS_H + +/* Target uses generic errno */ +#include "../generic/target_errno_defs.h" + +#endif diff --git a/linux-user/elfload.c b/linux-user/elfload.c index c6731013fd..01e9a833fb 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -172,33 +172,33 @@ typedef target_elf_greg_t target_elf_gregset_t[ELF_NREG]; */ static void elf_core_copy_regs(target_elf_gregset_t *regs, const CPUX86State *env) { - (*regs)[0] = env->regs[15]; - (*regs)[1] = env->regs[14]; - (*regs)[2] = env->regs[13]; - (*regs)[3] = env->regs[12]; - (*regs)[4] = env->regs[R_EBP]; - (*regs)[5] = env->regs[R_EBX]; - (*regs)[6] = env->regs[11]; - (*regs)[7] = env->regs[10]; - (*regs)[8] = env->regs[9]; - (*regs)[9] = env->regs[8]; - (*regs)[10] = env->regs[R_EAX]; - (*regs)[11] = env->regs[R_ECX]; - (*regs)[12] = env->regs[R_EDX]; - (*regs)[13] = env->regs[R_ESI]; - (*regs)[14] = env->regs[R_EDI]; - (*regs)[15] = env->regs[R_EAX]; /* XXX */ - (*regs)[16] = env->eip; - (*regs)[17] = env->segs[R_CS].selector & 0xffff; - (*regs)[18] = env->eflags; - (*regs)[19] = env->regs[R_ESP]; - (*regs)[20] = env->segs[R_SS].selector & 0xffff; - (*regs)[21] = env->segs[R_FS].selector & 0xffff; - (*regs)[22] = env->segs[R_GS].selector & 0xffff; - (*regs)[23] = env->segs[R_DS].selector & 0xffff; - (*regs)[24] = env->segs[R_ES].selector & 0xffff; - (*regs)[25] = env->segs[R_FS].selector & 0xffff; - (*regs)[26] = env->segs[R_GS].selector & 0xffff; + (*regs)[0] = tswapreg(env->regs[15]); + (*regs)[1] = tswapreg(env->regs[14]); + (*regs)[2] = tswapreg(env->regs[13]); + (*regs)[3] = tswapreg(env->regs[12]); + (*regs)[4] = tswapreg(env->regs[R_EBP]); + (*regs)[5] = tswapreg(env->regs[R_EBX]); + (*regs)[6] = tswapreg(env->regs[11]); + (*regs)[7] = tswapreg(env->regs[10]); + (*regs)[8] = tswapreg(env->regs[9]); + (*regs)[9] = tswapreg(env->regs[8]); + (*regs)[10] = tswapreg(env->regs[R_EAX]); + (*regs)[11] = tswapreg(env->regs[R_ECX]); + (*regs)[12] = tswapreg(env->regs[R_EDX]); + (*regs)[13] = tswapreg(env->regs[R_ESI]); + (*regs)[14] = tswapreg(env->regs[R_EDI]); + (*regs)[15] = tswapreg(env->regs[R_EAX]); /* XXX */ + (*regs)[16] = tswapreg(env->eip); + (*regs)[17] = tswapreg(env->segs[R_CS].selector & 0xffff); + (*regs)[18] = tswapreg(env->eflags); + (*regs)[19] = tswapreg(env->regs[R_ESP]); + (*regs)[20] = tswapreg(env->segs[R_SS].selector & 0xffff); + (*regs)[21] = tswapreg(env->segs[R_FS].selector & 0xffff); + (*regs)[22] = tswapreg(env->segs[R_GS].selector & 0xffff); + (*regs)[23] = tswapreg(env->segs[R_DS].selector & 0xffff); + (*regs)[24] = tswapreg(env->segs[R_ES].selector & 0xffff); + (*regs)[25] = tswapreg(env->segs[R_FS].selector & 0xffff); + (*regs)[26] = tswapreg(env->segs[R_GS].selector & 0xffff); } #else @@ -244,23 +244,23 @@ typedef target_elf_greg_t target_elf_gregset_t[ELF_NREG]; */ static void elf_core_copy_regs(target_elf_gregset_t *regs, const CPUX86State *env) { - (*regs)[0] = env->regs[R_EBX]; - (*regs)[1] = env->regs[R_ECX]; - (*regs)[2] = env->regs[R_EDX]; - (*regs)[3] = env->regs[R_ESI]; - (*regs)[4] = env->regs[R_EDI]; - (*regs)[5] = env->regs[R_EBP]; - (*regs)[6] = env->regs[R_EAX]; - (*regs)[7] = env->segs[R_DS].selector & 0xffff; - (*regs)[8] = env->segs[R_ES].selector & 0xffff; - (*regs)[9] = env->segs[R_FS].selector & 0xffff; - (*regs)[10] = env->segs[R_GS].selector & 0xffff; - (*regs)[11] = env->regs[R_EAX]; /* XXX */ - (*regs)[12] = env->eip; - (*regs)[13] = env->segs[R_CS].selector & 0xffff; - (*regs)[14] = env->eflags; - (*regs)[15] = env->regs[R_ESP]; - (*regs)[16] = env->segs[R_SS].selector & 0xffff; + (*regs)[0] = tswapreg(env->regs[R_EBX]); + (*regs)[1] = tswapreg(env->regs[R_ECX]); + (*regs)[2] = tswapreg(env->regs[R_EDX]); + (*regs)[3] = tswapreg(env->regs[R_ESI]); + (*regs)[4] = tswapreg(env->regs[R_EDI]); + (*regs)[5] = tswapreg(env->regs[R_EBP]); + (*regs)[6] = tswapreg(env->regs[R_EAX]); + (*regs)[7] = tswapreg(env->segs[R_DS].selector & 0xffff); + (*regs)[8] = tswapreg(env->segs[R_ES].selector & 0xffff); + (*regs)[9] = tswapreg(env->segs[R_FS].selector & 0xffff); + (*regs)[10] = tswapreg(env->segs[R_GS].selector & 0xffff); + (*regs)[11] = tswapreg(env->regs[R_EAX]); /* XXX */ + (*regs)[12] = tswapreg(env->eip); + (*regs)[13] = tswapreg(env->segs[R_CS].selector & 0xffff); + (*regs)[14] = tswapreg(env->eflags); + (*regs)[15] = tswapreg(env->regs[R_ESP]); + (*regs)[16] = tswapreg(env->segs[R_SS].selector & 0xffff); } #endif @@ -586,6 +586,16 @@ enum { ARM_HWCAP2_A64_SVESM4 = 1 << 6, ARM_HWCAP2_A64_FLAGM2 = 1 << 7, ARM_HWCAP2_A64_FRINT = 1 << 8, + ARM_HWCAP2_A64_SVEI8MM = 1 << 9, + ARM_HWCAP2_A64_SVEF32MM = 1 << 10, + ARM_HWCAP2_A64_SVEF64MM = 1 << 11, + ARM_HWCAP2_A64_SVEBF16 = 1 << 12, + ARM_HWCAP2_A64_I8MM = 1 << 13, + ARM_HWCAP2_A64_BF16 = 1 << 14, + ARM_HWCAP2_A64_DGH = 1 << 15, + ARM_HWCAP2_A64_RNG = 1 << 16, + ARM_HWCAP2_A64_BTI = 1 << 17, + ARM_HWCAP2_A64_MTE = 1 << 18, }; #define ELF_HWCAP get_elf_hwcap() @@ -638,8 +648,23 @@ static uint32_t get_elf_hwcap2(void) uint32_t hwcaps = 0; GET_FEATURE_ID(aa64_dcpodp, ARM_HWCAP2_A64_DCPODP); + GET_FEATURE_ID(aa64_sve2, ARM_HWCAP2_A64_SVE2); + GET_FEATURE_ID(aa64_sve2_aes, ARM_HWCAP2_A64_SVEAES); + GET_FEATURE_ID(aa64_sve2_pmull128, ARM_HWCAP2_A64_SVEPMULL); + GET_FEATURE_ID(aa64_sve2_bitperm, ARM_HWCAP2_A64_SVEBITPERM); + GET_FEATURE_ID(aa64_sve2_sha3, ARM_HWCAP2_A64_SVESHA3); + GET_FEATURE_ID(aa64_sve2_sm4, ARM_HWCAP2_A64_SVESM4); GET_FEATURE_ID(aa64_condm_5, ARM_HWCAP2_A64_FLAGM2); GET_FEATURE_ID(aa64_frint, ARM_HWCAP2_A64_FRINT); + GET_FEATURE_ID(aa64_sve_i8mm, ARM_HWCAP2_A64_SVEI8MM); + GET_FEATURE_ID(aa64_sve_f32mm, ARM_HWCAP2_A64_SVEF32MM); + GET_FEATURE_ID(aa64_sve_f64mm, ARM_HWCAP2_A64_SVEF64MM); + GET_FEATURE_ID(aa64_sve_bf16, ARM_HWCAP2_A64_SVEBF16); + GET_FEATURE_ID(aa64_i8mm, ARM_HWCAP2_A64_I8MM); + GET_FEATURE_ID(aa64_bf16, ARM_HWCAP2_A64_BF16); + GET_FEATURE_ID(aa64_rndr, ARM_HWCAP2_A64_RNG); + GET_FEATURE_ID(aa64_bti, ARM_HWCAP2_A64_BTI); + GET_FEATURE_ID(aa64_mte, ARM_HWCAP2_A64_MTE); return hwcaps; } @@ -663,48 +688,25 @@ static uint32_t get_elf_hwcap2(void) #define ELF_CLASS ELFCLASS64 #define ELF_ARCH EM_SPARCV9 - -#define STACK_BIAS 2047 - -static inline void init_thread(struct target_pt_regs *regs, - struct image_info *infop) -{ -#ifndef TARGET_ABI32 - regs->tstate = 0; -#endif - regs->pc = infop->entry; - regs->npc = regs->pc + 4; - regs->y = 0; -#ifdef TARGET_ABI32 - regs->u_regs[14] = infop->start_stack - 16 * 4; -#else - if (personality(infop->personality) == PER_LINUX32) - regs->u_regs[14] = infop->start_stack - 16 * 4; - else - regs->u_regs[14] = infop->start_stack - 16 * 8 - STACK_BIAS; -#endif -} - #else #define ELF_START_MMAP 0x80000000 #define ELF_HWCAP (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR | HWCAP_SPARC_SWAP \ | HWCAP_SPARC_MULDIV) - #define ELF_CLASS ELFCLASS32 #define ELF_ARCH EM_SPARC +#endif /* TARGET_SPARC64 */ static inline void init_thread(struct target_pt_regs *regs, struct image_info *infop) { - regs->psr = 0; + /* Note that target_cpu_copy_regs does not read psr/tstate. */ regs->pc = infop->entry; regs->npc = regs->pc + 4; regs->y = 0; - regs->u_regs[14] = infop->start_stack - 16 * 4; + regs->u_regs[14] = (infop->start_stack - 16 * sizeof(abi_ulong) + - TARGET_STACK_BIAS); } - -#endif -#endif +#endif /* TARGET_SPARC */ #ifdef TARGET_PPC @@ -828,7 +830,7 @@ static uint32_t get_elf_hwcap2(void) PPC2_ISA207S), QEMU_PPC_FEATURE2_ARCH_2_07 | QEMU_PPC_FEATURE2_VEC_CRYPTO); GET_FEATURE2(PPC2_ISA300, QEMU_PPC_FEATURE2_ARCH_3_00 | - QEMU_PPC_FEATURE2_DARN); + QEMU_PPC_FEATURE2_DARN | QEMU_PPC_FEATURE2_HAS_IEEE128); #undef GET_FEATURE #undef GET_FEATURE2 @@ -1374,6 +1376,7 @@ static uint32_t get_elf_hwcap(void) hwcap |= HWCAP_S390_ETF3EH; } GET_FEATURE(S390_FEAT_VECTOR, HWCAP_S390_VXRS); + GET_FEATURE(S390_FEAT_VECTOR_ENH, HWCAP_S390_VXRS_EXT); return hwcap; } @@ -1385,6 +1388,39 @@ static inline void init_thread(struct target_pt_regs *regs, struct image_info *i regs->gprs[15] = infop->start_stack; } +/* See linux kernel: arch/s390/include/uapi/asm/ptrace.h (s390_regs). */ +#define ELF_NREG 27 +typedef target_elf_greg_t target_elf_gregset_t[ELF_NREG]; + +enum { + TARGET_REG_PSWM = 0, + TARGET_REG_PSWA = 1, + TARGET_REG_GPRS = 2, + TARGET_REG_ARS = 18, + TARGET_REG_ORIG_R2 = 26, +}; + +static void elf_core_copy_regs(target_elf_gregset_t *regs, + const CPUS390XState *env) +{ + int i; + uint32_t *aregs; + + (*regs)[TARGET_REG_PSWM] = tswapreg(env->psw.mask); + (*regs)[TARGET_REG_PSWA] = tswapreg(env->psw.addr); + for (i = 0; i < 16; i++) { + (*regs)[TARGET_REG_GPRS + i] = tswapreg(env->regs[i]); + } + aregs = (uint32_t *)&((*regs)[TARGET_REG_ARS]); + for (i = 0; i < 16; i++) { + aregs[i] = tswap32(env->aregs[i]); + } + (*regs)[TARGET_REG_ORIG_R2] = 0; +} + +#define USE_ELF_CORE_DUMP +#define ELF_EXEC_PAGESIZE 4096 + #endif /* TARGET_S390X */ #ifdef TARGET_RISCV @@ -1398,6 +1434,19 @@ static inline void init_thread(struct target_pt_regs *regs, struct image_info *i #define ELF_CLASS ELFCLASS64 #endif +#define ELF_HWCAP get_elf_hwcap() + +static uint32_t get_elf_hwcap(void) +{ +#define MISA_BIT(EXT) (1 << (EXT - 'A')) + RISCVCPU *cpu = RISCV_CPU(thread_cpu); + uint32_t mask = MISA_BIT('I') | MISA_BIT('M') | MISA_BIT('A') + | MISA_BIT('F') | MISA_BIT('D') | MISA_BIT('C'); + + return cpu->env.misa & mask; +#undef MISA_BIT +} + static inline void init_thread(struct target_pt_regs *regs, struct image_info *infop) { @@ -3386,7 +3435,6 @@ static size_t note_size(const struct memelfnote *); static void free_note_info(struct elf_note_info *); static int fill_note_info(struct elf_note_info *, long, const CPUArchState *); static void fill_thread_info(struct elf_note_info *, const CPUArchState *); -static int core_dump_filename(const TaskState *, char *, size_t); static int dump_write(int, const void *, size_t); static int write_note(struct memelfnote *, int); @@ -3629,11 +3677,12 @@ static int fill_psinfo(struct target_elf_prpsinfo *psinfo, const TaskState *ts) (void) memset(psinfo, 0, sizeof (*psinfo)); - len = ts->info->arg_end - ts->info->arg_start; + len = ts->info->env_strings - ts->info->arg_strings; if (len >= ELF_PRARGSZ) len = ELF_PRARGSZ - 1; - if (copy_from_user(&psinfo->pr_psargs, ts->info->arg_start, len)) + if (copy_from_user(&psinfo->pr_psargs, ts->info->arg_strings, len)) { return -EFAULT; + } for (i = 0; i < len; i++) if (psinfo->pr_psargs[i] == 0) psinfo->pr_psargs[i] = ' '; @@ -3685,32 +3734,16 @@ static void fill_auxv_note(struct memelfnote *note, const TaskState *ts) * for the name: * qemu__-